Changelog: update

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
avcodec/4xm: Check for cfrm exhaustion
2023-11-10 01:00:22 +01:00 · 2023-11-10 00:25:37 +01:00 · 2023-11-10 00:24:18 +01:00 · 2023-11-09 00:22:33 +01:00 · 2023-11-09 00:16:17 +01:00 · 2023-11-03 23:34:59 +01:00
2074 changed files with 60463 additions and 111163 deletions
--- a/216
+++ b/216
@@ -1,43 +1,185 @@
 Entries are sorted chronologically from oldest to youngest within each release,
 releases are sorted from youngest to oldest.

-version <next>:
- libaribcaption decoder
- Playdate video decoder and demuxer
- Extend VAAPI support for libva-win32 on Windows
- afireqsrc audio source filter
- arls filter
- ffmpeg CLI new option: -readrate_initial_burst
- zoneplate video source filter
- command support in the setpts and asetpts filters
- Vulkan decode hwaccel, supporting H264, HEVC and AV1
- color_vulkan filter
- bwdif_vulkan filter
- nlmeans_vulkan filter
- RivaTuner video decoder
- xfade_vulkan filter
- vMix video decoder
- Essential Video Coding parser, muxer and demuxer
- Essential Video Coding frame merge bsf
- bwdif_cuda filter
- Microsoft RLE video encoder
- Raw AC-4 muxer and demuxer
- Raw VVC bitstream parser, muxer and demuxer
- Bitstream filter for editing metadata in VVC streams
- Bitstream filter for converting VVC from MP4 to Annex B
- scale_vt filter for videotoolbox
- transpose_vt filter for videotoolbox
- support for the P_SKIP hinting to speed up libx264 encoding
- Support HEVC,VP9,AV1 codec in enhanced flv format
- apsnr and asisdr audio filters
- OSQ demuxer and decoder
- Support HEVC,VP9,AV1 codec fourcclist in enhanced rtmp protocol
- CRI USM demuxer
- ffmpeg CLI '-top' option deprecated in favor of the setfield filter
- VAAPI AV1 encoder
- ffprobe XML output schema changed to account for multiple
-  variable-fields elements within the same parent element
- ffprobe -output_format option added as an alias of -of
+version 6.0.1:
+ avcodec/4xm: Check for cfrm exhaustion
+ avformat/mov: Disallow FTYP after streams
+ doc/html: fix styling issue with Texinfo 7.0
+ doc/html: support texinfo 7.0
+ Changelog: update
+ avformat/lafdec: Check for 0 parameters
+ avformat/lafdec: Check for 0 parameters
+ avfilter/buffersink: fix order of operation with = and <0
+ avfilter/framesync: fix order of operation with = and <0
+ tools/target_dec_fuzzer: Adjust threshold for CSCD
+ avcodec/dovi_rpu: Use 64 bit in get_us/se_coeff()
+ avformat/mov: Check that is_still_picture_avif has no trak based streams
+ avformat/matroskadec: Fix declaration-after-statement warnings
+ Update for FFmpeg 6.0.1
+ fftools/ffmpeg_mux_init: Restrict disabling automatic copying of metadata
+ avformat/rtsp: Use rtsp_st->stream_index
+ avformat/rtsp: Use rtsp_st->stream_index
+ avutil/tx_template: fix integer ovberflwo in fft3()
+ avcodec/jpeg2000dec: Check image offset
+ avformat/mxfdec: Check klv offset
+ libavutil/ppc/cpu.c: check that AT_HWCAP2 is defined
+ avcodec/h2645_parse: Avoid EAGAIN
+ avcodec/xvididct: Make c* unsigned to avoid undefined overflows
+ avcodec/bonk: Fix undefined overflow in predictor_calc_error()
+ avformat/tmv: Check video chunk size
+ avcodec/h264_parser: saturate dts a bit
+ avformat/asfdec_f: Saturate presentation time in marker
+ avformat/xwma: sanity check bits_per_coded_sample
+ avformat/matroskadec: Check prebuffered_ns for overflow
+ avformat/wavdec: Check left avio_tell for overflow
+ avformat/tta: Better totalframes check
+ avformat/rpl: Check for number_of_chunks overflow
+ avformat/mov: compute absolute dts difference without overflow in mov_find_next_sample()
+ avformat/jacosubdec: Check timeres
+ avformat/jacosubdec: avoid signed integer overflows in get_shift()
+ avformat/jacosubdec: Factorize code in get_shift() a bit
+ avformat/sbgdec: Check for negative duration or un-representable end pts
+ avcodec/escape124: Do not return random numbers
+ avcodec/apedec: Fix an integer overflow in predictor_update_filter()
+ tools/target_dec_fuzzer: Adjust wmapro threshold
+ avcodec/wavarc: Allocate AV_INPUT_BUFFER_PADDING_SIZE
+ avcodec/wavarc: Fix integer overflwo in do_stereo()
+ avutil/tx_template: Fix some signed integer overflows in DECL_FFT5()
+ avcodec/aacdec_template: Better avoidance of signed integer overflow in imdct_and_windowing_eld()
+ tools/target_dec_fuzzer: Adjust threshold for MVHA
+ avformat/avs: Check if return code is representable
+ avcodec/flacdec: Fix integer overflow in "33bit" DECODER_SUBFRAME_FIXED_WIDE()
+ avcodec/flacdec: Fix overflow in "33bit" decorrelate
+ avcodec/lcldec: Make PNG filter addressing match the code afterwards
+ avformat/westwood_vqa: Check chunk size
+ avformat/sbgdec: Check for period overflow
+ avformat/concatdec: Check in/outpoint for overflow
+ avformat/mov: Check avif_info
+ avformat/mxfdec: Remove this_partition
+ avcodec/xvididct: Fix integer overflow in idct_row()
+ avcodec/celp_math: avoid overflow in shift
+ tools/target_dec_fuzzer: Adjust threshold for rtv1
+ avformat/hls: reduce default max reload to 3
+ avformat/format: Stop reading data at EOF during probing
+ avcodec/bonk: Fix integer overflow in predictor_calc_error()
+ avcodec/jpeg2000dec: jpeg2000 has its own lowres option
+ avcodec/huffyuvdec: avoid undefined behavior with get_vlc2() failure
+ avcodec/cscd: Fix "CamStudio Lossless Codec 1.0" gzip files
+ avcodec/cscd: Check for CamStudio Lossless Codec 1.0 behavior in end check of LZO files
+ avcodec/mpeg4videodec: consider lowres in dest_pcm[]
+ avcodec/hevcdec: Fix undefined memcpy()
+ avcodec/mpeg4videodec: more unsigned in amv computation
+ avcodec/tta: fix signed overflow in decorrelate
+ avcodec/apedec: remove unused variable
+ avcodec/apedec: Fix 48khz 24bit below insane level
+ avcodec/apedec: Fix CRC for 24bps and bigendian
+ avcodec/wavarc: Check that nb_samples is not negative
+ avcodec/wavarc: Check shift
+ avcodec/xvididct: Fix integer overflow in idct_row()
+ avformat/avr: Check sample rate
+ avformat/imf_cpl: Replace NULL content_title_utf8 by ""
+ avformat/imf_cpl: xmlNodeListGetString() can return NULL
+ avcodec/aacdec_template: Fix undefined signed interger operations
+ avcodec/wavarc: Fix k limit
+ avcodec/rka: Fix integer overflow in decode_filter()
+ avformat/rka: bps < 8 is invalid
+ avcodec/pcm: allow Changing parameters
+ avutil/tx_template: extend to 2M
+ avcodec/jpeg2000dec: Check for reduction factor and image offset
+ avutil/softfloat: Basic documentation for av_sincos_sf()
+ avutil/softfloat: fix av_sincos_sf()
+ tools/target_dec_fuzzer: Adjust threshold for speex
+ avcodec/utils: fix 2 integer overflows in get_audio_frame_duration()
+ avcodec/hevcdec: Avoid null pointer dereferences in MC
+ avcodec/takdsp: Fix integer overflows
+ avcodec/mpegvideo_dec: consider interlaced lowres 4:2:0 chroma in edge emulation check better
+ avcodec/rka: use unsigned for buf0 additions
+ avcodec/rka: Avoid undefined left shift
+ avcodec: Ignoring errors is only possible before the input end
+ avformat/jpegxl_probe: Forward error codes
+ avformat/jpegxl_probe: check length instead of blindly reading
+ avformat/jpegxl_probe: Remove intermediate macro obfuscation around get_bits*()
+ avcodec/noise_bsf: Check for wrapped frames
+ avformat/oggparsetheora: clip duration within 64bit
+ avcodec/rka: avoid undefined multiply in  cmode==0
+ avcodec/rka: use 64bit for srate_pad computation
+ avcodec/bonk: Avoid undefined integer overflow in predictor_calc_error()
+ avformat/wavdec: Check that smv block fits in available space
+ avcodec/adpcm: Fix integer overflow in intermediate in ADPCM_XMD
+ avcodec/dpcm: fix undefined interger overflow in wady
+ avcodec/tiff: add a zero DNG_LINEARIZATION_TABLE check
+ avcodec/tak: Check remaining bits in ff_tak_decode_frame_header()
+ avcodec/sonic: Fix two undefined integer overflows
+ avcodec/utils: the IFF_ILBM implementation assumes that there are a multiple of 16 allocated
+ avcodec/flacdec: Fix signed integre overflow
+ avcodec/exr: Cleanup befor return
+ avcodec/pngdec: Do not pass AVFrame into global header decode
+ avcodec/pngdec: remove AVFrame argument from decode_iccp_chunk()
+ avcodec/wavarc: Check order before using it to write the list
+ avcodec/bonk: decode multiple passes in intlist_read() at once
+ avcodec/vorbisdec: Check codebook float values to be finite
+ avcodec/g2meet: Replace fake allocation avoidance for framebuf
+ avutil/tx_priv: Use unsigned in BF() to avoid signed overflows
+ avcodec/lcldec: More space for rgb24
+ avcodec/lcldec: Support 4:1:1 and 4:2:2 with odd width
+ libavcodec/lcldec: width and height should not be unsigned
+ avformat/imf: fix invalid resource handling
+ avcodec/escape124: Check that blocks are allocated before use
+ avcodec/rka: Fix signed integer overflow in decode_filter()
+ avcodec/huffyuvdec: Fix undefined behavior with shift
+ avcodec/j2kenc: Replace RGB24 special case by generic test
+ avcodec/j2kenc: Replace BGR48 / GRAY16 test by test for number of bits
+ avcodec/j2kenc: simplify pixel format setup
+ avcodec/j2kenc: Fix funky bpno errors on decoding
+ avcodec/j2kenc: remove misleading pred value
+ avcodec/j2kenc: fix 5/3 DWT identifer
+ avcodec/vp3: Check width to avoid assertion failure
+ avcodec/g729postfilter: Limit shift in long term filter
+ avcodec/wavarc: Fix several integer overflows
+ avcodec/tests/snowenc: Fix 2nd test
+ avcodec/tests/snowenc: return a failure if DWT/IDWT mismatches
+ avcodec/snowenc: Fix visual weight calculation
+ avcodec/tests/snowenc: unbreak DWT tests
+ avcodec/mpeg12dec: Check input size
+ avcodec/escape124: Fix some return codes
+ avcodec/escape124: fix signdness of end of input check
+ Use https for repository links
+ avcodec/nvdec_hevc: fail to initialize on unsupported profiles
+ fftools/ffmpeg_enc: apply -top to individual encoded frames
+ avcodec/on2avc: use correct fft sizes
+ avcodec/on2avc: use the matching AVTX context for the 512 sized iMDCT
+ examples: fix build of mux and resample_audio
+ avcodec/nvenc: stop using deprecated rc modes with SDK 12.1
+ configure: use non-deprecated nvenc GUID for conftest
+ avcodec/x86/mathops: clip constants used with shift instructions within inline assembly
+ avfilter/vsrc_ddagrab: calculate pointer position on rotated screens
+ avfilter/vsrc_ddagrab: account for mouse-only frames during probing
+ avcodec/aac_ac3_parser: add preprocessor checks for codec specific code
+ avcodec/nvenc: handle frame durations and AV_CODEC_CAP_ENCODER_REORDERED_OPAQUE
+ Revert "lavc/nvenc: handle frame durations and AV_CODEC_CAP_ENCODER_REORDERED_OPAQUE"
+ Revert "avcodec/nvenc: fix b-frame DTS behavior with fractional framerates"
+ avcodec/vdpau_mpeg4: fix order of quant matrix coefficients
+ avcodec/vdpau_mpeg12: fix order of quant matrix coefficients
+ avcodec/nvdec_mpeg4: fix order of quant matrix coefficients
+ avcodec/nvdec_mpeg2: fix order of quant matrix coefficients
+ fftools/ffmpeg_filter: fix leak of AVIOContext in read_binary()
+ fftools/ffmpeg: avoid possible invalid reads with short -tag values
+ avcodec/mp_cmp: reject invalid comparison function values
+ avcodec/aacpsy: clip global_quality within the psy_vbr_map array boundaries
+ avutil/wchar_filename: propagate MultiByteToWideChar() and WideCharToMultiByte() failures
+ avformat/concatf: check if any nodes were allocated
+ avcodec/nvenc: fix b-frame DTS behavior with fractional framerates
+ avcodec/vorbisdec: export skip_samples instead of dropping frames
+ fftools/ffmpeg_mux_init: avoid invalid reads in forced keyframe parsing
+ lavfi/vf_vpp_qsv: set the right timestamp for AVERROR_EOF
+ avfilter/vf_untile: swap the chroma shift values used for plane offsets
+ lavc/decode: stop mangling last_pkt_props->opaque
+ avcodec/nvenc: avoid failing b_ref_mode check when unset
+ lavu/vulkan: fix handle type for 32-bit targets
+ vulkan: Fix win/i386 calling convention
+ avfilter/graphparser: fix filter instance name when an id is provided
+ avcodec/aacps_tablegen: fix build error after avutil bump
+ avcodec/nvenc: fix potential NULL pointer dereference


 version 6.0:
--- a/8
+++ b/8
@@ -181,7 +181,6 @@ Codecs:
  interplayvideo.c                      Mike Melanson
  jni*, ffjni*                          Matthieu Bouron
  jpeg2000*                             Nicolas Bertrand
-  jpegxl*                               Leo Izen
  jvdec.c                               Peter Ross
  lcl*.c                                Roberto Togni, Reimar Doeffinger
  libcelt_dec.c                         Nicolas George
@@ -211,7 +210,6 @@ Codecs:
  mqc*                                  Nicolas Bertrand
  msmpeg4.c, msmpeg4data.h              Michael Niedermayer
  msrle.c                               Mike Melanson
-  msrleenc.c                            Tomas Härdin
  msvideo1.c                            Mike Melanson
  nuv.c                                 Reimar Doeffinger
  nvdec*, nvenc*                        Timo Rothenpieler
@@ -419,7 +417,6 @@ Muxers/Demuxers:
  dv.c                                  Roman Shaposhnik
  electronicarts.c                      Peter Ross
  epafdec.c                             Paul B Mahol
-  evc*                                  Samsung (Dawid Kozinski)
  ffm*                                  Baptiste Coudurier
  flic.c                                Mike Melanson
  flvdec.c                              Michael Niedermayer
@@ -435,7 +432,7 @@ Muxers/Demuxers:
  ipmovie.c                             Mike Melanson
  ircam*                                Paul B Mahol
  iss.c                                 Stefan Gehrer
-  jpegxl*                               Leo Izen
+  jpegxl_probe.*                        Leo Izen
  jvdec.c                               Peter Ross
  kvag.c                                Zane van Iperen
  libmodplug.c                          Clément Bœsch
@@ -546,7 +543,6 @@ LoongArch                               Shiyou Yin
 Mac OS X / PowerPC                      Romain Dolbeau, Guillaume Poirier
 Amiga / PowerPC                         Colin Ward
 Linux / PowerPC                         Lauri Kasanen
-RISC-V                                  Rémi Denis-Courmont
 Windows MinGW                           Alex Beregszaszi, Ramiro Polla
 Windows Cygwin                          Victor Paesa
 Windows MSVC                            Matthew Oliver, Hendrik Leppkes
@@ -618,7 +614,7 @@ Haihao Xiang (haihao)         1F0C 31E8 B4FE F7A4 4DC1 DC99 E0F5 76D4 76FC 437F
 Jaikrishnan Menon             61A1 F09F 01C9 2D45 78E1 C862 25DC 8831 AF70 D368
 James Almer                   7751 2E8C FD94 A169 57E6 9A7A 1463 01AD 7376 59E0
 Jean Delvare                  7CA6 9F44 60F1 BDC4 1FD2 C858 A552 6B9B B3CD 4E6A
-Leo Izen (Traneptora)         B6FD 3CFC 7ACF 83FC 9137 6945 5A71 C331 FD2F A19A
+Leo Izen (thebombzen)         B6FD 3CFC 7ACF 83FC 9137 6945 5A71 C331 FD2F A19A
 Loren Merritt                 ABD9 08F4 C920 3F65 D8BE 35D7 1540 DAA7 060F 56DE
 Lynne                         FE50 139C 6805 72CA FD52 1F8D A2FE A5F0 3F03 4464
 Michael Niedermayer           9FF2 128B 147E F673 0BAD F133 611E C787 040B 0FAB
--- a/4
+++ b/4
@@ -47,7 +47,7 @@ FF_DEP_LIBS  := $(DEP_LIBS)
 FF_STATIC_DEP_LIBS := $(STATIC_DEP_LIBS)

 $(TOOLS): %$(EXESUF): %.o
-	$(LD) $(LDFLAGS) $(LDEXEFLAGS) $(LD_O) $(filter-out $(FF_DEP_LIBS), $^) $(EXTRALIBS-$(*F)) $(EXTRALIBS) $(ELIBS)
+	$(LD) $(LDFLAGS) $(LDEXEFLAGS) $(LD_O) $^ $(EXTRALIBS-$(*F)) $(EXTRALIBS) $(ELIBS)

 target_dec_%_fuzzer$(EXESUF): target_dec_%_fuzzer.o $(FF_DEP_LIBS)
 	$(LD) $(LDFLAGS) $(LDEXEFLAGS) $(LD_O) $^ $(ELIBS) $(FF_EXTRALIBS) $(LIBFUZZER_PATH)
@@ -67,8 +67,6 @@ tools/target_io_dem_fuzzer$(EXESUF): tools/target_io_dem_fuzzer.o $(FF_DEP_LIBS)

 tools/enum_options$(EXESUF): ELIBS = $(FF_EXTRALIBS)
 tools/enum_options$(EXESUF): $(FF_DEP_LIBS)
-tools/enc_recon_frame_test$(EXESUF): $(FF_DEP_LIBS)
-tools/enc_recon_frame_test$(EXESUF): ELIBS = $(FF_EXTRALIBS)
 tools/scale_slice_test$(EXESUF): $(FF_DEP_LIBS)
 tools/scale_slice_test$(EXESUF): ELIBS = $(FF_EXTRALIBS)
 tools/sofa2wavs$(EXESUF): ELIBS = $(FF_EXTRALIBS)
--- a/2
+++ b/2
@@ -1 +1 @@
-5.1.git
+6.0.1
--- a/15
+++ b/15
@@ -0,0 +1,15 @@
+
+            ┌────────────────────────────────────────────┐
+            │ RELEASE NOTES for FFmpeg 6.0 "Von Neumann" │
+            └────────────────────────────────────────────┘
+
+   The FFmpeg Project proudly presents FFmpeg 6.0 "Von Neumann", about 6
+   months after the release of FFmpeg 5.1.
+
+   A complete Changelog is available at the root of the project, and the
+   complete Git history on https://git.ffmpeg.org/gitweb/ffmpeg.git
+
+   We hope you will like this release as much as we enjoyed working on it, and
+   as usual, if you have any questions about it, or any FFmpeg related topic,
+   feel free to join us on the #ffmpeg IRC channel (on irc.libera.chat) or ask
+   on the mailing-lists.
--- a/compat/atomics/win32/stdatomic.h
+++ b/compat/atomics/win32/stdatomic.h
@@ -19,6 +19,7 @@
 #ifndef COMPAT_ATOMICS_WIN32_STDATOMIC_H
 #define COMPAT_ATOMICS_WIN32_STDATOMIC_H

+#define WIN32_LEAN_AND_MEAN
 #include <stddef.h>
 #include <stdint.h>
 #include <windows.h>
--- a/compat/w32pthreads.h
+++ b/compat/w32pthreads.h
@@ -35,6 +35,7 @@
 * As most functions here are used without checking return values,
 * only implement return values as necessary. */

+#define WIN32_LEAN_AND_MEAN
 #include <windows.h>
 #include <process.h>
 #include <time.h>
@@ -65,14 +66,7 @@ typedef CONDITION_VARIABLE pthread_cond_t;
 #define PTHREAD_CANCEL_ENABLE 1
 #define PTHREAD_CANCEL_DISABLE 0

-#if HAVE_WINRT
-#define THREADFUNC_RETTYPE DWORD
-#else
-#define THREADFUNC_RETTYPE unsigned
-#endif
-
-static av_unused THREADFUNC_RETTYPE
-__stdcall attribute_align_arg win32thread_worker(void *arg)
+static av_unused unsigned __stdcall attribute_align_arg win32thread_worker(void *arg)
 {
    pthread_t *h = (pthread_t*)arg;
    h->ret = h->func(h->arg);
--- a/306
+++ b/306
@@ -136,9 +136,13 @@ Component options:
  --disable-w32threads     disable Win32 threads [autodetect]
  --disable-os2threads     disable OS/2 threads [autodetect]
  --disable-network        disable network support [no]
+  --disable-dct            disable DCT code
  --disable-dwt            disable DWT code
  --disable-error-resilience disable error resilience code
  --disable-lsp            disable LSP code
+  --disable-mdct           disable MDCT code
+  --disable-rdft           disable RDFT code
+  --disable-fft            disable FFT code
  --disable-faan           disable floating point AAN (I)DCT code
  --disable-pixelutils     disable pixel utils in libavutil

@@ -214,7 +218,6 @@ External library support:
  --enable-lcms2           enable ICC profile support via LittleCMS 2 [no]
  --enable-libaom          enable AV1 video encoding/decoding via libaom [no]
  --enable-libaribb24      enable ARIB text and caption decoding via libaribb24 [no]
-  --enable-libaribcaption  enable ARIB text and caption decoding via libaribcaption [no]
  --enable-libass          enable libass subtitles rendering,
                           needed for subtitles and ass filter [no]
  --enable-libbluray       enable BluRay reading using libbluray [no]
@@ -232,7 +235,6 @@ External library support:
  --enable-libfontconfig   enable libfontconfig, useful for drawtext filter [no]
  --enable-libfreetype     enable libfreetype, needed for drawtext filter [no]
  --enable-libfribidi      enable libfribidi, improves drawtext filter [no]
-  --enable-libharfbuzz     enable libharfbuzz, needed for drawtext filter [no]
  --enable-libglslang      enable GLSL->SPIRV compilation via libglslang [no]
  --enable-libgme          enable Game Music Emu via libgme [no]
  --enable-libgsm          enable GSM de/encoding via libgsm [no]
@@ -324,6 +326,7 @@ External library support:
  --disable-securetransport disable Secure Transport, needed for TLS support
                           on OSX if openssl and gnutls are not used [autodetect]
  --enable-vapoursynth     enable VapourSynth demuxer [no]
+  --disable-vulkan         disable Vulkan code [autodetect]
  --disable-xlib           disable xlib [autodetect]
  --disable-zlib           disable zlib [autodetect]

@@ -350,7 +353,6 @@ External library support:
  --disable-vaapi          disable Video Acceleration API (mainly Unix/Intel) code [autodetect]
  --disable-vdpau          disable Nvidia Video Decode and Presentation API for Unix code [autodetect]
  --disable-videotoolbox   disable VideoToolbox code [autodetect]
-  --disable-vulkan         disable Vulkan code [autodetect]

 Toolchain options:
  --arch=ARCH              select architecture [$arch]
@@ -410,7 +412,7 @@ Toolchain options:
  --build-suffix=SUFFIX    library name suffix []
  --enable-pic             build position-independent code
  --enable-thumb           compile for Thumb instruction set
-  --enable-lto[=arg]       use link-time optimization
+  --enable-lto             use link-time optimization
  --env="ENV=override"     override the environment variables

 Advanced options (experts only):
@@ -451,8 +453,6 @@ Optimization options (experts only):
  --disable-armv6t2        disable armv6t2 optimizations
  --disable-vfp            disable VFP optimizations
  --disable-neon           disable NEON optimizations
-  --disable-dotprod        disable DOTPROD optimizations
-  --disable-i8mm           disable I8MM optimizations
  --disable-inline-asm     disable use of inline assembly
  --disable-x86asm         disable use of standalone x86 assembly
  --disable-mipsdsp        disable MIPS DSP ASE R1 optimizations
@@ -1153,43 +1153,6 @@ check_insn(){
    check_as ${1}_external "$2"
 }

-check_arch_level(){
-    log check_arch_level "$@"
-    level="$1"
-    check_as tested_arch_level ".arch $level"
-    enabled tested_arch_level && as_arch_level="$level"
-}
-
-check_archext_insn(){
-    log check_archext_insn "$@"
-    feature="$1"
-    instr="$2"
-    # Check if the assembly is accepted in inline assembly.
-    check_inline_asm ${feature}_inline "\"$instr\""
-    # We don't check if the instruction is supported out of the box by the
-    # external assembler (we don't try to set ${feature}_external) as we don't
-    # need to use these instructions in non-runtime detected codepaths.
-
-    disable $feature
-
-    enabled as_arch_directive && arch_directive=".arch $as_arch_level" || arch_directive=""
-
-    # Test if the assembler supports the .arch_extension $feature directive.
-    arch_extension_directive=".arch_extension $feature"
-    test_as <<EOF && enable as_archext_${feature}_directive || arch_extension_directive=""
-$arch_directive
-$arch_extension_directive
-EOF
-
-    # Test if we can assemble the instruction after potential .arch and
-    # .arch_extension directives.
-    test_as <<EOF && enable ${feature}
-$arch_directive
-$arch_extension_directive
-$instr
-EOF
-}
-
 check_x86asm(){
    log check_x86asm "$@"
    name=$1
@@ -1842,7 +1805,6 @@ EXTERNAL_LIBRARY_LIST="
    ladspa
    lcms2
    libaom
-    libaribcaption
    libass
    libbluray
    libbs2b
@@ -1856,7 +1818,6 @@ EXTERNAL_LIBRARY_LIST="
    libfontconfig
    libfreetype
    libfribidi
-    libharfbuzz
    libglslang
    libgme
    libgsm
@@ -2000,13 +1961,17 @@ PROGRAM_LIST="
 "

 SUBSYSTEM_LIST="
+    dct
    dwt
    error_resilience
    faan
    fast_unaligned
+    fft
    lsp
+    mdct
    pixelutils
    network
+    rdft
 "

 # COMPONENT_LIST needs to come last to ensure correct dependency checking
@@ -2081,6 +2046,7 @@ ARCH_LIST="
    sparc64
    tilegx
    tilepro
+    tomi
    x86
    x86_32
    x86_64
@@ -2091,8 +2057,6 @@ ARCH_EXT_LIST_ARM="
    armv6
    armv6t2
    armv8
-    dotprod
-    i8mm
    neon
    vfp
    vfpv3
@@ -2291,7 +2255,7 @@ SYSTEM_FEATURES="
 SYSTEM_FUNCS="
    access
    aligned_malloc
-    arc4random_buf
+    arc4random
    clock_gettime
    closesocket
    CommandLineToArgvW
@@ -2340,7 +2304,6 @@ SYSTEM_FUNCS="
    strerror_r
    sysconf
    sysctl
-    sysctlbyname
    usleep
    UTGetOSTypeFromString
    VirtualAlloc
@@ -2351,14 +2314,11 @@ SYSTEM_LIBRARIES="
    bcrypt
    vaapi_drm
    vaapi_x11
-    vaapi_win32
    vdpau_x11
 "

 TOOLCHAIN_FEATURES="
    as_arch_directive
-    as_archext_dotprod_directive
-    as_archext_i8mm_directive
    as_dn_directive
    as_fpu_directive
    as_func
@@ -2450,7 +2410,6 @@ HAVE_LIST="
    texi2html
    xmllint
    zlib_gzip
-    openvino2
 "

 # options emitted with CONFIG_ prefix but not available on the command line
@@ -2468,7 +2427,6 @@ CONFIG_EXTRA="
    cbs_av1
    cbs_h264
    cbs_h265
-    cbs_h266
    cbs_jpeg
    cbs_mpeg2
    cbs_vp9
@@ -2477,7 +2435,6 @@ CONFIG_EXTRA="
    dnn
    dovi_rpu
    dvprofile
-    evcparse
    exif
    faandct
    faanidct
@@ -2567,6 +2524,7 @@ CMDLINE_SELECT="
    debug
    extra_warnings
    logging
+    lto
    optimizations
    rpath
    stripping
@@ -2659,11 +2617,9 @@ armv6t2_deps="arm"
 armv8_deps="aarch64"
 neon_deps_any="aarch64 arm"
 intrinsics_neon_deps="neon"
-vfp_deps="arm"
+vfp_deps_any="aarch64 arm"
 vfpv3_deps="vfp"
 setend_deps="arm"
-dotprod_deps="aarch64 neon"
-i8mm_deps="aarch64 neon"

 map 'eval ${v}_inline_deps=inline_asm' $ARCH_EXT_LIST_ARM

@@ -2753,17 +2709,16 @@ threads_if_any="$THREADS_LIST"
 cbs_av1_select="cbs"
 cbs_h264_select="cbs"
 cbs_h265_select="cbs"
-cbs_h266_select="cbs"
 cbs_jpeg_select="cbs"
 cbs_mpeg2_select="cbs"
 cbs_vp9_select="cbs"
+dct_select="rdft"
 deflate_wrapper_deps="zlib"
 dirac_parse_select="golomb"
 dovi_rpu_select="golomb"
 dnn_suggest="libtensorflow libopenvino"
 dnn_deps="avformat swscale"
 error_resilience_select="me_cmp"
-evcparse_select="golomb"
 faandct_deps="faan"
 faandct_select="fdctdsp"
 faanidct_deps="faan"
@@ -2776,15 +2731,18 @@ frame_thread_encoder_deps="encoders threads"
 inflate_wrapper_deps="zlib"
 intrax8_select="blockdsp wmv2dsp"
 iso_media_select="mpeg4audio"
+mdct_select="fft"
 me_cmp_select="idctdsp"
 mpeg_er_select="error_resilience"
 mpegaudio_select="mpegaudiodsp mpegaudioheader"
+mpegaudiodsp_select="dct"
 mpegvideo_select="blockdsp hpeldsp idctdsp videodsp"
 mpegvideodec_select="h264chroma mpegvideo mpeg_er"
 mpegvideoenc_select="aandcttables fdctdsp me_cmp mpegvideo pixblockdsp"
 msmpeg4dec_select="h263_decoder"
 msmpeg4enc_select="h263_encoder"
 vc1dsp_select="h264chroma qpeldsp startcode"
+rdft_select="fft"

 # decoders / encoders
 aac_decoder_select="adts_header mpeg4audio sinewin"
@@ -2816,7 +2774,7 @@ asv1_encoder_select="aandcttables bswapdsp fdctdsp pixblockdsp"
 asv2_decoder_select="blockdsp bswapdsp idctdsp"
 asv2_encoder_select="aandcttables bswapdsp fdctdsp pixblockdsp"
 atrac1_decoder_select="sinewin"
-av1_decoder_select="cbs_av1 atsc_a53"
+av1_decoder_select="av1_frame_split_bsf cbs_av1"
 bink_decoder_select="blockdsp hpeldsp"
 binkaudio_dct_decoder_select="wma_freqs"
 binkaudio_rdft_decoder_select="wma_freqs"
@@ -2940,7 +2898,6 @@ notchlc_decoder_select="lzf"
 nuv_decoder_select="idctdsp"
 opus_decoder_deps="swresample"
 opus_encoder_select="audio_frame_queue"
-pdv_decoder_deps="zlib"
 png_decoder_select="inflate_wrapper"
 png_encoder_select="deflate_wrapper llvidencdsp"
 prores_decoder_select="blockdsp idctdsp"
@@ -2955,7 +2912,6 @@ ralf_decoder_select="golomb"
 rasc_decoder_select="inflate_wrapper"
 rawvideo_decoder_select="bswapdsp"
 rscc_decoder_deps="zlib"
-rtv1_decoder_select="texturedsp"
 rv10_decoder_select="h263_decoder"
 rv10_encoder_select="h263_encoder"
 rv20_decoder_select="h263_decoder"
@@ -2966,7 +2922,7 @@ screenpresso_decoder_deps="zlib"
 shorten_decoder_select="bswapdsp"
 sipr_decoder_select="lsp"
 smvjpeg_decoder_select="mjpeg_decoder"
-snow_decoder_select="dwt h264qpel rangecoder videodsp"
+snow_decoder_select="dwt h264qpel hpeldsp rangecoder videodsp"
 snow_encoder_select="dwt h264qpel hpeldsp me_cmp mpegvideoenc rangecoder videodsp"
 sonic_decoder_select="golomb rangecoder"
 sonic_encoder_select="golomb rangecoder"
@@ -2999,7 +2955,6 @@ utvideo_encoder_select="bswapdsp huffman llvidencdsp"
 vble_decoder_select="llviddsp"
 vbn_decoder_select="texturedsp"
 vbn_encoder_select="texturedspenc"
-vmix_decoder_select="idctdsp"
 vc1_decoder_select="blockdsp h264qpel intrax8 mpegvideodec qpeldsp vc1dsp"
 vc1image_decoder_select="vc1_decoder"
 vorbis_encoder_select="audio_frame_queue"
@@ -3020,7 +2975,7 @@ wmav1_decoder_select="sinewin wma_freqs"
 wmav1_encoder_select="sinewin wma_freqs"
 wmav2_decoder_select="sinewin wma_freqs"
 wmav2_encoder_select="sinewin wma_freqs"
-wmavoice_decoder_select="lsp sinewin"
+wmavoice_decoder_select="lsp rdft dct sinewin"
 wmv1_decoder_select="msmpeg4dec"
 wmv1_encoder_select="msmpeg4enc"
 wmv2_decoder_select="blockdsp error_resilience idctdsp intrax8 msmpeg4dec videodsp wmv2dsp"
@@ -3043,7 +2998,6 @@ cuvid_deps="ffnvcodec"
 d3d11va_deps="dxva_h ID3D11VideoDecoder ID3D11VideoContext"
 dxva2_deps="dxva2api_h DXVA2_ConfigPictureDecode ole32 user32"
 ffnvcodec_deps_any="libdl LoadLibrary"
-mediacodec_deps="android"
 nvdec_deps="ffnvcodec"
 vaapi_x11_deps="xlib_x11"
 videotoolbox_hwaccel_deps="videotoolbox pthreads"
@@ -3062,8 +3016,6 @@ av1_vaapi_hwaccel_deps="vaapi VADecPictureParameterBufferAV1_bit_depth_idx"
 av1_vaapi_hwaccel_select="av1_decoder"
 av1_vdpau_hwaccel_deps="vdpau VdpPictureInfoAV1"
 av1_vdpau_hwaccel_select="av1_decoder"
-av1_vulkan_hwaccel_deps="vulkan"
-av1_vulkan_hwaccel_select="av1_decoder"
 h263_vaapi_hwaccel_deps="vaapi"
 h263_vaapi_hwaccel_select="h263_decoder"
 h263_videotoolbox_hwaccel_deps="videotoolbox"
@@ -3082,8 +3034,6 @@ h264_vdpau_hwaccel_deps="vdpau"
 h264_vdpau_hwaccel_select="h264_decoder"
 h264_videotoolbox_hwaccel_deps="videotoolbox"
 h264_videotoolbox_hwaccel_select="h264_decoder"
-h264_vulkan_hwaccel_deps="vulkan"
-h264_vulkan_hwaccel_select="h264_decoder"
 hevc_d3d11va_hwaccel_deps="d3d11va DXVA_PicParams_HEVC"
 hevc_d3d11va_hwaccel_select="hevc_decoder"
 hevc_d3d11va2_hwaccel_deps="d3d11va DXVA_PicParams_HEVC"
@@ -3098,8 +3048,6 @@ hevc_vdpau_hwaccel_deps="vdpau VdpPictureInfoHEVC"
 hevc_vdpau_hwaccel_select="hevc_decoder"
 hevc_videotoolbox_hwaccel_deps="videotoolbox"
 hevc_videotoolbox_hwaccel_select="hevc_decoder"
-hevc_vulkan_hwaccel_deps="vulkan"
-hevc_vulkan_hwaccel_select="hevc_decoder"
 mjpeg_nvdec_hwaccel_deps="nvdec"
 mjpeg_nvdec_hwaccel_select="mjpeg_decoder"
 mjpeg_vaapi_hwaccel_deps="vaapi"
@@ -3210,7 +3158,7 @@ aac_mf_encoder_deps="mediafoundation"
 ac3_mf_encoder_deps="mediafoundation"
 av1_cuvid_decoder_deps="cuvid CUVIDAV1PICPARAMS"
 av1_mediacodec_decoder_deps="mediacodec"
-av1_mediacodec_encoder_deps="mediacodec"
+av1_mediacodec_decoder_extralibs="-landroid"
 av1_nvenc_encoder_deps="nvenc NV_ENC_PIC_PARAMS_AV1"
 av1_nvenc_encoder_select="atsc_a53"
 h263_v4l2m2m_decoder_deps="v4l2_m2m h263_v4l2_m2m"
@@ -3220,8 +3168,10 @@ h264_crystalhd_decoder_select="crystalhd h264_mp4toannexb_bsf h264_parser"
 h264_cuvid_decoder_deps="cuvid"
 h264_cuvid_decoder_select="h264_mp4toannexb_bsf"
 h264_mediacodec_decoder_deps="mediacodec"
+h264_mediacodec_decoder_extralibs="-landroid"
 h264_mediacodec_decoder_select="h264_mp4toannexb_bsf h264_parser"
 h264_mediacodec_encoder_deps="mediacodec"
+h264_mediacodec_encoder_extralibs="-landroid"
 h264_mediacodec_encoder_select="h264_metadata"
 h264_mf_encoder_deps="mediafoundation"
 h264_mmal_decoder_deps="mmal"
@@ -3240,8 +3190,10 @@ hevc_amf_encoder_deps="amf"
 hevc_cuvid_decoder_deps="cuvid"
 hevc_cuvid_decoder_select="hevc_mp4toannexb_bsf"
 hevc_mediacodec_decoder_deps="mediacodec"
+hevc_mediacodec_decoder_extralibs="-landroid"
 hevc_mediacodec_decoder_select="hevc_mp4toannexb_bsf hevc_parser"
 hevc_mediacodec_encoder_deps="mediacodec"
+hevc_mediacodec_encoder_extralibs="-landroid"
 hevc_mediacodec_encoder_select="hevc_metadata"
 hevc_mf_encoder_deps="mediafoundation"
 hevc_nvenc_encoder_deps="nvenc"
@@ -3275,7 +3227,6 @@ mpeg2_v4l2m2m_decoder_deps="v4l2_m2m mpeg2_v4l2_m2m"
 mpeg4_crystalhd_decoder_select="crystalhd"
 mpeg4_cuvid_decoder_deps="cuvid"
 mpeg4_mediacodec_decoder_deps="mediacodec"
-mpeg4_mediacodec_encoder_deps="mediacodec"
 mpeg4_mmal_decoder_deps="mmal"
 mpeg4_omx_encoder_deps="omx"
 mpeg4_v4l2m2m_decoder_deps="v4l2_m2m mpeg4_v4l2_m2m"
@@ -3288,7 +3239,6 @@ vc1_qsv_decoder_select="qsvdec"
 vc1_v4l2m2m_decoder_deps="v4l2_m2m vc1_v4l2_m2m"
 vp8_cuvid_decoder_deps="cuvid"
 vp8_mediacodec_decoder_deps="mediacodec"
-vp8_mediacodec_encoder_deps="mediacodec"
 vp8_qsv_decoder_select="qsvdec"
 vp8_rkmpp_decoder_deps="rkmpp"
 vp8_vaapi_encoder_deps="VAEncPictureParameterBufferVP8"
@@ -3297,7 +3247,6 @@ vp8_v4l2m2m_decoder_deps="v4l2_m2m vp8_v4l2_m2m"
 vp8_v4l2m2m_encoder_deps="v4l2_m2m vp8_v4l2_m2m"
 vp9_cuvid_decoder_deps="cuvid"
 vp9_mediacodec_decoder_deps="mediacodec"
-vp9_mediacodec_encoder_deps="mediacodec"
 vp9_qsv_decoder_select="qsvdec"
 vp9_rkmpp_decoder_deps="rkmpp"
 vp9_vaapi_encoder_deps="VAEncPictureParameterBufferVP9"
@@ -3310,19 +3259,15 @@ av1_qsv_decoder_select="qsvdec"
 av1_qsv_encoder_select="qsvenc"
 av1_qsv_encoder_deps="libvpl"
 av1_amf_encoder_deps="amf"
-av1_vaapi_encoder_deps="VAEncPictureParameterBufferAV1"
-av1_vaapi_encoder_select="cbs_av1 vaapi_encode"

 # parsers
 aac_parser_select="adts_header mpeg4audio"
 av1_parser_select="cbs_av1"
-evc_parser_select="evcparse"
 h264_parser_select="golomb h264dsp h264parse h264_sei"
 hevc_parser_select="hevcparse hevc_sei"
 mpegaudio_parser_select="mpegaudioheader"
 mpeg4video_parser_select="h263dsp mpegvideodec qpeldsp"
 vc1_parser_select="vc1dsp"
-vvc_parser_select="cbs_h266"

 # bitstream_filters
 aac_adtstoasc_bsf_select="adts_header mpeg4audio"
@@ -3331,7 +3276,6 @@ av1_frame_split_bsf_select="cbs_av1"
 av1_metadata_bsf_select="cbs_av1"
 dts2pts_bsf_select="cbs_h264 h264parse"
 eac3_core_bsf_select="ac3_parser"
-evc_frame_merge_bsf_select="evcparse"
 filter_units_bsf_select="cbs"
 h264_metadata_bsf_deps="const_nan"
 h264_metadata_bsf_select="cbs_h264"
@@ -3341,7 +3285,6 @@ mjpeg2jpeg_bsf_select="jpegtables"
 mpeg2_metadata_bsf_select="cbs_mpeg2"
 trace_headers_bsf_select="cbs"
 vp9_metadata_bsf_select="cbs_vp9"
-vvc_metadata_bsf_select="cbs_h266"

 # external libraries
 aac_at_decoder_deps="audiotoolbox"
@@ -3389,7 +3332,6 @@ libaom_av1_decoder_deps="libaom"
 libaom_av1_encoder_deps="libaom"
 libaom_av1_encoder_select="extract_extradata_bsf"
 libaribb24_decoder_deps="libaribb24"
-libaribcaption_decoder_deps="libaribcaption"
 libcelt_decoder_deps="libcelt"
 libcodec2_decoder_deps="libcodec2"
 libcodec2_encoder_deps="libcodec2"
@@ -3420,6 +3362,7 @@ libopencore_amrwb_decoder_deps="libopencore_amrwb"
 libopenh264_decoder_deps="libopenh264"
 libopenh264_decoder_select="h264_mp4toannexb_bsf"
 libopenh264_encoder_deps="libopenh264"
+libopenjpeg_decoder_deps="libopenjpeg"
 libopenjpeg_encoder_deps="libopenjpeg"
 libopenmpt_demuxer_deps="libopenmpt"
 libopus_decoder_deps="libopus"
@@ -3487,7 +3430,6 @@ dv_demuxer_select="dvprofile"
 dv_muxer_select="dvprofile"
 dxa_demuxer_select="riffdec"
 eac3_demuxer_select="ac3_parser"
-evc_demuxer_select="evc_frame_merge_bsf evc_parser"
 f4v_muxer_select="mov_muxer"
 fifo_muxer_deps="threads"
 flac_demuxer_select="flac_parser"
@@ -3496,6 +3438,7 @@ gxf_muxer_select="pcm_rechunk_bsf"
 hds_muxer_select="flv_muxer"
 hls_demuxer_select="adts_header ac3_parser mov_demuxer mpegts_demuxer"
 hls_muxer_select="mov_muxer mpegts_muxer"
+hls_muxer_suggest="gcrypt openssl"
 image2_alias_pix_demuxer_select="image2_demuxer"
 image2_brender_pix_demuxer_select="image2_demuxer"
 imf_demuxer_deps="libxml2"
@@ -3519,7 +3462,7 @@ mp4_muxer_select="mov_muxer"
 mpegts_demuxer_select="iso_media"
 mpegts_muxer_select="ac3_parser adts_muxer latm_muxer h264_mp4toannexb_bsf hevc_mp4toannexb_bsf"
 mpegtsraw_demuxer_select="mpegts_demuxer"
-mxf_muxer_select="pcm_rechunk_bsf rangecoder"
+mxf_muxer_select="pcm_rechunk_bsf"
 mxf_d10_muxer_select="mxf_muxer"
 mxf_opatom_muxer_select="mxf_muxer"
 nut_muxer_select="riffenc"
@@ -3562,6 +3505,7 @@ xwma_demuxer_select="riffdec"

 # indevs / outdevs
 android_camera_indev_deps="android camera2ndk mediandk pthreads"
+android_camera_indev_extralibs="-landroid -lcamera2ndk -lmediandk"
 alsa_indev_deps="alsa"
 alsa_outdev_deps="alsa"
 avfoundation_indev_deps="avfoundation corevideo coremedia pthreads"
@@ -3694,11 +3638,7 @@ blend_vulkan_filter_deps="vulkan spirv_compiler"
 boxblur_filter_deps="gpl"
 boxblur_opencl_filter_deps="opencl gpl"
 bs2b_filter_deps="libbs2b"
-bwdif_cuda_filter_deps="ffnvcodec"
-bwdif_cuda_filter_deps_any="cuda_nvcc cuda_llvm"
-bwdif_vulkan_filter_deps="vulkan spirv_compiler"
 chromaber_vulkan_filter_deps="vulkan spirv_compiler"
-color_vulkan_filter_deps="vulkan spirv_compiler"
 colorkey_opencl_filter_deps="opencl"
 colormatrix_filter_deps="gpl"
 convolution_opencl_filter_deps="opencl"
@@ -3720,7 +3660,7 @@ dilation_opencl_filter_deps="opencl"
 dnn_classify_filter_select="dnn"
 dnn_detect_filter_select="dnn"
 dnn_processing_filter_select="dnn"
-drawtext_filter_deps="libfreetype libharfbuzz"
+drawtext_filter_deps="libfreetype"
 drawtext_filter_suggest="libfontconfig libfribidi"
 elbg_filter_deps="avcodec"
 eq_filter_deps="gpl"
@@ -3755,7 +3695,6 @@ minterpolate_filter_select="scene_sad"
 mptestsrc_filter_deps="gpl"
 negate_filter_deps="lut_filter"
 nlmeans_opencl_filter_deps="opencl"
-nlmeans_vulkan_filter_deps="vulkan spirv_compiler"
 nnedi_filter_deps="gpl"
 ocr_filter_deps="libtesseract"
 ocv_filter_deps="libopencv"
@@ -3796,7 +3735,7 @@ smartblur_filter_deps="gpl swscale"
 sobel_opencl_filter_deps="opencl"
 sofalizer_filter_deps="libmysofa"
 spp_filter_deps="gpl avcodec"
-spp_filter_select="idctdsp fdctdsp me_cmp pixblockdsp"
+spp_filter_select="fft idctdsp fdctdsp me_cmp pixblockdsp"
 sr_filter_deps="avformat swscale"
 sr_filter_select="dnn"
 stereo3d_filter_deps="gpl"
@@ -3811,7 +3750,6 @@ tonemap_vaapi_filter_deps="vaapi VAProcFilterParameterBufferHDRToneMapping"
 tonemap_opencl_filter_deps="opencl const_nan"
 transpose_opencl_filter_deps="opencl"
 transpose_vaapi_filter_deps="vaapi VAProcPipelineCaps_rotation_flags"
-transpose_vt_filter_deps="videotoolbox VTPixelRotationSessionCreate"
 transpose_vulkan_filter_deps="vulkan spirv_compiler"
 unsharp_opencl_filter_deps="opencl"
 uspp_filter_deps="gpl avcodec"
@@ -3820,17 +3758,14 @@ vflip_vulkan_filter_deps="vulkan spirv_compiler"
 vidstabdetect_filter_deps="libvidstab"
 vidstabtransform_filter_deps="libvidstab"
 libvmaf_filter_deps="libvmaf"
-libvmaf_cuda_filter_deps="libvmaf libvmaf_cuda ffnvcodec"
 zmq_filter_deps="libzmq"
 zoompan_filter_deps="swscale"
 zscale_filter_deps="libzimg const_nan"
 scale_vaapi_filter_deps="vaapi"
-scale_vt_filter_deps="videotoolbox"
 scale_vulkan_filter_deps="vulkan spirv_compiler"
 vpp_qsv_filter_deps="libmfx"
 vpp_qsv_filter_select="qsvvpp"
 xfade_opencl_filter_deps="opencl"
-xfade_vulkan_filter_deps="vulkan spirv_compiler"
 yadif_cuda_filter_deps="ffnvcodec"
 yadif_cuda_filter_deps_any="cuda_nvcc cuda_llvm"
 yadif_videotoolbox_filter_deps="metal corevideo videotoolbox"
@@ -3883,7 +3818,7 @@ avfilter_deps="avutil"
 avfilter_suggest="libm stdatomic"
 avformat_deps="avcodec avutil"
 avformat_suggest="libm network zlib stdatomic"
-avutil_suggest="clock_gettime ffnvcodec gcrypt libm libdrm libmfx opencl openssl user32 vaapi vulkan videotoolbox corefoundation corevideo coremedia bcrypt stdatomic"
+avutil_suggest="clock_gettime ffnvcodec libm libdrm libmfx opencl user32 vaapi vulkan videotoolbox corefoundation corevideo coremedia bcrypt stdatomic"
 postproc_deps="avutil gpl"
 postproc_suggest="libm stdatomic"
 swresample_deps="avutil"
@@ -3893,7 +3828,7 @@ swscale_suggest="libm stdatomic"

 avcodec_extralibs="pthreads_extralibs iconv_extralibs dxva2_extralibs lcms2_extralibs"
 avfilter_extralibs="pthreads_extralibs"
-avutil_extralibs="d3d11va_extralibs mediacodec_extralibs nanosleep_extralibs pthreads_extralibs vaapi_drm_extralibs vaapi_x11_extralibs vaapi_win32_extralibs vdpau_x11_extralibs"
+avutil_extralibs="d3d11va_extralibs nanosleep_extralibs pthreads_extralibs vaapi_drm_extralibs vaapi_x11_extralibs vdpau_x11_extralibs"

 # programs
 ffmpeg_deps="avcodec avfilter avformat threads"
@@ -3901,8 +3836,8 @@ ffmpeg_select="aformat_filter anull_filter atrim_filter format_filter
               hflip_filter null_filter
               transpose_filter trim_filter vflip_filter"
 ffmpeg_suggest="ole32 psapi shell32"
-ffplay_deps="avcodec avformat avfilter swscale swresample sdl2"
-ffplay_select="crop_filter transpose_filter hflip_filter vflip_filter rotate_filter"
+ffplay_deps="avcodec avformat swscale swresample sdl2"
+ffplay_select="rdft crop_filter transpose_filter hflip_filter vflip_filter rotate_filter"
 ffplay_suggest="shell32"
 ffprobe_deps="avcodec avformat"
 ffprobe_suggest="shell32"
@@ -4093,7 +4028,7 @@ CODEC_LIST="
 "
 PARSER_LIST=$(find_things_extern parser AVCodecParser libavcodec/parsers.c)
 BSF_LIST=$(find_things_extern bsf FFBitStreamFilter libavcodec/bitstream_filters.c)
-HWACCEL_LIST=$(find_things_extern hwaccel FFHWAccel libavcodec/hwaccels.h)
+HWACCEL_LIST=$(find_things_extern hwaccel AVHWAccel libavcodec/hwaccels.h)
 PROTOCOL_LIST=$(find_things_extern protocol URLProtocol libavformat/protocols.c)

 AVCODEC_COMPONENTS_LIST="
@@ -4235,9 +4170,6 @@ for opt do
        --enable-sdl)
            enable sdl2
        ;;
-        --enable-lto*)
-            lto=-f${opt#--enable-}
-        ;;
        --enable-*=*|--disable-*=*)
            eval $(echo "${opt%%=*}" | sed 's/--/action=/;s/-/ thing=/')
            is_in "${thing}s" $COMPONENT_LIST || die_unknown "$opt"
@@ -4707,7 +4639,7 @@ icl_flags(){
            # on Windows, does enable remarks so disable them here.
            -Wall)                echo $flag -Qdiag-disable:remark ;;
            -std=c99)             echo -Qstd=c99 ;;
-            -flto*)               echo -ipo ;;
+            -flto)                echo -ipo ;;
        esac
    done
 }
@@ -4715,7 +4647,7 @@ icl_flags(){
 icc_flags(){
    for flag; do
        case $flag in
-            -flto*)               echo -ipo ;;
+            -flto)                echo -ipo ;;
            *)                    echo $flag ;;
        esac
    done
@@ -5435,18 +5367,20 @@ elif enabled x86; then
            cpuflags="-march=$cpu"
            disable i686
        ;;
+        # targets that do support nopl and conditional mov (cmov)
+        i686|pentiumpro|pentium[23]|pentium-m|athlon|athlon-tbird|athlon-4|athlon-[mx]p|athlon64*|k8*|opteron*|athlon-fx\
+        |core*|atom|bonnell|nehalem|westmere|silvermont|sandybridge|ivybridge|haswell|broadwell|skylake*|knl\
+        |amdfam10|barcelona|b[dt]ver*|znver*)
+            cpuflags="-march=$cpu"
+            enable i686
+            enable fast_cmov
+        ;;
        # targets that do support conditional mov but on which it's slow
        pentium4|pentium4m|prescott|nocona)
            cpuflags="-march=$cpu"
            enable i686
            disable fast_cmov
        ;;
-        # everything else should support nopl and conditional mov (cmov)
-        *)
-            cpuflags="-march=$cpu"
-            enable i686
-            enable fast_cmov
-        ;;
    esac

 fi
@@ -5655,7 +5589,6 @@ case $target_os in
        fi
        ! enabled small && test_cmd $windres --version && enable gnu_windres
        enabled x86_32 && check_ldflags -Wl,--large-address-aware
-        add_cppflags -DWIN32_LEAN_AND_MEAN
        shlibdir_default="$bindir_default"
        SLIBPREF=""
        SLIBSUF=".dll"
@@ -5706,7 +5639,6 @@ case $target_os in
        fi
        ! enabled small && test_cmd $windres --version && enable gnu_windres
        enabled x86_32 && check_ldflags -LARGEADDRESSAWARE
-        add_cppflags -DWIN32_LEAN_AND_MEAN
        shlibdir_default="$bindir_default"
        SLIBPREF=""
        SLIBSUF=".dll"
@@ -5736,7 +5668,6 @@ case $target_os in
        enabled x86_64 && objformat="win64" || objformat="win32"
        enable dos_paths
        ! enabled small && test_cmd $windres --version && enable gnu_windres
-        add_cppflags -DWIN32_LEAN_AND_MEAN
        add_cppflags -D_POSIX_C_SOURCE=200112 -D_XOPEN_SOURCE=600
        ;;
    *-dos|freedos|opendos)
@@ -6043,26 +5974,12 @@ check_inline_asm inline_asm_labels '"1:\n"'
 check_inline_asm inline_asm_nonlocal_labels '"Label:\n"'

 if enabled aarch64; then
-    as_arch_level="armv8-a"
-    check_as as_arch_directive ".arch $as_arch_level"
-    enabled as_arch_directive && check_arch_level armv8.2-a
-
    enabled armv8 && check_insn armv8 'prfm   pldl1strm, [x0]'
    # internal assembler in clang 3.3 does not support this instruction
    enabled neon && check_insn neon 'ext   v0.8B, v0.8B, v1.8B, #1'
+    enabled vfp  && check_insn vfp  'fmadd d0,    d0,    d1,    d2'

-    archext_list="dotprod i8mm"
-    enabled dotprod && check_archext_insn dotprod 'udot v0.4s, v0.16b, v0.16b'
-    enabled i8mm    && check_archext_insn i8mm    'usdot v0.4s, v0.16b, v0.16b'
-
-    # Disable the main feature (e.g. HAVE_NEON) if neither inline nor external
-    # assembly support the feature out of the box. Skip this for the features
-    # checked with check_archext_insn above, as that function takes care of
-    # updating all the variables as necessary.
-    for v in $ARCH_EXT_LIST_ARM; do
-        is_in $v $archext_list && continue
-        enabled_any ${v}_external ${v}_inline || disable $v
-    done
+    map 'enabled_any ${v}_external ${v}_inline || disable $v' $ARCH_EXT_LIST_ARM

 elif enabled alpha; then

@@ -6091,12 +6008,6 @@ EOF
        warn "Compiler does not indicate floating-point ABI, guessing $fpabi."
    fi

-    # Test for various instruction sets, testing support both in inline and
-    # external assembly. This sets the ${v}_inline or ${v}_external flags
-    # if the instruction can be used unconditionally in either inline or
-    # external assembly. This means that if the ${v}_external feature is set,
-    # that feature can be used unconditionally in various support macros
-    # anywhere in external assembly, in any function.
    enabled armv5te && check_insn armv5te 'qadd r0, r0, r0'
    enabled armv6   && check_insn armv6   'sadd16 r0, r0, r0'
    enabled armv6t2 && check_insn armv6t2 'movt r0, #0'
@@ -6105,14 +6016,6 @@ EOF
    enabled vfpv3   && check_insn vfpv3   'vmov.f32 s0, #1.0'
    enabled setend  && check_insn setend  'setend be'

-    # If neither inline nor external assembly can use the feature by default,
-    # disable the main unsuffixed feature (e.g. HAVE_NEON).
-    #
-    # For targets that support runtime CPU feature detection, don't disable
-    # the main feature flag - there we assume that all supported toolchains
-    # can assemble code for all instruction set features (e.g. NEON) with
-    # suitable assembly flags (such as ".fpu neon"); we don't check
-    # specifically that they really do.
    [ $target_os = linux ] || [ $target_os = android ] ||
        map 'enabled_any ${v}_external ${v}_inline || disable $v' \
            $ARCH_EXT_LIST_ARM
@@ -6357,32 +6260,22 @@ if enabled float16; then
 fi

 case "$custom_allocator" in
-    "")
-    ;;
    jemalloc)
-        test -n "$malloc_prefix" ||
-            malloc_prefix=$($pkg_config --variable=jemalloc_prefix $pkg_config_flags jemalloc 2>/dev/null)
-        require_pkg_config custom_allocator jemalloc jemalloc/jemalloc.h ${malloc_prefix}malloc
+        # jemalloc by default does not use a prefix
+        require libjemalloc jemalloc/jemalloc.h malloc -ljemalloc
    ;;
    tcmalloc)
-        require_pkg_config custom_allocator libtcmalloc gperftools/tcmalloc.h tc_malloc
+        require_pkg_config libtcmalloc libtcmalloc gperftools/tcmalloc.h tc_malloc
        malloc_prefix=tc_
    ;;
-    *)
-        require_pkg_config custom_allocator "$custom_allocator" stdlib.h malloc
-    ;;
 esac

-if test -n "$custom_allocator"; then
-    add_extralibs "$custom_allocator_extralibs"
-fi
-
 check_func_headers malloc.h _aligned_malloc     && enable aligned_malloc
 check_func  ${malloc_prefix}memalign            && enable memalign
 check_func  ${malloc_prefix}posix_memalign      && enable posix_memalign

 check_func  access
-check_func_headers stdlib.h arc4random_buf
+check_func_headers stdlib.h arc4random
 check_lib   clock_gettime time.h clock_gettime || check_lib clock_gettime time.h clock_gettime -lrt
 check_func  fcntl
 check_func  fork
@@ -6412,7 +6305,6 @@ check_func_headers mach/mach_time.h mach_absolute_time
 check_func_headers stdlib.h getenv
 check_func_headers sys/stat.h lstat
 check_func_headers sys/auxv.h getauxval
-check_func_headers sys/sysctl.h sysctlbyname

 check_func_headers windows.h GetModuleHandle
 check_func_headers windows.h GetProcessAffinityMask
@@ -6467,7 +6359,6 @@ check_headers termios.h
 check_headers unistd.h
 check_headers valgrind/valgrind.h
 check_func_headers VideoToolbox/VTCompressionSession.h VTCompressionSessionPrepareToEncodeFrames -framework VideoToolbox
-check_func_headers VideoToolbox/VideoToolbox.h VTPixelRotationSessionCreate -framework VideoToolbox
 check_headers windows.h
 check_headers asm/types.h

@@ -6486,7 +6377,7 @@ done
 check_lib advapi32 "windows.h"            RegCloseKey          -ladvapi32
 check_lib bcrypt   "windows.h bcrypt.h"   BCryptGenRandom      -lbcrypt &&
    check_cpp_condition bcrypt bcrypt.h "defined BCRYPT_RNG_ALGORITHM"
-check_lib ole32    "windows.h objbase.h"  CoTaskMemFree        -lole32
+check_lib ole32    "windows.h"            CoTaskMemFree        -lole32
 check_lib shell32  "windows.h shellapi.h" CommandLineToArgvW   -lshell32
 check_lib psapi    "windows.h psapi.h"    GetProcessMemoryInfo -lpsapi

@@ -6573,11 +6464,10 @@ fi

 if ! disabled ffnvcodec; then
    ffnv_hdr_list="ffnvcodec/nvEncodeAPI.h ffnvcodec/dynlink_cuda.h ffnvcodec/dynlink_cuviddec.h ffnvcodec/dynlink_nvcuvid.h"
-    check_pkg_config ffnvcodec "ffnvcodec >= 12.1.14.0" "$ffnv_hdr_list" "" || \
-      check_pkg_config ffnvcodec "ffnvcodec >= 12.0.16.1 ffnvcodec < 12.1" "$ffnv_hdr_list" "" || \
-      check_pkg_config ffnvcodec "ffnvcodec >= 11.1.5.3 ffnvcodec < 12.0" "$ffnv_hdr_list" "" || \
-      check_pkg_config ffnvcodec "ffnvcodec >= 11.0.10.3 ffnvcodec < 11.1" "$ffnv_hdr_list" "" || \
-      check_pkg_config ffnvcodec "ffnvcodec >= 8.1.24.15 ffnvcodec < 8.2" "$ffnv_hdr_list" ""
+    check_pkg_config ffnvcodec "ffnvcodec >= 12.0.16.0" "$ffnv_hdr_list" "" || \
+      check_pkg_config ffnvcodec "ffnvcodec >= 11.1.5.2 ffnvcodec < 12.0" "$ffnv_hdr_list" "" || \
+      check_pkg_config ffnvcodec "ffnvcodec >= 11.0.10.2 ffnvcodec < 11.1" "$ffnv_hdr_list" "" || \
+      check_pkg_config ffnvcodec "ffnvcodec >= 8.1.24.14 ffnvcodec < 8.2" "$ffnv_hdr_list" ""
 fi

 if enabled_all libglslang libshaderc; then
@@ -6660,8 +6550,8 @@ done

 # these are off by default, so fail if requested and not available
 enabled avisynth          && { require_headers "avisynth/avisynth_c.h avisynth/avs/version.h" &&
-                               { test_cpp_condition avisynth/avs/version.h "AVS_MAJOR_VER >= 3 && AVS_MINOR_VER >= 7 && AVS_BUGFIX_VER >= 3 || AVS_MAJOR_VER >= 3 && AVS_MINOR_VER > 7 || AVS_MAJOR_VER > 3" ||
-                                 die "ERROR: AviSynth+ header version must be >= 3.7.3"; } }
+                               { test_cpp_condition avisynth/avs/version.h "AVS_MAJOR_VER >= 3 && AVS_MINOR_VER >= 7 && AVS_BUGFIX_VER >= 1 || AVS_MAJOR_VER >= 3 && AVS_MINOR_VER > 7 || AVS_MAJOR_VER > 3" ||
+                                 die "ERROR: AviSynth+ header version must be >= 3.7.1"; } }
 enabled cuda_nvcc         && { check_nvcc cuda_nvcc || die "ERROR: failed checking for nvcc."; }
 enabled chromaprint       && { check_pkg_config chromaprint libchromaprint "chromaprint.h" chromaprint_get_version ||
                               require chromaprint chromaprint.h chromaprint_get_version -lchromaprint; }
@@ -6677,7 +6567,6 @@ enabled libaom            && require_pkg_config libaom "aom >= 1.0.0" aom/aom_co
 enabled libaribb24        && { check_pkg_config libaribb24 "aribb24 > 1.0.3" "aribb24/aribb24.h" arib_instance_new ||
                               { enabled gpl && require_pkg_config libaribb24 aribb24 "aribb24/aribb24.h" arib_instance_new; } ||
                               die "ERROR: libaribb24 requires version higher than 1.0.3 or --enable-gpl."; }
-enabled libaribcaption    && require_pkg_config libaribcaption "libaribcaption >= 0.1.0" "aribcaption/aribcaption.h" aribcc_context_alloc
 enabled lv2               && require_pkg_config lv2 lilv-0 "lilv/lilv.h" lilv_world_new
 enabled libiec61883       && require libiec61883 libiec61883/iec61883.h iec61883_cmp_connect -lraw1394 -lavc1394 -lrom1394 -liec61883
 enabled libass            && require_pkg_config libass "libass >= 0.11.0" ass/ass.h ass_library_init
@@ -6701,7 +6590,6 @@ enabled fontconfig        && enable libfontconfig
 enabled libfontconfig     && require_pkg_config libfontconfig fontconfig "fontconfig/fontconfig.h" FcInit
 enabled libfreetype       && require_pkg_config libfreetype freetype2 "ft2build.h FT_FREETYPE_H" FT_Init_FreeType
 enabled libfribidi        && require_pkg_config libfribidi fribidi fribidi.h fribidi_version_info
-enabled libharfbuzz       && require_pkg_config libharfbuzz harfbuzz hb.h hb_buffer_create
 enabled libglslang && { check_lib spirv_compiler glslang/Include/glslang_c_interface.h glslang_initialize_process \
                            -lglslang -lMachineIndependent -lOSDependent -lHLSL -lOGLCompiler -lGenericCodeGen \
                            -lSPVRemapper -lSPIRV -lSPIRV-Tools-opt -lSPIRV-Tools -lpthread -lstdc++ -lm ||
@@ -6717,7 +6605,7 @@ enabled libilbc           && require libilbc ilbc.h WebRtcIlbcfix_InitDecode -li
 enabled libjxl            && require_pkg_config libjxl "libjxl >= 0.7.0" jxl/decode.h JxlDecoderVersion &&
                             require_pkg_config libjxl_threads "libjxl_threads >= 0.7.0" jxl/thread_parallel_runner.h JxlThreadParallelRunner
 enabled libklvanc         && require libklvanc libklvanc/vanc.h klvanc_context_create -lklvanc
-enabled libkvazaar        && require_pkg_config libkvazaar "kvazaar >= 2.0.0" kvazaar.h kvz_api_get
+enabled libkvazaar        && require_pkg_config libkvazaar "kvazaar >= 0.8.1" kvazaar.h kvz_api_get
 enabled liblensfun        && require_pkg_config liblensfun lensfun lensfun.h lf_db_new

 if enabled libmfx && enabled libvpl; then
@@ -6738,7 +6626,8 @@ elif enabled libmfx; then
      { require libmfx "mfxvideo.h mfxdefs.h" MFXInit "-llibmfx $advapi32_extralibs" &&
        { test_cpp_condition mfxdefs.h "MFX_VERSION >= 1028 && MFX_VERSION < 2000" || die "ERROR: libmfx version must be >= 1.28 and < 2.0"; }  &&
        warn "using libmfx without pkg-config"; } } &&
-    warn "libmfx is deprecated. Please run configure with --enable-libvpl to use libvpl instead."
+    warn "build FFmpeg against libmfx 1.x, obsolete features of libmfx such as OPAQUE memory,\n"\
+         "multi-frame encode, user plugins and LA_EXT rate control mode are enabled"
 elif enabled libvpl; then
 # Consider pkg-config only. The name of libmfx is still passed to check_pkg_config function for --enable-libvpl option
 # because QSV has dependency on libmfx, we can use the same dependency if using libmfx in this check. The package name
@@ -6768,9 +6657,7 @@ enabled libopenh264       && require_pkg_config libopenh264 openh264 wels/codec_
 enabled libopenjpeg       && { check_pkg_config libopenjpeg "libopenjp2 >= 2.1.0" openjpeg.h opj_version ||
                               { require_pkg_config libopenjpeg "libopenjp2 >= 2.1.0" openjpeg.h opj_version -DOPJ_STATIC && add_cppflags -DOPJ_STATIC; } }
 enabled libopenmpt        && require_pkg_config libopenmpt "libopenmpt >= 0.2.6557" libopenmpt/libopenmpt.h openmpt_module_create -lstdc++ && append libopenmpt_extralibs "-lstdc++"
-enabled libopenvino       && { { check_pkg_config libopenvino openvino openvino/c/openvino.h ov_core_create && enable openvino2; } ||
-                                { check_pkg_config libopenvino openvino c_api/ie_c_api.h ie_c_api_version ||
-                                  require libopenvino c_api/ie_c_api.h ie_c_api_version -linference_engine_c_api; } }
+enabled libopenvino       && require libopenvino c_api/ie_c_api.h ie_c_api_version -linference_engine_c_api
 enabled libopus           && {
    enabled libopus_decoder && {
        require_pkg_config libopus opus opus_multistream.h opus_multistream_decoder_create
@@ -6784,7 +6671,7 @@ enabled libpulse          && require_pkg_config libpulse libpulse pulse/pulseaud
 enabled librabbitmq       && require_pkg_config librabbitmq "librabbitmq >= 0.7.1" amqp.h amqp_new_connection
 enabled librav1e          && require_pkg_config librav1e "rav1e >= 0.5.0" rav1e.h rav1e_context_new
 enabled librist           && require_pkg_config librist "librist >= 0.2.7" librist/librist.h rist_receiver_create
-enabled librsvg           && require_pkg_config librsvg librsvg-2.0 librsvg-2.0/librsvg/rsvg.h rsvg_handle_new_from_data
+enabled librsvg           && require_pkg_config librsvg librsvg-2.0 librsvg-2.0/librsvg/rsvg.h rsvg_handle_render_cairo
 enabled librtmp           && require_pkg_config librtmp librtmp librtmp/rtmp.h RTMP_Socket
 enabled librubberband     && require_pkg_config librubberband "rubberband >= 1.8.1" rubberband/rubberband-c.h rubberband_new -lstdc++ && append librubberband_extralibs "-lstdc++"
 enabled libshaderc        && require_pkg_config spirv_compiler "shaderc >= 2019.1" shaderc/shaderc.h shaderc_compiler_initialize
@@ -6793,7 +6680,7 @@ enabled libsmbclient      && { check_pkg_config libsmbclient smbclient libsmbcli
                               require libsmbclient libsmbclient.h smbc_init -lsmbclient; }
 enabled libsnappy         && require libsnappy snappy-c.h snappy_compress -lsnappy -lstdc++
 enabled libsoxr           && require libsoxr soxr.h soxr_create -lsoxr
-enabled libssh            && require_pkg_config libssh "libssh >= 0.6.0" libssh/sftp.h sftp_init
+enabled libssh            && require_pkg_config libssh libssh libssh/sftp.h sftp_init
 enabled libspeex          && require_pkg_config libspeex speex speex/speex.h speex_decoder_init
 enabled libsrt            && require_pkg_config libsrt "srt >= 1.3.0" srt/srt.h srt_socket
 enabled libsvtav1         && require_pkg_config libsvtav1 "SvtAv1Enc >= 0.9.0" EbSvtAv1Enc.h svt_av1_enc_init_handle
@@ -6808,7 +6695,6 @@ enabled libuavs3d         && require_pkg_config libuavs3d "uavs3d >= 1.1.41" uav
 enabled libv4l2           && require_pkg_config libv4l2 libv4l2 libv4l2.h v4l2_ioctl
 enabled libvidstab        && require_pkg_config libvidstab "vidstab >= 0.98" vid.stab/libvidstab.h vsMotionDetectInit
 enabled libvmaf           && require_pkg_config libvmaf "libvmaf >= 2.0.0" libvmaf.h vmaf_init
-enabled libvmaf           && check_pkg_config libvmaf_cuda "libvmaf >= 2.0.0" libvmaf_cuda.h vmaf_cuda_state_init
 enabled libvo_amrwbenc    && require libvo_amrwbenc vo-amrwbenc/enc_if.h E_IF_init -lvo-amrwbenc
 enabled libvorbis         && require_pkg_config libvorbis vorbis vorbis/codec.h vorbis_info_init &&
                             require_pkg_config libvorbisenc vorbisenc vorbis/vorbisenc.h vorbis_encode_init
@@ -7022,7 +6908,8 @@ enabled alsa && { check_pkg_config alsa alsa "alsa/asoundlib.h" snd_pcm_htimesta
 enabled libjack &&
    require_pkg_config libjack jack jack/jack.h jack_port_get_latency_range

-enabled sndio && check_pkg_config sndio sndio sndio.h sio_open
+enabled sndio && { check_pkg_config sndio sndio "sndio.h" sio_open ||
+                   check_lib sndio sndio.h sio_open -lsndio; }

 if enabled libcdio; then
    check_pkg_config libcdio libcdio_paranoia "cdio/cdda.h cdio/paranoia.h" cdio_cddap_open ||
@@ -7058,21 +6945,6 @@ test_cpp <<EOF && enable uwp && d3d11va_extralibs="-ldxgi -ld3d11"
 #endif
 EOF

-# vaapi_win32 requires linking directly to dxgi if not building for
-# the desktop api partition
-test_cpp <<EOF && enable uwp && vaapi_win32_extralibs="-ldxgi"
-#ifdef WINAPI_FAMILY
-#include <winapifamily.h>
-#if WINAPI_FAMILY_PARTITION(WINAPI_PARTITION_DESKTOP)
-#error desktop, not uwp
-#else
-// WINAPI_FAMILY_APP, WINAPI_FAMILY_PHONE_APP => UWP
-#endif
-#else
-#error no family set
-#endif
-EOF
-
 # mediafoundation requires linking directly to mfplat if building for uwp target
 enabled uwp && mediafoundation_extralibs="-lmfplat -lmfuuid -lole32 -lstrmiids" || mediafoundation_extralibs="-lmfuuid -lole32 -lstrmiids"

@@ -7083,14 +6955,7 @@ enabled vaapi &&
    check_pkg_config vaapi "libva >= 0.35.0" "va/va.h" vaInitialize

 if enabled vaapi; then
-    case $target_os in
-        mingw32*|mingw64*|win32|win64)
-            check_pkg_config vaapi_win32 "libva-win32" "va/va_win32.h" vaGetDisplayWin32
-            ;;
-        *)
-            check_pkg_config vaapi_drm "libva-drm" "va/va_drm.h" vaGetDisplayDRM
-            ;;
-    esac
+    check_pkg_config vaapi_drm "libva-drm" "va/va_drm.h" vaGetDisplayDRM

    if enabled xlib_x11; then
        check_pkg_config vaapi_x11 "libva-x11" "va/va_x11.h" vaGetDisplay
@@ -7108,7 +6973,6 @@ if enabled vaapi; then
    check_type "va/va.h va/va_enc_jpeg.h" "VAEncPictureParameterBufferJPEG"
    check_type "va/va.h va/va_enc_vp8.h"  "VAEncPictureParameterBufferVP8"
    check_type "va/va.h va/va_enc_vp9.h"  "VAEncPictureParameterBufferVP9"
-    check_type "va/va.h va/va_enc_av1.h"  "VAEncPictureParameterBufferAV1"
 fi

 if enabled_all opencl libdrm ; then
@@ -7148,12 +7012,8 @@ enabled crystalhd && check_lib crystalhd "stdint.h libcrystalhd/libcrystalhd_if.
         "in maintaining it."

 if enabled vulkan; then
-    check_pkg_config_header_only vulkan "vulkan >= 1.3.255" "vulkan/vulkan.h" "defined VK_VERSION_1_3" ||
-        check_cpp_condition vulkan "vulkan/vulkan.h" "defined(VK_VERSION_1_4) || (defined(VK_VERSION_1_3) && VK_HEADER_VERSION >= 255)"
-fi
-
-if disabled vulkan; then
-    disable libglslang libshaderc spirv_compiler
+    check_pkg_config_header_only vulkan "vulkan >= 1.2.189" "vulkan/vulkan.h" "defined VK_VERSION_1_2" ||
+        check_cpp_condition vulkan "vulkan/vulkan.h" "defined(VK_VERSION_1_3) || (defined(VK_VERSION_1_2) && VK_HEADER_VERSION >= 189)"
 fi

 if enabled x86; then
@@ -7196,7 +7056,7 @@ fi

 enabled amf &&
    check_cpp_condition amf "AMF/core/Version.h" \
-        "(AMF_VERSION_MAJOR << 48 | AMF_VERSION_MINOR << 32 | AMF_VERSION_RELEASE << 16 | AMF_VERSION_BUILD_NUM) >= 0x00010004001d0000"
+        "(AMF_VERSION_MAJOR << 48 | AMF_VERSION_MINOR << 32 | AMF_VERSION_RELEASE << 16 | AMF_VERSION_BUILD_NUM) >= 0x00010004001c0000"

 # Funny iconv installations are not unusual, so check it after all flags have been set
 if enabled libc_iconv; then
@@ -7322,17 +7182,17 @@ fi

 check_optflags(){
    check_cflags "$@"
-    [ -n "$lto" ] && check_ldflags "$@"
+    enabled lto && check_ldflags "$@"
 }

 check_optflags $optflags
 check_optflags -fno-math-errno
 check_optflags -fno-signed-zeros

-if [ -n "$lto" ]; then
+if enabled lto; then
    test "$cc_type" != "$ld_type" && die "LTO requires same compiler and linker"
-    check_cflags  $lto
-    check_ldflags $lto $cpuflags
+    check_cflags  -flto
+    check_ldflags -flto $cpuflags
    disable inline_asm_direct_symbol_refs
 fi

@@ -7363,7 +7223,7 @@ if enabled icc; then
    # icc 11.0 and 11.1 work with ebp_available, but don't pass the test
    enable ebp_available
    # The test above does not test linking
-    [ -n "$lto" ] && disable symver_asm_label
+    enabled lto && disable symver_asm_label
    if enabled x86_32; then
        icc_version=$($cc -dumpversion)
        test ${icc_version%%.*} -ge 11 &&
@@ -7495,6 +7355,12 @@ esac

 enable frame_thread_encoder

+# these filters depend on removed avcodec APIs
+# they are kept disabled for now, but will be removed if
+# nobody updates and re-enables them
+disable mcdeint_filter
+disable uspp_filter
+
 enabled asm || { arch=c; disable $ARCH_LIST $ARCH_EXT_LIST; }

 check_deps $CONFIG_LIST       \
@@ -7712,8 +7578,7 @@ if enabled x86; then
 fi
 if enabled aarch64; then
    echo "NEON enabled              ${neon-no}"
-    echo "DOTPROD enabled           ${dotprod-no}"
-    echo "I8MM enabled              ${i8mm-no}"
+    echo "VFP enabled               ${vfp-no}"
 fi
 if enabled arm; then
    echo "ARMv5TE enabled           ${armv5te-no}"
@@ -8004,9 +7869,6 @@ test -n "$assert_level" &&
 test -n "$malloc_prefix" &&
    echo "#define MALLOC_PREFIX $malloc_prefix" >>$TMPH

-enabled aarch64 &&
-    echo "#define AS_ARCH_LEVEL $as_arch_level" >>$TMPH
-
 if enabled x86asm; then
    append config_files $TMPASM
    cat > $TMPASM <<EOF
--- a/doc/APIchanges
+++ b/doc/APIchanges
@@ -2,178 +2,6 @@ The last version increases of all libraries were on 2023-02-09

 API changes, most recent first:

-------- 8< --------- FFmpeg 6.1 was cut here -------- 8< ---------
-
-2023-10-27 - xxxxxxxxxx - lavu 58.28.100 - channel_layout.h
-  Add AV_CH_LAYOUT_3POINT1POINT2 and AV_CHANNEL_LAYOUT_3POINT1POINT2.
-  Add AV_CH_LAYOUT_5POINT1POINT2_BACK and AV_CHANNEL_LAYOUT_5POINT1POINT2_BACK.
-  Add AV_CH_LAYOUT_5POINT1POINT4_BACK and AV_CHANNEL_LAYOUT_5POINT1POINT4_BACK.
-  Add AV_CH_LAYOUT_7POINT1POINT2 and AV_CHANNEL_LAYOUT_7POINT1POINT2.
-  Add AV_CH_LAYOUT_7POINT1POINT4_BACK and AV_CHANNEL_LAYOUT_7POINT1POINT4_BACK.
-
-2023-10-06 - xxxxxxxxxx - lavc 60.30.101 - avcodec.h
-  AVCodecContext.coded_side_data may now be used during decoding, to be set
-  by user before calling avcodec_open2() for initialization.
-
-2023-10-06 - xxxxxxxxxx - lavc 60.15.100 - avformat.h
-  Deprecate AVFormatContext.{nb_,}side_data, av_stream_add_side_data(),
-  av_stream_new_side_data(), and av_stream_get_side_data(). Side data fields
-  from AVFormatContext.codecpar should be used from now on.
-
-2023-10-06 - xxxxxxxxxx - lavc 60.30.100 - codec_par.h
-  Added {nb_,}coded_side_data to AVCodecParameters.
-  The AVCodecParameters helpers will copy it to and from its AVCodecContext
-  namesake.
-
-2023-10-06 - xxxxxxxxxx - lavc 60.29.100 - packet.h
-  Added av_packet_side_data_new(), av_packet_side_data_add(),
-  av_packet_side_data_get(), av_packet_side_data_remove, and
-  av_packet_side_data_free().
-
-2023-10-03 - xxxxxxxxxx - lavc 60.28.100 - codec_par.h defs.h
-  Move the definition of enum AVFieldOrder from codec_par.h to defs.h.
-
-2023-10-03 - xxxxxxxxxx - lavf 60.14.100 - avformat.h
-  Deprecate AVFMT_ALLOW_FLUSH without replacement. Users can always
-  flush any muxer by sending a NULL packet.
-
-2023-09-28 - xxxxxxxxxx - lavu 58.27.100 - pixfmt.h
-  Add AV_PIX_FMT_GBRAP14BE, AV_PIX_FMT_GBRAP14LE pixel formats.
-
-2023-09-28 - xxxxxxxxxx - lavu 58.26.100 - hwcontext_cuda.h
-  Add AV_CUDA_USE_CURRENT_CONTEXT.
-
-2023-09-19 - xxxxxxxxxx - lavu 58.25.100 - avutil.h
-  Make AV_TIME_BASE_Q compatible with C++.
-
-2023-09-xx - xxxxxxxxxx - lavf 60 - avformat.h
-  Deprecate AVFMT_FLAG_SHORTEST without replacement.
-
-2023-09-07 - xxxxxxxxxx - lavu 58.24.100 - imgutils.h
-  Add av_image_copy2(), a wrapper around the av_image_copy()
-  to overcome limitations of automatic conversions.
-
-2023-09-07 - xxxxxxxxxx - lavu 58.23.100 - fifo.h
-  Constify the AVFifo pointees in av_fifo_peek() and av_fifo_peek_to_cb().
-
-2023-09-07 - xxxxxxxxxx - lavu 58.22.100 - audio_fifo.h
-  Constify some pointees in av_audio_fifo_write(), av_audio_fifo_read(),
-  av_audio_fifo_peek() and av_audio_fifo_peek_at().
-
-2023-09-07 - xxxxxxxxxx - lavu 58.21.100 - samplefmt.h
-  Constify some pointees in av_samples_copy() and av_samples_set_silence().
-
-2023-09-07 - xxxxxxxxxx - lavu 58.20.100 - imgutils.h
-  Constify some pointees in av_image_copy(), av_image_copy_uc_from() and
-  av_image_fill_black().
-
-2023-09-07 - xxxxxxxxxx - lavf 60.12.100 - avio.h
-  Constify the buffer pointees in the write_packet and write_data_type
-  callbacks of AVIOContext on the next major bump.
-
-2023-09-07 - xxxxxxxxxx - lavc 60.26.100 - defs.h
-  Add AV_PROFILE_* and AV_LEVEL_* replacements in defs.h for the
-  defines from avcodec.h. The latter are deprecated.
-
-2023-09-06 - xxxxxxxxxx - lavc 60.25.101 - avcodec.h
-  AVCodecContext.rc_buffer_size may now be set by decoders.
-
-2023-09-02 - xxxxxxxxxx - lavu 58.19.100 - executor.h
-  Add AVExecutor API
-
-2023-09-xx - xxxxxxxxxx - lavc 60.25.100 - avfft.h
-  The entire header will be deprecated and removed in two major bumps.
-  For a replacement to av_dct, av_rdft, av_fft and av_mdct, use
-  the new API from libavutil/tx.h.
-
-2023-07-xx - xxxxxxxxxx - lavu 58.18.100 - tx.h
-  Add AV_TX_REAL_TO_REAL and AV_TX_REAL_TO_IMAGINARY
-
-2023-08-18 - xxxxxxxxxx - lavu 58.17.100 - channel_layout.h
-  All AV_CHANNEL_LAYOUT_* macros are now compatible with C++ 17 and older.
-
-2023-08-08 - xxxxxxxxxx - lavu 58.15.100 - video_hint.h
-  Add AVVideoHint API.
-
-2023-07-xx - xxxxxxxxxx - lavc 60 - avcodec.h
-  Deprecate AV_CODEC_FLAG_DROPCHANGED without replacement.
-
-2023-07-05 - xxxxxxxxxx - lavu 58.14.100 - random_seed.h
-  Add av_random_bytes()
-
-2023-05-29 - xxxxxxxxxx - lavc 60.16.100 - avcodec.h codec_id.h
-  Add AV_CODEC_ID_EVC, FF_PROFILE_EVC_BASELINE, and FF_PROFILE_EVC_MAIN.
-
-2023-05-29 - xxxxxxxxxx - lavu 58.12.100 - mathematics.h
-  Add av_bessel_i0()
-
-2023-05-xx - xxxxxxxxxx - lavc 60.15.100 - avcodec.h
-  Add AVHWAccel.update_thread_context, AVHWAccel.free_frame_priv,
-  AVHWAccel.flush.
-
-2023-05-xx - xxxxxxxxxx - lavu 58.11.100 - hwcontext_vulkan.h
-  Add AVVulkanDeviceContext.lock_queue, AVVulkanDeviceContext.unlock_queue,
-  AVVulkanFramesContext.format, AVVulkanFramesContext.lock_frame,
-  AVVulkanFramesContext.unlock_frame, AVVkFrame.queue_family.
-  Deprecate AV_VK_FRAME_FLAG_CONTIGUOUS_MEMORY (use multiplane images instead).
-
-2023-05-xx - xxxxxxxxxx - lavu 58.10.100 - pixfmt.h
-  Add AV_PIX_FMT_P212BE, AV_PIX_FMT_P212LE, AV_PIX_FMT_P412BE,
-  AV_PIX_FMT_P412LE.
-
-2023-05-xx - xxxxxxxxxx - lavu 58.8.100 - frame.h
-  Add av_frame_replace().
-
-2023-05-xx - xxxxxxxxxx - lavu 58 - frame.h
-  Deprecate AVFrame.palette_has_changed without replacement.
-
-2023-05-xx - xxxxxxxxxx - lavc 60 - avcodec.h
-  Depreate AVCodecContext.ticks_per_frame in favor of
-  AVCodecContext.framerate (encoding) and
-  AV_CODEC_PROP_FIELDS (decoding).
-
-2023-05-xx - xxxxxxxxxx - lavc 60.12.100 - codec_desc.h
-  Add AV_CODEC_PROP_FIELDS.
-
-2023-05-xx - xxxxxxxxxx - lavc 60 - codec.h
-  Depreate AV_CODEC_CAP_SUBFRAMES without replacement.
-
-2023-05-xx - xxxxxxxxxx - lavc 60.11.100 - codec_par.h
-  Add AVCodecParameters.framerate.
-
-2023-05-04 - xxxxxxxxxx - lavu 58.7.100 - frame.h
-  Deprecate AVFrame.interlaced_frame, AVFrame.top_field_first, and
-  AVFrame.key_frame.
-  Add AV_FRAME_FLAG_INTERLACED, AV_FRAME_FLAG_TOP_FIELD_FIRST, and
-  AV_FRAME_FLAG_KEY flags as replacement.
-
-2023-04-10 - xxxxxxxxxx - lavu 58.6.100 - frame.h
-  av_frame_get_plane_buffer() now accepts const AVFrame*.
-
-2023-04-04 - xxxxxxxxxx - lavu 58.6.100 - hdr_dynamic_metadata.h
-  Add AV_HDR_PLUS_MAX_PAYLOAD_SIZE.
-  av_dynamic_hdr_plus_create_side_data() now accepts a user provided
-  buffer.
-
-2023-03-xx - xxxxxxxxxx - lavfi 9.5.100 - avfilter.h
-  Add AVFILTER_FLAG_HWDEVICE.
-
-2023-03-21 - xxxxxxxxxx - lavu 58.5.100 - hdr_dynamic_metadata.h
-  Add av_dynamic_hdr_plus_from_t35() and av_dynamic_hdr_plus_to_t35()
-  functions to convert between raw T.35 payloads containing dynamic
-  HDR10+ metadata and their parsed representations as AVDynamicHDRPlus.
-
-2023-03-17 - xxxxxxxxxx - lavu 58.4.100 - hdr_dynamic_vivid_metadata.h
-  Add two group of three spline params.
-  Deprecate previous define which only supports one group of params.
-
-2023-03-02 - xxxxxxxxxx - lavc 60.6.100 - avcodec.h
-  Add FF_PROFILE_EAC3_DDP_ATMOS, FF_PROFILE_TRUEHD_ATMOS,
-  FF_PROFILE_DTS_HD_MA_X and FF_PROFILE_DTS_HD_MA_X_IMAX.
-
-2023-02-25 - xxxxxxxxxx - lavc 60.5.100 - avcodec.h
-  Add FF_PROFILE_HEVC_SCC.
-
 -------- 8< --------- FFmpeg 6.0 was cut here -------- 8< ---------

 2023-02-16 - 927042b409 - lavf 60.2.100 - avformat.h
--- a/doc/Doxyfile
+++ b/doc/Doxyfile
@@ -38,7 +38,7 @@ PROJECT_NAME           = FFmpeg
 # could be handy for archiving the generated documentation or if some version
 # control system is used.

-PROJECT_NUMBER         =
+PROJECT_NUMBER         = 6.0.1

 # Using the PROJECT_BRIEF tag one can provide an optional one line description
 # for a project that appears at the top of each page and should give viewer a
--- a/doc/Makefile
+++ b/doc/Makefile
@@ -19,7 +19,6 @@ MANPAGES3   = $(LIBRARIES-yes:%=doc/%.3)
 MANPAGES    = $(MANPAGES1) $(MANPAGES3)
 PODPAGES    = $(AVPROGS-yes:%=doc/%.pod)  $(AVPROGS-yes:%=doc/%-all.pod)  $(COMPONENTS-yes:%=doc/%.pod)  $(LIBRARIES-yes:%=doc/%.pod)
 HTMLPAGES   = $(AVPROGS-yes:%=doc/%.html) $(AVPROGS-yes:%=doc/%-all.html) $(COMPONENTS-yes:%=doc/%.html) $(LIBRARIES-yes:%=doc/%.html) \
-              doc/community.html                                        \
              doc/developer.html                                        \
              doc/faq.html                                              \
              doc/fate.html                                             \
--- a/doc/bootstrap.min.css
+++ b/doc/bootstrap.min.css
--- a/doc/codecs.texi
+++ b/doc/codecs.texi
@@ -697,13 +697,10 @@ profiles are documented in the relevant encoder documentation.

@item level @var{integer} (@emph{encoding,audio,video})

-Set the encoder level. This level depends on the specific codec, and
-might correspond to the profile level. It is set by default to
-@samp{unknown}.
-
 Possible values:
@table @samp
@item unknown
+
@end table

@item lowres @var{integer} (@emph{decoding,audio,video})
@@ -778,6 +775,7 @@ Possible values:
@end table
@item rc_max_vbv_use @var{float} (@emph{encoding,video})
@item rc_min_vbv_use @var{float} (@emph{encoding,video})
+@item ticks_per_frame @var{integer} (@emph{decoding/encoding,audio,video})

@item color_primaries @var{integer} (@emph{decoding/encoding,video})
 Possible values:
@@ -892,11 +890,9 @@ Possible values:
@table @samp
@item tv
@item mpeg
-@item limited
 MPEG (219*2^(n-8))
@item pc
@item jpeg
-@item full
 JPEG (2^n-1)
@end table

--- a/doc/community.texi
+++ b/doc/community.texi
@@ -1,175 +0,0 @@
-\input texinfo @c -*- texinfo -*-
-@documentencoding UTF-8
-
-@settitle Community
-@titlepage
-@center @titlefont{Community}
-@end titlepage
-
-@top
-
-@contents
-
-@anchor{Organisation}
-@chapter Organisation
-
-The FFmpeg project is organized through a community working on global consensus.
-
-Decisions are taken by the ensemble of active members, through voting and are aided by two committees.
-
-@anchor{General Assembly}
-@chapter General Assembly
-
-The ensemble of active members is called the General Assembly (GA).
-
-The General Assembly is sovereign and legitimate for all its decisions regarding the FFmpeg project.
-
-The General Assembly is made up of active contributors.
-
-Contributors are considered "active contributors" if they have pushed more than 20 patches in the last 36 months in the main FFmpeg repository, or if they have been voted in by the GA.
-
-Additional members are added to the General Assembly through a vote after proposal by a member of the General Assembly. They are part of the GA for two years, after which they need a confirmation by the GA.
-
-A script to generate the current members of the general assembly (minus members voted in) can be found in `tools/general_assembly.pl`.
-
-@anchor{Voting}
-@chapter Voting
-
-Voting is done using a ranked voting system, currently running on https://vote.ffmpeg.org/ .
-
-Majority vote means more than 50% of the expressed ballots.
-
-@anchor{Technical Committee}
-@chapter Technical Committee
-
-The Technical Committee (TC) is here to arbitrate and make decisions when technical conflicts occur in the project. They will consider the merits of all the positions, judge them and make a decision.
-
-The TC resolves technical conflicts but is not a technical steering committee.
-
-Decisions by the TC are binding for all the contributors.
-
-Decisions made by the TC can be re-opened after 1 year or by a majority vote of the General Assembly, requested by one of the member of the GA.
-
-The TC is elected by the General Assembly for a duration of 1 year, and is composed of 5 members. Members can be re-elected if they wish. A majority vote in the General Assembly can trigger a new election of the TC.
-
-The members of the TC can be elected from outside of the GA. Candidates for election can either be suggested or self-nominated.
-
-The conflict resolution process is detailed in the resolution process document.
-
-The TC can be contacted at <tc@@ffmpeg>.
-
-@anchor{Resolution Process}
-@section Resolution Process
-
-The Technical Committee (TC) is here to arbitrate and make decisions when technical conflicts occur in the project.
-
-The TC main role is to resolve technical conflicts. It is therefore not a technical steering committee, but it is understood that some decisions might impact the future of the project.
-
-@subsection Seizing
-
-The TC can take possession of any technical matter that it sees fit.
-
-To involve the TC in a matter, email tc@ or CC them on an ongoing discussion.
-
-As members of TC are developers, they also can email tc@ to raise an issue.
-@subsection Announcement
-
-The TC, once seized, must announce itself on the main mailing list, with a [TC] tag.
-
-The TC has 2 modes of operation: a RFC one and an internal one.
-
-If the TC thinks it needs the input from the larger community, the TC can call for a RFC. Else, it can decide by itself.
-
-If the disagreement involves a member of the TC, that member should recuse themselves from the decision.
-
-The decision to use a RFC process or an internal discussion is a discretionary decision of the TC.
-
-The TC can also reject a seizure for a few reasons such as: the matter was not discussed enough previously; it lacks expertise to reach a beneficial decision on the matter; or the matter is too trivial.
-@subsection RFC call
-
-In the RFC mode, one person from the TC posts on the mailing list the technical question and will request input from the community.
-
-The mail will have the following specification:
-
-    a precise title
-    a specific tag [TC RFC]
-    a top-level email
-    contain a precise question that does not exceed 100 words and that is answerable by developers
-    may have an extra description, or a link to a previous discussion, if deemed necessary,
-    contain a precise end date for the answers.
-
-The answers from the community must be on the main mailing list and must have the following specification:
-
-    keep the tag and the title unchanged
-    limited to 400 words
-    a first-level, answering directly to the main email
-    answering to the question.
-
-Further replies to answers are permitted, as long as they conform to the community standards of politeness, they are limited to 100 words, and are not nested more than once. (max-depth=2)
-
-After the end-date, mails on the thread will be ignored.
-
-Violations of those rules will be escalated through the Community Committee.
-
-After all the emails are in, the TC has 96 hours to give its final decision. Exceptionally, the TC can request an extra delay, that will be notified on the mailing list.
-@subsection Within TC
-
-In the internal case, the TC has 96 hours to give its final decision. Exceptionally, the TC can request an extra delay.
-@subsection Decisions
-
-The decisions from the TC will be sent on the mailing list, with the [TC] tag.
-
-Internally, the TC should take decisions with a majority, or using ranked-choice voting.
-
-The decision from the TC should be published with a summary of the reasons that lead to this decision.
-
-The decisions from the TC are final, until the matters are reopened after no less than one year.
-
-@anchor{Community Committee}
-@chapter Community Committee
-
-The Community Committee (CC) is here to arbitrage and make decisions when inter-personal conflicts occur in the project. It will decide quickly and take actions, for the sake of the project.
-
-The CC can remove privileges of offending members, including removal of commit access and temporary ban from the community.
-
-Decisions made by the CC can be re-opened after 1 year or by a majority vote of the General Assembly. Indefinite bans from the community must be confirmed by the General Assembly, in a majority vote.
-
-The CC is elected by the General Assembly for a duration of 1 year, and is composed of 5 members. Members can be re-elected if they wish. A majority vote in the General Assembly can trigger a new election of the CC.
-
-The members of the CC can be elected from outside of the GA. Candidates for election can either be suggested or self-nominated.
-
-The CC is governed by and responsible for enforcing the Code of Conduct.
-
-The CC can be contacted at <cc@@ffmpeg>.
-
-@anchor{Code of Conduct}
-@chapter Code of Conduct
-
-Be friendly and respectful towards others and third parties.
-Treat others the way you yourself want to be treated.
-
-Be considerate. Not everyone shares the same viewpoint and priorities as you do.
-Different opinions and interpretations help the project.
-Looking at issues from a different perspective assists development.
-
-Do not assume malice for things that can be attributed to incompetence. Even if
-it is malice, it's rarely good to start with that as initial assumption.
-
-Stay friendly even if someone acts contrarily. Everyone has a bad day
-once in a while.
-If you yourself have a bad day or are angry then try to take a break and reply
-once you are calm and without anger if you have to.
-
-Try to help other team members and cooperate if you can.
-
-The goal of software development is to create technical excellence, not for any
-individual to be better and "win" against the others. Large software projects
-are only possible and successful through teamwork.
-
-If someone struggles do not put them down. Give them a helping hand
-instead and point them in the right direction.
-
-Finally, keep in mind the immortal words of Bill and Ted,
-"Be excellent to each other."
-
-@bye
--- a/doc/decoders.texi
+++ b/doc/decoders.texi
@@ -353,156 +353,6 @@ Enabled by default.

@end table

-@section libaribcaption
-
-Yet another ARIB STD-B24 caption decoder using external @dfn{libaribcaption}
-library.
-
-Implements profiles A and C of the Japanse ARIB STD-B24 standard,
-Brazilian ABNT NBR 15606-1, and Philippines version of ISDB-T.
-
-Requires the presence of the libaribcaption headers and library
-(@url{https://github.com/xqq/libaribcaption}) during configuration.
-You need to explicitly configure the build with @code{--enable-libaribcaption}.
-If both @dfn{libaribb24} and @dfn{libaribcaption} are enabled, @dfn{libaribcaption}
-decoder precedes.
-
-@subsection libaribcaption Decoder Options
-
-@table @option
-
-@item -sub_type @var{subtitle_type}
-Specifies the format of the decoded subtitles.
-
-@table @samp
-@item bitmap
-Graphical image.
-@item ass
-ASS formatted text.
-@item text
-Simple text based output without formatting.
-@end table
-
-The default is @dfn{ass} as same as @dfn{libaribb24} decoder.
-Some present players (e.g., @dfn{mpv}) expect ASS format for ARIB caption.
-
-@item -caption_encoding @var{encoding_scheme}
-Specifies the encoding scheme of input subtitle text.
-
-@table @samp
-@item auto
-Automatically detect text encoding.
-@item jis
-8bit-char JIS encoding defined in ARIB STD B24.
-This encoding used in Japan for ISDB captions.
-@item utf8
-UTF-8 encoding defined in ARIB STD B24.
-This encoding is used in Philippines for ISDB-T captions.
-@item latin
-Latin character encoding defined in ABNT NBR 15606-1.
-This encoding is used in South America for SBTVD / ISDB-Tb captions.
-@end table
-
-The default is @dfn{ass} as same as @dfn{libaribb24} decoder.
-Some present players (e.g., @dfn{mpv}) expect ASS format for ARIB caption.
-
-@item -font @var{font_name[,font_name2,...]}
-Specify comma-separated list of font family names to be used for @dfn{bitmap}
-or @dfn{ass} type subtitle rendering.
-Only first font name is used for @dfn{ass} type subtitle.
-
-If not specified, use internaly defined default font family.
-
-@item -ass_single_rect @var{boolean}
-ARIB STD-B24 specifies that some captions may be displayed at different
-positions at a time (multi-rectangle subtitle).
-Since some players (e.g., old @dfn{mpv}) can't handle multiple ASS rectangles
-in a single AVSubtitle, or multiple ASS rectangles of indeterminate duration
-with the same start timestamp, this option can change the behavior so that
-all the texts are displayed in a single ASS rectangle.
-
-The default is @var{false}.
-
-If your player cannot handle AVSubtitles with multiple ASS rectangles properly,
-set this option to @var{true} or define @env{ASS_SINGLE_RECT=1} to change
-default behavior at compilation.
-
-@item -replace_fullwidth_ascii @var{boolean}
-Specify whether to replace MSZ (Middle Size, half width) fullwidth
-alphanumerics with halfwidth alphanumerics.
-
-The default is @var{true}.
-
-@item -force_outline_text @var{boolean}
-Specify whether always render outline text for all characters regardless of
-the indication by charactor style.
-
-The default is @var{false}.
-
-@item -outline_width @var{number} (0.0 - 3.0)
-Specify width for outline text, in dots (relative).
-
-The default is @var{1.5}.
-
-@item -ignore_background @var{boolean}
-Specify whether to ignore background color rendering.
-
-The default is @var{false}.
-
-@item -ignore_ruby @var{boolean}
-Specify whether to ignore rendering for ruby-like (furigana) characters.
-
-The default is @var{false}.
-
-@item -replace_drcs @var{boolean}
-Specify whether to render replaced DRCS characters as Unicode characters.
-
-The default is @var{true}.
-
-@item -canvas_size @var{image_size}
-Specify the resolution of the canvas to render subtitles to; usually, this
-should be frame size of input video.
-This only applies when @code{-subtitle_type} is set to @var{bitmap}.
-
-The libaribcaption decoder assumes input frame size for bitmap rendering as below:
-@enumerate
-@item
-PROFILE_A : 1440 x 1080 with SAR (PAR) 4:3
-@item
-PROFILE_C : 320 x 180 with SAR (PAR) 1:1
-@end enumerate
-
-If actual frame size of input video does not match above assumption,
-the rendered captions may be distorted.
-To make the captions undistorted, add @code{-canvas_size} option to specify
-actual input video size.
-
-Note that the @code{-canvas_size} option is not required for video with
-different size but same aspect ratio.
-In such cases, the caption will be stretched or shrunk to actual video size
-if @code{-canvas_size} option is not specified.
-If @code{-canvas_size} option is specified with different size,
-the caption will be stretched or shrunk as specified size with calculated SAR.
-
-@end table
-
-@subsection libaribcaption decoder usage examples
-
-Display MPEG-TS file with ARIB subtitle by @code{ffplay} tool:
-@example
-ffplay -sub_type bitmap MPEG.TS
-@end example
-
-Display MPEG-TS file with input frame size 1920x1080 by @code{ffplay} tool:
-@example
-ffplay -sub_type bitmap -canvas_size 1920x1080 MPEG.TS
-@end example
-
-Embed ARIB subtitle in transcoded video:
-@example
-ffmpeg -sub_type bitmap -i src.m2t -filter_complex "[0:v][0:s]overlay" -vcodec h264 dest.mp4
-@end example
-
@section dvbsub

@subsection Options
--- a/doc/demuxers.texi
+++ b/doc/demuxers.texi
@@ -307,15 +307,7 @@ stream which contains the alpha channel in addition to the ordinary video.

 Interoperable Master Format demuxer.

-This demuxer presents audio and video streams found in an IMF Composition, as
-specified in @url{https://doi.org/10.5594/SMPTE.ST2067-2.2020, SMPTE ST 2067-2}.
-
-@example
-ffmpeg [-assetmaps <path of ASSETMAP1>,<path of ASSETMAP2>,...] -i <path of CPL> ...
-@end example
-
-If @code{-assetmaps} is not specified, the demuxer looks for a file called
-@file{ASSETMAP.xml} in the same directory as the CPL.
+This demuxer presents audio and video streams found in an IMF Composition.

@section flv, live_flv, kux

@@ -779,13 +771,6 @@ cast to int32 are used to adjust onward dts.

 Unit is the track time scale. Range is 0 to UINT_MAX. Default is @code{UINT_MAX - 48000*10} which allows upto
 a 10 second dts correction for 48 kHz audio streams while accommodating 99.9% of @code{uint32} range.
-
-@item interleaved_read
-Interleave packets from multiple tracks at demuxer level. For badly interleaved files, this prevents playback issues
-caused by large gaps between packets in different tracks, as MOV/MP4 do not have packet placement requirements.
-However, this can cause excessive seeking on very badly interleaved files, due to seeking between tracks, so disabling
-it may prevent I/O issues, at the expense of playback.
-
@end table

@subsection Audible AAX
--- a/doc/dev_community/community.md
+++ b/doc/dev_community/community.md
@@ -0,0 +1,82 @@
+# FFmpeg project
+
+## Organisation
+
+The FFmpeg project is organized through a community working on global consensus.
+
+Decisions are taken by the ensemble of active members, through voting and
+are aided by two committees.
+
+## General Assembly
+
+The ensemble of active members is called the General Assembly (GA).
+
+The General Assembly is sovereign and legitimate for all its decisions
+regarding the FFmpeg project.
+
+The General Assembly is made up of active contributors.
+
+Contributors are considered "active contributors" if they have pushed more
+than 20 patches in the last 36 months in the main FFmpeg repository, or
+if they have been voted in by the GA.
+
+Additional members are added to the General Assembly through a vote after
+proposal by a member of the General Assembly.
+They are part of the GA for two years, after which they need a confirmation by
+the GA.
+
+A script to generate the current members of the general assembly (minus members
+voted in) can be found in `tools/general_assembly.pl`.
+
+## Voting
+
+Voting is done using a ranked voting system, currently running on https://vote.ffmpeg.org/ .
+
+Majority vote means more than 50% of the expressed ballots.
+
+## Technical Committee
+
+The Technical Committee (TC) is here to arbitrate and make decisions when
+technical conflicts occur in the project.
+They will consider the merits of all the positions, judge them and make a
+decision.
+
+The TC resolves technical conflicts but is not a technical steering committee.
+
+Decisions by the TC are binding for all the contributors.
+
+Decisions made by the TC can be re-opened after 1 year or by a majority vote
+of the General Assembly, requested by one of the member of the GA.
+
+The TC is elected by the General Assembly for a duration of 1 year, and
+is composed of 5 members.
+Members can be re-elected if they wish. A majority vote in the General Assembly
+can trigger a new election of the TC.
+
+The members of the TC can be elected from outside of the GA.
+Candidates for election can either be suggested or self-nominated.
+
+The conflict resolution process is detailed in the [resolution process](resolution_process.md) document.
+
+## Community committee
+
+The Community Committee (CC) is here to arbitrage and make decisions when
+inter-personal conflicts occur in the project. It will decide quickly and
+take actions, for the sake of the project.
+
+The CC can remove privileges of offending members, including removal of
+commit access and temporary ban from the community.
+
+Decisions made by the CC can be re-opened after 1 year or by a majority vote
+of the General Assembly. Indefinite bans from the community must be confirmed
+by the General Assembly, in a majority vote.
+
+The CC is elected by the General Assembly for a duration of 1 year, and is
+composed of 5 members.
+Members can be re-elected if they wish. A majority vote in the General Assembly
+can trigger a new election of the CC.
+
+The members of the CC can be elected from outside of the GA.
+Candidates for election can either be suggested or self-nominated.
+
+The CC is governed by and responsible for enforcing the Code of Conduct.
--- a/doc/dev_community/resolution_process.md
+++ b/doc/dev_community/resolution_process.md
@@ -0,0 +1,91 @@
+# Technical Committee
+
+_This document only makes sense with the rules from [the community document](community)_.
+
+The Technical Committee (**TC**) is here to arbitrate and make decisions when
+technical conflicts occur in the project.
+
+The TC main role is to resolve technical conflicts.
+It is therefore not a technical steering committee, but it is understood that
+some decisions might impact the future of the project.
+
+# Process
+
+## Seizing
+
+The TC can take possession of any technical matter that it sees fit.
+
+To involve the TC in a matter, email tc@ or CC them on an ongoing discussion.
+
+As members of TC are developers, they also can email tc@ to raise an issue.
+
+## Announcement
+
+The TC, once seized, must announce itself on the main mailing list, with a _[TC]_ tag.
+
+The TC has 2 modes of operation: a RFC one and an internal one.
+
+If the TC thinks it needs the input from the larger community, the TC can call
+for a RFC. Else, it can decide by itself.
+
+If the disagreement involves a member of the TC, that member should recuse
+themselves from the decision.
+
+The decision to use a RFC process or an internal discussion is a discretionary
+decision of the TC.
+
+The TC can also reject a seizure for a few reasons such as:
+the matter was not discussed enough previously; it lacks expertise to reach a
+beneficial decision on the matter; or the matter is too trivial.
+
+### RFC call
+
+In the RFC mode, one person from the TC posts on the mailing list the
+technical question and will request input from the community.
+
+The mail will have the following specification:
+* a precise title
+* a specific tag [TC RFC]
+* a top-level email
+* contain a precise question that does not exceed 100 words and that is answerable by developers
+* may have an extra description, or a link to a previous discussion, if deemed necessary,
+* contain a precise end date for the answers.
+
+The answers from the community must be on the main mailing list and must have
+the following specification:
+* keep the tag and the title unchanged
+* limited to 400 words
+* a first-level, answering directly to the main email
+* answering to the question.
+
+Further replies to answers are permitted, as long as they conform to the
+community standards of politeness, they are limited to 100 words, and are not
+nested more than once. (max-depth=2)
+
+After the end-date, mails on the thread will be ignored.
+
+Violations of those rules will be escalated through the Community Committee.
+
+After all the emails are in, the TC has 96 hours to give its final decision.
+Exceptionally, the TC can request an extra delay, that will be notified on the
+mailing list.
+
+### Within TC
+
+In the internal case, the TC has 96 hours to give its final decision.
+Exceptionally, the TC can request an extra delay.
+
+
+## Decisions
+
+The decisions from the TC will be sent on the mailing list, with the _[TC]_ tag.
+
+Internally, the TC should take decisions with a majority, or using
+ranked-choice voting.
+
+The decision from the TC should be published with a summary of the reasons that
+lead to this decision.
+
+The decisions from the TC are final, until the matters are reopened after
+no less than one year.
+
--- a/doc/developer.texi
+++ b/doc/developer.texi
@@ -24,10 +24,6 @@ generated from the headers
 the examples under @file{doc/examples}
@end itemize

-For more detailed legal information about the use of FFmpeg in
-external programs read the @file{LICENSE} file in the source tree and
-consult @url{https://ffmpeg.org/legal.html}.
-
 If you modify FFmpeg code for your own use case, you are highly encouraged to
@emph{submit your changes back to us}, using this document as a guide. There are
 both pragmatic and ideological reasons to do so:
@@ -44,6 +40,12 @@ By supporting the project you find useful you ensure it continues to be
 maintained and developed.
@end itemize

+For more detailed legal information about the use of FFmpeg in
+external programs read the @file{LICENSE} file in the source tree and
+consult @url{https://ffmpeg.org/legal.html}.
+
+@section Contributing code
+
 All proposed code changes should be submitted for review to
@url{mailto:ffmpeg-devel@@ffmpeg.org, the development mailing list}, as
 described in more detail in the @ref{Submitting patches} chapter. The code
@@ -54,9 +56,9 @@ and should try to fix issues their commit causes.
@anchor{Coding Rules}
@chapter Coding Rules

-@section Language
+@section C language features

-FFmpeg is mainly programmed in the ISO C99 language, extended with:
+FFmpeg is programmed in the ISO C99 language, extended with:
@itemize @bullet
@item
 Atomic operations from C11 @file{stdatomic.h}. They are emulated on
@@ -81,44 +83,6 @@ complex numbers;
 mixed statements and declarations.
@end itemize

-@subsection SIMD/DSP
-@anchor{SIMD/DSP}
-
-As modern compilers are unable to generate efficient SIMD or other
-performance-critical DSP code from plain C, handwritten assembly is used.
-Usually such code is isolated in a separate function. Then the standard approach
-is writing multiple versions of this function – a plain C one that works
-everywhere and may also be useful for debugging, and potentially multiple
-architecture-specific optimized implementations. Initialization code then
-chooses the best available version at runtime and loads it into a function
-pointer; the function in question is then always called through this pointer.
-
-The specific syntax used for writing assembly is:
-@itemize @bullet
-@item
-NASM on x86;
-
-@item
-GAS on ARM.
-@end itemize
-
-A unit testing framework for assembly called @code{checkasm} lives under
-@file{tests/checkasm}. All new assembly should come with @code{checkasm} tests;
-adding tests for existing assembly that lacks them is also strongly encouraged.
-
-@subsection Other languages
-
-Other languages than C may be used in special cases:
-@itemize @bullet
-@item
-Compiler intrinsics or inline assembly when the code in question cannot be
-written in the standard way described in the @ref{SIMD/DSP} section. This
-typically applies to code that needs to be inlined.
-
-@item
-Objective-C where required for interacting with macOS-specific interfaces.
-@end itemize
-
@section Code formatting conventions

 There are the following guidelines regarding the indentation in files:
@@ -215,7 +179,6 @@ int myfunc(int my_parameter)
 ...
@end example

-@anchor{Naming conventions}
@section Naming conventions

 Names of functions, variables, and struct members must be lowercase, using
@@ -274,6 +237,10 @@ symbols. If in doubt, just avoid names starting with @code{_} altogether.
@section Miscellaneous conventions

@itemize @bullet
+@item
+fprintf and printf are forbidden in libavformat and libavcodec,
+please use av_log() instead.
+
@item
 Casts should be used only when necessary. Unneeded parentheses
 should also be avoided if they don't make the code easier to understand.
@@ -282,42 +249,6 @@ should also be avoided if they don't make the code easier to understand.
@anchor{Development Policy}
@chapter Development Policy

-@section Code behaviour
-
-@subheading Correctness
-The code must be valid. It must not crash, abort, access invalid pointers, leak
-memory, cause data races or signed integer overflow, or otherwise cause
-undefined behaviour. Error codes should be checked and, when applicable,
-forwarded to the caller.
-
-@subheading Thread- and library-safety
-Our libraries may be called by multiple independent callers in the same process.
-These calls may happen from any number of threads and the different call sites
-may not be aware of each other - e.g. a user program may be calling our
-libraries directly, and use one or more libraries that also call our libraries.
-The code must behave correctly under such conditions.
-
-@subheading Robustness
-The code must treat as untrusted any bytestream received from a caller or read
-from a file, network, etc. It must not misbehave when arbitrary data is sent to
-it - typically it should print an error message and return
-@code{AVERROR_INVALIDDATA} on encountering invalid input data.
-
-@subheading Memory allocation
-The code must use the @code{av_malloc()} family of functions from
-@file{libavutil/mem.h} to perform all memory allocation, except in special cases
-(e.g. when interacting with an external library that requires a specific
-allocator to be used).
-
-All allocations should be checked and @code{AVERROR(ENOMEM)} returned on
-failure. A common mistake is that error paths leak memory - make sure that does
-not happen.
-
-@subheading stdio
-Our libraries must not access the stdio streams stdin/stdout/stderr directly
-(e.g. via @code{printf()} family of functions), as that is not library-safe. For
-logging, use @code{av_log()}.
-
@section Patches/Committing
@subheading Licenses for patches must be compatible with FFmpeg.
 Contributions should be licensed under the
@@ -340,24 +271,13 @@ missing samples or an implementation with a small subset of features.
 Always check the mailing list for any reviewers with issues and test
 FATE before you push.

-@subheading Commit messages
-Commit messages are highly important tools for informing other developers on
-what a given change does and why. Every commit must always have a properly
-filled out commit message with the following format:
-@example
-area changed: short 1 line description
-
-details describing what and why and giving references.
-@end example
-
-If the commit addresses a known bug on our bug tracker or other external issue
-(e.g. CVE), the commit message should include the relevant bug ID(s) or other
-external identifiers. Note that this should be done in addition to a proper
-explanation and not instead of it. Comments such as "fixed!" or "Changed it."
-are not acceptable.
-
-When applying patches that have been discussed at length on the mailing list,
-reference the thread in the commit message.
+@subheading Keep the main commit message short with an extended description below.
+The commit message should have a short first line in the form of
+a @samp{topic: short description} as a header, separated by a newline
+from the body consisting of an explanation of why the change is necessary.
+If the commit fixes a known bug on the bug tracker, the commit message
+should include its bug ID. Referring to the issue on the bug tracker does
+not exempt you from writing an excerpt of the bug in the commit message.

@subheading Testing must be adequate but not excessive.
 If it works for you, others, and passes FATE then it should be OK to commit
@@ -376,6 +296,15 @@ later on.
 Also if you have doubts about splitting or not splitting, do not hesitate to
 ask/discuss it on the developer mailing list.

+@subheading Ask before you change the build system (configure, etc).
+Do not commit changes to the build system (Makefiles, configure script)
+which change behavior, defaults etc, without asking first. The same
+applies to compiler warning fixes, trivial looking fixes and to code
+maintained by other developers. We usually have a reason for doing things
+the way we do. Send your changes as patches to the ffmpeg-devel mailing
+list, and if the code maintainers say OK, you may commit. This does not
+apply to files you wrote and/or maintain.
+
@subheading Cosmetic changes should be kept in separate patches.
 We refuse source indentation and other cosmetic changes if they are mixed
 with functional changes, such commits will be rejected and removed. Every
@@ -390,12 +319,28 @@ NOTE: If you had to put if()@{ .. @} over a large (> 5 lines) chunk of code,
 then either do NOT change the indentation of the inner part within (do not
 move it to the right)! or do so in a separate commit

+@subheading Commit messages should always be filled out properly.
+Always fill out the commit log message. Describe in a few lines what you
+changed and why. You can refer to mailing list postings if you fix a
+particular bug. Comments such as "fixed!" or "Changed it." are unacceptable.
+Recommended format:
+
+@example
+area changed: Short 1 line description
+
+details describing what and why and giving references.
+@end example
+
@subheading Credit the author of the patch.
 Make sure the author of the commit is set correctly. (see git commit --author)
 If you apply a patch, send an
 answer to ffmpeg-devel (or wherever you got the patch from) saying that
 you applied the patch.

+@subheading Complex patches should refer to discussion surrounding them.
+When applying patches that have been discussed (at length) on the mailing
+list, reference the thread in the log message.
+
@subheading Always wait long enough before pushing changes
 Do NOT commit to code actively maintained by others without permission.
 Send a patch to ffmpeg-devel. If no one answers within a reasonable
@@ -404,6 +349,22 @@ time-frame (12h for build failures and security fixes, 3 days small changes,
 Also note, the maintainer can simply ask for more time to review!

@section Code
+@subheading API/ABI changes should be discussed before they are made.
+Do not change behavior of the programs (renaming options etc) or public
+API or ABI without first discussing it on the ffmpeg-devel mailing list.
+Do not remove widely used functionality or features (redundant code can be removed).
+
+@subheading Remember to check if you need to bump versions for libav*.
+Depending on the change, you may need to change the version integer.
+Incrementing the first component means no backward compatibility to
+previous versions (e.g. removal of a function from the public API).
+Incrementing the second component means backward compatible change
+(e.g. addition of a function to the public API or extension of an
+existing data structure).
+Incrementing the third component means a noteworthy binary compatible
+change (e.g. encoder bug fix that matters for the decoder). The third
+component always starts at 100 to distinguish FFmpeg from Libav.
+
@subheading Warnings for correct code may be disabled if there is no other option.
 Compiler warnings indicate potential bugs or code with bad style. If a type of
 warning always points to correct and clean code, that warning should
@@ -413,150 +374,10 @@ If it is a bug, the bug has to be fixed. If it is not, the code should
 be changed to not generate a warning unless that causes a slowdown
 or obfuscates the code.

-@section Library public interfaces
-Every library in FFmpeg provides a set of public APIs in its installed headers,
-which are those listed in the variable @code{HEADERS} in that library's
-@file{Makefile}. All identifiers defined in those headers (except for those
-explicitly documented otherwise), and corresponding symbols exported from
-compiled shared or static libraries are considered public interfaces and must
-comply with the API and ABI compatibility rules described in this section.
-
-Public APIs must be backward compatible within a given major version. I.e. any
-valid user code that compiles and works with a given library version must still
-compile and work with any later version, as long as the major version number is
-unchanged. "Valid user code" here means code that is calling our APIs in a
-documented and/or intended manner and is not relying on any undefined behavior.
-Incrementing the major version may break backward compatibility, but only to the
-extent described in @ref{Major version bumps}.
-
-We also guarantee backward ABI compatibility for shared and static libraries.
-I.e. it should be possible to replace a shared or static build of our library
-with a build of any later version (re-linking the user binary in the static
-case) without breaking any valid user binaries, as long as the major version
-number remains unchanged.
-
-@subsection Adding new interfaces
-Any new public identifiers in installed headers are considered new API - this
-includes new functions, structs, macros, enum values, typedefs, new fields in
-existing structs, new installed headers, etc. Consider the following
-guidelines when adding new APIs.
-
-@subsubheading Motivation
-While new APIs can be added relatively easily, changing or removing them is much
-harder due to abovementioned compatibility requirements. You should then
-consider carefully whether the functionality you are adding really needs to be
-exposed to our callers as new public API.
-
-Your new API should have at least one well-established use case outside of the
-library that cannot be easily achieved with existing APIs. Every library in
-FFmpeg also has a defined scope - your new API must fit within it.
-
-@subsubheading Replacing existing APIs
-If your new API is replacing an existing one, it should be strictly superior to
-it, so that the advantages of using the new API outweight the cost to the
-callers of changing their code. After adding the new API you should then
-deprecate the old one and schedule it for removal, as described in
-@ref{Removing interfaces}.
-
-If you deem an existing API deficient and want to fix it, the preferred approach
-in most cases is to add a differently-named replacement and deprecate the
-existing API rather than modify it. It is important to make the changes visible
-to our callers (e.g. through compile- or run-time deprecation warnings) and make
-it clear how to transition to the new API (e.g. in the Doxygen documentation or
-on the wiki).
-
-@subsubheading API design
-The FFmpeg libraries are used by a variety of callers to perform a wide range of
-multimedia-related processing tasks. You should therefore - within reason - try
-to design your new API for the broadest feasible set of use cases and avoid
-unnecessarily limiting it to a specific type of callers (e.g. just media
-playback or just transcoding).
-
-@subsubheading Consistency
-Check whether similar APIs already exist in FFmpeg. If they do, try to model
-your new addition on them to achieve better overall consistency.
-
-The naming of your new identifiers should follow the @ref{Naming conventions}
-and be aligned with other similar APIs, if applicable.
-
-@subsubheading Extensibility
-You should also consider how your API might be extended in the future in a
-backward-compatible way. If you are adding a new struct @code{AVFoo}, the
-standard approach is requiring the caller to always allocate it through a
-constructor function, typically named @code{av_foo_alloc()}. This way new fields
-may be added to the end of the struct without breaking ABI compatibility.
-Typically you will also want a destructor - @code{av_foo_free(AVFoo**)} that
-frees the indirectly supplied object (and its contents, if applicable) and
-writes @code{NULL} to the supplied pointer, thus eliminating the potential
-dangling pointer in the caller's memory.
-
-If you are adding new functions, consider whether it might be desirable to tweak
-their behavior in the future - you may want to add a flags argument, even though
-it would be unused initially.
-
-@subsubheading Documentation
-All new APIs must be documented as Doxygen-formatted comments above the
-identifiers you add to the public headers. You should also briefly mention the
-change in @file{doc/APIchanges}.
-
-@subsubheading Bump the version
-Backward-incompatible API or ABI changes require incrementing (bumping) the
-major version number, as described in @ref{Major version bumps}. Major
-bumps are significant events that happen on a schedule - so if your change
-strictly requires one you should add it under @code{#if} preprocesor guards that
-disable it until the next major bump happens.
-
-New APIs that can be added without breaking API or ABI compatibility require
-bumping the minor version number.
-
-Incrementing the third (micro) version component means a noteworthy binary
-compatible change (e.g. encoder bug fix that matters for the decoder). The third
-component always starts at 100 to distinguish FFmpeg from Libav.
-
-@anchor{Removing interfaces}
-@subsection Removing interfaces
-Due to abovementioned compatibility guarantees, removing APIs is an involved
-process that should only be undertaken with good reason. Typically a deficient,
-restrictive, or otherwise inadequate API is replaced by a superior one, though
-it does at times happen that we remove an API without any replacement (e.g. when
-the feature it provides is deemed not worth the maintenance effort, out of scope
-of the project, fundamentally flawed, etc.).
-
-The removal has two steps - first the API is deprecated and scheduled for
-removal, but remains present and functional. The second step is actually
-removing the API - this is described in @ref{Major version bumps}.
-
-To deprecate an API you should signal to our users that they should stop using
-it. E.g. if you intend to remove struct members or functions, you should mark
-them with @code{attribute_deprecated}. When this cannot be done, it may be
-possible to detect the use of the deprecated API at runtime and print a warning
-(though take care not to print it too often). You should also document the
-deprecation (and the replacement, if applicable) in the relevant Doxygen
-documentation block.
-
-Finally, you should define a deprecation guard along the lines of
-@code{#define FF_API_<FOO> (LIBAVBAR_VERSION_MAJOR < XX)} (where XX is the major
-version in which the API will be removed) in @file{libavbar/version_major.h}
-(@file{version.h} in case of @code{libavutil}). Then wrap all uses of the
-deprecated API in @code{#if FF_API_<FOO> .... #endif}, so that the code will
-automatically get disabled once the major version reaches XX. You can also use
-@code{FF_DISABLE_DEPRECATION_WARNINGS} and @code{FF_ENABLE_DEPRECATION_WARNINGS}
-to suppress compiler deprecation warnings inside these guards. You should test
-that the code compiles and works with the guard macro evaluating to both true
-and false.
-
-@anchor{Major version bumps}
-@subsection Major version bumps
-A major version bump signifies an API and/or ABI compatibility break. To reduce
-the negative effects on our callers, who are required to adapt their code,
-backward-incompatible changes during a major bump should be limited to:
-@itemize @bullet
-@item
-Removing previously deprecated APIs.
-
-@item
-Performing ABI- but not API-breaking changes, like reordering struct contents.
-@end itemize
+@subheading Check untrusted input properly.
+Never write to unallocated memory, never write over the end of arrays,
+always check values read from some untrusted source before using them
+as array index or other risky things.

@section Documentation/Other
@subheading Subscribe to the ffmpeg-devel mailing list.
@@ -600,6 +421,35 @@ finding a new maintainer and also don't forget to update the @file{MAINTAINERS}

 We think our rules are not too hard. If you have comments, contact us.

+@chapter Code of conduct
+
+Be friendly and respectful towards others and third parties.
+Treat others the way you yourself want to be treated.
+
+Be considerate. Not everyone shares the same viewpoint and priorities as you do.
+Different opinions and interpretations help the project.
+Looking at issues from a different perspective assists development.
+
+Do not assume malice for things that can be attributed to incompetence. Even if
+it is malice, it's rarely good to start with that as initial assumption.
+
+Stay friendly even if someone acts contrarily. Everyone has a bad day
+once in a while.
+If you yourself have a bad day or are angry then try to take a break and reply
+once you are calm and without anger if you have to.
+
+Try to help other team members and cooperate if you can.
+
+The goal of software development is to create technical excellence, not for any
+individual to be better and "win" against the others. Large software projects
+are only possible and successful through teamwork.
+
+If someone struggles do not put them down. Give them a helping hand
+instead and point them in the right direction.
+
+Finally, keep in mind the immortal words of Bill and Ted,
+"Be excellent to each other."
+
@anchor{Submitting patches}
@chapter Submitting patches

@@ -816,14 +666,16 @@ Lines with similar content should be aligned vertically when doing so
 improves readability.

@item
-Consider adding a regression test for your code. All new modules
-should be covered by tests. That includes demuxers, muxers, decoders, encoders
-filters, bitstream filters, parsers. If its not possible to do that, add
-an explanation why to your patchset, its ok to not test if theres a reason.
+Consider adding a regression test for your code.

@item
 If you added YASM code please check that things still work with --disable-yasm.

+@item
+Make sure you check the return values of function and return appropriate
+error codes. Especially memory allocation functions like @code{av_malloc()}
+are notoriously left unchecked, which is a serious problem.
+
@item
 Test your code with valgrind and or Address Sanitizer to ensure it's free
 of leaks, out of array accesses, etc.
@@ -873,8 +725,6 @@ accordingly].

@section Adding files to the fate-suite dataset

-If you need a sample uploaded send a mail to samples-request.
-
 When there is no muxer or encoder available to generate test media for a
 specific test then the media has to be included in the fate-suite.
 First please make sure that the sample file is as small as possible to test the
--- a/doc/encoders.texi
+++ b/doc/encoders.texi
@@ -789,11 +789,6 @@ about 80-96 kbps/channel
@end table

 Default value is 0.
-
-@item frame_length
-Set the audio frame length in samples. Default value is the internal
-default of the library. Refer to the library's documentation for information
-about supported values.
@end table

@subsection Examples
@@ -864,13 +859,6 @@ Enable the encoder to use ABR when set to 1. The @command{lame}
@option{--abr} sets the target bitrate, while this options only
 tells FFmpeg to use ABR still relies on @option{b} to set bitrate.

-@item copyright (@emph{-c})
-Set MPEG audio copyright flag when set to 1. The default value is 0
-(disabled).
-
-@item original (@emph{-o})
-Set MPEG audio original flag when set to 1. The default value is 1
-(enabled).
@end table

@section libopencore-amrnb
@@ -977,17 +965,14 @@ Favor improved speech intelligibility.
@item audio
 Favor faithfulness to the input (the default).
@item lowdelay
-Restrict to only the lowest delay modes by disabling voice-optimized
-modes.
+Restrict to only the lowest delay modes.
@end table

@item cutoff (N.A.)
 Set cutoff bandwidth in Hz. The argument must be exactly one of the
 following: 4000, 6000, 8000, 12000, or 20000, corresponding to
 narrowband, mediumband, wideband, super wideband, and fullband
-respectively. The default is 0 (cutoff disabled). Note that libopus
-forces a wideband cutoff for bitrates < 15 kbps, unless CELT-only
-(@option{application} set to @samp{lowdelay}) mode is used.
+respectively. The default is 0 (cutoff disabled).

@item mapping_family (@emph{mapping_family})
 Set channel mapping family to be used by the encoder. The default value of -1
@@ -2449,20 +2434,6 @@ Quantizer curve compression factor
@item refs (@emph{ref})
 Number of reference frames each P-frame can use. The range is from @var{0-16}.

-@item level (@emph{level})
-Set the @code{x264_param_t.i_level_idc} value in case the value is
-positive, it is ignored otherwise.
-
-This value can be set using the @code{AVCodecContext} API (e.g. by
-setting the @code{AVCodecContext} value directly), and is specified as
-an integer mapped on a corresponding level (e.g. the value 31 maps
-to H.264 level IDC "3.1", as defined in the @code{x264_levels}
-table). It is ignored when set to a non positive value.
-
-Alternatively it can be set as a private option, overriding the value
-set in @code{AVCodecContext}, and in this case must be specified as
-the level IDC identifier (e.g. "3.1"), as defined by H.264 Annex A.
-
@item sc_threshold (@emph{scenecut})
 Sets the threshold for the scene change detection.

@@ -2755,10 +2726,6 @@ Only the mpeg2 and h264 decoders provide these. Default is 1 (on).
@item udu_sei @var{boolean}
 Import user data unregistered SEI if available into output. Default is 0 (off).

-@item mb_info @var{boolean}
-Set mb_info data through AVFrameSideData, only useful when used from the
-API. Default is 0 (off).
-
@item x264-params (N.A.)
 Override the x264 configuration using a :-separated list of key=value
 parameters.
@@ -2979,24 +2946,27 @@ Place global headers in extradata instead of every keyframe.

@item trellis

-@item me_quality
-Set motion estimation quality level. Possible values in decreasing order of
+@item me_method
+Set motion estimation method. Possible values in decreasing order of
 speed and increasing order of quality:

@table @samp
-@item 0
+@item zero
 Use no motion estimation (default).

-@item 1, 2
+@item phods
+@item x1
+@item log
 Enable advanced diamond zonal search for 16x16 blocks and half-pixel
-refinement for 16x16 blocks.
+refinement for 16x16 blocks. @samp{x1} and @samp{log} are aliases for
+@samp{phods}.

-@item 3, 4
+@item epzs
 Enable all of the things described above, plus advanced diamond zonal
-search for 8x8 blocks and half-pixel refinement for 8x8 blocks, also
-enable motion estimation on chroma planes for P and B-frames.
+search for 8x8 blocks, half-pixel refinement for 8x8 blocks, and motion
+estimation on chroma planes.

-@item 5, 6
+@item full
 Enable all of the things described above, plus extended 16x16 and 8x8
 blocks search.
@end table
@@ -3079,20 +3049,6 @@ Video encoders can take input in either of nv12 or yuv420p form
 (some encoders support both, some support only either - in practice,
 nv12 is the safer choice, especially among HW encoders).

-@section Microsoft RLE
-
-Microsoft RLE aka MSRLE encoder.
-Only 8-bit palette mode supported.
-Compatible with Windows 3.1 and Windows 95.
-
-@subsection Options
-
-@table @option
-@item g @var{integer}
-Keyframe interval.
-A keyframe is inserted at least every @code{-g} frames, sometimes sooner.
-@end table
-
@section mpeg2

 MPEG-2 video encoder.
@@ -3232,8 +3188,8 @@ recommended value) and do not set a size constraint.

@section QSV Encoders

-The family of Intel QuickSync Video encoders (MPEG-2, H.264, HEVC, JPEG/MJPEG,
-VP9, AV1)
+The family of Intel QuickSync Video encoders (MPEG-2, H.264, HEVC, JPEG/MJPEG
+and VP9)

@subsection Ratecontrol Method
 The ratecontrol method is selected as follows:
@@ -3388,7 +3344,7 @@ Supported in h264_qsv.
 Change these value to reset qsv codec's max/min qp configuration.

@item @var{low_delay_brc}
-Supported in h264_qsv, hevc_qsv and av1_qsv.
+Supported in h264_qsv and hevc_qsv.
 Change this value to reset qsv codec's low_delay_brc configuration.

@item @var{framerate}
@@ -4009,20 +3965,6 @@ Average variable bitrate.
 Each encoder also has its own specific options:
@table @option

-@item av1_vaapi
-@option{profile} sets the value of @emph{seq_profile}.
-@option{tier} sets the value of @emph{seq_tier}.
-@option{level} sets the value of @emph{seq_level_idx}.
-
-@table @option
-@item tiles
-Set the number of tiles to encode the input video with, as columns x rows.
-(default is auto, which means use minimal tile column/row number).
-@item tile_groups
-Set tile groups number. All the tiles will be distributed as evenly as possible to
-each tile group. (default is 1).
-@end table
-
@item h264_vaapi
@option{profile} sets the value of @emph{profile_idc} and the @emph{constraint_set*_flag}s.
@option{level} sets the value of @emph{level_idc}.
--- a/doc/examples/demux_decode.c
+++ b/doc/examples/demux_decode.c
@@ -78,9 +78,9 @@ static int output_video_frame(AVFrame *frame)

    /* copy decoded frame to destination buffer:
     * this is required since rawvideo expects non aligned data */
-    av_image_copy2(video_dst_data, video_dst_linesize,
-                   frame->data, frame->linesize,
-                   pix_fmt, width, height);
+    av_image_copy(video_dst_data, video_dst_linesize,
+                  (const uint8_t **)(frame->data), frame->linesize,
+                  pix_fmt, width, height);

    /* write to rawvideo file */
    fwrite(video_dst_data[0], 1, video_dst_bufsize, video_dst_file);
--- a/doc/examples/mux.c
+++ b/doc/examples/mux.c
@@ -379,27 +379,27 @@ static int write_audio_frame(AVFormatContext *oc, OutputStream *ost)
 /**************************************************************/
 /* video output */

-static AVFrame *alloc_frame(enum AVPixelFormat pix_fmt, int width, int height)
+static AVFrame *alloc_picture(enum AVPixelFormat pix_fmt, int width, int height)
 {
-    AVFrame *frame;
+    AVFrame *picture;
    int ret;

-    frame = av_frame_alloc();
-    if (!frame)
+    picture = av_frame_alloc();
+    if (!picture)
        return NULL;

-    frame->format = pix_fmt;
-    frame->width  = width;
-    frame->height = height;
+    picture->format = pix_fmt;
+    picture->width  = width;
+    picture->height = height;

    /* allocate the buffers for the frame data */
-    ret = av_frame_get_buffer(frame, 0);
+    ret = av_frame_get_buffer(picture, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate frame data.\n");
        exit(1);
    }

-    return frame;
+    return picture;
 }

 static void open_video(AVFormatContext *oc, const AVCodec *codec,
@@ -420,7 +420,7 @@ static void open_video(AVFormatContext *oc, const AVCodec *codec,
    }

    /* allocate and init a re-usable frame */
-    ost->frame = alloc_frame(c->pix_fmt, c->width, c->height);
+    ost->frame = alloc_picture(c->pix_fmt, c->width, c->height);
    if (!ost->frame) {
        fprintf(stderr, "Could not allocate video frame\n");
        exit(1);
@@ -431,9 +431,9 @@ static void open_video(AVFormatContext *oc, const AVCodec *codec,
     * output format. */
    ost->tmp_frame = NULL;
    if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
-        ost->tmp_frame = alloc_frame(AV_PIX_FMT_YUV420P, c->width, c->height);
+        ost->tmp_frame = alloc_picture(AV_PIX_FMT_YUV420P, c->width, c->height);
        if (!ost->tmp_frame) {
-            fprintf(stderr, "Could not allocate temporary video frame\n");
+            fprintf(stderr, "Could not allocate temporary picture\n");
            exit(1);
        }
    }
--- a/doc/examples/qsv_transcode.c
+++ b/doc/examples/qsv_transcode.c
@@ -88,7 +88,7 @@ static int dynamic_set_parameter(AVCodecContext *avctx)
    if (current_setting_number < setting_number &&
        frame_number == dynamic_setting[current_setting_number].frame_number) {
        AVDictionaryEntry *e = NULL;
-        ret = str_to_dict(dynamic_setting[current_setting_number++].optstr, &opts);
+        ret = str_to_dict(dynamic_setting[current_setting_number].optstr, &opts);
        if (ret < 0) {
            fprintf(stderr, "The dynamic parameter is wrong\n");
            goto fail;
--- a/doc/examples/transcode.c
+++ b/doc/examples/transcode.c
@@ -97,11 +97,6 @@ static int open_input_file(const char *filename)
                   "for stream #%u\n", i);
            return ret;
        }
-
-        /* Inform the decoder about the timebase for the packet timestamps.
-         * This is highly recommended, but not mandatory. */
-        codec_ctx->pkt_timebase = stream->time_base;
-
        /* Reencode video & audio and remux subtitles etc. */
        if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
                || codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
@@ -271,7 +266,7 @@ static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
        snprintf(args, sizeof(args),
                "video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
                dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
-                dec_ctx->pkt_timebase.num, dec_ctx->pkt_timebase.den,
+                dec_ctx->time_base.num, dec_ctx->time_base.den,
                dec_ctx->sample_aspect_ratio.num,
                dec_ctx->sample_aspect_ratio.den);

@@ -311,7 +306,7 @@ static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
        av_channel_layout_describe(&dec_ctx->ch_layout, buf, sizeof(buf));
        snprintf(args, sizeof(args),
                "time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=%s",
-                dec_ctx->pkt_timebase.num, dec_ctx->pkt_timebase.den, dec_ctx->sample_rate,
+                dec_ctx->time_base.num, dec_ctx->time_base.den, dec_ctx->sample_rate,
                av_get_sample_fmt_name(dec_ctx->sample_fmt),
                buf);
        ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
@@ -441,10 +436,6 @@ static int encode_write_frame(unsigned int stream_index, int flush)
    /* encode filtered frame */
    av_packet_unref(enc_pkt);

-    if (filt_frame && filt_frame->pts != AV_NOPTS_VALUE)
-        filt_frame->pts = av_rescale_q(filt_frame->pts, filt_frame->time_base,
-                                       stream->enc_ctx->time_base);
-
    ret = avcodec_send_frame(stream->enc_ctx, filt_frame);

    if (ret < 0)
@@ -499,7 +490,6 @@ static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index)
            break;
        }

-        filter->filtered_frame->time_base = av_buffersink_get_time_base(filter->buffersink_ctx);;
        filter->filtered_frame->pict_type = AV_PICTURE_TYPE_NONE;
        ret = encode_write_frame(stream_index, 0);
        av_frame_unref(filter->filtered_frame);
@@ -554,6 +544,9 @@ int main(int argc, char **argv)

            av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");

+            av_packet_rescale_ts(packet,
+                                 ifmt_ctx->streams[stream_index]->time_base,
+                                 stream->dec_ctx->time_base);
            ret = avcodec_send_packet(stream->dec_ctx, packet);
            if (ret < 0) {
                av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
@@ -585,38 +578,11 @@ int main(int argc, char **argv)
        av_packet_unref(packet);
    }

-    /* flush decoders, filters and encoders */
+    /* flush filters and encoders */
    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
-        StreamContext *stream;
-
+        /* flush filter */
        if (!filter_ctx[i].filter_graph)
            continue;
-
-        stream = &stream_ctx[i];
-
-        av_log(NULL, AV_LOG_INFO, "Flushing stream %u decoder\n", i);
-
-        /* flush decoder */
-        ret = avcodec_send_packet(stream->dec_ctx, NULL);
-        if (ret < 0) {
-            av_log(NULL, AV_LOG_ERROR, "Flushing decoding failed\n");
-            goto end;
-        }
-
-        while (ret >= 0) {
-            ret = avcodec_receive_frame(stream->dec_ctx, stream->dec_frame);
-            if (ret == AVERROR_EOF)
-                break;
-            else if (ret < 0)
-                goto end;
-
-            stream->dec_frame->pts = stream->dec_frame->best_effort_timestamp;
-            ret = filter_encode_write_frame(stream->dec_frame, i);
-            if (ret < 0)
-                goto end;
-        }
-
-        /* flush filter */
        ret = filter_encode_write_frame(NULL, i);
        if (ret < 0) {
            av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n");
--- a/doc/examples/transcode_aac.c
+++ b/doc/examples/transcode_aac.c
@@ -447,17 +447,26 @@ static int init_converted_samples(uint8_t ***converted_input_samples,
    int error;

    /* Allocate as many pointers as there are audio channels.
-     * Each pointer will point to the audio samples of the corresponding
+     * Each pointer will later point to the audio samples of the corresponding
     * channels (although it may be NULL for interleaved formats).
-     * Allocate memory for the samples of all channels in one consecutive
+     */
+    if (!(*converted_input_samples = calloc(output_codec_context->ch_layout.nb_channels,
+                                            sizeof(**converted_input_samples)))) {
+        fprintf(stderr, "Could not allocate converted input sample pointers\n");
+        return AVERROR(ENOMEM);
+    }
+
+    /* Allocate memory for the samples of all channels in one consecutive
     * block for convenience. */
-    if ((error = av_samples_alloc_array_and_samples(converted_input_samples, NULL,
+    if ((error = av_samples_alloc(*converted_input_samples, NULL,
                                  output_codec_context->ch_layout.nb_channels,
                                  frame_size,
                                  output_codec_context->sample_fmt, 0)) < 0) {
        fprintf(stderr,
                "Could not allocate converted input samples (error '%s')\n",
                av_err2str(error));
+        av_freep(&(*converted_input_samples)[0]);
+        free(*converted_input_samples);
        return error;
    }
    return 0;
@@ -589,9 +598,10 @@ static int read_decode_convert_and_store(AVAudioFifo *fifo,
    ret = 0;

 cleanup:
-    if (converted_input_samples)
+    if (converted_input_samples) {
        av_freep(&converted_input_samples[0]);
-    av_freep(&converted_input_samples);
+        free(converted_input_samples);
+    }
    av_frame_free(&input_frame);

    return ret;
--- a/doc/fate.texi
+++ b/doc/fate.texi
@@ -223,14 +223,6 @@ meaning only while running the regression tests.
 Specify how many threads to use while running regression tests, it is
 quite useful to detect thread-related regressions.

-This variable may be set to the string "random", optionally followed by a
-number, like "random99", This will cause each test to use a random number of
-threads. If a number is specified, it is used as a maximum number of threads,
-otherwise 16 is the maximum.
-
-In case a test fails, the thread count used for it will be written into the
-errfile.
-
@item THREAD_TYPE
 Specify which threading strategy test, either @samp{slice} or @samp{frame},
 by default @samp{slice+frame}
--- a/doc/ffmpeg.texi
+++ b/doc/ffmpeg.texi
@@ -17,9 +17,9 @@ ffmpeg [@var{global_options}] @{[@var{input_file_options}] -i @file{input_url}@}
@chapter Description
@c man begin DESCRIPTION

-@command{ffmpeg} is a universal media converter. It can read a wide variety of
-inputs - including live grabbing/recording devices - filter, and transcode them
-into a plethora of output formats.
+@command{ffmpeg} is a very fast video and audio converter that can also grab from
+a live audio/video source. It can also convert between arbitrary sample
+rates and resize video on the fly with a high quality polyphase filter.

@command{ffmpeg} reads from an arbitrary number of input "files" (which can be regular
 files, pipes, network streams, grabbing devices, etc.), specified by the
@@ -49,32 +49,24 @@ Do not mix input and output files -- first specify all input files, then all
 output files. Also do not mix options which belong to different files. All
 options apply ONLY to the next input or output file and are reset between files.

-Some simple examples follow.
-
@itemize
@item
-Convert an input media file to a different format, by re-encoding media streams:
+To set the video bitrate of the output file to 64 kbit/s:
@example
-ffmpeg -i input.avi output.mp4
+ffmpeg -i input.avi -b:v 64k -bufsize 64k output.avi
@end example

@item
-Set the video bitrate of the output file to 64 kbit/s:
+To force the frame rate of the output file to 24 fps:
@example
-ffmpeg -i input.avi -b:v 64k -bufsize 64k output.mp4
+ffmpeg -i input.avi -r 24 output.avi
@end example

@item
-Force the frame rate of the output file to 24 fps:
+To force the frame rate of the input file (valid for raw formats only)
+to 1 fps and the frame rate of the output file to 24 fps:
@example
-ffmpeg -i input.avi -r 24 output.mp4
-@end example
-
-@item
-Force the frame rate of the input file (valid for raw formats only) to 1 fps and
-the frame rate of the output file to 24 fps:
-@example
-ffmpeg -r 1 -i input.m2v -r 24 output.mp4
+ffmpeg -r 1 -i input.m2v -r 24 output.avi
@end example
@end itemize

@@ -777,7 +769,6 @@ syntax.
 See the @ref{filter_complex_option,,-filter_complex option} if you
 want to create filtergraphs with multiple inputs and/or outputs.

-@anchor{filter_script option}
@item -filter_script[:@var{stream_specifier}] @var{filename} (@emph{output,per-stream})
 This option is similar to @option{-filter}, the only difference is that its
 argument is the name of the file from which a filtergraph description is to be
@@ -1023,12 +1014,7 @@ If @var{pix_fmt} is a single @code{+}, ffmpeg selects the same pixel format
 as the input (or graph output) and automatic conversions are disabled.

@item -sws_flags @var{flags} (@emph{input/output})
-Set default flags for the libswscale library. These flags are used by
-automatically inserted @code{scale} filters and those within simple
-filtergraphs, if not overridden within the filtergraph definition.
-
-See the @ref{scaler_options,,ffmpeg-scaler manual,ffmpeg-scaler} for a list
-of scaler options.
+Set SwScaler flags.

@item -rc_override[:@var{stream_specifier}] @var{override} (@emph{output,per-stream})
 Rate control override for specific intervals, formatted as "int,int,int"
@@ -1039,27 +1025,33 @@ factor if negative.
@item -psnr
 Calculate PSNR of compressed frames. This option is deprecated, pass the
 PSNR flag to the encoder instead, using @code{-flags +psnr}.
-
@item -vstats
-Dump video coding statistics to @file{vstats_HHMMSS.log}. See the
-@ref{vstats_file_format,,vstats file format} section for the format description.
-
+Dump video coding statistics to @file{vstats_HHMMSS.log}.
@item -vstats_file @var{file}
-Dump video coding statistics to @var{file}. See the
-@ref{vstats_file_format,,vstats file format} section for the format description.
-
+Dump video coding statistics to @var{file}.
@item -vstats_version @var{file}
-Specify which version of the vstats format to use. Default is @code{2}. See the
-@ref{vstats_file_format,,vstats file format} section for the format description.
+Specifies which version of the vstats format to use. Default is 2.

+version = 1 :
+
+@code{frame= %5d q= %2.1f PSNR= %6.2f f_size= %6d s_size= %8.0fkB time= %0.3f br= %7.1fkbits/s avg_br= %7.1fkbits/s}
+
+version > 1:
+
+@code{out= %2d st= %2d frame= %5d q= %2.1f PSNR= %6.2f f_size= %6d s_size= %8.0fkB time= %0.3f br= %7.1fkbits/s avg_br= %7.1fkbits/s}
+@item -top[:@var{stream_specifier}] @var{n} (@emph{output,per-stream})
+top=1/bottom=0/auto=-1 field first
@item -vtag @var{fourcc/tag} (@emph{output})
 Force video tag/fourcc. This is an alias for @code{-tag:v}.
+@item -qphist (@emph{global})
+Show QP histogram
@item -vbsf @var{bitstream_filter}
 Deprecated see -bsf

@item -force_key_frames[:@var{stream_specifier}] @var{time}[,@var{time}...] (@emph{output,per-stream})
@item -force_key_frames[:@var{stream_specifier}] expr:@var{expr} (@emph{output,per-stream})
@item -force_key_frames[:@var{stream_specifier}] source (@emph{output,per-stream})
+@item -force_key_frames[:@var{stream_specifier}] source_no_drop (@emph{output,per-stream})

@var{force_key_frames} can take arguments of the following form:

@@ -1120,6 +1112,10 @@ starting from second 13:
@item source
 If the argument is @code{source}, ffmpeg will force a key frame if
 the current frame being encoded is marked as a key frame in its source.
+
+@item source_no_drop
+If the argument is @code{source_no_drop}, ffmpeg will force a key frame if
+the current frame being encoded is marked as a key frame in its source.
 In cases where this particular source frame has to be dropped,
 enforce the next available frame to become a key frame instead.

@@ -1167,10 +1163,9 @@ Choose the first device and use the primary device context.
@var{device} is the number of the Direct3D 11 display adapter.

@item vaapi
-@var{device} is either an X11 display name, a DRM render node or a DirectX adapter index.
+@var{device} is either an X11 display name or a DRM render node.
 If not specified, it will attempt to open the default X11 display (@emph{$DISPLAY})
-and then the first DRM render node (@emph{/dev/dri/renderD128}), or the default
-DirectX adapter on Windows.
+and then the first DRM render node (@emph{/dev/dri/renderD128}).

@item vdpau
@var{device} is an X11 display name.
@@ -1706,9 +1701,6 @@ it may cause packet loss.
 It is useful for when flow speed of output packets is important, such as live streaming.
@item -re (@emph{input})
 Read input at native frame rate. This is equivalent to setting @code{-readrate 1}.
-@item -readrate_initial_burst @var{seconds}
-Set an initial read burst time, in seconds, after which @option{-re/-readrate}
-will be enforced.
@item -vsync @var{parameter} (@emph{global})
@itemx -fps_mode[:@var{stream_specifier}] @var{parameter} (@emph{output,per-stream})
 Set video sync method / framerate mode. vsync is applied to all output video streams
@@ -1750,6 +1742,12 @@ The default is -1.1. One possible usecase is to avoid framedrops in case
 of noisy timestamps or to increase frame drop precision in case of exact
 timestamps.

+@item -adrift_threshold @var{time}
+Set the minimum difference between timestamps and audio data (in seconds) to trigger
+adding/dropping samples to make it match the timestamps. This option effectively is
+a threshold to select between hard (add/drop) and soft (squeeze/stretch) compensation.
+@code{-async} must be set to a positive value.
+
@item -apad @var{parameters} (@emph{output,per-stream})
 Pad the output audio stream(s). This is the same as applying @code{-af apad}.
 Argument is a string of filter parameters composed the same as with the @code{apad} filter.
@@ -1796,7 +1794,8 @@ Try to make the choice automatically, in order to generate a sane output.
 Default value is -1.

@item -enc_time_base[:@var{stream_specifier}] @var{timebase} (@emph{output,per-stream})
-Set the encoder timebase. @var{timebase} can assume one of the following values:
+Set the encoder timebase. @var{timebase} is a floating point number,
+and can assume one of the following values:

@table @option
@item 0
@@ -1804,17 +1803,16 @@ Assign a default value according to the media type.

 For video - use 1/framerate, for audio - use 1/samplerate.

-@item demux
-Use the timebase from the demuxer.
+@item -1
+Use the input stream timebase when possible.

-@item filter
-Use the timebase from the filtergraph.
+If an input stream is not available, the default timebase will be used.

-@item a positive number
+@item >0
 Use the provided number as the timebase.

 This field can be provided as a ratio of two integers (e.g. 1:24, 1:48000)
-or as a decimal number (e.g. 0.04166, 2.0833e-5)
+or as a floating point number (e.g. 0.04166, 2.0833e-5)
@end table

 Default value is 0.
@@ -1839,38 +1837,12 @@ results, but increase memory use and latency.

 The default value is 10 seconds.

-@item -dts_delta_threshold @var{threshold}
-Timestamp discontinuity delta threshold, expressed as a decimal number
-of seconds.
-
-The timestamp discontinuity correction enabled by this option is only
-applied to input formats accepting timestamp discontinuity (for which
-the @code{AV_FMT_DISCONT} flag is enabled), e.g. MPEG-TS and HLS, and
-is automatically disabled when employing the @code{-copy_ts} option
-(unless wrapping is detected).
-
-If a timestamp discontinuity is detected whose absolute value is
-greater than @var{threshold}, ffmpeg will remove the discontinuity by
-decreasing/increasing the current DTS and PTS by the corresponding
-delta value.
-
-The default value is 10.
-
-@item -dts_error_threshold @var{threshold}
-Timestamp error delta threshold, expressed as a decimal number of
-seconds.
-
-The timestamp correction enabled by this option is only applied to
-input formats not accepting timestamp discontinuity (for which the
-@code{AV_FMT_DISCONT} flag is not enabled).
-
-If a timestamp discontinuity is detected whose absolute value is
-greater than @var{threshold}, ffmpeg will drop the PTS/DTS timestamp
-value.
-
-The default value is @code{3600*30} (30 hours), which is arbitrarily
-picked and quite conservative.
-
+@item -dts_delta_threshold
+Timestamp discontinuity delta threshold.
+@item -dts_error_threshold @var{seconds}
+Timestamp error delta threshold. This threshold use to discard crazy/damaged
+timestamps and the default is 30 hours which is arbitrarily picked and quite
+conservative.
@item -muxdelay @var{seconds} (@emph{output})
 Set the maximum demux-decode delay.
@item -muxpreload @var{seconds} (@emph{output})
@@ -1981,7 +1953,6 @@ The default is the number of available CPUs.
 Define a complex filtergraph, i.e. one with arbitrary number of inputs and/or
 outputs. Equivalent to @option{-filter_complex}.

-@anchor{filter_complex_script option}
@item -filter_complex_script @var{filename} (@emph{global})
 This option is similar to @option{-filter_complex}, the only difference is that
 its argument is the name of the file from which a complex filtergraph
@@ -2090,7 +2061,6 @@ encoder/muxer, it does not change the stream to conform to this value. Setting
 values that do not match the stream properties may result in encoding failures
 or invalid output files.

-@anchor{stats_enc_options}
@item -stats_enc_pre[:@var{stream_specifier}] @var{path} (@emph{output,per-stream})
@item -stats_enc_post[:@var{stream_specifier}] @var{path} (@emph{output,per-stream})
@item -stats_mux_pre[:@var{stream_specifier}] @var{path} (@emph{output,per-stream})
@@ -2138,8 +2108,8 @@ Input frame number. Index of the input frame (i.e. output by a decoder) that
 corresponds to this output frame or packet. -1 if unavailable.

@item tb
-Timebase in which this frame/packet's timestamps are expressed, as a rational
-number @var{num/den}. Note that encoder and muxer may use different timebases.
+Encoder timebase, as a rational number @var{num/den}. Note that this may be
+different from the timebase used by the muxer.

@item tbi
 Timebase for @var{ptsi}, as a rational number @var{num/den}. Available when
@@ -2162,39 +2132,31 @@ Presentation time of the frame or packet, as a decimal number. Equal to
 Presentation time of the input frame (see @var{ni}), as a decimal number. Equal
 to @var{ptsi} multiplied by @var{tbi}. Printed as inf when not available.

-@item dts (@emph{packet})
+@item dts
 Decoding timestamp of the packet, as an integer. Should be multiplied by the
-timebase to compute presentation time.
+timebase to compute presentation time. Post-encoding only.

-@item dt (@emph{packet})
+@item dt
 Decoding time of the frame or packet, as a decimal number. Equal to
@var{dts} multiplied by @var{tb}.

-@item sn (@emph{frame,audio})
-Number of audio samples sent to the encoder so far.
+@item sn
+Number of audio samples sent to the encoder so far. Audio and pre-encoding only.

-@item samp (@emph{frame,audio})
-Number of audio samples in the frame.
+@item samp
+Number of audio samples in the frame. Audio and pre-encoding only.

-@item size (@emph{packet})
-Size of the encoded packet in bytes.
+@item size
+Size of the encoded packet in bytes. Post-encoding only.

-@item br (@emph{packet})
+@item br
 Current bitrate in bits per second. Post-encoding only.

-@item abr (@emph{packet})
+@item abr
 Average bitrate for the whole stream so far, in bits per second, -1 if it cannot
 be determined at this point. Post-encoding only.
@end table

-Directives tagged with @emph{packet} may only be used with
-@option{-stats_enc_post_fmt} and @option{-stats_mux_pre_fmt}.
-
-Directives tagged with @emph{frame} may only be used with
-@option{-stats_enc_pre_fmt}.
-
-Directives tagged with @emph{audio} may only be used with audio streams.
-
 The default format strings are:
@table @option
@item pre-encoding
@@ -2266,63 +2228,6 @@ search for the file @file{libvpx-1080p.avpreset}.
 If no such file is found, then ffmpeg will search for a file named
@var{arg}.avpreset in the same directories.

-@anchor{vstats_file_format}
-@section vstats file format
-The @code{-vstats} and @code{-vstats_file} options enable generation of a file
-containing statistics about the generated video outputs.
-
-The @code{-vstats_version} option controls the format version of the generated
-file.
-
-With version @code{1} the format is:
-@example
-frame= @var{FRAME} q= @var{FRAME_QUALITY} PSNR= @var{PSNR} f_size= @var{FRAME_SIZE} s_size= @var{STREAM_SIZE}kB time= @var{TIMESTAMP} br= @var{BITRATE}kbits/s avg_br= @var{AVERAGE_BITRATE}kbits/s
-@end example
-
-With version @code{2} the format is:
-@example
-out= @var{OUT_FILE_INDEX} st= @var{OUT_FILE_STREAM_INDEX} frame= @var{FRAME_NUMBER} q= @var{FRAME_QUALITY}f PSNR= @var{PSNR} f_size= @var{FRAME_SIZE} s_size= @var{STREAM_SIZE}kB time= @var{TIMESTAMP} br= @var{BITRATE}kbits/s avg_br= @var{AVERAGE_BITRATE}kbits/s
-@end example
-
-The value corresponding to each key is described below:
-@table @option
-@item avg_br
-average bitrate expressed in Kbits/s
-
-@item br
-bitrate expressed in Kbits/s
-
-@item frame
-number of encoded frame
-
-@item out
-out file index
-
-@item PSNR
-Peak Signal to Noise Ratio
-
-@item q
-quality of the frame
-
-@item f_size
-encoded packet size expressed as number of bytes
-
-@item s_size
-stream size expressed in KiB
-
-@item st
-out file stream index
-
-@item time
-time of the packet
-
-@item type
-picture type
-@end table
-
-See also the @ref{stats_enc_options,,-stats_enc options} for an alternative way
-to show encoding statistics.
-
@c man end OPTIONS

@chapter Examples
@@ -2586,7 +2491,7 @@ ffmpeg-devices(1), ffmpeg-protocols(1), ffmpeg-filters(1)
@ignore

@setfilename ffmpeg
-@settitle ffmpeg media converter
+@settitle ffmpeg video converter

@end ignore

--- a/doc/ffprobe.texi
+++ b/doc/ffprobe.texi
@@ -41,7 +41,7 @@ ffprobe will show it.

 ffprobe output is designed to be easily parsable by a textual filter,
 and consists of one or more sections of a form defined by the selected
-writer, which is specified by the @option{output_format} option.
+writer, which is specified by the @option{print_format} option.

 Sections may contain other nested sections, and are identified by a
 name (which may be shared by other sections), and an unique
@@ -83,7 +83,7 @@ Use sexagesimal format HH:MM:SS.MICROSECONDS for time values.
 Prettify the format of the displayed values, it corresponds to the
 options "-unit -prefix -byte_binary_prefix -sexagesimal".

-@item -output_format, -of, -print_format @var{writer_name}[=@var{writer_options}]
+@item -of, -print_format @var{writer_name}[=@var{writer_options}]
 Set the output printing format.

@var{writer_name} specifies the name of the writer, and
@@ -91,7 +91,7 @@ Set the output printing format.

 For example for printing the output in JSON format, specify:
@example
-output_format json
+-print_format json
@end example

 For more details on the available output printing formats, see the
--- a/doc/ffprobe.xsd
+++ b/doc/ffprobe.xsd
@@ -1,409 +1,389 @@
 <?xml version="1.0" encoding="UTF-8"?>

 <xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
-            targetNamespace="http://www.ffmpeg.org/schema/ffprobe"
-            xmlns:ffprobe="http://www.ffmpeg.org/schema/ffprobe">
+    targetNamespace="http://www.ffmpeg.org/schema/ffprobe"
+    xmlns:ffprobe="http://www.ffmpeg.org/schema/ffprobe">

-  <xsd:element name="ffprobe" type="ffprobe:ffprobeType"/>
+    <xsd:element name="ffprobe" type="ffprobe:ffprobeType"/>

-  <xsd:complexType name="ffprobeType">
-    <xsd:sequence>
-      <xsd:element name="program_version"  type="ffprobe:programVersionType"  minOccurs="0" maxOccurs="1" />
-      <xsd:element name="library_versions" type="ffprobe:libraryVersionsType" minOccurs="0" maxOccurs="1" />
-      <xsd:element name="pixel_formats"    type="ffprobe:pixelFormatsType"    minOccurs="0" maxOccurs="1" />
-      <xsd:element name="packets"  type="ffprobe:packetsType" minOccurs="0" maxOccurs="1" />
-      <xsd:element name="frames"   type="ffprobe:framesType"  minOccurs="0" maxOccurs="1" />
-      <xsd:element name="packets_and_frames" type="ffprobe:packetsAndFramesType" minOccurs="0" maxOccurs="1" />
-      <xsd:element name="programs" type="ffprobe:programsType" minOccurs="0" maxOccurs="1" />
-      <xsd:element name="streams"  type="ffprobe:streamsType" minOccurs="0" maxOccurs="1" />
-      <xsd:element name="chapters" type="ffprobe:chaptersType" minOccurs="0" maxOccurs="1" />
-      <xsd:element name="format"   type="ffprobe:formatType"  minOccurs="0" maxOccurs="1" />
-      <xsd:element name="error"    type="ffprobe:errorType"   minOccurs="0" maxOccurs="1" />
-    </xsd:sequence>
-  </xsd:complexType>
+    <xsd:complexType name="ffprobeType">
+        <xsd:sequence>
+            <xsd:element name="program_version"  type="ffprobe:programVersionType"  minOccurs="0" maxOccurs="1" />
+            <xsd:element name="library_versions" type="ffprobe:libraryVersionsType" minOccurs="0" maxOccurs="1" />
+            <xsd:element name="pixel_formats"    type="ffprobe:pixelFormatsType"    minOccurs="0" maxOccurs="1" />
+            <xsd:element name="packets"  type="ffprobe:packetsType" minOccurs="0" maxOccurs="1" />
+            <xsd:element name="frames"   type="ffprobe:framesType"  minOccurs="0" maxOccurs="1" />
+            <xsd:element name="packets_and_frames" type="ffprobe:packetsAndFramesType" minOccurs="0" maxOccurs="1" />
+            <xsd:element name="programs" type="ffprobe:programsType" minOccurs="0" maxOccurs="1" />
+            <xsd:element name="streams"  type="ffprobe:streamsType" minOccurs="0" maxOccurs="1" />
+            <xsd:element name="chapters" type="ffprobe:chaptersType" minOccurs="0" maxOccurs="1" />
+            <xsd:element name="format"   type="ffprobe:formatType"  minOccurs="0" maxOccurs="1" />
+            <xsd:element name="error"    type="ffprobe:errorType"   minOccurs="0" maxOccurs="1" />
+        </xsd:sequence>
+    </xsd:complexType>

-  <xsd:complexType name="packetsType">
-    <xsd:sequence>
-      <xsd:element name="packet" type="ffprobe:packetType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
+    <xsd:complexType name="packetsType">
+        <xsd:sequence>
+            <xsd:element name="packet" type="ffprobe:packetType" minOccurs="0" maxOccurs="unbounded"/>
+        </xsd:sequence>
+    </xsd:complexType>

-  <xsd:complexType name="framesType">
-    <xsd:choice minOccurs="0" maxOccurs="unbounded">
-      <xsd:element name="frame"    type="ffprobe:frameType"/>
-      <xsd:element name="subtitle" type="ffprobe:subtitleType"/>
-    </xsd:choice>
-  </xsd:complexType>
+    <xsd:complexType name="framesType">
+        <xsd:choice minOccurs="0" maxOccurs="unbounded">
+            <xsd:element name="frame"    type="ffprobe:frameType"/>
+            <xsd:element name="subtitle" type="ffprobe:subtitleType"/>
+        </xsd:choice>
+    </xsd:complexType>

-  <xsd:complexType name="packetsAndFramesType">
-    <xsd:choice minOccurs="0" maxOccurs="unbounded">
-      <xsd:element name="packet"   type="ffprobe:packetType"/>
-      <xsd:element name="frame"    type="ffprobe:frameType"/>
-      <xsd:element name="subtitle" type="ffprobe:subtitleType"/>
-    </xsd:choice>
-  </xsd:complexType>
+    <xsd:complexType name="packetsAndFramesType">
+        <xsd:choice minOccurs="0" maxOccurs="unbounded">
+            <xsd:element name="packet"   type="ffprobe:packetType"/>
+            <xsd:element name="frame"    type="ffprobe:frameType"/>
+            <xsd:element name="subtitle" type="ffprobe:subtitleType"/>
+        </xsd:choice>
+    </xsd:complexType>

-  <xsd:complexType name="tagsType">
-    <xsd:sequence>
-      <xsd:element name="tag" type="ffprobe:tagType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
+    <xsd:complexType name="packetType">
+      <xsd:sequence>
+        <xsd:element name="tag" type="ffprobe:tagType" minOccurs="0" maxOccurs="unbounded"/>
+        <xsd:element name="side_data_list" type="ffprobe:packetSideDataListType"   minOccurs="0" maxOccurs="1" />
+      </xsd:sequence>

-  <xsd:complexType name="packetType">
-    <xsd:sequence>
-      <xsd:element name="tags" type="ffprobe:tagsType" minOccurs="0" maxOccurs="1"/>
-      <xsd:element name="side_data_list" type="ffprobe:packetSideDataListType"   minOccurs="0" maxOccurs="1" />
-    </xsd:sequence>
+      <xsd:attribute name="codec_type"    type="xsd:string" use="required" />
+      <xsd:attribute name="stream_index"  type="xsd:int" use="required" />
+      <xsd:attribute name="pts"           type="xsd:long"  />
+      <xsd:attribute name="pts_time"      type="xsd:float" />
+      <xsd:attribute name="dts"           type="xsd:long"  />
+      <xsd:attribute name="dts_time"      type="xsd:float" />
+      <xsd:attribute name="duration"      type="xsd:long"  />
+      <xsd:attribute name="duration_time" type="xsd:float" />
+      <xsd:attribute name="size"          type="xsd:long" use="required" />
+      <xsd:attribute name="pos"           type="xsd:long"  />
+      <xsd:attribute name="flags"         type="xsd:string" use="required" />
+      <xsd:attribute name="data"          type="xsd:string" />
+      <xsd:attribute name="data_hash"     type="xsd:string" />
+    </xsd:complexType>

-    <xsd:attribute name="codec_type"    type="xsd:string" use="required" />
-    <xsd:attribute name="stream_index"  type="xsd:int" use="required" />
-    <xsd:attribute name="pts"           type="xsd:long"  />
-    <xsd:attribute name="pts_time"      type="xsd:float" />
-    <xsd:attribute name="dts"           type="xsd:long"  />
-    <xsd:attribute name="dts_time"      type="xsd:float" />
-    <xsd:attribute name="duration"      type="xsd:long"  />
-    <xsd:attribute name="duration_time" type="xsd:float" />
-    <xsd:attribute name="size"          type="xsd:long" use="required" />
-    <xsd:attribute name="pos"           type="xsd:long"  />
-    <xsd:attribute name="flags"         type="xsd:string" use="required" />
-    <xsd:attribute name="data"          type="xsd:string" />
-    <xsd:attribute name="data_hash"     type="xsd:string" />
-  </xsd:complexType>
+    <xsd:complexType name="packetSideDataListType">
+        <xsd:sequence>
+            <xsd:element name="side_data" type="ffprobe:packetSideDataType" minOccurs="1" maxOccurs="unbounded"/>
+        </xsd:sequence>
+    </xsd:complexType>
+    <xsd:complexType name="packetSideDataType">
+        <xsd:attribute name="side_data_type"              type="xsd:string"/>
+        <xsd:attribute name="side_data_size"              type="xsd:int"   />
+    </xsd:complexType>

-  <xsd:complexType name="packetSideDataListType">
-    <xsd:sequence>
-      <xsd:element name="side_data" type="ffprobe:packetSideDataType" minOccurs="1" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
+    <xsd:complexType name="frameType">
+      <xsd:sequence>
+            <xsd:element name="tag" type="ffprobe:tagType" minOccurs="0" maxOccurs="unbounded"/>
+            <xsd:element name="logs" type="ffprobe:logsType" minOccurs="0" maxOccurs="1"/>
+            <xsd:element name="side_data_list" type="ffprobe:frameSideDataListType"   minOccurs="0" maxOccurs="1" />
+      </xsd:sequence>

-  <xsd:complexType name="packetSideDataType">
-    <xsd:sequence>
-      <xsd:element name="side_datum" type="ffprobe:packetSideDatumType" minOccurs="1" maxOccurs="unbounded"/>
-    </xsd:sequence>
+      <xsd:attribute name="media_type"    type="xsd:string" use="required"/>
+      <xsd:attribute name="stream_index"  type="xsd:int"  />
+      <xsd:attribute name="key_frame"     type="xsd:int"    use="required"/>
+      <xsd:attribute name="pts"           type="xsd:long" />
+      <xsd:attribute name="pts_time"      type="xsd:float"/>
+      <xsd:attribute name="pkt_dts"       type="xsd:long" />
+      <xsd:attribute name="pkt_dts_time"  type="xsd:float"/>
+      <xsd:attribute name="best_effort_timestamp"      type="xsd:long" />
+      <xsd:attribute name="best_effort_timestamp_time" type="xsd:float" />
+      <xsd:attribute name="pkt_duration"  type="xsd:long" />
+      <xsd:attribute name="pkt_duration_time" type="xsd:float"/>
+      <xsd:attribute name="duration"      type="xsd:long" />
+      <xsd:attribute name="duration_time" type="xsd:float"/>
+      <xsd:attribute name="pkt_pos"       type="xsd:long" />
+      <xsd:attribute name="pkt_size"      type="xsd:int" />

-    <xsd:attribute name="type" type="xsd:string"/>
-  </xsd:complexType>
+      <!-- audio attributes -->
+      <xsd:attribute name="sample_fmt"             type="xsd:string"/>
+      <xsd:attribute name="nb_samples"             type="xsd:long"  />
+      <xsd:attribute name="channels"               type="xsd:int"   />
+      <xsd:attribute name="channel_layout"         type="xsd:string"/>

-  <xsd:complexType name="packetSideDatumType">
-    <xsd:attribute name="key"   type="xsd:string"/>
-    <xsd:attribute name="value" type="xsd:string"/>
-  </xsd:complexType>
+      <!-- video attributes -->
+      <xsd:attribute name="width"                  type="xsd:long"  />
+      <xsd:attribute name="height"                 type="xsd:long"  />
+      <xsd:attribute name="pix_fmt"                type="xsd:string"/>
+      <xsd:attribute name="sample_aspect_ratio"    type="xsd:string"/>
+      <xsd:attribute name="pict_type"              type="xsd:string"/>
+      <xsd:attribute name="coded_picture_number"   type="xsd:long"  />
+      <xsd:attribute name="display_picture_number" type="xsd:long"  />
+      <xsd:attribute name="interlaced_frame"       type="xsd:int"   />
+      <xsd:attribute name="top_field_first"        type="xsd:int"   />
+      <xsd:attribute name="repeat_pict"            type="xsd:int"   />
+      <xsd:attribute name="color_range"            type="xsd:string"/>
+      <xsd:attribute name="color_space"            type="xsd:string"/>
+      <xsd:attribute name="color_primaries"        type="xsd:string"/>
+      <xsd:attribute name="color_transfer"         type="xsd:string"/>
+      <xsd:attribute name="chroma_location"        type="xsd:string"/>
+    </xsd:complexType>

-  <xsd:complexType name="frameType">
-    <xsd:sequence>
-      <xsd:element name="tags" type="ffprobe:tagsType" minOccurs="0" maxOccurs="1"/>
-      <xsd:element name="logs" type="ffprobe:logsType" minOccurs="0" maxOccurs="1"/>
-      <xsd:element name="side_data_list" type="ffprobe:frameSideDataListType"   minOccurs="0" maxOccurs="1" />
-    </xsd:sequence>
+    <xsd:complexType name="logsType">
+        <xsd:sequence>
+            <xsd:element name="log" type="ffprobe:logType" minOccurs="1" maxOccurs="unbounded"/>
+        </xsd:sequence>
+    </xsd:complexType>
+    <xsd:complexType name="logType">
+        <xsd:attribute name="context"                     type="xsd:string"/>
+        <xsd:attribute name="level"                       type="xsd:int"   />
+        <xsd:attribute name="category"                    type="xsd:int"   />
+        <xsd:attribute name="parent_context"              type="xsd:string"/>
+        <xsd:attribute name="parent_category"             type="xsd:int"   />
+        <xsd:attribute name="message"                     type="xsd:string"/>
+    </xsd:complexType>

-    <xsd:attribute name="media_type"    type="xsd:string" use="required"/>
-    <xsd:attribute name="stream_index"  type="xsd:int"  />
-    <xsd:attribute name="key_frame"     type="xsd:int"    use="required"/>
-    <xsd:attribute name="pts"           type="xsd:long" />
-    <xsd:attribute name="pts_time"      type="xsd:float"/>
-    <xsd:attribute name="pkt_dts"       type="xsd:long" />
-    <xsd:attribute name="pkt_dts_time"  type="xsd:float"/>
-    <xsd:attribute name="best_effort_timestamp"      type="xsd:long" />
-    <xsd:attribute name="best_effort_timestamp_time" type="xsd:float" />
-    <xsd:attribute name="pkt_duration"  type="xsd:long" />
-    <xsd:attribute name="pkt_duration_time" type="xsd:float"/>
-    <xsd:attribute name="duration"      type="xsd:long" />
-    <xsd:attribute name="duration_time" type="xsd:float"/>
-    <xsd:attribute name="pkt_pos"       type="xsd:long" />
-    <xsd:attribute name="pkt_size"      type="xsd:int" />
+    <xsd:complexType name="frameSideDataListType">
+        <xsd:sequence>
+            <xsd:element name="side_data" type="ffprobe:frameSideDataType" minOccurs="1" maxOccurs="unbounded"/>
+        </xsd:sequence>
+    </xsd:complexType>
+    <xsd:complexType name="frameSideDataType">
+        <xsd:sequence>
+            <xsd:element name="timecodes" type="ffprobe:frameSideDataTimecodeList" minOccurs="0" maxOccurs="1"/>
+        </xsd:sequence>

-    <!-- audio attributes -->
-    <xsd:attribute name="sample_fmt"             type="xsd:string"/>
-    <xsd:attribute name="nb_samples"             type="xsd:long"  />
-    <xsd:attribute name="channels"               type="xsd:int"   />
-    <xsd:attribute name="channel_layout"         type="xsd:string"/>
+        <xsd:attribute name="side_data_type"              type="xsd:string"/>
+        <xsd:attribute name="side_data_size"              type="xsd:int"   />
+        <xsd:attribute name="timecode"                    type="xsd:string"/>
+    </xsd:complexType>

-    <!-- video attributes -->
-    <xsd:attribute name="width"                  type="xsd:long"  />
-    <xsd:attribute name="height"                 type="xsd:long"  />
-    <xsd:attribute name="crop_top"               type="xsd:long"  />
-    <xsd:attribute name="crop_bottom"            type="xsd:long"  />
-    <xsd:attribute name="crop_left"              type="xsd:long"  />
-    <xsd:attribute name="crop_right"             type="xsd:long"  />
-    <xsd:attribute name="pix_fmt"                type="xsd:string"/>
-    <xsd:attribute name="sample_aspect_ratio"    type="xsd:string"/>
-    <xsd:attribute name="pict_type"              type="xsd:string"/>
-    <xsd:attribute name="coded_picture_number"   type="xsd:long"  />
-    <xsd:attribute name="display_picture_number" type="xsd:long"  />
-    <xsd:attribute name="interlaced_frame"       type="xsd:int"   />
-    <xsd:attribute name="top_field_first"        type="xsd:int"   />
-    <xsd:attribute name="repeat_pict"            type="xsd:int"   />
-    <xsd:attribute name="color_range"            type="xsd:string"/>
-    <xsd:attribute name="color_space"            type="xsd:string"/>
-    <xsd:attribute name="color_primaries"        type="xsd:string"/>
-    <xsd:attribute name="color_transfer"         type="xsd:string"/>
-    <xsd:attribute name="chroma_location"        type="xsd:string"/>
-  </xsd:complexType>
+    <xsd:complexType name="frameSideDataTimecodeList">
+        <xsd:sequence>
+            <xsd:element name="timecode" type="ffprobe:frameSideDataTimecodeType" minOccurs="0" maxOccurs="unbounded"/>
+        </xsd:sequence>
+    </xsd:complexType>

-  <xsd:complexType name="logsType">
-    <xsd:sequence>
-      <xsd:element name="log" type="ffprobe:logType" minOccurs="1" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
-  <xsd:complexType name="logType">
-    <xsd:attribute name="context"                     type="xsd:string"/>
-    <xsd:attribute name="level"                       type="xsd:int"   />
-    <xsd:attribute name="category"                    type="xsd:int"   />
-    <xsd:attribute name="parent_context"              type="xsd:string"/>
-    <xsd:attribute name="parent_category"             type="xsd:int"   />
-    <xsd:attribute name="message"                     type="xsd:string"/>
-  </xsd:complexType>
+    <xsd:complexType name="frameSideDataTimecodeType">
+        <xsd:attribute name="value"              type="xsd:string"/>
+    </xsd:complexType>

-  <xsd:complexType name="frameSideDataListType">
-    <xsd:sequence>
-      <xsd:element name="side_data" type="ffprobe:frameSideDataType" minOccurs="1" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
-  <xsd:complexType name="frameSideDataType">
-    <xsd:sequence>
-      <xsd:element name="timecodes" type="ffprobe:frameSideDataTimecodeList" minOccurs="0" maxOccurs="1"/>
-    </xsd:sequence>
+    <xsd:complexType name="subtitleType">
+      <xsd:attribute name="media_type"         type="xsd:string" fixed="subtitle" use="required"/>
+      <xsd:attribute name="pts"                type="xsd:long" />
+      <xsd:attribute name="pts_time"           type="xsd:float"/>
+      <xsd:attribute name="format"             type="xsd:int"  />
+      <xsd:attribute name="start_display_time" type="xsd:int"  />
+      <xsd:attribute name="end_display_time"   type="xsd:int"  />
+      <xsd:attribute name="num_rects"          type="xsd:int"  />
+    </xsd:complexType>

-    <xsd:attribute name="side_data_type"              type="xsd:string"/>
-    <xsd:attribute name="side_data_size"              type="xsd:int"   />
-    <xsd:attribute name="timecode"                    type="xsd:string"/>
-  </xsd:complexType>
+    <xsd:complexType name="streamsType">
+        <xsd:sequence>
+            <xsd:element name="stream" type="ffprobe:streamType" minOccurs="0" maxOccurs="unbounded"/>
+        </xsd:sequence>
+    </xsd:complexType>

-  <xsd:complexType name="frameSideDataTimecodeList">
-    <xsd:sequence>
-      <xsd:element name="timecode" type="ffprobe:frameSideDataTimecodeType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
+    <xsd:complexType name="programsType">
+        <xsd:sequence>
+            <xsd:element name="program" type="ffprobe:programType" minOccurs="0" maxOccurs="unbounded"/>
+        </xsd:sequence>
+    </xsd:complexType>

-  <xsd:complexType name="frameSideDataTimecodeType">
-    <xsd:attribute name="value"              type="xsd:string"/>
-  </xsd:complexType>
+    <xsd:complexType name="streamDispositionType">
+      <xsd:attribute name="default"          type="xsd:int" use="required" />
+      <xsd:attribute name="dub"              type="xsd:int" use="required" />
+      <xsd:attribute name="original"         type="xsd:int" use="required" />
+      <xsd:attribute name="comment"          type="xsd:int" use="required" />
+      <xsd:attribute name="lyrics"           type="xsd:int" use="required" />
+      <xsd:attribute name="karaoke"          type="xsd:int" use="required" />
+      <xsd:attribute name="forced"           type="xsd:int" use="required" />
+      <xsd:attribute name="hearing_impaired" type="xsd:int" use="required" />
+      <xsd:attribute name="visual_impaired"  type="xsd:int" use="required" />
+      <xsd:attribute name="clean_effects"    type="xsd:int" use="required" />
+      <xsd:attribute name="attached_pic"     type="xsd:int" use="required" />
+      <xsd:attribute name="timed_thumbnails" type="xsd:int" use="required" />
+      <xsd:attribute name="captions"         type="xsd:int" use="required" />
+      <xsd:attribute name="descriptions"     type="xsd:int" use="required" />
+      <xsd:attribute name="metadata"         type="xsd:int" use="required" />
+      <xsd:attribute name="dependent"        type="xsd:int" use="required" />
+      <xsd:attribute name="still_image"      type="xsd:int" use="required" />
+    </xsd:complexType>

-  <xsd:complexType name="subtitleType">
-    <xsd:attribute name="media_type"         type="xsd:string" fixed="subtitle" use="required"/>
-    <xsd:attribute name="pts"                type="xsd:long" />
-    <xsd:attribute name="pts_time"           type="xsd:float"/>
-    <xsd:attribute name="format"             type="xsd:int"  />
-    <xsd:attribute name="start_display_time" type="xsd:int"  />
-    <xsd:attribute name="end_display_time"   type="xsd:int"  />
-    <xsd:attribute name="num_rects"          type="xsd:int"  />
-  </xsd:complexType>
+    <xsd:complexType name="streamType">
+      <xsd:sequence>
+        <xsd:element name="disposition" type="ffprobe:streamDispositionType" minOccurs="0" maxOccurs="1"/>
+        <xsd:element name="tag" type="ffprobe:tagType" minOccurs="0" maxOccurs="unbounded"/>
+        <xsd:element name="side_data_list" type="ffprobe:packetSideDataListType"   minOccurs="0" maxOccurs="1" />
+      </xsd:sequence>

-  <xsd:complexType name="streamsType">
-    <xsd:sequence>
-      <xsd:element name="stream" type="ffprobe:streamType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
+      <xsd:attribute name="index"            type="xsd:int" use="required"/>
+      <xsd:attribute name="codec_name"       type="xsd:string" />
+      <xsd:attribute name="codec_long_name"  type="xsd:string" />
+      <xsd:attribute name="profile"          type="xsd:string" />
+      <xsd:attribute name="codec_type"       type="xsd:string" />
+      <xsd:attribute name="codec_tag"        type="xsd:string" use="required"/>
+      <xsd:attribute name="codec_tag_string" type="xsd:string" use="required"/>
+      <xsd:attribute name="extradata"        type="xsd:string" />
+      <xsd:attribute name="extradata_size"   type="xsd:int"    />
+      <xsd:attribute name="extradata_hash"   type="xsd:string" />

-  <xsd:complexType name="programsType">
-    <xsd:sequence>
-      <xsd:element name="program" type="ffprobe:programType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
+      <!-- video attributes -->
+      <xsd:attribute name="width"                type="xsd:int"/>
+      <xsd:attribute name="height"               type="xsd:int"/>
+      <xsd:attribute name="coded_width"          type="xsd:int"/>
+      <xsd:attribute name="coded_height"         type="xsd:int"/>
+      <xsd:attribute name="closed_captions"      type="xsd:boolean"/>
+      <xsd:attribute name="film_grain"           type="xsd:boolean"/>
+      <xsd:attribute name="has_b_frames"         type="xsd:int"/>
+      <xsd:attribute name="sample_aspect_ratio"  type="xsd:string"/>
+      <xsd:attribute name="display_aspect_ratio" type="xsd:string"/>
+      <xsd:attribute name="pix_fmt"              type="xsd:string"/>
+      <xsd:attribute name="level"                type="xsd:int"/>
+      <xsd:attribute name="color_range"          type="xsd:string"/>
+      <xsd:attribute name="color_space"          type="xsd:string"/>
+      <xsd:attribute name="color_transfer"       type="xsd:string"/>
+      <xsd:attribute name="color_primaries"      type="xsd:string"/>
+      <xsd:attribute name="chroma_location"      type="xsd:string"/>
+      <xsd:attribute name="field_order"          type="xsd:string"/>
+      <xsd:attribute name="refs"                 type="xsd:int"/>

-  <xsd:complexType name="streamDispositionType">
-    <xsd:attribute name="default"          type="xsd:int" use="required" />
-    <xsd:attribute name="dub"              type="xsd:int" use="required" />
-    <xsd:attribute name="original"         type="xsd:int" use="required" />
-    <xsd:attribute name="comment"          type="xsd:int" use="required" />
-    <xsd:attribute name="lyrics"           type="xsd:int" use="required" />
-    <xsd:attribute name="karaoke"          type="xsd:int" use="required" />
-    <xsd:attribute name="forced"           type="xsd:int" use="required" />
-    <xsd:attribute name="hearing_impaired" type="xsd:int" use="required" />
-    <xsd:attribute name="visual_impaired"  type="xsd:int" use="required" />
-    <xsd:attribute name="clean_effects"    type="xsd:int" use="required" />
-    <xsd:attribute name="attached_pic"     type="xsd:int" use="required" />
-    <xsd:attribute name="timed_thumbnails" type="xsd:int" use="required" />
-    <xsd:attribute name="non_diegetic"     type="xsd:int" use="required" />
-    <xsd:attribute name="captions"         type="xsd:int" use="required" />
-    <xsd:attribute name="descriptions"     type="xsd:int" use="required" />
-    <xsd:attribute name="metadata"         type="xsd:int" use="required" />
-    <xsd:attribute name="dependent"        type="xsd:int" use="required" />
-    <xsd:attribute name="still_image"      type="xsd:int" use="required" />
-  </xsd:complexType>
+      <!-- audio attributes -->
+      <xsd:attribute name="sample_fmt"       type="xsd:string"/>
+      <xsd:attribute name="sample_rate"      type="xsd:int"/>
+      <xsd:attribute name="channels"         type="xsd:int"/>
+      <xsd:attribute name="channel_layout"   type="xsd:string"/>
+      <xsd:attribute name="bits_per_sample"  type="xsd:int"/>
+      <xsd:attribute name="initial_padding"  type="xsd:int"/>

-  <xsd:complexType name="streamType">
-    <xsd:sequence>
-      <xsd:element name="disposition" type="ffprobe:streamDispositionType" minOccurs="0" maxOccurs="1"/>
-      <xsd:element name="tags" type="ffprobe:tagsType" minOccurs="0" maxOccurs="1"/>
-      <xsd:element name="side_data_list" type="ffprobe:packetSideDataListType"   minOccurs="0" maxOccurs="1" />
-    </xsd:sequence>
+      <xsd:attribute name="id"               type="xsd:string"/>
+      <xsd:attribute name="r_frame_rate"     type="xsd:string" use="required"/>
+      <xsd:attribute name="avg_frame_rate"   type="xsd:string" use="required"/>
+      <xsd:attribute name="time_base"        type="xsd:string" use="required"/>
+      <xsd:attribute name="start_pts"        type="xsd:long"/>
+      <xsd:attribute name="start_time"       type="xsd:float"/>
+      <xsd:attribute name="duration_ts"      type="xsd:long"/>
+      <xsd:attribute name="duration"         type="xsd:float"/>
+      <xsd:attribute name="bit_rate"         type="xsd:int"/>
+      <xsd:attribute name="max_bit_rate"     type="xsd:int"/>
+      <xsd:attribute name="bits_per_raw_sample" type="xsd:int"/>
+      <xsd:attribute name="nb_frames"        type="xsd:int"/>
+      <xsd:attribute name="nb_read_frames"   type="xsd:int"/>
+      <xsd:attribute name="nb_read_packets"  type="xsd:int"/>
+    </xsd:complexType>

-    <xsd:attribute name="index"            type="xsd:int" use="required"/>
-    <xsd:attribute name="codec_name"       type="xsd:string" />
-    <xsd:attribute name="codec_long_name"  type="xsd:string" />
-    <xsd:attribute name="profile"          type="xsd:string" />
-    <xsd:attribute name="codec_type"       type="xsd:string" />
-    <xsd:attribute name="codec_tag"        type="xsd:string" use="required"/>
-    <xsd:attribute name="codec_tag_string" type="xsd:string" use="required"/>
-    <xsd:attribute name="extradata"        type="xsd:string" />
-    <xsd:attribute name="extradata_size"   type="xsd:int"    />
-    <xsd:attribute name="extradata_hash"   type="xsd:string" />
+    <xsd:complexType name="programType">
+      <xsd:sequence>
+        <xsd:element name="tag" type="ffprobe:tagType" minOccurs="0" maxOccurs="unbounded"/>
+        <xsd:element name="streams" type="ffprobe:streamsType" minOccurs="0" maxOccurs="1"/>
+      </xsd:sequence>

-    <!-- video attributes -->
-    <xsd:attribute name="width"                type="xsd:int"/>
-    <xsd:attribute name="height"               type="xsd:int"/>
-    <xsd:attribute name="coded_width"          type="xsd:int"/>
-    <xsd:attribute name="coded_height"         type="xsd:int"/>
-    <xsd:attribute name="closed_captions"      type="xsd:boolean"/>
-    <xsd:attribute name="film_grain"           type="xsd:boolean"/>
-    <xsd:attribute name="has_b_frames"         type="xsd:int"/>
-    <xsd:attribute name="sample_aspect_ratio"  type="xsd:string"/>
-    <xsd:attribute name="display_aspect_ratio" type="xsd:string"/>
-    <xsd:attribute name="pix_fmt"              type="xsd:string"/>
-    <xsd:attribute name="level"                type="xsd:int"/>
-    <xsd:attribute name="color_range"          type="xsd:string"/>
-    <xsd:attribute name="color_space"          type="xsd:string"/>
-    <xsd:attribute name="color_transfer"       type="xsd:string"/>
-    <xsd:attribute name="color_primaries"      type="xsd:string"/>
-    <xsd:attribute name="chroma_location"      type="xsd:string"/>
-    <xsd:attribute name="field_order"          type="xsd:string"/>
-    <xsd:attribute name="refs"                 type="xsd:int"/>
+      <xsd:attribute name="program_id"           type="xsd:int"    use="required"/>
+      <xsd:attribute name="program_num"          type="xsd:int"    use="required"/>
+      <xsd:attribute name="nb_streams"           type="xsd:int"    use="required"/>
+      <xsd:attribute name="pmt_pid"              type="xsd:int"    use="required"/>
+      <xsd:attribute name="pcr_pid"              type="xsd:int"    use="required"/>
+    </xsd:complexType>

-    <!-- audio attributes -->
-    <xsd:attribute name="sample_fmt"       type="xsd:string"/>
-    <xsd:attribute name="sample_rate"      type="xsd:int"/>
-    <xsd:attribute name="channels"         type="xsd:int"/>
-    <xsd:attribute name="channel_layout"   type="xsd:string"/>
-    <xsd:attribute name="bits_per_sample"  type="xsd:int"/>
-    <xsd:attribute name="initial_padding"  type="xsd:int"/>
+    <xsd:complexType name="formatType">
+      <xsd:sequence>
+        <xsd:element name="tag" type="ffprobe:tagType" minOccurs="0" maxOccurs="unbounded"/>
+      </xsd:sequence>

-    <xsd:attribute name="id"               type="xsd:string"/>
-    <xsd:attribute name="r_frame_rate"     type="xsd:string" use="required"/>
-    <xsd:attribute name="avg_frame_rate"   type="xsd:string" use="required"/>
-    <xsd:attribute name="time_base"        type="xsd:string" use="required"/>
-    <xsd:attribute name="start_pts"        type="xsd:long"/>
-    <xsd:attribute name="start_time"       type="xsd:float"/>
-    <xsd:attribute name="duration_ts"      type="xsd:long"/>
-    <xsd:attribute name="duration"         type="xsd:float"/>
-    <xsd:attribute name="bit_rate"         type="xsd:int"/>
-    <xsd:attribute name="max_bit_rate"     type="xsd:int"/>
-    <xsd:attribute name="bits_per_raw_sample" type="xsd:int"/>
-    <xsd:attribute name="nb_frames"        type="xsd:int"/>
-    <xsd:attribute name="nb_read_frames"   type="xsd:int"/>
-    <xsd:attribute name="nb_read_packets"  type="xsd:int"/>
-  </xsd:complexType>
+      <xsd:attribute name="filename"         type="xsd:string" use="required"/>
+      <xsd:attribute name="nb_streams"       type="xsd:int"    use="required"/>
+      <xsd:attribute name="nb_programs"      type="xsd:int"    use="required"/>
+      <xsd:attribute name="format_name"      type="xsd:string" use="required"/>
+      <xsd:attribute name="format_long_name" type="xsd:string"/>
+      <xsd:attribute name="start_time"       type="xsd:float"/>
+      <xsd:attribute name="duration"         type="xsd:float"/>
+      <xsd:attribute name="size"             type="xsd:long"/>
+      <xsd:attribute name="bit_rate"         type="xsd:long"/>
+      <xsd:attribute name="probe_score"      type="xsd:int"/>
+    </xsd:complexType>

-  <xsd:complexType name="programType">
-    <xsd:sequence>
-      <xsd:element name="tags" type="ffprobe:tagsType" minOccurs="0" maxOccurs="1"/>
-      <xsd:element name="streams" type="ffprobe:streamsType" minOccurs="0" maxOccurs="1"/>
-    </xsd:sequence>
+    <xsd:complexType name="tagType">
+      <xsd:attribute name="key"   type="xsd:string" use="required"/>
+      <xsd:attribute name="value" type="xsd:string" use="required"/>
+    </xsd:complexType>

-    <xsd:attribute name="program_id"           type="xsd:int"    use="required"/>
-    <xsd:attribute name="program_num"          type="xsd:int"    use="required"/>
-    <xsd:attribute name="nb_streams"           type="xsd:int"    use="required"/>
-    <xsd:attribute name="pmt_pid"              type="xsd:int"    use="required"/>
-    <xsd:attribute name="pcr_pid"              type="xsd:int"    use="required"/>
-  </xsd:complexType>
+    <xsd:complexType name="errorType">
+      <xsd:attribute name="code"   type="xsd:int"    use="required"/>
+      <xsd:attribute name="string" type="xsd:string" use="required"/>
+    </xsd:complexType>

-  <xsd:complexType name="formatType">
-    <xsd:sequence>
-      <xsd:element name="tags" type="ffprobe:tagsType" minOccurs="0" maxOccurs="1"/>
-    </xsd:sequence>
+    <xsd:complexType name="programVersionType">
+      <xsd:attribute name="version"          type="xsd:string" use="required"/>
+      <xsd:attribute name="copyright"        type="xsd:string" use="required"/>
+      <xsd:attribute name="build_date"       type="xsd:string"/>
+      <xsd:attribute name="build_time"       type="xsd:string"/>
+      <xsd:attribute name="compiler_ident"   type="xsd:string" use="required"/>
+      <xsd:attribute name="configuration"    type="xsd:string" use="required"/>
+    </xsd:complexType>

-    <xsd:attribute name="filename"         type="xsd:string" use="required"/>
-    <xsd:attribute name="nb_streams"       type="xsd:int"    use="required"/>
-    <xsd:attribute name="nb_programs"      type="xsd:int"    use="required"/>
-    <xsd:attribute name="format_name"      type="xsd:string" use="required"/>
-    <xsd:attribute name="format_long_name" type="xsd:string"/>
-    <xsd:attribute name="start_time"       type="xsd:float"/>
-    <xsd:attribute name="duration"         type="xsd:float"/>
-    <xsd:attribute name="size"             type="xsd:long"/>
-    <xsd:attribute name="bit_rate"         type="xsd:long"/>
-    <xsd:attribute name="probe_score"      type="xsd:int"/>
-  </xsd:complexType>
+    <xsd:complexType name="chaptersType">
+      <xsd:sequence>
+        <xsd:element name="chapter" type="ffprobe:chapterType" minOccurs="0" maxOccurs="unbounded"/>
+      </xsd:sequence>
+    </xsd:complexType>

-  <xsd:complexType name="tagType">
-    <xsd:attribute name="key"   type="xsd:string" use="required"/>
-    <xsd:attribute name="value" type="xsd:string" use="required"/>
-  </xsd:complexType>
+    <xsd:complexType name="chapterType">
+      <xsd:sequence>
+        <xsd:element name="tag" type="ffprobe:tagType" minOccurs="0" maxOccurs="unbounded"/>
+      </xsd:sequence>

-  <xsd:complexType name="errorType">
-    <xsd:attribute name="code"   type="xsd:int"    use="required"/>
-    <xsd:attribute name="string" type="xsd:string" use="required"/>
-  </xsd:complexType>
+      <xsd:attribute name="id"         type="xsd:int" use="required"/>
+      <xsd:attribute name="time_base"  type="xsd:string" use="required"/>
+      <xsd:attribute name="start"      type="xsd:int" use="required"/>
+      <xsd:attribute name="start_time" type="xsd:float"/>
+      <xsd:attribute name="end"        type="xsd:int" use="required"/>
+      <xsd:attribute name="end_time"   type="xsd:float" use="required"/>
+    </xsd:complexType>

-  <xsd:complexType name="programVersionType">
-    <xsd:attribute name="version"          type="xsd:string" use="required"/>
-    <xsd:attribute name="copyright"        type="xsd:string" use="required"/>
-    <xsd:attribute name="build_date"       type="xsd:string"/>
-    <xsd:attribute name="build_time"       type="xsd:string"/>
-    <xsd:attribute name="compiler_ident"   type="xsd:string" use="required"/>
-    <xsd:attribute name="configuration"    type="xsd:string" use="required"/>
-  </xsd:complexType>
+    <xsd:complexType name="libraryVersionType">
+      <xsd:attribute name="name"        type="xsd:string" use="required"/>
+      <xsd:attribute name="major"       type="xsd:int"    use="required"/>
+      <xsd:attribute name="minor"       type="xsd:int"    use="required"/>
+      <xsd:attribute name="micro"       type="xsd:int"    use="required"/>
+      <xsd:attribute name="version"     type="xsd:int"    use="required"/>
+      <xsd:attribute name="ident"       type="xsd:string" use="required"/>
+    </xsd:complexType>

-  <xsd:complexType name="chaptersType">
-    <xsd:sequence>
-      <xsd:element name="chapter" type="ffprobe:chapterType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
+    <xsd:complexType name="libraryVersionsType">
+        <xsd:sequence>
+          <xsd:element name="library_version" type="ffprobe:libraryVersionType" minOccurs="0" maxOccurs="unbounded"/>
+        </xsd:sequence>
+    </xsd:complexType>

-  <xsd:complexType name="chapterType">
-    <xsd:sequence>
-      <xsd:element name="tags" type="ffprobe:tagsType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
+    <xsd:complexType name="pixelFormatFlagsType">
+      <xsd:attribute name="big_endian" type="xsd:int" use="required"/>
+      <xsd:attribute name="palette"    type="xsd:int" use="required"/>
+      <xsd:attribute name="bitstream"  type="xsd:int" use="required"/>
+      <xsd:attribute name="hwaccel"    type="xsd:int" use="required"/>
+      <xsd:attribute name="planar"     type="xsd:int" use="required"/>
+      <xsd:attribute name="rgb"        type="xsd:int" use="required"/>
+      <xsd:attribute name="alpha"      type="xsd:int" use="required"/>
+    </xsd:complexType>

-    <xsd:attribute name="id"         type="xsd:int" use="required"/>
-    <xsd:attribute name="time_base"  type="xsd:string" use="required"/>
-    <xsd:attribute name="start"      type="xsd:int" use="required"/>
-    <xsd:attribute name="start_time" type="xsd:float"/>
-    <xsd:attribute name="end"        type="xsd:int" use="required"/>
-    <xsd:attribute name="end_time"   type="xsd:float" use="required"/>
-  </xsd:complexType>
+    <xsd:complexType name="pixelFormatComponentType">
+      <xsd:attribute name="index"      type="xsd:int" use="required"/>
+      <xsd:attribute name="bit_depth"  type="xsd:int" use="required"/>
+    </xsd:complexType>

-  <xsd:complexType name="libraryVersionType">
-    <xsd:attribute name="name"        type="xsd:string" use="required"/>
-    <xsd:attribute name="major"       type="xsd:int"    use="required"/>
-    <xsd:attribute name="minor"       type="xsd:int"    use="required"/>
-    <xsd:attribute name="micro"       type="xsd:int"    use="required"/>
-    <xsd:attribute name="version"     type="xsd:int"    use="required"/>
-    <xsd:attribute name="ident"       type="xsd:string" use="required"/>
-  </xsd:complexType>
+    <xsd:complexType name="pixelFormatComponentsType">
+      <xsd:sequence>
+        <xsd:element name="component" type="ffprobe:pixelFormatComponentType" minOccurs="0" maxOccurs="unbounded"/>
+      </xsd:sequence>
+    </xsd:complexType>

-  <xsd:complexType name="libraryVersionsType">
-    <xsd:sequence>
-      <xsd:element name="library_version" type="ffprobe:libraryVersionType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
+    <xsd:complexType name="pixelFormatType">
+      <xsd:sequence>
+        <xsd:element name="flags" type="ffprobe:pixelFormatFlagsType" minOccurs="0" maxOccurs="1"/>
+        <xsd:element name="components" type="ffprobe:pixelFormatComponentsType" minOccurs="0" maxOccurs="1"/>
+      </xsd:sequence>

-  <xsd:complexType name="pixelFormatFlagsType">
-    <xsd:attribute name="big_endian" type="xsd:int" use="required"/>
-    <xsd:attribute name="palette"    type="xsd:int" use="required"/>
-    <xsd:attribute name="bitstream"  type="xsd:int" use="required"/>
-    <xsd:attribute name="hwaccel"    type="xsd:int" use="required"/>
-    <xsd:attribute name="planar"     type="xsd:int" use="required"/>
-    <xsd:attribute name="rgb"        type="xsd:int" use="required"/>
-    <xsd:attribute name="alpha"      type="xsd:int" use="required"/>
-  </xsd:complexType>
+      <xsd:attribute name="name"                type="xsd:string" use="required"/>
+      <xsd:attribute name="nb_components"       type="xsd:int"    use="required"/>
+      <xsd:attribute name="log2_chroma_w"       type="xsd:int"/>
+      <xsd:attribute name="log2_chroma_h"       type="xsd:int"/>
+      <xsd:attribute name="bits_per_pixel"      type="xsd:int"/>
+    </xsd:complexType>

-  <xsd:complexType name="pixelFormatComponentType">
-    <xsd:attribute name="index"      type="xsd:int" use="required"/>
-    <xsd:attribute name="bit_depth"  type="xsd:int" use="required"/>
-  </xsd:complexType>
-
-  <xsd:complexType name="pixelFormatComponentsType">
-    <xsd:sequence>
-      <xsd:element name="component" type="ffprobe:pixelFormatComponentType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
-
-  <xsd:complexType name="pixelFormatType">
-    <xsd:sequence>
-      <xsd:element name="flags" type="ffprobe:pixelFormatFlagsType" minOccurs="0" maxOccurs="1"/>
-      <xsd:element name="components" type="ffprobe:pixelFormatComponentsType" minOccurs="0" maxOccurs="1"/>
-    </xsd:sequence>
-
-    <xsd:attribute name="name"                type="xsd:string" use="required"/>
-    <xsd:attribute name="nb_components"       type="xsd:int"    use="required"/>
-    <xsd:attribute name="log2_chroma_w"       type="xsd:int"/>
-    <xsd:attribute name="log2_chroma_h"       type="xsd:int"/>
-    <xsd:attribute name="bits_per_pixel"      type="xsd:int"/>
-  </xsd:complexType>
-
-  <xsd:complexType name="pixelFormatsType">
-    <xsd:sequence>
-      <xsd:element name="pixel_format" type="ffprobe:pixelFormatType" minOccurs="0" maxOccurs="unbounded"/>
-    </xsd:sequence>
-  </xsd:complexType>
+    <xsd:complexType name="pixelFormatsType">
+      <xsd:sequence>
+        <xsd:element name="pixel_format" type="ffprobe:pixelFormatType" minOccurs="0" maxOccurs="unbounded"/>
+      </xsd:sequence>
+    </xsd:complexType>
 </xsd:schema>
--- a/doc/filters.texi
+++ b/doc/filters.texi
--- a/doc/general_contents.texi
+++ b/doc/general_contents.texi
@@ -615,7 +615,6 @@ library:
@item raw video                 @tab X @tab X
@item raw id RoQ                @tab X @tab
@item raw OBU                   @tab X @tab X
-@item raw OSQ                   @tab   @tab X
@item raw SBC                   @tab X @tab X
@item raw Shorten               @tab   @tab X
@item raw TAK                   @tab   @tab X
@@ -1007,7 +1006,7 @@ following image formats are supported:
    @tab Also known as Microsoft Screen 3.
@item Microsoft Expression Encoder Screen  @tab     @tab  X
    @tab Also known as Microsoft Titanium Screen 2.
-@item Microsoft RLE          @tab  X  @tab  X
+@item Microsoft RLE          @tab     @tab  X
@item Microsoft Screen 1     @tab     @tab  X
    @tab Also known as Windows Media Video V7 Screen.
@item Microsoft Screen 2     @tab     @tab  X
@@ -1067,8 +1066,6 @@ following image formats are supported:
@item RealVideo 4.0          @tab     @tab  X
@item Renderware TXD (TeXture Dictionary)  @tab     @tab  X
    @tab Texture dictionaries used by the Renderware Engine.
-@item RivaTuner Video        @tab     @tab  X
-    @tab fourcc: 'RTV1'
@item RL2 video              @tab     @tab  X
    @tab used in some games by Entertainment Software Partners
@item ScreenPressor          @tab     @tab  X
@@ -1105,8 +1102,6 @@ following image formats are supported:
@item v408 QuickTime uncompressed 4:4:4:4          @tab  X  @tab  X
@item v410 QuickTime uncompressed 4:4:4 10-bit     @tab  X  @tab  X
@item VBLE Lossless Codec    @tab     @tab  X
-@item vMix Video             @tab     @tab  X
-    @tab fourcc: 'VMX1'
@item VMware Screen Codec / VMware Video  @tab     @tab  X
    @tab Codec used in videos captured by VMware.
@item Westwood Studios VQA (Vector Quantized Animation) video  @tab     @tab  X
@@ -1299,7 +1294,6 @@ following image formats are supported:
@item On2 AVC (Audio for Video Codec) @tab     @tab  X
@item Opus                   @tab  E  @tab  X
    @tab encoding supported through external library libopus
-@item OSQ (Original Sound Quality)  @tab     @tab  X
@item PCM A-law              @tab  X  @tab  X
@item PCM mu-law             @tab  X  @tab  X
@item PCM Archimedes VIDC    @tab  X  @tab  X
--- a/doc/indevs.texi
+++ b/doc/indevs.texi
@@ -991,8 +991,9 @@ This input device reads data from the open output pads of a libavfilter
 filtergraph.

 For each filtergraph open output, the input device will create a
-corresponding stream which is mapped to the generated output.
-The filtergraph is specified through the option @option{graph}.
+corresponding stream which is mapped to the generated output. Currently
+only video data is supported. The filtergraph is specified through the
+option @option{graph}.

@subsection Options

--- a/doc/mailing-list-faq.texi
+++ b/doc/mailing-list-faq.texi
@@ -344,7 +344,7 @@ recommended.
 Avoid sending the same message to multiple mailing lists.

@item
-Please follow our @url{https://ffmpeg.org/community.html#Code-of-conduct, Code of Conduct}.
+Please follow our @url{https://ffmpeg.org/developer.html#Code-of-conduct, Code of Conduct}.
@end itemize

@chapter Help
--- a/doc/mips.txt
+++ b/doc/mips.txt
@@ -48,6 +48,11 @@ Files that have MIPS copyright notice in them:
      float_dsp_mips.c
      libm_mips.h
      softfloat_tables.h
+* libavcodec/
+      fft_fixed_32.c
+      fft_init_table.c
+      fft_table.h
+      mdct_fixed_32.c
 * libavcodec/mips/
      aacdec_fixed.c
      aacsbr_fixed.c
@@ -65,6 +70,9 @@ Files that have MIPS copyright notice in them:
      compute_antialias_float.h
      lsp_mips.h
      dsputil_mips.c
+      fft_mips.c
+      fft_table.h
+      fft_init_table.c
      fmtconvert_mips.c
      iirfilter_mips.c
      mpegaudiodsp_mips_fixed.c
--- a/doc/multithreading.txt
+++ b/doc/multithreading.txt
@@ -55,7 +55,8 @@ speed gain at this point but it should work.

 If there are inter-frame dependencies, so the codec calls
 ff_thread_report/await_progress(), set FF_CODEC_CAP_ALLOCATE_PROGRESS in
-FFCodec.caps_internal and use ff_thread_get_buffer() to allocate frames.
+AVCodec.caps_internal and use ff_thread_get_buffer() to allocate frames. The
+frames must then be freed with ff_thread_release_buffer().
 Otherwise decode directly into the user-supplied frames.

 Call ff_thread_report_progress() after some part of the current picture has decoded.
--- a/doc/muxers.texi
+++ b/doc/muxers.texi
@@ -1325,7 +1325,7 @@ Use persistent HTTP connections. Applicable only for HTTP output.
@item timeout
 Set timeout for socket I/O operations. Applicable only for HTTP output.

-@item ignore_io_errors
+@item -ignore_io_errors
 Ignore IO errors during open, write and delete. Useful for long-duration runs with network output.

@item headers
@@ -1468,7 +1468,7 @@ ffmpeg -f v4l2 -r 1 -i /dev/video0 -f image2 -strftime 1 "%Y-%m-%d_%H-%M-%S.jpg"

 You can set the file name with current frame's PTS:
@example
-ffmpeg -f v4l2 -r 1 -i /dev/video0 -copyts -f image2 -frame_pts true %d.jpg
+ffmpeg -f v4l2 -r 1 -i /dev/video0 -copyts -f image2 -frame_pts true %d.jpg"
@end example

 A more complex example is to publish contents of your desktop directly to a
@@ -1630,10 +1630,8 @@ MOV/MP4/ISMV (Smooth Streaming) muxer.
 The mov/mp4/ismv muxer supports fragmentation. Normally, a MOV/MP4
 file has all the metadata about all packets stored in one location
 (written at the end of the file, it can be moved to the start for
-better playback by adding @code{+faststart} to the @code{-movflags}, or
-using the @command{qt-faststart} tool).
-
-A fragmented
+better playback by adding @var{faststart} to the @var{movflags}, or
+using the @command{qt-faststart} tool). A fragmented
 file consists of a number of fragments, where packets and metadata
 about these packets are stored together. Writing a fragmented
 file has the advantage that the file is decodable even if the
@@ -1643,34 +1641,40 @@ very long files (since writing normal MOV/MP4 files stores info about
 every single packet in memory until the file is closed). The downside
 is that it is less compatible with other applications.

-Fragmentation is enabled by setting one of the options that define
-how to cut the file into fragments: @code{-frag_duration}, @code{-frag_size},
-@code{-min_frag_duration}, @code{-movflags +frag_keyframe} and
-@code{-movflags +frag_custom}. If more than one condition is specified,
-fragments are cut when one of the specified conditions is fulfilled. The
-exception to this is @code{-min_frag_duration}, which has to be fulfilled for
-any of the other conditions to apply.
-
@subsection Options

+Fragmentation is enabled by setting one of the AVOptions that define
+how to cut the file into fragments:
+
@table @option
-@item frag_duration @var{duration}
-Create fragments that are @var{duration} microseconds long.
-@item frag_size @var{size}
-Create fragments that contain up to @var{size} bytes of payload data.
-@item min_frag_duration @var{duration}
-Don't create fragments that are shorter than @var{duration} microseconds long.
-@item movflags @var{flags}
-Set various muxing switches. The following flags can be used:
-@table @samp
-@item frag_keyframe
+@item -moov_size @var{bytes}
+Reserves space for the moov atom at the beginning of the file instead of placing the
+moov atom at the end. If the space reserved is insufficient, muxing will fail.
+@item -movflags frag_keyframe
 Start a new fragment at each video keyframe.
-@item frag_custom
+@item -frag_duration @var{duration}
+Create fragments that are @var{duration} microseconds long.
+@item -frag_size @var{size}
+Create fragments that contain up to @var{size} bytes of payload data.
+@item -movflags frag_custom
 Allow the caller to manually choose when to cut fragments, by
 calling @code{av_write_frame(ctx, NULL)} to write a fragment with
 the packets written so far. (This is only useful with other
 applications integrating libavformat, not from @command{ffmpeg}.)
-@item empty_moov
+@item -min_frag_duration @var{duration}
+Don't create fragments that are shorter than @var{duration} microseconds long.
+@end table
+
+If more than one condition is specified, fragments are cut when
+one of the specified conditions is fulfilled. The exception to this is
+@code{-min_frag_duration}, which has to be fulfilled for any of the other
+conditions to apply.
+
+Additionally, the way the output file is written can be adjusted
+through a few other options:
+
+@table @option
+@item -movflags empty_moov
 Write an initial moov atom directly at the start of the file, without
 describing any samples in it. Generally, an mdat/moov pair is written
 at the start of the file, as a normal MOV/MP4 file, containing only
@@ -1679,40 +1683,43 @@ mdat atom, and the moov atom only describes the tracks but has
 a zero duration.

 This option is implicitly set when writing ismv (Smooth Streaming) files.
-@item separate_moof
+@item -movflags separate_moof
 Write a separate moof (movie fragment) atom for each track. Normally,
 packets for all tracks are written in a moof atom (which is slightly
 more efficient), but with this option set, the muxer writes one moof/mdat
 pair for each track, making it easier to separate tracks.

 This option is implicitly set when writing ismv (Smooth Streaming) files.
-@item skip_sidx
+@item -movflags skip_sidx
 Skip writing of sidx atom. When bitrate overhead due to sidx atom is high,
 this option could be used for cases where sidx atom is not mandatory.
 When global_sidx flag is enabled, this option will be ignored.
-@item faststart
+@item -movflags faststart
 Run a second pass moving the index (moov atom) to the beginning of the file.
 This operation can take a while, and will not work in various situations such
 as fragmented output, thus it is not enabled by default.
-@item rtphint
+@item -movflags rtphint
 Add RTP hinting tracks to the output file.
-@item disable_chpl
+@item -movflags disable_chpl
 Disable Nero chapter markers (chpl atom).  Normally, both Nero chapters
 and a QuickTime chapter track are written to the file. With this option
 set, only the QuickTime chapter track will be written. Nero chapters can
 cause failures when the file is reprocessed with certain tagging programs, like
 mp3Tag 2.61a and iTunes 11.3, most likely other versions are affected as well.
-@item omit_tfhd_offset
+@item -movflags omit_tfhd_offset
 Do not write any absolute base_data_offset in tfhd atoms. This avoids
 tying fragments to absolute byte positions in the file/streams.
-@item default_base_moof
+@item -movflags default_base_moof
 Similarly to the omit_tfhd_offset, this flag avoids writing the
 absolute base_data_offset field in tfhd atoms, but does so by using
 the new default-base-is-moof flag instead. This flag is new from
 14496-12:2012. This may make the fragments easier to parse in certain
 circumstances (avoiding basing track fragment location calculations
 on the implicit end of the previous track fragment).
-@item negative_cts_offsets
+@item -write_tmcd
+Specify @code{on} to force writing a timecode track, @code{off} to disable it
+and @code{auto} to write a timecode track only for mov and mp4 output (default).
+@item -movflags negative_cts_offsets
 Enables utilization of version 1 of the CTTS box, in which the CTS offsets can
 be negative. This enables the initial sample to have DTS/CTS of zero, and
 reduces the need for edit lists for some cases such as video tracks with
@@ -1720,24 +1727,15 @@ B-frames. Additionally, eases conformance with the DASH-IF interoperability
 guidelines.

 This option is implicitly set when writing ismv (Smooth Streaming) files.
-@end table

-@item moov_size @var{bytes}
-Reserves space for the moov atom at the beginning of the file instead of placing the
-moov atom at the end. If the space reserved is insufficient, muxing will fail.
-
-@item write_tmcd
-Specify @code{on} to force writing a timecode track, @code{off} to disable it
-and @code{auto} to write a timecode track only for mov and mp4 output (default).
-
-@item write_btrt @var{bool}
+@item -write_btrt @var{bool}
 Force or disable writing bitrate box inside stsd box of a track.
 The box contains decoding buffer size (in bytes), maximum bitrate and
 average bitrate for the track. The box will be skipped if none of these values
 can be computed.
 Default is @code{-1} or @code{auto}, which will write the box only in MP4 mode.

-@item write_prft
+@item -write_prft
 Write producer time reference box (PRFT) with a specified time source for the
 NTP field in the PRFT box. Set value as @samp{wallclock} to specify timesource
 as wallclock time and @samp{pts} to specify timesource as input packets' PTS
@@ -1748,15 +1746,15 @@ where PTS values are set as as wallclock time at the source. For example, an
 encoding use case with decklink capture source where @option{video_pts} and
@option{audio_pts} are set to @samp{abs_wallclock}.

-@item empty_hdlr_name @var{bool}
+@item -empty_hdlr_name @var{bool}
 Enable to skip writing the name inside a @code{hdlr} box.
 Default is @code{false}.

-@item movie_timescale @var{scale}
+@item -movie_timescale @var{scale}
 Set the timescale written in the movie header box (@code{mvhd}).
 Range is 1 to INT_MAX. Default is 1000.

-@item video_track_timescale @var{scale}
+@item -video_track_timescale @var{scale}
 Set the timescale used for video tracks. Range is 0 to INT_MAX.
 If set to @code{0}, the timescale is automatically set based on
 the native stream time base. Default is 0.
@@ -2122,12 +2120,6 @@ DTS Coherent Acoustics (DCA) audio.

 Dolby Digital Plus, also known as Enhanced AC-3, audio.

-@subsection evc
-
-MPEG-5 Essential Video Coding (EVC) / EVC / MPEG-5 Part 1 EVC video.
-
-Extensions: evc
-
@subsection g722

 ITU-T G.722 audio.
--- a/doc/outdevs.texi
+++ b/doc/outdevs.texi
@@ -235,11 +235,6 @@ Enable SMPTE Level A mode on the used output.
 Must be @samp{unset}, @samp{true} or @samp{false}.
 Defaults to @option{unset}.

-@item vanc_queue_size
-Sets maximum output buffer size in bytes for VANC data. If the buffering reaches this value,
-outgoing VANC data will be dropped.
-Defaults to @samp{1048576}.
-
@end table

@subsection Examples
@@ -426,18 +421,13 @@ For more information about SDL, check:

@table @option

-@item window_borderless
-Set SDL window border off.
-Default value is 0 (enable window border).
+@item window_title
+Set the SDL window title, if not specified default to the filename
+specified for the output device.

-@item window_enable_quit
-Enable quit action (using window button or keyboard key)
-when non-zero value is provided.
-Default value is 1 (enable quit action).
-
-@item window_fullscreen
-Set fullscreen mode when non-zero value is provided.
-Default value is zero.
+@item icon_title
+Set the name of the iconified SDL window, if not specified it is set
+to the same value of @var{window_title}.

@item window_size
 Set the SDL window size, can be a string of the form
@@ -445,13 +435,18 @@ Set the SDL window size, can be a string of the form
 If not specified it defaults to the size of the input video,
 downscaled according to the aspect ratio.

-@item window_title
-Set the SDL window title, if not specified default to the filename
-specified for the output device.
-
@item window_x
@item window_y
 Set the position of the window on the screen.
+
+@item window_fullscreen
+Set fullscreen mode when non-zero value is provided.
+Default value is zero.
+
+@item window_enable_quit
+Enable quit action (using window button or keyboard key)
+when non-zero value is provided.
+Default value is 1 (enable quit action)
@end table

@subsection Interactive commands
--- a/doc/platform.texi
+++ b/doc/platform.texi
@@ -92,6 +92,9 @@ For information about compiling FFmpeg on OS/2 see

@chapter Windows

+To get help and instructions for building FFmpeg under Windows, check out
+the FFmpeg Windows Help Forum at @url{http://ffmpeg.zeranoe.com/forum/}.
+
@section Native Windows compilation using MinGW or MinGW-w64

 FFmpeg can be built to run natively on Windows using the MinGW-w64
--- a/doc/protocols.texi
+++ b/doc/protocols.texi
@@ -896,13 +896,6 @@ be named, by prefixing the type with 'N' and specifying the name before
 the value (i.e. @code{NB:myFlag:1}). This option may be used multiple
 times to construct arbitrary AMF sequences.

-@item rtmp_enhanced_codecs
-Specify the list of codecs the client advertises to support in an
-enhanced RTMP stream. This option should be set to a comma separated
-list of fourcc values, like @code{hvc1,av01,vp09} for multiple codecs
-or @code{hvc1} for only one codec. The specified list will be presented
-in the "fourCcLive" property of the Connect Command Message.
-
@item rtmp_flashver
 Version of the Flash plugin used to run the SWF player. The default
 is LNX 9,0,124,2. (When publishing, the default is FMLE/3.0 (compatible;
@@ -1889,12 +1882,6 @@ The list of supported options follows.
 Listen for an incoming connection. 0 disables listen, 1 enables listen in
 single client mode, 2 enables listen in multi-client mode. Default value is 0.

-@item local_addr=@var{addr}
-Local IP address of a network interface used for tcp socket connect.
-
-@item local_port=@var{port}
-Local port used for tcp socket connect.
-
@item timeout=@var{microseconds}
 Set raise error timeout, expressed in microseconds.

--- a/doc/t2h.pm
+++ b/doc/t2h.pm
@@ -20,8 +20,45 @@
 # License along with FFmpeg; if not, write to the Free Software
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA

+# Texinfo 7.0 changed the syntax of various functions.
+# Provide a shim for older versions.
+sub ff_set_from_init_file($$) {
+    my $key = shift;
+    my $value = shift;
+    if (exists &{'texinfo_set_from_init_file'}) {
+        texinfo_set_from_init_file($key, $value);
+    } else {
+        set_from_init_file($key, $value);
+    }
+}
+
+sub ff_get_conf($) {
+    my $key = shift;
+    if (exists &{'texinfo_get_conf'}) {
+        texinfo_get_conf($key);
+    } else {
+        get_conf($key);
+    }
+}
+
+sub get_formatting_function($$) {
+    my $obj = shift;
+    my $func = shift;
+
+    my $sub = $obj->can('formatting_function');
+    if ($sub) {
+        return $obj->formatting_function($func);
+    } else {
+        return $obj->{$func};
+    }
+}
+
+# determine texinfo version
+my $program_version_num = version->declare(ff_get_conf('PACKAGE_VERSION'))->numify;
+my $program_version_6_8 = $program_version_num >= 6.008000;
+
 # no navigation elements
-set_from_init_file('HEADERS', 0);
+ff_set_from_init_file('HEADERS', 0);

 sub ffmpeg_heading_command($$$$$)
 {
@@ -55,7 +92,7 @@ sub ffmpeg_heading_command($$$$$)
        $element = $command->{'parent'};
    }
    if ($element) {
-        $result .= &{$self->{'format_element_header'}}($self, $cmdname,
+        $result .= &{get_formatting_function($self, 'format_element_header')}($self, $cmdname,
                                                       $command, $element);
    }

@@ -112,7 +149,11 @@ sub ffmpeg_heading_command($$$$$)
                $cmdname
                    = $Texinfo::Common::level_to_structuring_command{$cmdname}->[$heading_level];
            }
-            $result .= &{$self->{'format_heading_text'}}(
+            # format_heading_text expects an array of headings for texinfo >= 7.0
+            if ($program_version_num >= 7.000000) {
+                $heading = [$heading];
+            }
+            $result .= &{get_formatting_function($self,'format_heading_text')}(
                        $self, $cmdname, $heading,
                        $heading_level +
                        $self->get_conf('CHAPTER_HEADER_LEVEL') - 1, $command);
@@ -126,23 +167,19 @@ foreach my $command (keys(%Texinfo::Common::sectioning_commands), 'node') {
    texinfo_register_command_formatting($command, \&ffmpeg_heading_command);
 }

-# determine if texinfo is at least version 6.8
-my $program_version_num = version->declare(get_conf('PACKAGE_VERSION'))->numify;
-my $program_version_6_8 = $program_version_num >= 6.008000;
-
 # print the TOC where @contents is used
 if ($program_version_6_8) {
-    set_from_init_file('CONTENTS_OUTPUT_LOCATION', 'inline');
+    ff_set_from_init_file('CONTENTS_OUTPUT_LOCATION', 'inline');
 } else {
-    set_from_init_file('INLINE_CONTENTS', 1);
+    ff_set_from_init_file('INLINE_CONTENTS', 1);
 }

 # make chapters <h2>
-set_from_init_file('CHAPTER_HEADER_LEVEL', 2);
+ff_set_from_init_file('CHAPTER_HEADER_LEVEL', 2);

 # Do not add <hr>
-set_from_init_file('DEFAULT_RULE', '');
-set_from_init_file('BIG_RULE', '');
+ff_set_from_init_file('DEFAULT_RULE', '');
+ff_set_from_init_file('BIG_RULE', '');

 # Customized file beginning
 sub ffmpeg_begin_file($$$)
@@ -159,7 +196,18 @@ sub ffmpeg_begin_file($$$)
    my ($title, $description, $encoding, $date, $css_lines,
        $doctype, $bodytext, $copying_comment, $after_body_open,
        $extra_head, $program_and_version, $program_homepage,
-        $program, $generator) = $self->_file_header_informations($command);
+        $program, $generator);
+    if ($program_version_num >= 7.000000) {
+        ($title, $description, $encoding, $date, $css_lines,
+         $doctype, $bodytext, $copying_comment, $after_body_open,
+         $extra_head, $program_and_version, $program_homepage,
+         $program, $generator) = $self->_file_header_information($command);
+    } else {
+        ($title, $description, $encoding, $date, $css_lines,
+         $doctype, $bodytext, $copying_comment, $after_body_open,
+         $extra_head, $program_and_version, $program_homepage,
+         $program, $generator) = $self->_file_header_informations($command);
+    }

    my $links = $self->_get_links ($filename, $element);

@@ -223,7 +271,7 @@ if ($program_version_6_8) {
 sub ffmpeg_end_file($)
 {
    my $self = shift;
-    my $program_string = &{$self->{'format_program_string'}}($self);
+    my $program_string = &{get_formatting_function($self,'format_program_string')}($self);
    my $program_text = <<EOT;
      <p style="font-size: small;">
        $program_string
@@ -244,7 +292,7 @@ if ($program_version_6_8) {

 # Dummy title command
 # Ignore title. Title is handled through ffmpeg_begin_file().
-set_from_init_file('USE_TITLEPAGE_FOR_TITLE', 1);
+ff_set_from_init_file('USE_TITLEPAGE_FOR_TITLE', 1);
 sub ffmpeg_title($$$$)
 {
    return '';
@@ -262,8 +310,14 @@ sub ffmpeg_float($$$$$)
    my $args = shift;
    my $content = shift;

-    my ($caption, $prepended) = Texinfo::Common::float_name_caption($self,
-                                                                $command);
+    my ($caption, $prepended);
+    if ($program_version_num >= 7.000000) {
+        ($caption, $prepended) = Texinfo::Convert::Converter::float_name_caption($self,
+                                                                                 $command);
+    } else {
+        ($caption, $prepended) = Texinfo::Common::float_name_caption($self,
+                                                                     $command);
+    }
    my $caption_text = '';
    my $prepended_text;
    my $prepended_save = '';
@@ -335,8 +389,13 @@ sub ffmpeg_float($$$$$)
            $caption->{'args'}->[0], 'float caption');
    }
    if ($prepended_text.$caption_text ne '') {
-        $prepended_text = $self->_attribute_class('div','float-caption'). '>'
-                . $prepended_text;
+        if ($program_version_num >= 7.000000) {
+            $prepended_text = $self->html_attribute_class('div',['float-caption']). '>'
+                    . $prepended_text;
+        } else {
+            $prepended_text = $self->_attribute_class('div','float-caption'). '>'
+                    . $prepended_text;
+        }
        $caption_text .= '</div>';
    }
    my $html_class = '';
@@ -349,8 +408,13 @@ sub ffmpeg_float($$$$$)
        $prepended_text = '';
        $caption_text   = '';
    }
-    return $self->_attribute_class('div', $html_class). '>' . "\n" .
-        $prepended_text . $caption_text . $content . '</div>';
+    if ($program_version_num >= 7.000000) {
+        return $self->html_attribute_class('div', [$html_class]). '>' . "\n" .
+            $prepended_text . $caption_text . $content . '</div>';
+    } else {
+        return $self->_attribute_class('div', $html_class). '>' . "\n" .
+            $prepended_text . $caption_text . $content . '</div>';
+    }
 }

 texinfo_register_command_formatting('float',
--- a/doc/utils.texi
+++ b/doc/utils.texi
@@ -695,8 +695,6 @@ FL+FR+FC+LFE+SL+SR
 FL+FR+FC+BC+SL+SR
@item 6.0(front)
 FL+FR+FLC+FRC+SL+SR
-@item 3.1.2
-FL+FR+FC+LFE+TFL+TFR
@item hexagonal
 FL+FR+FC+BL+BR+BC
@item 6.1
@@ -715,18 +713,12 @@ FL+FR+FC+LFE+BL+BR+SL+SR
 FL+FR+FC+LFE+BL+BR+FLC+FRC
@item 7.1(wide-side)
 FL+FR+FC+LFE+FLC+FRC+SL+SR
-@item 5.1.2
+@item 7.1(top)
 FL+FR+FC+LFE+BL+BR+TFL+TFR
@item octagonal
 FL+FR+FC+BL+BR+BC+SL+SR
@item cube
 FL+FR+BL+BR+TFL+TFR+TBL+TBR
-@item 5.1.4
-FL+FR+FC+LFE+BL+BR+TFL+TFR+TBL+TBR
-@item 7.1.2
-FL+FR+FC+LFE+BL+BR+SL+SR+TFL+TFR
-@item 7.1.4
-FL+FR+FC+LFE+BL+BR+SL+SR+TFL+TFR+TBL+TBR
@item hexadecagonal
 FL+FR+FC+BL+BR+BC+SL+SR+WL+WR+TBL+TBR+TBC+TFC+TFL+TFR
@item downmix
--- a/fftools/Makefile
+++ b/fftools/Makefile
@@ -10,9 +10,7 @@ ALLAVPROGS   = $(AVBASENAMES:%=%$(PROGSSUF)$(EXESUF))
 ALLAVPROGS_G = $(AVBASENAMES:%=%$(PROGSSUF)_g$(EXESUF))

 OBJS-ffmpeg +=                  \
-    fftools/ffmpeg_dec.o        \
    fftools/ffmpeg_demux.o      \
-    fftools/ffmpeg_enc.o        \
    fftools/ffmpeg_filter.o     \
    fftools/ffmpeg_hw.o         \
    fftools/ffmpeg_mux.o        \
--- a/fftools/cmdutils.c
+++ b/fftools/cmdutils.c
@@ -83,8 +83,29 @@ void init_dynload(void)
 #endif
 }

-int parse_number(const char *context, const char *numstr, int type,
-                 double min, double max, double *dst)
+static void (*program_exit)(int ret);
+
+void register_exit(void (*cb)(int ret))
+{
+    program_exit = cb;
+}
+
+void report_and_exit(int ret)
+{
+    av_log(NULL, AV_LOG_FATAL, "%s\n", av_err2str(ret));
+    exit_program(AVUNERROR(ret));
+}
+
+void exit_program(int ret)
+{
+    if (program_exit)
+        program_exit(ret);
+
+    exit(ret);
+}
+
+double parse_number_or_die(const char *context, const char *numstr, int type,
+                           double min, double max)
 {
    char *tail;
    const char *error;
@@ -97,13 +118,23 @@ int parse_number(const char *context, const char *numstr, int type,
        error = "Expected int64 for %s but found %s\n";
    else if (type == OPT_INT && (int)d != d)
        error = "Expected int for %s but found %s\n";
-    else {
-        *dst = d;
-        return 0;
-    }
-
+    else
+        return d;
    av_log(NULL, AV_LOG_FATAL, error, context, numstr, min, max);
-    return AVERROR(EINVAL);
+    exit_program(1);
+    return 0;
+}
+
+int64_t parse_time_or_die(const char *context, const char *timestr,
+                          int is_duration)
+{
+    int64_t us;
+    if (av_parse_time(&us, timestr, is_duration) < 0) {
+        av_log(NULL, AV_LOG_FATAL, "Invalid %s specification for %s: %s\n",
+               is_duration ? "duration" : "date", context, timestr);
+        exit_program(1);
+    }
+    return us;
 }

 void show_help_options(const OptionDef *options, const char *msg, int req_flags,
@@ -231,8 +262,6 @@ static int write_option(void *optctx, const OptionDef *po, const char *opt,
    void *dst = po->flags & (OPT_OFFSET | OPT_SPEC) ?
                (uint8_t *)optctx + po->u.off : po->u.dst_ptr;
    int *dstcount;
-    double num;
-    int ret;

    if (po->flags & OPT_SPEC) {
        SpecifierOpt **so = dst;
@@ -240,10 +269,7 @@ static int write_option(void *optctx, const OptionDef *po, const char *opt,
        char *str;

        dstcount = (int *)(so + 1);
-        ret = grow_array((void**)so, sizeof(**so), dstcount, *dstcount + 1);
-        if (ret < 0)
-            return ret;
-
+        *so = grow_array(*so, sizeof(**so), dstcount, *dstcount + 1);
        str = av_strdup(p ? p + 1 : "");
        if (!str)
            return AVERROR(ENOMEM);
@@ -259,36 +285,15 @@ static int write_option(void *optctx, const OptionDef *po, const char *opt,
            return AVERROR(ENOMEM);
        *(char **)dst = str;
    } else if (po->flags & OPT_BOOL || po->flags & OPT_INT) {
-        ret = parse_number(opt, arg, OPT_INT64, INT_MIN, INT_MAX, &num);
-        if (ret < 0)
-            return ret;
-
-        *(int *)dst = num;
+        *(int *)dst = parse_number_or_die(opt, arg, OPT_INT64, INT_MIN, INT_MAX);
    } else if (po->flags & OPT_INT64) {
-        ret = parse_number(opt, arg, OPT_INT64, INT64_MIN, INT64_MAX, &num);
-        if (ret < 0)
-            return ret;
-
-        *(int64_t *)dst = num;
+        *(int64_t *)dst = parse_number_or_die(opt, arg, OPT_INT64, INT64_MIN, INT64_MAX);
    } else if (po->flags & OPT_TIME) {
-        ret = av_parse_time(dst, arg, 1);
-        if (ret < 0) {
-            av_log(NULL, AV_LOG_ERROR, "Invalid duration for option %s: %s\n",
-                   opt, arg);
-            return ret;
-        }
+        *(int64_t *)dst = parse_time_or_die(opt, arg, 1);
    } else if (po->flags & OPT_FLOAT) {
-        ret = parse_number(opt, arg, OPT_FLOAT, -INFINITY, INFINITY, &num);
-        if (ret < 0)
-            return ret;
-
-        *(float *)dst = num;
+        *(float *)dst = parse_number_or_die(opt, arg, OPT_FLOAT, -INFINITY, INFINITY);
    } else if (po->flags & OPT_DOUBLE) {
-        ret = parse_number(opt, arg, OPT_DOUBLE, -INFINITY, INFINITY, &num);
-        if (ret < 0)
-            return ret;
-
-        *(double *)dst = num;
+        *(double *)dst = parse_number_or_die(opt, arg, OPT_DOUBLE, -INFINITY, INFINITY);
    } else if (po->u.func_arg) {
        int ret = po->u.func_arg(optctx, opt, arg);
        if (ret < 0) {
@@ -299,7 +304,7 @@ static int write_option(void *optctx, const OptionDef *po, const char *opt,
        }
    }
    if (po->flags & OPT_EXIT)
-        return AVERROR_EXIT;
+        exit_program(0);

    return 0;
 }
@@ -343,8 +348,8 @@ int parse_option(void *optctx, const char *opt, const char *arg,
    return !!(po->flags & HAS_ARG);
 }

-int parse_options(void *optctx, int argc, char **argv, const OptionDef *options,
-                  int (*parse_arg_function)(void *, const char*))
+void parse_options(void *optctx, int argc, char **argv, const OptionDef *options,
+                   void (*parse_arg_function)(void *, const char*))
 {
    const char *opt;
    int optindex, handleoptions = 1, ret;
@@ -365,18 +370,13 @@ int parse_options(void *optctx, int argc, char **argv, const OptionDef *options,
            opt++;

            if ((ret = parse_option(optctx, opt, argv[optindex], options)) < 0)
-                return ret;
+                exit_program(1);
            optindex += ret;
        } else {
-            if (parse_arg_function) {
-                ret = parse_arg_function(optctx, opt);
-                if (ret < 0)
-                    return ret;
-            }
+            if (parse_arg_function)
+                parse_arg_function(optctx, opt);
        }
    }
-
-    return 0;
 }

 int parse_optgroup(void *optctx, OptionGroup *g)
@@ -605,17 +605,13 @@ static int match_group_separator(const OptionGroupDef *groups, int nb_groups,
 * @param group_idx which group definition should this group belong to
 * @param arg argument of the group delimiting option
 */
-static int finish_group(OptionParseContext *octx, int group_idx,
-                        const char *arg)
+static void finish_group(OptionParseContext *octx, int group_idx,
+                         const char *arg)
 {
    OptionGroupList *l = &octx->groups[group_idx];
    OptionGroup *g;
-    int ret;
-
-    ret = GROW_ARRAY(l->groups, l->nb_groups);
-    if (ret < 0)
-        return ret;

+    GROW_ARRAY(l->groups, l->nb_groups);
    g = &l->groups[l->nb_groups - 1];

    *g             = octx->cur_group;
@@ -632,33 +628,25 @@ static int finish_group(OptionParseContext *octx, int group_idx,
    swr_opts    = NULL;

    memset(&octx->cur_group, 0, sizeof(octx->cur_group));
-
-    return ret;
 }

 /*
 * Add an option instance to currently parsed group.
 */
-static int add_opt(OptionParseContext *octx, const OptionDef *opt,
-                   const char *key, const char *val)
+static void add_opt(OptionParseContext *octx, const OptionDef *opt,
+                    const char *key, const char *val)
 {
    int global = !(opt->flags & (OPT_PERFILE | OPT_SPEC | OPT_OFFSET));
    OptionGroup *g = global ? &octx->global_opts : &octx->cur_group;
-    int ret;
-
-    ret = GROW_ARRAY(g->opts, g->nb_opts);
-    if (ret < 0)
-        return ret;

+    GROW_ARRAY(g->opts, g->nb_opts);
    g->opts[g->nb_opts - 1].opt = opt;
    g->opts[g->nb_opts - 1].key = key;
    g->opts[g->nb_opts - 1].val = val;
-
-    return 0;
 }

-static int init_parse_context(OptionParseContext *octx,
-                              const OptionGroupDef *groups, int nb_groups)
+static void init_parse_context(OptionParseContext *octx,
+                               const OptionGroupDef *groups, int nb_groups)
 {
    static const OptionGroupDef global_group = { "global" };
    int i;
@@ -668,15 +656,13 @@ static int init_parse_context(OptionParseContext *octx,
    octx->nb_groups = nb_groups;
    octx->groups    = av_calloc(octx->nb_groups, sizeof(*octx->groups));
    if (!octx->groups)
-        return AVERROR(ENOMEM);
+        report_and_exit(AVERROR(ENOMEM));

    for (i = 0; i < octx->nb_groups; i++)
        octx->groups[i].group_def = &groups[i];

    octx->global_opts.group_def = &global_group;
    octx->global_opts.arg       = "";
-
-    return 0;
 }

 void uninit_parse_context(OptionParseContext *octx)
@@ -708,17 +694,13 @@ int split_commandline(OptionParseContext *octx, int argc, char *argv[],
                      const OptionDef *options,
                      const OptionGroupDef *groups, int nb_groups)
 {
-    int ret;
    int optindex = 1;
    int dashdash = -2;

    /* perform system-dependent conversions for arguments list */
    prepare_app_arguments(&argc, &argv);

-    ret = init_parse_context(octx, groups, nb_groups);
-    if (ret < 0)
-        return ret;
-
+    init_parse_context(octx, groups, nb_groups);
    av_log(NULL, AV_LOG_DEBUG, "Splitting the commandline.\n");

    while (optindex < argc) {
@@ -734,10 +716,7 @@ int split_commandline(OptionParseContext *octx, int argc, char *argv[],
        }
        /* unnamed group separators, e.g. output filename */
        if (opt[0] != '-' || !opt[1] || dashdash+1 == optindex) {
-            ret = finish_group(octx, 0, opt);
-            if (ret < 0)
-                return ret;
-
+            finish_group(octx, 0, opt);
            av_log(NULL, AV_LOG_DEBUG, " matched as %s.\n", groups[0].name);
            continue;
        }
@@ -755,10 +734,7 @@ do {                                                                           \
        /* named group separators, e.g. -i */
        if ((ret = match_group_separator(groups, nb_groups, opt)) >= 0) {
            GET_ARG(arg);
-            ret = finish_group(octx, ret, arg);
-            if (ret < 0)
-                return ret;
-
+            finish_group(octx, ret, arg);
            av_log(NULL, AV_LOG_DEBUG, " matched as %s with argument '%s'.\n",
                   groups[ret].name, arg);
            continue;
@@ -776,10 +752,7 @@ do {                                                                           \
                arg = "1";
            }

-            ret = add_opt(octx, po, opt, arg);
-            if (ret < 0)
-                return ret;
-
+            add_opt(octx, po, opt, arg);
            av_log(NULL, AV_LOG_DEBUG, " matched as option '%s' (%s) with "
                   "argument '%s'.\n", po->name, po->help, arg);
            continue;
@@ -804,10 +777,7 @@ do {                                                                           \
        if (opt[0] == 'n' && opt[1] == 'o' &&
            (po = find_option(options, opt + 2)) &&
            po->name && po->flags & OPT_BOOL) {
-            ret = add_opt(octx, po, opt, "0");
-            if (ret < 0)
-                return ret;
-
+            add_opt(octx, po, opt, "0");
            av_log(NULL, AV_LOG_DEBUG, " matched as option '%s' (%s) with "
                   "argument 0.\n", po->name, po->help);
            continue;
@@ -922,9 +892,8 @@ int check_stream_specifier(AVFormatContext *s, AVStream *st, const char *spec)
    return ret;
 }

-int filter_codec_opts(const AVDictionary *opts, enum AVCodecID codec_id,
-                      AVFormatContext *s, AVStream *st, const AVCodec *codec,
-                      AVDictionary **dst)
+AVDictionary *filter_codec_opts(AVDictionary *opts, enum AVCodecID codec_id,
+                                AVFormatContext *s, AVStream *st, const AVCodec *codec)
 {
    AVDictionary    *ret = NULL;
    const AVDictionaryEntry *t = NULL;
@@ -957,16 +926,12 @@ int filter_codec_opts(const AVDictionary *opts, enum AVCodecID codec_id,
        char *p = strchr(t->key, ':');

        /* check stream specification in opt name */
-        if (p) {
-            int err = check_stream_specifier(s, st, p + 1);
-            if (err < 0) {
-                av_dict_free(&ret);
-                return err;
-            } else if (!err)
-                continue;
-
-            *p = 0;
-        }
+        if (p)
+            switch (check_stream_specifier(s, st, p + 1)) {
+            case  1: *p = 0; break;
+            case  0:         continue;
+            default:         exit_program(1);
+            }

        if (av_opt_find(&cc, t->key, NULL, flags, AV_OPT_SEARCH_FAKE_OBJ) ||
            !codec ||
@@ -982,58 +947,41 @@ int filter_codec_opts(const AVDictionary *opts, enum AVCodecID codec_id,
        if (p)
            *p = ':';
    }
-
-    *dst = ret;
-    return 0;
-}
-
-int setup_find_stream_info_opts(AVFormatContext *s,
-                                AVDictionary *codec_opts,
-                                AVDictionary ***dst)
-{
-    int ret;
-    AVDictionary **opts;
-
-    *dst = NULL;
-
-    if (!s->nb_streams)
-        return 0;
-
-    opts = av_calloc(s->nb_streams, sizeof(*opts));
-    if (!opts)
-        return AVERROR(ENOMEM);
-
-    for (int i = 0; i < s->nb_streams; i++) {
-        ret = filter_codec_opts(codec_opts, s->streams[i]->codecpar->codec_id,
-                                s, s->streams[i], NULL, &opts[i]);
-        if (ret < 0)
-            goto fail;
-    }
-    *dst = opts;
-    return 0;
-fail:
-    for (int i = 0; i < s->nb_streams; i++)
-        av_dict_free(&opts[i]);
-    av_freep(&opts);
    return ret;
 }

-int grow_array(void **array, int elem_size, int *size, int new_size)
+AVDictionary **setup_find_stream_info_opts(AVFormatContext *s,
+                                           AVDictionary *codec_opts)
+{
+    int i;
+    AVDictionary **opts;
+
+    if (!s->nb_streams)
+        return NULL;
+    opts = av_calloc(s->nb_streams, sizeof(*opts));
+    if (!opts)
+        report_and_exit(AVERROR(ENOMEM));
+    for (i = 0; i < s->nb_streams; i++)
+        opts[i] = filter_codec_opts(codec_opts, s->streams[i]->codecpar->codec_id,
+                                    s, s->streams[i], NULL);
+    return opts;
+}
+
+void *grow_array(void *array, int elem_size, int *size, int new_size)
 {
    if (new_size >= INT_MAX / elem_size) {
        av_log(NULL, AV_LOG_ERROR, "Array too big.\n");
-        return AVERROR(ERANGE);
+        exit_program(1);
    }
    if (*size < new_size) {
-        uint8_t *tmp = av_realloc_array(*array, new_size, elem_size);
+        uint8_t *tmp = av_realloc_array(array, new_size, elem_size);
        if (!tmp)
-            return AVERROR(ENOMEM);
+            report_and_exit(AVERROR(ENOMEM));
        memset(tmp + *size*elem_size, 0, (new_size-*size) * elem_size);
        *size = new_size;
-        *array = tmp;
-        return 0;
+        return tmp;
    }
-    return 0;
+    return array;
 }

 void *allocate_array_elem(void *ptr, size_t elem_size, int *nb_elems)
@@ -1042,11 +990,11 @@ void *allocate_array_elem(void *ptr, size_t elem_size, int *nb_elems)

    if (!(new_elem = av_mallocz(elem_size)) ||
        av_dynarray_add_nofree(ptr, nb_elems, new_elem) < 0)
-        return NULL;
+        report_and_exit(AVERROR(ENOMEM));
    return new_elem;
 }

-double get_rotation(const int32_t *displaymatrix)
+double get_rotation(int32_t *displaymatrix)
 {
    double theta = 0;
    if (displaymatrix)
--- a/fftools/cmdutils.h
+++ b/fftools/cmdutils.h
@@ -49,6 +49,27 @@ extern AVDictionary *swr_opts;
 extern AVDictionary *format_opts, *codec_opts;
 extern int hide_banner;

+/**
+ * Register a program-specific cleanup routine.
+ */
+void register_exit(void (*cb)(int ret));
+
+/**
+ * Reports an error corresponding to the provided
+ * AVERROR code and calls exit_program() with the
+ * corresponding POSIX error code.
+ * @note ret must be an AVERROR-value of a POSIX error code
+ *       (i.e. AVERROR(EFOO) and not AVERROR_FOO).
+ *       library functions can return both, so call this only
+ *       with AVERROR(EFOO) of your own.
+ */
+void report_and_exit(int ret) av_noreturn;
+
+/**
+ * Wraps exit with a program-specific cleanup routine.
+ */
+void exit_program(int ret) av_noreturn;
+
 /**
 * Initialize dynamic library loading
 */
@@ -79,6 +100,8 @@ int opt_timelimit(void *optctx, const char *opt, const char *arg);

 /**
 * Parse a string and return its corresponding value as a double.
+ * Exit from the application if the string cannot be correctly
+ * parsed or the corresponding value is invalid.
 *
 * @param context the context of the value to be set (e.g. the
 * corresponding command line option name)
@@ -88,8 +111,25 @@ int opt_timelimit(void *optctx, const char *opt, const char *arg);
 * @param min the minimum valid accepted value
 * @param max the maximum valid accepted value
 */
-int parse_number(const char *context, const char *numstr, int type,
-                 double min, double max, double *dst);
+double parse_number_or_die(const char *context, const char *numstr, int type,
+                           double min, double max);
+
+/**
+ * Parse a string specifying a time and return its corresponding
+ * value as a number of microseconds. Exit from the application if
+ * the string cannot be correctly parsed.
+ *
+ * @param context the context of the value to be set (e.g. the
+ * corresponding command line option name)
+ * @param timestr the string to be parsed
+ * @param is_duration a flag which tells how to interpret timestr, if
+ * not zero timestr is interpreted as a duration, otherwise as a
+ * date
+ *
+ * @see av_parse_time()
+ */
+int64_t parse_time_or_die(const char *context, const char *timestr,
+                          int is_duration);

 typedef struct SpecifierOpt {
    char *specifier;    /**< stream/chapter/program/... specifier */
@@ -173,8 +213,8 @@ void show_help_default(const char *opt, const char *arg);
 * argument without a leading option name flag. NULL if such arguments do
 * not have to be processed.
 */
-int parse_options(void *optctx, int argc, char **argv, const OptionDef *options,
-                  int (* parse_arg_function)(void *optctx, const char*));
+void parse_options(void *optctx, int argc, char **argv, const OptionDef *options,
+                   void (* parse_arg_function)(void *optctx, const char*));

 /**
 * Parse one given option.
@@ -312,12 +352,10 @@ int check_stream_specifier(AVFormatContext *s, AVStream *st, const char *spec);
 * @param st A stream from s for which the options should be filtered.
 * @param codec The particular codec for which the options should be filtered.
 *              If null, the default one is looked up according to the codec id.
- * @param dst a pointer to the created dictionary
- * @return a non-negative number on success, a negative error code on failure
+ * @return a pointer to the created dictionary
 */
-int filter_codec_opts(const AVDictionary *opts, enum AVCodecID codec_id,
-                      AVFormatContext *s, AVStream *st, const AVCodec *codec,
-                      AVDictionary **dst);
+AVDictionary *filter_codec_opts(AVDictionary *opts, enum AVCodecID codec_id,
+                                AVFormatContext *s, AVStream *st, const AVCodec *codec);

 /**
 * Setup AVCodecContext options for avformat_find_stream_info().
@@ -326,10 +364,12 @@ int filter_codec_opts(const AVDictionary *opts, enum AVCodecID codec_id,
 * contained in s.
 * Each dictionary will contain the options from codec_opts which can
 * be applied to the corresponding stream codec context.
+ *
+ * @return pointer to the created array of dictionaries.
+ * Calls exit() on failure.
 */
-int setup_find_stream_info_opts(AVFormatContext *s,
-                                AVDictionary *codec_opts,
-                                AVDictionary ***dst);
+AVDictionary **setup_find_stream_info_opts(AVFormatContext *s,
+                                           AVDictionary *codec_opts);

 /**
 * Print an error message to stderr, indicating filename and a human
@@ -378,31 +418,35 @@ FILE *get_preset_file(char *filename, size_t filename_size,

 /**
 * Realloc array to hold new_size elements of elem_size.
+ * Calls exit() on failure.
 *
- * @param array pointer to the array to reallocate, will be updated
- *              with a new pointer on success
+ * @param array array to reallocate
 * @param elem_size size in bytes of each element
 * @param size new element count will be written here
 * @param new_size number of elements to place in reallocated array
- * @return a non-negative number on success, a negative error code on failure
+ * @return reallocated array
 */
-int grow_array(void **array, int elem_size, int *size, int new_size);
+void *grow_array(void *array, int elem_size, int *size, int new_size);

 /**
 * Atomically add a new element to an array of pointers, i.e. allocate
 * a new entry, reallocate the array of pointers and make the new last
 * member of this array point to the newly allocated buffer.
+ * Calls exit() on failure.
 *
 * @param array     array of pointers to reallocate
 * @param elem_size size of the new element to allocate
 * @param nb_elems  pointer to the number of elements of the array array;
 *                  *nb_elems will be incremented by one by this function.
- * @return pointer to the newly allocated entry or NULL on failure
+ * @return pointer to the newly allocated entry
 */
 void *allocate_array_elem(void *array, size_t elem_size, int *nb_elems);

 #define GROW_ARRAY(array, nb_elems)\
-    grow_array((void**)&array, sizeof(*array), &nb_elems, nb_elems + 1)
+    array = grow_array(array, sizeof(*array), &nb_elems, nb_elems + 1)
+
+#define ALLOC_ARRAY_ELEM(array, nb_elems)\
+    allocate_array_elem(&array, sizeof(*array[0]), &nb_elems)

 #define GET_PIX_FMT_NAME(pix_fmt)\
    const char *name = av_get_pix_fmt_name(pix_fmt);
@@ -417,6 +461,6 @@ void *allocate_array_elem(void *array, size_t elem_size, int *nb_elems);
    char name[16];\
    snprintf(name, sizeof(name), "%d", rate);

-double get_rotation(const int32_t *displaymatrix);
+double get_rotation(int32_t *displaymatrix);

 #endif /* FFTOOLS_CMDUTILS_H */
--- a/fftools/ffmpeg.c
+++ b/fftools/ffmpeg.c
--- a/fftools/ffmpeg.h
+++ b/fftools/ffmpeg.h
@@ -54,11 +54,6 @@
 #define FFMPEG_OPT_MAP_CHANNEL 1
 #define FFMPEG_OPT_MAP_SYNC 1
 #define FFMPEG_ROTATION_METADATA 1
-#define FFMPEG_OPT_QPHIST 1
-#define FFMPEG_OPT_ADRIFT_THRESHOLD 1
-#define FFMPEG_OPT_ENC_TIME_BASE_NUM 1
-#define FFMPEG_OPT_TOP 1
-#define FFMPEG_OPT_FORCE_KF_SOURCE_NO_DROP 1

 enum VideoSyncMethod {
    VSYNC_AUTO = -1,
@@ -69,10 +64,7 @@ enum VideoSyncMethod {
    VSYNC_DROP,
 };

-enum EncTimeBase {
-    ENC_TIME_BASE_DEMUX  = -1,
-    ENC_TIME_BASE_FILTER = -2,
-};
+#define MAX_STREAMS 1024    /* arbitrary sanity check value */

 enum HWAccelID {
    HWACCEL_NONE = 0,
@@ -101,12 +93,6 @@ typedef struct {
 } AudioChannelMap;
 #endif

-typedef struct DemuxPktData {
-    // estimated dts in AV_TIME_BASE_Q,
-    // to be used when real dts is missing
-    int64_t dts_est;
-} DemuxPktData;
-
 typedef struct OptionsContext {
    OptionGroup *g;

@@ -138,7 +124,6 @@ typedef struct OptionsContext {
    int loop;
    int rate_emu;
    float readrate;
-    double readrate_initial_burst;
    int accurate_seek;
    int thread_queue_size;
    int input_sync_ref;
@@ -183,8 +168,9 @@ typedef struct OptionsContext {
    int subtitle_disable;
    int data_disable;

-    // keys are stream indices
-    AVDictionary *streamid;
+    /* indexed by output file stream index */
+    int   *streamid_map;
+    int nb_streamid_map;

    SpecifierOpt *metadata;
    int        nb_metadata;
@@ -220,10 +206,8 @@ typedef struct OptionsContext {
    int        nb_inter_matrices;
    SpecifierOpt *chroma_intra_matrices;
    int        nb_chroma_intra_matrices;
-#if FFMPEG_OPT_TOP
    SpecifierOpt *top_field_first;
    int        nb_top_field_first;
-#endif
    SpecifierOpt *metadata_map;
    int        nb_metadata_map;
    SpecifierOpt *presets;
@@ -285,33 +269,62 @@ typedef struct OptionsContext {
 } OptionsContext;

 typedef struct InputFilter {
+    AVFilterContext    *filter;
+    struct InputStream *ist;
    struct FilterGraph *graph;
    uint8_t            *name;
+    enum AVMediaType    type;   // AVMEDIA_TYPE_SUBTITLE for sub2video
+
+    AVFifo *frame_queue;
+
+    // parameters configured for this input
+    int format;
+
+    int width, height;
+    AVRational sample_aspect_ratio;
+
+    int sample_rate;
+    AVChannelLayout ch_layout;
+
+    AVBufferRef *hw_frames_ctx;
+    int32_t *displaymatrix;
+
+    int eof;
 } InputFilter;

 typedef struct OutputFilter {
+    AVFilterContext     *filter;
    struct OutputStream *ost;
    struct FilterGraph  *graph;
    uint8_t             *name;

-    /* for filters that are not yet bound to an output stream,
-     * this stores the output linklabel, if any */
-    uint8_t             *linklabel;
-
+    /* temporary storage until stream maps are processed */
+    AVFilterInOut       *out_tmp;
    enum AVMediaType     type;

-    /* pts of the last frame received from this filter, in AV_TIME_BASE_Q */
-    int64_t last_pts;
+    /* desired output stream properties */
+    int width, height;
+    AVRational frame_rate;
+    int format;
+    int sample_rate;
+    AVChannelLayout ch_layout;

-    uint64_t nb_frames_dup;
-    uint64_t nb_frames_drop;
+    // those are only set if no format is specified and the encoder gives us multiple options
+    // They point directly to the relevant lists of the encoder.
+    const int *formats;
+    const AVChannelLayout *ch_layouts;
+    const int *sample_rates;
 } OutputFilter;

 typedef struct FilterGraph {
-    const AVClass *class;
    int            index;
+    const char    *graph_desc;

    AVFilterGraph *graph;
+    int reconfiguration;
+    // true when the filtergraph contains only meta filters
+    // that do not modify the frame data
+    int is_meta;

    InputFilter   **inputs;
    int          nb_inputs;
@@ -319,20 +332,17 @@ typedef struct FilterGraph {
    int         nb_outputs;
 } FilterGraph;

-typedef struct Decoder Decoder;
-
 typedef struct InputStream {
-    const AVClass *class;
-
    int file_index;
-    int index;
-
    AVStream *st;
    int discard;             /* true if stream data should be discarded */
    int user_set_discard;
    int decoding_needed;     /* non zero if the packets must be decoded in 'raw_fifo', see DECODING_FOR_* */
 #define DECODING_FOR_OST    1
 #define DECODING_FOR_FILTER 2
+    int processing_needed;   /* non zero if the packets must be processed */
+    // should attach FrameData as opaque_ref after decoding
+    int want_frame_data;

    /**
     * Codec parameters - to be used by the decoding/streamcopy code.
@@ -340,27 +350,65 @@ typedef struct InputStream {
     * concurrently by the demuxing thread.
     */
    AVCodecParameters *par;
-    Decoder *decoder;
    AVCodecContext *dec_ctx;
    const AVCodec *dec;
-    const AVCodecDescriptor *codec_desc;
+    AVFrame *decoded_frame;
+    AVPacket *pkt;

    AVRational framerate_guessed;

+    int64_t       prev_pkt_pts;
+    int64_t       start;     /* time when read started */
+    /* predicted dts of the next packet read for this stream or (when there are
+     * several frames in a packet) of the next frame in current packet (in AV_TIME_BASE units) */
+    int64_t       next_dts;
+    int64_t first_dts;       ///< dts of the first packet read for this stream (in AV_TIME_BASE units)
+    int64_t       dts;       ///< dts of the last packet read for this stream (in AV_TIME_BASE units)
+
+    int64_t       next_pts;  ///< synthetic pts for the next decode frame (in AV_TIME_BASE units)
+    int64_t       pts;       ///< current pts of the decoded frame  (in AV_TIME_BASE units)
+    int           wrap_correction_done;
+
+    // the value of AVCodecParserContext.repeat_pict from the AVStream parser
+    // for the last packet returned from ifile_get_packet()
+    // -1 if unknown
+    // FIXME: this is a hack, the avstream parser should not be used
+    int last_pkt_repeat_pict;
+
+    int64_t filter_in_rescale_delta_last;
+
+    int64_t min_pts; /* pts with the smallest value in a current stream */
+    int64_t max_pts; /* pts with the higher value in a current stream */
+
+    // when forcing constant input framerate through -r,
+    // this contains the pts that will be given to the next decoded frame
+    int64_t cfr_next_pts;
+
    int64_t nb_samples; /* number of samples in the last decoded audio frame before looping */

+    double ts_scale;
+    int saw_first_ts;
    AVDictionary *decoder_opts;
    AVRational framerate;               /* framerate forced with -r */
-#if FFMPEG_OPT_TOP
    int top_field_first;
-#endif
+    int guess_layout_max;

    int autorotate;

    int fix_sub_duration;
+    struct { /* previous decoded subtitle and related variables */
+        int got_output;
+        int ret;
+        AVSubtitle subtitle;
+    } prev_sub;

    struct sub2video {
+        int64_t last_pts;
+        int64_t end_pts;
+        AVFifo *sub_queue;    ///< queue of AVSubtitle* before filter init
+        AVFrame *frame;
        int w, h;
+        unsigned int initialize; ///< marks if sub2video_update should force an initialization
    } sub2video;

    /* decoded data from this stream goes into all those filters
@@ -368,14 +416,6 @@ typedef struct InputStream {
    InputFilter **filters;
    int        nb_filters;

-    /*
-     * Output targets that do not go through lavfi, i.e. subtitles or
-     * streamcopy. Those two cases are distinguished by the OutputStream
-     * having an encoder or not.
-     */
-    struct OutputStream **outputs;
-    int                nb_outputs;
-
    int reinit_filters;

    /* hwaccel options */
@@ -384,11 +424,22 @@ typedef struct InputStream {
    char  *hwaccel_device;
    enum AVPixelFormat hwaccel_output_format;

+    int  (*hwaccel_retrieve_data)(AVCodecContext *s, AVFrame *frame);
+    enum AVPixelFormat hwaccel_pix_fmt;
+
    /* stats */
+    // combined size of all the packets read
+    uint64_t data_size;
+    /* number of packets successfully read for this stream */
+    uint64_t nb_packets;
    // number of frames/samples retrieved from the decoder
    uint64_t frames_decoded;
    uint64_t samples_decoded;
-    uint64_t decode_errors;
+
+    int64_t *dts_buffer;
+    int nb_dts_buffer;
+
+    int got_output;
 } InputStream;

 typedef struct LastFrameDuration {
@@ -397,13 +448,8 @@ typedef struct LastFrameDuration {
 } LastFrameDuration;

 typedef struct InputFile {
-    const AVClass *class;
-
    int index;

-    // input format has no timestamps
-    int format_nots;
-
    AVFormatContext *ctx;
    int eof_reached;      /* true if eof reached */
    int eagain;           /* true if last read attempt returned EAGAIN */
@@ -414,6 +460,11 @@ typedef struct InputFile {
     */
    int64_t start_time_effective;
    int64_t ts_offset;
+    /**
+     * Extra timestamp offset added by discontinuity handling.
+     */
+    int64_t ts_offset_discont;
+    int64_t last_ts;
    int64_t start_time;   /* user-specified start time in AV_TIME_BASE or AV_NOPTS_VALUE */
    int64_t recording_time;

@@ -423,6 +474,7 @@ typedef struct InputFile {
    InputStream **streams;
    int        nb_streams;

+    int rate_emu;
    float readrate;
    int accurate_seek;

@@ -488,9 +540,7 @@ typedef enum {

 enum {
    KF_FORCE_SOURCE         = 1,
-#if FFMPEG_OPT_FORCE_KF_SOURCE_NO_DROP
    KF_FORCE_SOURCE_NO_DROP = 2,
-#endif
 };

 typedef struct KeyframeForceCtx {
@@ -509,35 +559,44 @@ typedef struct KeyframeForceCtx {
    int          dropped_keyframe;
 } KeyframeForceCtx;

-typedef struct Encoder Encoder;
-
 typedef struct OutputStream {
    const AVClass *class;

-    enum AVMediaType type;
-
    int file_index;          /* file index */
    int index;               /* stream index in the output file */

-    /**
-     * Codec parameters for packets submitted to the muxer (i.e. before
-     * bitstream filtering, if any).
-     */
-    AVCodecParameters *par_in;
-
    /* input stream that is the source for this output stream;
     * may be NULL for streams with no well-defined source, e.g.
     * attachments or outputs from complex filtergraphs */
    InputStream *ist;

    AVStream *st;            /* stream in the output file */
+    /* number of frames emitted by the video-encoding sync code */
+    int64_t vsync_frame_number;
+    /* predicted pts of the next frame to be encoded
+     * audio/video encoding only */
+    int64_t next_pts;
    /* dts of the last packet sent to the muxing queue, in AV_TIME_BASE_Q */
    int64_t last_mux_dts;
+    /* pts of the last frame received from the filters, in AV_TIME_BASE_Q */
+    int64_t last_filter_pts;

+    // timestamp from which the streamcopied streams should start,
+    // in AV_TIME_BASE_Q;
+    // everything before it should be discarded
+    int64_t ts_copy_start;
+
+    // the timebase of the packets sent to the muxer
+    AVRational mux_timebase;
    AVRational enc_timebase;

-    Encoder *enc;
    AVCodecContext *enc_ctx;
+    AVFrame *filtered_frame;
+    AVFrame *last_frame;
+    AVFrame *sq_frame;
+    AVPacket *pkt;
+    int64_t last_dropped;
+    int64_t last_nb0_frames[3];

    /* video only */
    AVRational frame_rate;
@@ -545,9 +604,7 @@ typedef struct OutputStream {
    enum VideoSyncMethod vsync_method;
    int is_cfr;
    int force_fps;
-#if FFMPEG_OPT_TOP
    int top_field_first;
-#endif
 #if FFMPEG_ROTATION_METADATA
    int rotate_overridden;
 #endif
@@ -572,6 +629,9 @@ typedef struct OutputStream {
    FILE *logfile;

    OutputFilter *filter;
+    char *avfilter;
+    char *filters;         ///< filtergraph associated to the -filter option
+    char *filters_script;  ///< filtergraph script associated to the -filter_script option

    AVDictionary *encoder_opts;
    AVDictionary *sws_dict;
@@ -585,20 +645,37 @@ typedef struct OutputStream {
    // parameters are set in the AVStream.
    int initialized;

+    int inputs_done;
+
    const char *attachment_filename;
+    int streamcopy_started;
+    int copy_initial_nonkeyframes;
+    int copy_prior_start;

    int keep_pix_fmt;

    /* stats */
+    // combined size of all the packets sent to the muxer
+    uint64_t data_size_mux;
+    // combined size of all the packets received from the encoder
+    uint64_t data_size_enc;
    // number of packets send to the muxer
    atomic_uint_least64_t packets_written;
    // number of frames/samples sent to the encoder
    uint64_t frames_encoded;
    uint64_t samples_encoded;
+    // number of packets received from the encoder
+    uint64_t packets_encoded;

    /* packet quality factor */
    int quality;

+    /* packet picture type */
+    int pict_type;
+
+    /* frame encode sum of squared error values */
+    int64_t error[4];
+
    int sq_idx_encode;
    int sq_idx_mux;

@@ -632,21 +709,6 @@ typedef struct OutputFile {
    int bitexact;
 } OutputFile;

-// optionally attached as opaque_ref to decoded AVFrames
-typedef struct FrameData {
-    // properties that come from the decoder
-    struct {
-        uint64_t   frame_num;
-
-        int64_t    pts;
-        AVRational tb;
-    } dec;
-
-    AVRational frame_rate_filter;
-
-    int        bits_per_raw_sample;
-} FrameData;
-
 extern InputFile   **input_files;
 extern int        nb_input_files;

@@ -659,6 +721,7 @@ extern int        nb_filtergraphs;
 extern char *vstats_filename;
 extern char *sdp_filename;

+extern float audio_drift_threshold;
 extern float dts_delta_threshold;
 extern float dts_error_threshold;

@@ -676,6 +739,7 @@ extern int exit_on_error;
 extern int abort_on_flags;
 extern int print_stats;
 extern int64_t stats_period;
+extern int qp_hist;
 extern int stdin_interaction;
 extern AVIOContext *progress_avio;
 extern float max_error_rate;
@@ -691,14 +755,13 @@ extern const OptionDef options[];
 extern HWDevice *filter_hw_device;

 extern unsigned nb_output_dumped;
+extern int main_return_code;

 extern int ignore_unknown_streams;
 extern int copy_unknown_streams;

 extern int recast_media;

-extern FILE *vstats_file;
-
 #if FFMPEG_OPT_PSNR
 extern int do_psnr;
 #endif
@@ -709,73 +772,24 @@ void term_exit(void);
 void show_usage(void);

 void remove_avoptions(AVDictionary **a, AVDictionary *b);
-int check_avoptions(AVDictionary *m);
+void assert_avoptions(AVDictionary *m);

-int assert_file_overwrite(const char *filename);
+void assert_file_overwrite(const char *filename);
 char *file_read(const char *filename);
 AVDictionary *strip_specifiers(const AVDictionary *dict);
-int find_codec(void *logctx, const char *name,
-               enum AVMediaType type, int encoder, const AVCodec **codec);
+const AVCodec *find_codec_or_die(void *logctx, const char *name,
+                                 enum AVMediaType type, int encoder);
 int parse_and_set_vsync(const char *arg, int *vsync_var, int file_idx, int st_idx, int is_global);

-int check_filter_outputs(void);
-int filtergraph_is_simple(const FilterGraph *fg);
-int init_simple_filtergraph(InputStream *ist, OutputStream *ost,
-                            char *graph_desc);
+int configure_filtergraph(FilterGraph *fg);
+void check_filter_outputs(void);
+int filtergraph_is_simple(FilterGraph *fg);
+int init_simple_filtergraph(InputStream *ist, OutputStream *ost);
 int init_complex_filtergraph(FilterGraph *fg);

-int copy_av_subtitle(AVSubtitle *dst, const AVSubtitle *src);
-int subtitle_wrap_frame(AVFrame *frame, AVSubtitle *subtitle, int copy);
+void sub2video_update(InputStream *ist, int64_t heartbeat_pts, AVSubtitle *sub);

-/**
- * Get our axiliary frame data attached to the frame, allocating it
- * if needed.
- */
-FrameData *frame_data(AVFrame *frame);
-
-int ifilter_send_frame(InputFilter *ifilter, AVFrame *frame, int keep_reference);
-int ifilter_send_eof(InputFilter *ifilter, int64_t pts, AVRational tb);
-int ifilter_sub2video(InputFilter *ifilter, const AVFrame *frame);
-void ifilter_sub2video_heartbeat(InputFilter *ifilter, int64_t pts, AVRational tb);
-
-/**
- * Set up fallback filtering parameters from a decoder context. They will only
- * be used if no frames are ever sent on this input, otherwise the actual
- * parameters are taken from the frame.
- */
-int ifilter_parameters_from_dec(InputFilter *ifilter, const AVCodecContext *dec);
-
-int ofilter_bind_ost(OutputFilter *ofilter, OutputStream *ost);
-
-/**
- * Create a new filtergraph in the global filtergraph list.
- *
- * @param graph_desc Graph description; an av_malloc()ed string, filtergraph
- *                   takes ownership of it.
- */
-int fg_create(FilterGraph **pfg, char *graph_desc);
-
-void fg_free(FilterGraph **pfg);
-
-/**
- * Perform a step of transcoding for the specified filter graph.
- *
- * @param[in]  graph     filter graph to consider
- * @param[out] best_ist  input stream where a frame would allow to continue
- * @return  0 for success, <0 for error
- */
-int fg_transcode_step(FilterGraph *graph, InputStream **best_ist);
-
-void fg_send_command(FilterGraph *fg, double time, const char *target,
-                     const char *command, const char *arg, int all_filters);
-
-/**
- * Get and encode new output from specified filtergraph, without causing
- * activity.
- *
- * @return  0 for success, <0 for severe errors
- */
-int reap_filters(FilterGraph *fg, int flush);
+int ifilter_parameters_from_frame(InputFilter *ifilter, const AVFrame *frame);

 int ffmpeg_parse_options(int argc, char **argv);

@@ -784,43 +798,14 @@ void enc_stats_write(OutputStream *ost, EncStats *es,
                     uint64_t frame_num);

 HWDevice *hw_device_get_by_name(const char *name);
-HWDevice *hw_device_get_by_type(enum AVHWDeviceType type);
 int hw_device_init_from_string(const char *arg, HWDevice **dev);
-int hw_device_init_from_type(enum AVHWDeviceType type,
-                             const char *device,
-                             HWDevice **dev_out);
 void hw_device_free_all(void);

-/**
- * Get a hardware device to be used with this filtergraph.
- * The returned reference is owned by the callee, the caller
- * must ref it explicitly for long-term use.
- */
-AVBufferRef *hw_device_for_filter(void);
+int hw_device_setup_for_decode(InputStream *ist);
+int hw_device_setup_for_encode(OutputStream *ost);
+int hw_device_setup_for_filter(FilterGraph *fg);

-int hwaccel_retrieve_data(AVCodecContext *avctx, AVFrame *input);
-
-int dec_open(InputStream *ist);
-void dec_free(Decoder **pdec);
-
-/**
- * Submit a packet for decoding
- *
- * When pkt==NULL and no_eof=0, there will be no more input. Flush decoders and
- * mark all downstreams as finished.
- *
- * When pkt==NULL and no_eof=1, the stream was reset (e.g. after a seek). Flush
- * decoders and await further input.
- */
-int dec_packet(InputStream *ist, const AVPacket *pkt, int no_eof);
-
-int enc_alloc(Encoder **penc, const AVCodec *codec);
-void enc_free(Encoder **penc);
-
-int enc_open(OutputStream *ost, const AVFrame *frame);
-int enc_subtitle(OutputFile *of, OutputStream *ost, const AVSubtitle *sub);
-int enc_frame(OutputStream *ost, AVFrame *frame);
-int enc_flush(void);
+int hwaccel_decode_init(AVCodecContext *avctx);

 /*
 * Initialize muxing state for the given stream, should be called
@@ -831,17 +816,22 @@ int enc_flush(void);
 int of_stream_init(OutputFile *of, OutputStream *ost);
 int of_write_trailer(OutputFile *of);
 int of_open(const OptionsContext *o, const char *filename);
-void of_free(OutputFile **pof);
+void of_close(OutputFile **pof);

 void of_enc_stats_close(void);

-int of_output_packet(OutputFile *of, OutputStream *ost, AVPacket *pkt);
-
-/**
- * @param dts predicted packet dts in AV_TIME_BASE_Q
+/*
+ * Send a single packet to the output, applying any bitstream filters
+ * associated with the output stream.  This may result in any number
+ * of packets actually being written, depending on what bitstream
+ * filters are applied.  The supplied packet is consumed and will be
+ * blank (as if newly-allocated) when this function returns.
+ *
+ * If eof is set, instead indicate EOF to all bitstream filters and
+ * therefore flush any delayed packets to the output.  A blank packet
+ * must be supplied in this case.
 */
-int of_streamcopy(OutputStream *ost, const AVPacket *pkt, int64_t dts);
-
+void of_output_packet(OutputFile *of, AVPacket *pkt, OutputStream *ost, int eof);
 int64_t of_filesize(OutputFile *of);

 int ifile_open(const OptionsContext *o, const char *filename);
@@ -859,38 +849,10 @@ void ifile_close(InputFile **f);
 */
 int ifile_get_packet(InputFile *f, AVPacket **pkt);

-int ist_output_add(InputStream *ist, OutputStream *ost);
-int ist_filter_add(InputStream *ist, InputFilter *ifilter, int is_simple);
-
-/**
- * Find an unused input stream of given type.
- */
-InputStream *ist_find_unused(enum AVMediaType type);
-
 /* iterate over all input streams in all input files;
 * pass NULL to start iteration */
 InputStream *ist_iter(InputStream *prev);

-/* iterate over all output streams in all output files;
- * pass NULL to start iteration */
-OutputStream *ost_iter(OutputStream *prev);
-
-void close_output_stream(OutputStream *ost);
-int trigger_fix_sub_duration_heartbeat(OutputStream *ost, const AVPacket *pkt);
-int fix_sub_duration_heartbeat(InputStream *ist, int64_t signal_pts);
-void update_benchmark(const char *fmt, ...);
-
-/**
- * Merge two return codes - return one of the error codes if at least one of
- * them was negative, 0 otherwise.
- * Currently just picks the first one, eventually we might want to do something
- * more sophisticated, like sorting them by priority.
- */
-static inline int err_merge(int err0, int err1)
-{
-    return (err0 < 0) ? err0 : FFMIN(err1, 0);
-}
-
 #define SPECIFIER_OPT_FMT_str  "%s"
 #define SPECIFIER_OPT_FMT_i    "%i"
 #define SPECIFIER_OPT_FMT_i64  "%"PRId64
@@ -919,7 +881,7 @@ static inline int err_merge(int err0, int err1)
            so = &o->name[_i];\
            _matches++;\
        } else if (_ret < 0)\
-            return _ret;\
+            exit_program(1);\
    }\
    if (_matches > 1)\
       WARN_MULTIPLE_OPT_USAGE(name, type, so, st);\
@@ -938,18 +900,6 @@ static inline int err_merge(int err0, int err1)
 extern const char * const opt_name_codec_names[];
 extern const char * const opt_name_codec_tags[];
 extern const char * const opt_name_frame_rates[];
-#if FFMPEG_OPT_TOP
 extern const char * const opt_name_top_field_first[];
-#endif
-
-static inline void pkt_move(void *dst, void *src)
-{
-    av_packet_move_ref(dst, src);
-}
-
-static inline void frame_move(void *dst, void *src)
-{
-    av_frame_move_ref(dst, src);
-}

 #endif /* FFTOOLS_FFMPEG_H */
--- a/fftools/ffmpeg_dec.c
+++ b/fftools/ffmpeg_dec.c
--- a/fftools/ffmpeg_demux.c
+++ b/fftools/ffmpeg_demux.c
--- a/fftools/ffmpeg_enc.c
+++ b/fftools/ffmpeg_enc.c
@@ -1,888 +0,0 @@
-/*
- * This file is part of FFmpeg.
- *
- * FFmpeg is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2.1 of the License, or (at your option) any later version.
- *
- * FFmpeg is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with FFmpeg; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
-#include <math.h>
-#include <stdint.h>
-
-#include "ffmpeg.h"
-
-#include "libavutil/avassert.h"
-#include "libavutil/avstring.h"
-#include "libavutil/avutil.h"
-#include "libavutil/dict.h"
-#include "libavutil/display.h"
-#include "libavutil/eval.h"
-#include "libavutil/frame.h"
-#include "libavutil/intreadwrite.h"
-#include "libavutil/log.h"
-#include "libavutil/pixdesc.h"
-#include "libavutil/rational.h"
-#include "libavutil/timestamp.h"
-
-#include "libavcodec/avcodec.h"
-
-#include "libavformat/avformat.h"
-
-struct Encoder {
-    AVFrame *sq_frame;
-
-    // packet for receiving encoded output
-    AVPacket *pkt;
-
-    // combined size of all the packets received from the encoder
-    uint64_t data_size;
-
-    // number of packets received from the encoder
-    uint64_t packets_encoded;
-
-    int opened;
-};
-
-void enc_free(Encoder **penc)
-{
-    Encoder *enc = *penc;
-
-    if (!enc)
-        return;
-
-    av_frame_free(&enc->sq_frame);
-
-    av_packet_free(&enc->pkt);
-
-    av_freep(penc);
-}
-
-int enc_alloc(Encoder **penc, const AVCodec *codec)
-{
-    Encoder *enc;
-
-    *penc = NULL;
-
-    enc = av_mallocz(sizeof(*enc));
-    if (!enc)
-        return AVERROR(ENOMEM);
-
-    enc->pkt = av_packet_alloc();
-    if (!enc->pkt)
-        goto fail;
-
-    *penc = enc;
-
-    return 0;
-fail:
-    enc_free(&enc);
-    return AVERROR(ENOMEM);
-}
-
-static int hw_device_setup_for_encode(OutputStream *ost, AVBufferRef *frames_ref)
-{
-    const AVCodecHWConfig *config;
-    HWDevice *dev = NULL;
-    int i;
-
-    if (frames_ref &&
-        ((AVHWFramesContext*)frames_ref->data)->format ==
-        ost->enc_ctx->pix_fmt) {
-        // Matching format, will try to use hw_frames_ctx.
-    } else {
-        frames_ref = NULL;
-    }
-
-    for (i = 0;; i++) {
-        config = avcodec_get_hw_config(ost->enc_ctx->codec, i);
-        if (!config)
-            break;
-
-        if (frames_ref &&
-            config->methods & AV_CODEC_HW_CONFIG_METHOD_HW_FRAMES_CTX &&
-            (config->pix_fmt == AV_PIX_FMT_NONE ||
-             config->pix_fmt == ost->enc_ctx->pix_fmt)) {
-            av_log(ost->enc_ctx, AV_LOG_VERBOSE, "Using input "
-                   "frames context (format %s) with %s encoder.\n",
-                   av_get_pix_fmt_name(ost->enc_ctx->pix_fmt),
-                   ost->enc_ctx->codec->name);
-            ost->enc_ctx->hw_frames_ctx = av_buffer_ref(frames_ref);
-            if (!ost->enc_ctx->hw_frames_ctx)
-                return AVERROR(ENOMEM);
-            return 0;
-        }
-
-        if (!dev &&
-            config->methods & AV_CODEC_HW_CONFIG_METHOD_HW_DEVICE_CTX)
-            dev = hw_device_get_by_type(config->device_type);
-    }
-
-    if (dev) {
-        av_log(ost->enc_ctx, AV_LOG_VERBOSE, "Using device %s "
-               "(type %s) with %s encoder.\n", dev->name,
-               av_hwdevice_get_type_name(dev->type), ost->enc_ctx->codec->name);
-        ost->enc_ctx->hw_device_ctx = av_buffer_ref(dev->device_ref);
-        if (!ost->enc_ctx->hw_device_ctx)
-            return AVERROR(ENOMEM);
-    } else {
-        // No device required, or no device available.
-    }
-    return 0;
-}
-
-static int set_encoder_id(OutputFile *of, OutputStream *ost)
-{
-    const char *cname = ost->enc_ctx->codec->name;
-    uint8_t *encoder_string;
-    int encoder_string_len;
-
-    if (av_dict_get(ost->st->metadata, "encoder",  NULL, 0))
-        return 0;
-
-    encoder_string_len = sizeof(LIBAVCODEC_IDENT) + strlen(cname) + 2;
-    encoder_string     = av_mallocz(encoder_string_len);
-    if (!encoder_string)
-        return AVERROR(ENOMEM);
-
-    if (!of->bitexact && !ost->bitexact)
-        av_strlcpy(encoder_string, LIBAVCODEC_IDENT " ", encoder_string_len);
-    else
-        av_strlcpy(encoder_string, "Lavc ", encoder_string_len);
-    av_strlcat(encoder_string, cname, encoder_string_len);
-    av_dict_set(&ost->st->metadata, "encoder",  encoder_string,
-                AV_DICT_DONT_STRDUP_VAL | AV_DICT_DONT_OVERWRITE);
-
-    return 0;
-}
-
-int enc_open(OutputStream *ost, const AVFrame *frame)
-{
-    InputStream *ist = ost->ist;
-    Encoder              *e = ost->enc;
-    AVCodecContext *enc_ctx = ost->enc_ctx;
-    AVCodecContext *dec_ctx = NULL;
-    const AVCodec      *enc = enc_ctx->codec;
-    OutputFile      *of = output_files[ost->file_index];
-    FrameData *fd;
-    int ret;
-
-    if (e->opened)
-        return 0;
-
-    // frame is always non-NULL for audio and video
-    av_assert0(frame || (enc->type != AVMEDIA_TYPE_VIDEO && enc->type != AVMEDIA_TYPE_AUDIO));
-
-    if (frame) {
-        av_assert0(frame->opaque_ref);
-        fd = (FrameData*)frame->opaque_ref->data;
-    }
-
-    ret = set_encoder_id(output_files[ost->file_index], ost);
-    if (ret < 0)
-        return ret;
-
-    if (ist) {
-        dec_ctx = ist->dec_ctx;
-    }
-
-    // the timebase is chosen by filtering code
-    if (ost->type == AVMEDIA_TYPE_AUDIO || ost->type == AVMEDIA_TYPE_VIDEO) {
-        enc_ctx->time_base      = frame->time_base;
-        enc_ctx->framerate      = fd->frame_rate_filter;
-        ost->st->avg_frame_rate = fd->frame_rate_filter;
-    }
-
-    switch (enc_ctx->codec_type) {
-    case AVMEDIA_TYPE_AUDIO:
-        enc_ctx->sample_fmt     = frame->format;
-        enc_ctx->sample_rate    = frame->sample_rate;
-        ret = av_channel_layout_copy(&enc_ctx->ch_layout, &frame->ch_layout);
-        if (ret < 0)
-            return ret;
-
-        if (ost->bits_per_raw_sample)
-            enc_ctx->bits_per_raw_sample = ost->bits_per_raw_sample;
-        else
-            enc_ctx->bits_per_raw_sample = FFMIN(fd->bits_per_raw_sample,
-                                                 av_get_bytes_per_sample(enc_ctx->sample_fmt) << 3);
-        break;
-
-    case AVMEDIA_TYPE_VIDEO: {
-        enc_ctx->width  = frame->width;
-        enc_ctx->height = frame->height;
-        enc_ctx->sample_aspect_ratio = ost->st->sample_aspect_ratio =
-            ost->frame_aspect_ratio.num ? // overridden by the -aspect cli option
-            av_mul_q(ost->frame_aspect_ratio, (AVRational){ enc_ctx->height, enc_ctx->width }) :
-            frame->sample_aspect_ratio;
-
-        enc_ctx->pix_fmt = frame->format;
-
-        if (ost->bits_per_raw_sample)
-            enc_ctx->bits_per_raw_sample = ost->bits_per_raw_sample;
-        else
-            enc_ctx->bits_per_raw_sample = FFMIN(fd->bits_per_raw_sample,
-                                                 av_pix_fmt_desc_get(enc_ctx->pix_fmt)->comp[0].depth);
-
-        enc_ctx->color_range            = frame->color_range;
-        enc_ctx->color_primaries        = frame->color_primaries;
-        enc_ctx->color_trc              = frame->color_trc;
-        enc_ctx->colorspace             = frame->colorspace;
-        enc_ctx->chroma_sample_location = frame->chroma_location;
-
-        if (enc_ctx->flags & (AV_CODEC_FLAG_INTERLACED_DCT | AV_CODEC_FLAG_INTERLACED_ME) ||
-            (frame->flags & AV_FRAME_FLAG_INTERLACED)
-#if FFMPEG_OPT_TOP
-            || ost->top_field_first >= 0
-#endif
-            ) {
-            int top_field_first =
-#if FFMPEG_OPT_TOP
-                ost->top_field_first >= 0 ?
-                ost->top_field_first :
-#endif
-                !!(frame->flags & AV_FRAME_FLAG_TOP_FIELD_FIRST);
-
-            if (enc->id == AV_CODEC_ID_MJPEG)
-                enc_ctx->field_order = top_field_first ? AV_FIELD_TT : AV_FIELD_BB;
-            else
-                enc_ctx->field_order = top_field_first ? AV_FIELD_TB : AV_FIELD_BT;
-        } else
-            enc_ctx->field_order = AV_FIELD_PROGRESSIVE;
-
-        break;
-        }
-    case AVMEDIA_TYPE_SUBTITLE:
-        if (ost->enc_timebase.num)
-            av_log(ost, AV_LOG_WARNING,
-                   "-enc_time_base not supported for subtitles, ignoring\n");
-        enc_ctx->time_base = AV_TIME_BASE_Q;
-
-        if (!enc_ctx->width) {
-            enc_ctx->width     = ost->ist->par->width;
-            enc_ctx->height    = ost->ist->par->height;
-        }
-        if (dec_ctx && dec_ctx->subtitle_header) {
-            /* ASS code assumes this buffer is null terminated so add extra byte. */
-            enc_ctx->subtitle_header = av_mallocz(dec_ctx->subtitle_header_size + 1);
-            if (!enc_ctx->subtitle_header)
-                return AVERROR(ENOMEM);
-            memcpy(enc_ctx->subtitle_header, dec_ctx->subtitle_header,
-                   dec_ctx->subtitle_header_size);
-            enc_ctx->subtitle_header_size = dec_ctx->subtitle_header_size;
-        }
-
-        break;
-    default:
-        av_assert0(0);
-        break;
-    }
-
-    if (ost->bitexact)
-        enc_ctx->flags |= AV_CODEC_FLAG_BITEXACT;
-
-    if (!av_dict_get(ost->encoder_opts, "threads", NULL, 0))
-        av_dict_set(&ost->encoder_opts, "threads", "auto", 0);
-
-    if (enc->capabilities & AV_CODEC_CAP_ENCODER_REORDERED_OPAQUE) {
-        ret = av_dict_set(&ost->encoder_opts, "flags", "+copy_opaque", AV_DICT_MULTIKEY);
-        if (ret < 0)
-            return ret;
-    }
-
-    av_dict_set(&ost->encoder_opts, "flags", "+frame_duration", AV_DICT_MULTIKEY);
-
-    ret = hw_device_setup_for_encode(ost, frame ? frame->hw_frames_ctx : NULL);
-    if (ret < 0) {
-        av_log(ost, AV_LOG_ERROR,
-               "Encoding hardware device setup failed: %s\n", av_err2str(ret));
-        return ret;
-    }
-
-    if ((ret = avcodec_open2(ost->enc_ctx, enc, &ost->encoder_opts)) < 0) {
-        if (ret != AVERROR_EXPERIMENTAL)
-            av_log(ost, AV_LOG_ERROR, "Error while opening encoder - maybe "
-                   "incorrect parameters such as bit_rate, rate, width or height.\n");
-        return ret;
-    }
-
-    e->opened = 1;
-
-    if (ost->sq_idx_encode >= 0) {
-        e->sq_frame = av_frame_alloc();
-        if (!e->sq_frame)
-            return AVERROR(ENOMEM);
-    }
-
-    if (ost->enc_ctx->frame_size) {
-        av_assert0(ost->sq_idx_encode >= 0);
-        sq_frame_samples(output_files[ost->file_index]->sq_encode,
-                         ost->sq_idx_encode, ost->enc_ctx->frame_size);
-    }
-
-    ret = check_avoptions(ost->encoder_opts);
-    if (ret < 0)
-        return ret;
-
-    if (ost->enc_ctx->bit_rate && ost->enc_ctx->bit_rate < 1000 &&
-        ost->enc_ctx->codec_id != AV_CODEC_ID_CODEC2 /* don't complain about 700 bit/s modes */)
-        av_log(ost, AV_LOG_WARNING, "The bitrate parameter is set too low."
-                                    " It takes bits/s as argument, not kbits/s\n");
-
-    ret = avcodec_parameters_from_context(ost->par_in, ost->enc_ctx);
-    if (ret < 0) {
-        av_log(ost, AV_LOG_FATAL,
-               "Error initializing the output stream codec context.\n");
-        return ret;
-    }
-
-    /*
-     * Add global input side data. For now this is naive, and copies it
-     * from the input stream's global side data. All side data should
-     * really be funneled over AVFrame and libavfilter, then added back to
-     * packet side data, and then potentially using the first packet for
-     * global side data.
-     */
-    if (ist) {
-        int i;
-        for (i = 0; i < ist->st->codecpar->nb_coded_side_data; i++) {
-            AVPacketSideData *sd_src = &ist->st->codecpar->coded_side_data[i];
-            if (sd_src->type != AV_PKT_DATA_CPB_PROPERTIES) {
-                AVPacketSideData *sd_dst = av_packet_side_data_new(&ost->par_in->coded_side_data,
-                                                                   &ost->par_in->nb_coded_side_data,
-                                                                   sd_src->type, sd_src->size, 0);
-                if (!sd_dst)
-                    return AVERROR(ENOMEM);
-                memcpy(sd_dst->data, sd_src->data, sd_src->size);
-                if (ist->autorotate && sd_src->type == AV_PKT_DATA_DISPLAYMATRIX)
-                    av_display_rotation_set((int32_t *)sd_dst->data, 0);
-            }
-        }
-    }
-
-    // copy timebase while removing common factors
-    if (ost->st->time_base.num <= 0 || ost->st->time_base.den <= 0)
-        ost->st->time_base = av_add_q(ost->enc_ctx->time_base, (AVRational){0, 1});
-
-    ret = of_stream_init(of, ost);
-    if (ret < 0)
-        return ret;
-
-    return 0;
-}
-
-static int check_recording_time(OutputStream *ost, int64_t ts, AVRational tb)
-{
-    OutputFile *of = output_files[ost->file_index];
-
-    if (of->recording_time != INT64_MAX &&
-        av_compare_ts(ts, tb, of->recording_time, AV_TIME_BASE_Q) >= 0) {
-        close_output_stream(ost);
-        return 0;
-    }
-    return 1;
-}
-
-int enc_subtitle(OutputFile *of, OutputStream *ost, const AVSubtitle *sub)
-{
-    Encoder *e = ost->enc;
-    int subtitle_out_max_size = 1024 * 1024;
-    int subtitle_out_size, nb, i, ret;
-    AVCodecContext *enc;
-    AVPacket *pkt = e->pkt;
-    int64_t pts;
-
-    if (sub->pts == AV_NOPTS_VALUE) {
-        av_log(ost, AV_LOG_ERROR, "Subtitle packets must have a pts\n");
-        return exit_on_error ? AVERROR(EINVAL) : 0;
-    }
-    if (ost->finished ||
-        (of->start_time != AV_NOPTS_VALUE && sub->pts < of->start_time))
-        return 0;
-
-    enc = ost->enc_ctx;
-
-    /* Note: DVB subtitle need one packet to draw them and one other
-       packet to clear them */
-    /* XXX: signal it in the codec context ? */
-    if (enc->codec_id == AV_CODEC_ID_DVB_SUBTITLE)
-        nb = 2;
-    else if (enc->codec_id == AV_CODEC_ID_ASS)
-        nb = FFMAX(sub->num_rects, 1);
-    else
-        nb = 1;
-
-    /* shift timestamp to honor -ss and make check_recording_time() work with -t */
-    pts = sub->pts;
-    if (output_files[ost->file_index]->start_time != AV_NOPTS_VALUE)
-        pts -= output_files[ost->file_index]->start_time;
-    for (i = 0; i < nb; i++) {
-        AVSubtitle local_sub = *sub;
-
-        if (!check_recording_time(ost, pts, AV_TIME_BASE_Q))
-            return 0;
-
-        ret = av_new_packet(pkt, subtitle_out_max_size);
-        if (ret < 0)
-            return AVERROR(ENOMEM);
-
-        local_sub.pts = pts;
-        // start_display_time is required to be 0
-        local_sub.pts               += av_rescale_q(sub->start_display_time, (AVRational){ 1, 1000 }, AV_TIME_BASE_Q);
-        local_sub.end_display_time  -= sub->start_display_time;
-        local_sub.start_display_time = 0;
-
-        if (enc->codec_id == AV_CODEC_ID_DVB_SUBTITLE && i == 1)
-            local_sub.num_rects = 0;
-        else if (enc->codec_id == AV_CODEC_ID_ASS && sub->num_rects > 0) {
-            local_sub.num_rects = 1;
-            local_sub.rects += i;
-        }
-
-        ost->frames_encoded++;
-
-        subtitle_out_size = avcodec_encode_subtitle(enc, pkt->data, pkt->size, &local_sub);
-        if (subtitle_out_size < 0) {
-            av_log(ost, AV_LOG_FATAL, "Subtitle encoding failed\n");
-            return subtitle_out_size;
-        }
-
-        av_shrink_packet(pkt, subtitle_out_size);
-        pkt->time_base = AV_TIME_BASE_Q;
-        pkt->pts       = sub->pts;
-        pkt->duration = av_rescale_q(sub->end_display_time, (AVRational){ 1, 1000 }, pkt->time_base);
-        if (enc->codec_id == AV_CODEC_ID_DVB_SUBTITLE) {
-            /* XXX: the pts correction is handled here. Maybe handling
-               it in the codec would be better */
-            if (i == 0)
-                pkt->pts += av_rescale_q(sub->start_display_time, (AVRational){ 1, 1000 }, pkt->time_base);
-            else
-                pkt->pts += av_rescale_q(sub->end_display_time, (AVRational){ 1, 1000 }, pkt->time_base);
-        }
-        pkt->dts = pkt->pts;
-
-        ret = of_output_packet(of, ost, pkt);
-        if (ret < 0)
-            return ret;
-    }
-
-    return 0;
-}
-
-void enc_stats_write(OutputStream *ost, EncStats *es,
-                     const AVFrame *frame, const AVPacket *pkt,
-                     uint64_t frame_num)
-{
-    Encoder      *e = ost->enc;
-    AVIOContext *io = es->io;
-    AVRational   tb = frame ? frame->time_base : pkt->time_base;
-    int64_t     pts = frame ? frame->pts : pkt->pts;
-
-    AVRational  tbi = (AVRational){ 0, 1};
-    int64_t    ptsi = INT64_MAX;
-
-    const FrameData *fd;
-
-    if ((frame && frame->opaque_ref) || (pkt && pkt->opaque_ref)) {
-        fd   = (const FrameData*)(frame ? frame->opaque_ref->data : pkt->opaque_ref->data);
-        tbi  = fd->dec.tb;
-        ptsi = fd->dec.pts;
-    }
-
-    for (size_t i = 0; i < es->nb_components; i++) {
-        const EncStatsComponent *c = &es->components[i];
-
-        switch (c->type) {
-        case ENC_STATS_LITERAL:         avio_write (io, c->str,     c->str_len);                    continue;
-        case ENC_STATS_FILE_IDX:        avio_printf(io, "%d",       ost->file_index);               continue;
-        case ENC_STATS_STREAM_IDX:      avio_printf(io, "%d",       ost->index);                    continue;
-        case ENC_STATS_TIMEBASE:        avio_printf(io, "%d/%d",    tb.num, tb.den);                continue;
-        case ENC_STATS_TIMEBASE_IN:     avio_printf(io, "%d/%d",    tbi.num, tbi.den);              continue;
-        case ENC_STATS_PTS:             avio_printf(io, "%"PRId64,  pts);                           continue;
-        case ENC_STATS_PTS_IN:          avio_printf(io, "%"PRId64,  ptsi);                          continue;
-        case ENC_STATS_PTS_TIME:        avio_printf(io, "%g",       pts * av_q2d(tb));              continue;
-        case ENC_STATS_PTS_TIME_IN:     avio_printf(io, "%g",       ptsi == INT64_MAX ?
-                                                                    INFINITY : ptsi * av_q2d(tbi)); continue;
-        case ENC_STATS_FRAME_NUM:       avio_printf(io, "%"PRIu64,  frame_num);                     continue;
-        case ENC_STATS_FRAME_NUM_IN:    avio_printf(io, "%"PRIu64,  fd ? fd->dec.frame_num : -1);   continue;
-        }
-
-        if (frame) {
-            switch (c->type) {
-            case ENC_STATS_SAMPLE_NUM:  avio_printf(io, "%"PRIu64,  ost->samples_encoded);          continue;
-            case ENC_STATS_NB_SAMPLES:  avio_printf(io, "%d",       frame->nb_samples);             continue;
-            default: av_assert0(0);
-            }
-        } else {
-            switch (c->type) {
-            case ENC_STATS_DTS:         avio_printf(io, "%"PRId64,  pkt->dts);                      continue;
-            case ENC_STATS_DTS_TIME:    avio_printf(io, "%g",       pkt->dts * av_q2d(tb));         continue;
-            case ENC_STATS_PKT_SIZE:    avio_printf(io, "%d",       pkt->size);                     continue;
-            case ENC_STATS_BITRATE: {
-                double duration = FFMAX(pkt->duration, 1) * av_q2d(tb);
-                avio_printf(io, "%g",  8.0 * pkt->size / duration);
-                continue;
-            }
-            case ENC_STATS_AVG_BITRATE: {
-                double duration = pkt->dts * av_q2d(tb);
-                avio_printf(io, "%g",  duration > 0 ? 8.0 * e->data_size / duration : -1.);
-                continue;
-            }
-            default: av_assert0(0);
-            }
-        }
-    }
-    avio_w8(io, '\n');
-    avio_flush(io);
-}
-
-static inline double psnr(double d)
-{
-    return -10.0 * log10(d);
-}
-
-static int update_video_stats(OutputStream *ost, const AVPacket *pkt, int write_vstats)
-{
-    Encoder        *e = ost->enc;
-    const uint8_t *sd = av_packet_get_side_data(pkt, AV_PKT_DATA_QUALITY_STATS,
-                                                NULL);
-    AVCodecContext *enc = ost->enc_ctx;
-    enum AVPictureType pict_type;
-    int64_t frame_number;
-    double ti1, bitrate, avg_bitrate;
-    double psnr_val = -1;
-
-    ost->quality   = sd ? AV_RL32(sd) : -1;
-    pict_type      = sd ? sd[4] : AV_PICTURE_TYPE_NONE;
-
-    if ((enc->flags & AV_CODEC_FLAG_PSNR) && sd && sd[5]) {
-        // FIXME the scaling assumes 8bit
-        double error = AV_RL64(sd + 8) / (enc->width * enc->height * 255.0 * 255.0);
-        if (error >= 0 && error <= 1)
-            psnr_val = psnr(error);
-    }
-
-    if (!write_vstats)
-        return 0;
-
-    /* this is executed just the first time update_video_stats is called */
-    if (!vstats_file) {
-        vstats_file = fopen(vstats_filename, "w");
-        if (!vstats_file) {
-            perror("fopen");
-            return AVERROR(errno);
-        }
-    }
-
-    frame_number = e->packets_encoded;
-    if (vstats_version <= 1) {
-        fprintf(vstats_file, "frame= %5"PRId64" q= %2.1f ", frame_number,
-                ost->quality / (float)FF_QP2LAMBDA);
-    } else  {
-        fprintf(vstats_file, "out= %2d st= %2d frame= %5"PRId64" q= %2.1f ", ost->file_index, ost->index, frame_number,
-                ost->quality / (float)FF_QP2LAMBDA);
-    }
-
-    if (psnr_val >= 0)
-        fprintf(vstats_file, "PSNR= %6.2f ", psnr_val);
-
-    fprintf(vstats_file,"f_size= %6d ", pkt->size);
-    /* compute pts value */
-    ti1 = pkt->dts * av_q2d(pkt->time_base);
-    if (ti1 < 0.01)
-        ti1 = 0.01;
-
-    bitrate     = (pkt->size * 8) / av_q2d(enc->time_base) / 1000.0;
-    avg_bitrate = (double)(e->data_size * 8) / ti1 / 1000.0;
-    fprintf(vstats_file, "s_size= %8.0fkB time= %0.3f br= %7.1fkbits/s avg_br= %7.1fkbits/s ",
-           (double)e->data_size / 1024, ti1, bitrate, avg_bitrate);
-    fprintf(vstats_file, "type= %c\n", av_get_picture_type_char(pict_type));
-
-    return 0;
-}
-
-static int encode_frame(OutputFile *of, OutputStream *ost, AVFrame *frame)
-{
-    Encoder            *e = ost->enc;
-    AVCodecContext   *enc = ost->enc_ctx;
-    AVPacket         *pkt = e->pkt;
-    const char *type_desc = av_get_media_type_string(enc->codec_type);
-    const char    *action = frame ? "encode" : "flush";
-    int ret;
-
-    if (frame) {
-        if (ost->enc_stats_pre.io)
-            enc_stats_write(ost, &ost->enc_stats_pre, frame, NULL,
-                            ost->frames_encoded);
-
-        ost->frames_encoded++;
-        ost->samples_encoded += frame->nb_samples;
-
-        if (debug_ts) {
-            av_log(ost, AV_LOG_INFO, "encoder <- type:%s "
-                   "frame_pts:%s frame_pts_time:%s time_base:%d/%d\n",
-                   type_desc,
-                   av_ts2str(frame->pts), av_ts2timestr(frame->pts, &enc->time_base),
-                   enc->time_base.num, enc->time_base.den);
-        }
-
-        if (frame->sample_aspect_ratio.num && !ost->frame_aspect_ratio.num)
-            enc->sample_aspect_ratio = frame->sample_aspect_ratio;
-    }
-
-    update_benchmark(NULL);
-
-    ret = avcodec_send_frame(enc, frame);
-    if (ret < 0 && !(ret == AVERROR_EOF && !frame)) {
-        av_log(ost, AV_LOG_ERROR, "Error submitting %s frame to the encoder\n",
-               type_desc);
-        return ret;
-    }
-
-    while (1) {
-        av_packet_unref(pkt);
-
-        ret = avcodec_receive_packet(enc, pkt);
-        update_benchmark("%s_%s %d.%d", action, type_desc,
-                         ost->file_index, ost->index);
-
-        pkt->time_base = enc->time_base;
-
-        /* if two pass, output log on success and EOF */
-        if ((ret >= 0 || ret == AVERROR_EOF) && ost->logfile && enc->stats_out)
-            fprintf(ost->logfile, "%s", enc->stats_out);
-
-        if (ret == AVERROR(EAGAIN)) {
-            av_assert0(frame); // should never happen during flushing
-            return 0;
-        } else if (ret == AVERROR_EOF) {
-            ret = of_output_packet(of, ost, NULL);
-            return ret < 0 ? ret : AVERROR_EOF;
-        } else if (ret < 0) {
-            av_log(ost, AV_LOG_ERROR, "%s encoding failed\n", type_desc);
-            return ret;
-        }
-
-        if (enc->codec_type == AVMEDIA_TYPE_VIDEO) {
-            ret = update_video_stats(ost, pkt, !!vstats_filename);
-            if (ret < 0)
-                return ret;
-        }
-
-        if (ost->enc_stats_post.io)
-            enc_stats_write(ost, &ost->enc_stats_post, NULL, pkt,
-                            e->packets_encoded);
-
-        if (debug_ts) {
-            av_log(ost, AV_LOG_INFO, "encoder -> type:%s "
-                   "pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s "
-                   "duration:%s duration_time:%s\n",
-                   type_desc,
-                   av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, &enc->time_base),
-                   av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, &enc->time_base),
-                   av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, &enc->time_base));
-        }
-
-        if ((ret = trigger_fix_sub_duration_heartbeat(ost, pkt)) < 0) {
-            av_log(NULL, AV_LOG_ERROR,
-                   "Subtitle heartbeat logic failed in %s! (%s)\n",
-                   __func__, av_err2str(ret));
-            return ret;
-        }
-
-        e->data_size += pkt->size;
-
-        e->packets_encoded++;
-
-        ret = of_output_packet(of, ost, pkt);
-        if (ret < 0)
-            return ret;
-    }
-
-    av_assert0(0);
-}
-
-static int submit_encode_frame(OutputFile *of, OutputStream *ost,
-                               AVFrame *frame)
-{
-    Encoder *e = ost->enc;
-    int ret;
-
-    if (ost->sq_idx_encode < 0)
-        return encode_frame(of, ost, frame);
-
-    if (frame) {
-        ret = av_frame_ref(e->sq_frame, frame);
-        if (ret < 0)
-            return ret;
-        frame = e->sq_frame;
-    }
-
-    ret = sq_send(of->sq_encode, ost->sq_idx_encode,
-                  SQFRAME(frame));
-    if (ret < 0) {
-        if (frame)
-            av_frame_unref(frame);
-        if (ret != AVERROR_EOF)
-            return ret;
-    }
-
-    while (1) {
-        AVFrame *enc_frame = e->sq_frame;
-
-        ret = sq_receive(of->sq_encode, ost->sq_idx_encode,
-                               SQFRAME(enc_frame));
-        if (ret == AVERROR_EOF) {
-            enc_frame = NULL;
-        } else if (ret < 0) {
-            return (ret == AVERROR(EAGAIN)) ? 0 : ret;
-        }
-
-        ret = encode_frame(of, ost, enc_frame);
-        if (enc_frame)
-            av_frame_unref(enc_frame);
-        if (ret < 0) {
-            if (ret == AVERROR_EOF)
-                close_output_stream(ost);
-            return ret;
-        }
-    }
-}
-
-static int do_audio_out(OutputFile *of, OutputStream *ost,
-                        AVFrame *frame)
-{
-    AVCodecContext *enc = ost->enc_ctx;
-    int ret;
-
-    if (!(enc->codec->capabilities & AV_CODEC_CAP_PARAM_CHANGE) &&
-        enc->ch_layout.nb_channels != frame->ch_layout.nb_channels) {
-        av_log(ost, AV_LOG_ERROR,
-               "Audio channel count changed and encoder does not support parameter changes\n");
-        return 0;
-    }
-
-    if (!check_recording_time(ost, frame->pts, frame->time_base))
-        return 0;
-
-    ret = submit_encode_frame(of, ost, frame);
-    return (ret < 0 && ret != AVERROR_EOF) ? ret : 0;
-}
-
-static enum AVPictureType forced_kf_apply(void *logctx, KeyframeForceCtx *kf,
-                                          AVRational tb, const AVFrame *in_picture)
-{
-    double pts_time;
-
-    if (kf->ref_pts == AV_NOPTS_VALUE)
-        kf->ref_pts = in_picture->pts;
-
-    pts_time = (in_picture->pts - kf->ref_pts) * av_q2d(tb);
-    if (kf->index < kf->nb_pts &&
-        av_compare_ts(in_picture->pts, tb, kf->pts[kf->index], AV_TIME_BASE_Q) >= 0) {
-        kf->index++;
-        goto force_keyframe;
-    } else if (kf->pexpr) {
-        double res;
-        kf->expr_const_values[FKF_T] = pts_time;
-        res = av_expr_eval(kf->pexpr,
-                           kf->expr_const_values, NULL);
-        av_log(logctx, AV_LOG_TRACE,
-               "force_key_frame: n:%f n_forced:%f prev_forced_n:%f t:%f prev_forced_t:%f -> res:%f\n",
-               kf->expr_const_values[FKF_N],
-               kf->expr_const_values[FKF_N_FORCED],
-               kf->expr_const_values[FKF_PREV_FORCED_N],
-               kf->expr_const_values[FKF_T],
-               kf->expr_const_values[FKF_PREV_FORCED_T],
-               res);
-
-        kf->expr_const_values[FKF_N] += 1;
-
-        if (res) {
-            kf->expr_const_values[FKF_PREV_FORCED_N] = kf->expr_const_values[FKF_N] - 1;
-            kf->expr_const_values[FKF_PREV_FORCED_T] = kf->expr_const_values[FKF_T];
-            kf->expr_const_values[FKF_N_FORCED]     += 1;
-            goto force_keyframe;
-        }
-    } else if (kf->type == KF_FORCE_SOURCE && (in_picture->flags & AV_FRAME_FLAG_KEY)) {
-        goto force_keyframe;
-    }
-
-    return AV_PICTURE_TYPE_NONE;
-
-force_keyframe:
-    av_log(logctx, AV_LOG_DEBUG, "Forced keyframe at time %f\n", pts_time);
-    return AV_PICTURE_TYPE_I;
-}
-
-/* May modify/reset frame */
-static int do_video_out(OutputFile *of, OutputStream *ost, AVFrame *in_picture)
-{
-    int ret;
-    AVCodecContext *enc = ost->enc_ctx;
-
-    if (!check_recording_time(ost, in_picture->pts, ost->enc_ctx->time_base))
-        return 0;
-
-    in_picture->quality = enc->global_quality;
-    in_picture->pict_type = forced_kf_apply(ost, &ost->kf, enc->time_base, in_picture);
-
-#if FFMPEG_OPT_TOP
-    if (ost->top_field_first >= 0) {
-        in_picture->flags &= ~AV_FRAME_FLAG_TOP_FIELD_FIRST;
-        in_picture->flags |= AV_FRAME_FLAG_TOP_FIELD_FIRST * (!!ost->top_field_first);
-    }
-#endif
-
-    ret = submit_encode_frame(of, ost, in_picture);
-    return (ret == AVERROR_EOF) ? 0 : ret;
-}
-
-int enc_frame(OutputStream *ost, AVFrame *frame)
-{
-    OutputFile *of = output_files[ost->file_index];
-    int ret;
-
-    ret = enc_open(ost, frame);
-    if (ret < 0)
-        return ret;
-
-    return ost->enc_ctx->codec_type == AVMEDIA_TYPE_VIDEO ?
-           do_video_out(of, ost, frame) : do_audio_out(of, ost, frame);
-}
-
-int enc_flush(void)
-{
-    int ret;
-
-    for (OutputStream *ost = ost_iter(NULL); ost; ost = ost_iter(ost)) {
-        OutputFile      *of = output_files[ost->file_index];
-        if (ost->sq_idx_encode >= 0)
-            sq_send(of->sq_encode, ost->sq_idx_encode, SQFRAME(NULL));
-    }
-
-    for (OutputStream *ost = ost_iter(NULL); ost; ost = ost_iter(ost)) {
-        Encoder          *e = ost->enc;
-        AVCodecContext *enc = ost->enc_ctx;
-        OutputFile      *of = output_files[ost->file_index];
-
-        if (!enc || !e->opened ||
-            (enc->codec_type != AVMEDIA_TYPE_VIDEO && enc->codec_type != AVMEDIA_TYPE_AUDIO))
-            continue;
-
-        ret = submit_encode_frame(of, ost, NULL);
-        if (ret != AVERROR_EOF)
-            return ret;
-    }
-
-    return 0;
-}
--- a/fftools/ffmpeg_filter.c
+++ b/fftools/ffmpeg_filter.c
--- a/fftools/ffmpeg_hw.c
+++ b/fftools/ffmpeg_hw.c
@@ -27,7 +27,7 @@
 static int nb_hw_devices;
 static HWDevice **hw_devices;

-HWDevice *hw_device_get_by_type(enum AVHWDeviceType type)
+static HWDevice *hw_device_get_by_type(enum AVHWDeviceType type)
 {
    HWDevice *found = NULL;
    int i;
@@ -242,9 +242,9 @@ fail:
    goto done;
 }

-int hw_device_init_from_type(enum AVHWDeviceType type,
-                             const char *device,
-                             HWDevice **dev_out)
+static int hw_device_init_from_type(enum AVHWDeviceType type,
+                                    const char *device,
+                                    HWDevice **dev_out)
 {
    AVBufferRef *device_ref = NULL;
    HWDevice *dev;
@@ -297,7 +297,207 @@ void hw_device_free_all(void)
    nb_hw_devices = 0;
 }

-int hwaccel_retrieve_data(AVCodecContext *avctx, AVFrame *input)
+static HWDevice *hw_device_match_by_codec(const AVCodec *codec)
+{
+    const AVCodecHWConfig *config;
+    HWDevice *dev;
+    int i;
+    for (i = 0;; i++) {
+        config = avcodec_get_hw_config(codec, i);
+        if (!config)
+            return NULL;
+        if (!(config->methods & AV_CODEC_HW_CONFIG_METHOD_HW_DEVICE_CTX))
+            continue;
+        dev = hw_device_get_by_type(config->device_type);
+        if (dev)
+            return dev;
+    }
+}
+
+int hw_device_setup_for_decode(InputStream *ist)
+{
+    const AVCodecHWConfig *config;
+    enum AVHWDeviceType type;
+    HWDevice *dev = NULL;
+    int err, auto_device = 0;
+
+    if (ist->hwaccel_device) {
+        dev = hw_device_get_by_name(ist->hwaccel_device);
+        if (!dev) {
+            if (ist->hwaccel_id == HWACCEL_AUTO) {
+                auto_device = 1;
+            } else if (ist->hwaccel_id == HWACCEL_GENERIC) {
+                type = ist->hwaccel_device_type;
+                err = hw_device_init_from_type(type, ist->hwaccel_device,
+                                               &dev);
+            } else {
+                // This will be dealt with by API-specific initialisation
+                // (using hwaccel_device), so nothing further needed here.
+                return 0;
+            }
+        } else {
+            if (ist->hwaccel_id == HWACCEL_AUTO) {
+                ist->hwaccel_device_type = dev->type;
+            } else if (ist->hwaccel_device_type != dev->type) {
+                av_log(NULL, AV_LOG_ERROR, "Invalid hwaccel device "
+                       "specified for decoder: device %s of type %s is not "
+                       "usable with hwaccel %s.\n", dev->name,
+                       av_hwdevice_get_type_name(dev->type),
+                       av_hwdevice_get_type_name(ist->hwaccel_device_type));
+                return AVERROR(EINVAL);
+            }
+        }
+    } else {
+        if (ist->hwaccel_id == HWACCEL_AUTO) {
+            auto_device = 1;
+        } else if (ist->hwaccel_id == HWACCEL_GENERIC) {
+            type = ist->hwaccel_device_type;
+            dev = hw_device_get_by_type(type);
+
+            // When "-qsv_device device" is used, an internal QSV device named
+            // as "__qsv_device" is created. Another QSV device is created too
+            // if "-init_hw_device qsv=name:device" is used. There are 2 QSV devices
+            // if both "-qsv_device device" and "-init_hw_device qsv=name:device"
+            // are used, hw_device_get_by_type(AV_HWDEVICE_TYPE_QSV) returns NULL.
+            // To keep back-compatibility with the removed ad-hoc libmfx setup code,
+            // call hw_device_get_by_name("__qsv_device") to select the internal QSV
+            // device.
+            if (!dev && type == AV_HWDEVICE_TYPE_QSV)
+                dev = hw_device_get_by_name("__qsv_device");
+
+            if (!dev)
+                err = hw_device_init_from_type(type, NULL, &dev);
+        } else {
+            dev = hw_device_match_by_codec(ist->dec);
+            if (!dev) {
+                // No device for this codec, but not using generic hwaccel
+                // and therefore may well not need one - ignore.
+                return 0;
+            }
+        }
+    }
+
+    if (auto_device) {
+        int i;
+        if (!avcodec_get_hw_config(ist->dec, 0)) {
+            // Decoder does not support any hardware devices.
+            return 0;
+        }
+        for (i = 0; !dev; i++) {
+            config = avcodec_get_hw_config(ist->dec, i);
+            if (!config)
+                break;
+            type = config->device_type;
+            dev = hw_device_get_by_type(type);
+            if (dev) {
+                av_log(NULL, AV_LOG_INFO, "Using auto "
+                       "hwaccel type %s with existing device %s.\n",
+                       av_hwdevice_get_type_name(type), dev->name);
+            }
+        }
+        for (i = 0; !dev; i++) {
+            config = avcodec_get_hw_config(ist->dec, i);
+            if (!config)
+                break;
+            type = config->device_type;
+            // Try to make a new device of this type.
+            err = hw_device_init_from_type(type, ist->hwaccel_device,
+                                           &dev);
+            if (err < 0) {
+                // Can't make a device of this type.
+                continue;
+            }
+            if (ist->hwaccel_device) {
+                av_log(NULL, AV_LOG_INFO, "Using auto "
+                       "hwaccel type %s with new device created "
+                       "from %s.\n", av_hwdevice_get_type_name(type),
+                       ist->hwaccel_device);
+            } else {
+                av_log(NULL, AV_LOG_INFO, "Using auto "
+                       "hwaccel type %s with new default device.\n",
+                       av_hwdevice_get_type_name(type));
+            }
+        }
+        if (dev) {
+            ist->hwaccel_device_type = type;
+        } else {
+            av_log(NULL, AV_LOG_INFO, "Auto hwaccel "
+                   "disabled: no device found.\n");
+            ist->hwaccel_id = HWACCEL_NONE;
+            return 0;
+        }
+    }
+
+    if (!dev) {
+        av_log(NULL, AV_LOG_ERROR, "No device available "
+               "for decoder: device type %s needed for codec %s.\n",
+               av_hwdevice_get_type_name(type), ist->dec->name);
+        return err;
+    }
+
+    ist->dec_ctx->hw_device_ctx = av_buffer_ref(dev->device_ref);
+    if (!ist->dec_ctx->hw_device_ctx)
+        return AVERROR(ENOMEM);
+
+    return 0;
+}
+
+int hw_device_setup_for_encode(OutputStream *ost)
+{
+    const AVCodecHWConfig *config;
+    HWDevice *dev = NULL;
+    AVBufferRef *frames_ref = NULL;
+    int i;
+
+    if (ost->filter) {
+        frames_ref = av_buffersink_get_hw_frames_ctx(ost->filter->filter);
+        if (frames_ref &&
+            ((AVHWFramesContext*)frames_ref->data)->format ==
+            ost->enc_ctx->pix_fmt) {
+            // Matching format, will try to use hw_frames_ctx.
+        } else {
+            frames_ref = NULL;
+        }
+    }
+
+    for (i = 0;; i++) {
+        config = avcodec_get_hw_config(ost->enc_ctx->codec, i);
+        if (!config)
+            break;
+
+        if (frames_ref &&
+            config->methods & AV_CODEC_HW_CONFIG_METHOD_HW_FRAMES_CTX &&
+            (config->pix_fmt == AV_PIX_FMT_NONE ||
+             config->pix_fmt == ost->enc_ctx->pix_fmt)) {
+            av_log(ost->enc_ctx, AV_LOG_VERBOSE, "Using input "
+                   "frames context (format %s) with %s encoder.\n",
+                   av_get_pix_fmt_name(ost->enc_ctx->pix_fmt),
+                   ost->enc_ctx->codec->name);
+            ost->enc_ctx->hw_frames_ctx = av_buffer_ref(frames_ref);
+            if (!ost->enc_ctx->hw_frames_ctx)
+                return AVERROR(ENOMEM);
+            return 0;
+        }
+
+        if (!dev &&
+            config->methods & AV_CODEC_HW_CONFIG_METHOD_HW_DEVICE_CTX)
+            dev = hw_device_get_by_type(config->device_type);
+    }
+
+    if (dev) {
+        av_log(ost->enc_ctx, AV_LOG_VERBOSE, "Using device %s "
+               "(type %s) with %s encoder.\n", dev->name,
+               av_hwdevice_get_type_name(dev->type), ost->enc_ctx->codec->name);
+        ost->enc_ctx->hw_device_ctx = av_buffer_ref(dev->device_ref);
+        if (!ost->enc_ctx->hw_device_ctx)
+            return AVERROR(ENOMEM);
+    } else {
+        // No device required, or no device available.
+    }
+    return 0;
+}
+
+static int hwaccel_retrieve_data(AVCodecContext *avctx, AVFrame *input)
 {
    InputStream *ist = avctx->opaque;
    AVFrame *output = NULL;
@@ -339,14 +539,26 @@ fail:
    return err;
 }

-AVBufferRef *hw_device_for_filter(void)
+int hwaccel_decode_init(AVCodecContext *avctx)
 {
+    InputStream *ist = avctx->opaque;
+
+    ist->hwaccel_retrieve_data = &hwaccel_retrieve_data;
+
+    return 0;
+}
+
+int hw_device_setup_for_filter(FilterGraph *fg)
+{
+    HWDevice *dev;
+    int i;
+
    // Pick the last hardware device if the user doesn't pick the device for
    // filters explicitly with the filter_hw_device option.
    if (filter_hw_device)
-        return filter_hw_device->device_ref;
+        dev = filter_hw_device;
    else if (nb_hw_devices > 0) {
-        HWDevice *dev = hw_devices[nb_hw_devices - 1];
+        dev = hw_devices[nb_hw_devices - 1];

        if (nb_hw_devices > 1)
            av_log(NULL, AV_LOG_WARNING, "There are %d hardware devices. device "
@@ -355,9 +567,17 @@ AVBufferRef *hw_device_for_filter(void)
                   "%s is not usable for filters.\n",
                   nb_hw_devices, dev->name,
                   av_hwdevice_get_type_name(dev->type), dev->name);
+    } else
+        dev = NULL;

-        return dev->device_ref;
+    if (dev) {
+        for (i = 0; i < fg->graph->nb_filters; i++) {
+            fg->graph->filters[i]->hw_device_ctx =
+                av_buffer_ref(dev->device_ref);
+            if (!fg->graph->filters[i]->hw_device_ctx)
+                return AVERROR(ENOMEM);
+        }
    }

-    return NULL;
+    return 0;
 }
--- a/fftools/ffmpeg_mux.c
+++ b/fftools/ffmpeg_mux.c
@@ -62,6 +62,7 @@ static int write_packet(Muxer *mux, OutputStream *ost, AVPacket *pkt)
 {
    MuxStream *ms = ms_from_ost(ost);
    AVFormatContext *s = mux->fc;
+    AVStream *st = ost->st;
    int64_t fs;
    uint64_t frame_num;
    int ret;
@@ -73,26 +74,19 @@ static int write_packet(Muxer *mux, OutputStream *ost, AVPacket *pkt)
        goto fail;
    }

-    if (ost->type == AVMEDIA_TYPE_VIDEO && ost->vsync_method == VSYNC_DROP)
+    if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO && ost->vsync_method == VSYNC_DROP)
        pkt->pts = pkt->dts = AV_NOPTS_VALUE;

-    // rescale timestamps to the stream timebase
-    if (ost->type == AVMEDIA_TYPE_AUDIO && !ost->enc) {
-        // use av_rescale_delta() for streamcopying audio, to preserve
-        // accuracy with coarse input timebases
-        int duration = av_get_audio_frame_duration2(ost->st->codecpar, pkt->size);
+    if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) {
+        if (ost->frame_rate.num && ost->is_cfr) {
+            if (pkt->duration > 0)
+                av_log(ost, AV_LOG_WARNING, "Overriding packet duration by frame rate, this should not happen\n");
+            pkt->duration = av_rescale_q(1, av_inv_q(ost->frame_rate),
+                                         pkt->time_base);
+        }
+    }

-        if (!duration)
-            duration = ost->st->codecpar->frame_size;
-
-        pkt->dts = av_rescale_delta(pkt->time_base, pkt->dts,
-                                    (AVRational){1, ost->st->codecpar->sample_rate}, duration,
-                                    &ms->ts_rescale_delta_last, ost->st->time_base);
-        pkt->pts = pkt->dts;
-
-        pkt->duration = av_rescale_q(pkt->duration, pkt->time_base, ost->st->time_base);
-    } else
-        av_packet_rescale_ts(pkt, pkt->time_base, ost->st->time_base);
+    av_packet_rescale_ts(pkt, pkt->time_base, ost->st->time_base);
    pkt->time_base = ost->st->time_base;

    if (!(s->oformat->flags & AVFMT_NOTIMESTAMPS)) {
@@ -107,15 +101,15 @@ static int write_packet(Muxer *mux, OutputStream *ost, AVPacket *pkt)
                     - FFMIN3(pkt->pts, pkt->dts, ms->last_mux_dts + 1)
                     - FFMAX3(pkt->pts, pkt->dts, ms->last_mux_dts + 1);
        }
-        if ((ost->type == AVMEDIA_TYPE_AUDIO || ost->type == AVMEDIA_TYPE_VIDEO || ost->type == AVMEDIA_TYPE_SUBTITLE) &&
+        if ((st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO || st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO || st->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE) &&
            pkt->dts != AV_NOPTS_VALUE &&
            ms->last_mux_dts != AV_NOPTS_VALUE) {
            int64_t max = ms->last_mux_dts + !(s->oformat->flags & AVFMT_TS_NONSTRICT);
            if (pkt->dts < max) {
-                int loglevel = max - pkt->dts > 2 || ost->type == AVMEDIA_TYPE_VIDEO ? AV_LOG_WARNING : AV_LOG_DEBUG;
+                int loglevel = max - pkt->dts > 2 || st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO ? AV_LOG_WARNING : AV_LOG_DEBUG;
                if (exit_on_error)
                    loglevel = AV_LOG_ERROR;
-                av_log(s, loglevel, "Non-monotonic DTS in output stream "
+                av_log(s, loglevel, "Non-monotonous DTS in output stream "
                       "%d:%d; previous: %"PRId64", current: %"PRId64"; ",
                       ost->file_index, ost->st->index, ms->last_mux_dts, pkt->dts);
                if (exit_on_error) {
@@ -134,7 +128,7 @@ static int write_packet(Muxer *mux, OutputStream *ost, AVPacket *pkt)
    }
    ms->last_mux_dts = pkt->dts;

-    ms->data_size_mux += pkt->size;
+    ost->data_size_mux += pkt->size;
    frame_num = atomic_fetch_add(&ost->packets_written, 1);

    pkt->stream_index = ost->index;
@@ -142,7 +136,7 @@ static int write_packet(Muxer *mux, OutputStream *ost, AVPacket *pkt)
    if (debug_ts) {
        av_log(ost, AV_LOG_INFO, "muxer <- type:%s "
                "pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s duration:%s duration_time:%s size:%d\n",
-                av_get_media_type_string(ost->type),
+                av_get_media_type_string(st->codecpar->codec_type),
                av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, &ost->st->time_base),
                av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, &ost->st->time_base),
                av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, &ost->st->time_base),
@@ -155,9 +149,7 @@ static int write_packet(Muxer *mux, OutputStream *ost, AVPacket *pkt)

    ret = av_interleaved_write_frame(s, pkt);
    if (ret < 0) {
-        av_log(ost, AV_LOG_ERROR,
-               "Error submitting a packet to the muxer: %s\n",
-               av_err2str(ret));
+        print_error("av_interleaved_write_frame()", ret);
        goto fail;
    }

@@ -182,14 +174,8 @@ static int sync_queue_process(Muxer *mux, OutputStream *ost, AVPacket *pkt, int

        while (1) {
            ret = sq_receive(mux->sq_mux, -1, SQPKT(mux->sq_pkt));
-            if (ret < 0) {
-                /* n.b.: We forward EOF from the sync queue, terminating muxing.
-                 * This assumes that if a muxing sync queue is present, then all
-                 * the streams use it. That is true currently, but may change in
-                 * the future, then this code needs to be revisited.
-                 */
-                return ret == AVERROR(EAGAIN) ? 0 : ret;
-            }
+            if (ret < 0)
+                return (ret == AVERROR_EOF || ret == AVERROR(EAGAIN)) ? 0 : ret;

            ret = write_packet(mux, of->streams[ret],
                               mux->sq_pkt);
@@ -238,15 +224,9 @@ static void *muxer_thread(void *arg)
        ost = of->streams[stream_idx];
        ret = sync_queue_process(mux, ost, ret < 0 ? NULL : pkt, &stream_eof);
        av_packet_unref(pkt);
-        if (ret == AVERROR_EOF) {
-            if (stream_eof) {
-                tq_receive_finish(mux->tq, stream_idx);
-            } else {
-                av_log(mux, AV_LOG_VERBOSE, "Muxer returned EOF\n");
-                ret = 0;
-                break;
-            }
-        } else if (ret < 0) {
+        if (ret == AVERROR_EOF && stream_eof)
+            tq_receive_finish(mux->tq, stream_idx);
+        else if (ret < 0) {
            av_log(mux, AV_LOG_ERROR, "Error muxing a packet\n");
            break;
        }
@@ -285,7 +265,7 @@ finish:
    return ret == AVERROR_EOF ? 0 : ret;
 }

-static int queue_packet(OutputStream *ost, AVPacket *pkt)
+static int queue_packet(Muxer *mux, OutputStream *ost, AVPacket *pkt)
 {
    MuxStream *ms = ms_from_ost(ost);
    AVPacket *tmp_pkt = NULL;
@@ -335,7 +315,7 @@ static int submit_packet(Muxer *mux, AVPacket *pkt, OutputStream *ost)
        return thread_submit_packet(mux, ost, pkt);
    } else {
        /* the muxer is not initialized yet, buffer the packet */
-        ret = queue_packet(ost, pkt);
+        ret = queue_packet(mux, ost, pkt);
        if (ret < 0) {
            if (pkt)
                av_packet_unref(pkt);
@@ -346,33 +326,30 @@ static int submit_packet(Muxer *mux, AVPacket *pkt, OutputStream *ost)
    return 0;
 }

-int of_output_packet(OutputFile *of, OutputStream *ost, AVPacket *pkt)
+void of_output_packet(OutputFile *of, AVPacket *pkt, OutputStream *ost, int eof)
 {
    Muxer *mux = mux_from_of(of);
    MuxStream *ms = ms_from_ost(ost);
    const char *err_msg;
    int ret = 0;

-    if (pkt && pkt->dts != AV_NOPTS_VALUE)
+    if (!eof && pkt->dts != AV_NOPTS_VALUE)
        ost->last_mux_dts = av_rescale_q(pkt->dts, pkt->time_base, AV_TIME_BASE_Q);

    /* apply the output bitstream filters */
    if (ms->bsf_ctx) {
        int bsf_eof = 0;

-        if (pkt)
-            av_packet_rescale_ts(pkt, pkt->time_base, ms->bsf_ctx->time_base_in);
-
-        ret = av_bsf_send_packet(ms->bsf_ctx, pkt);
+        ret = av_bsf_send_packet(ms->bsf_ctx, eof ? NULL : pkt);
        if (ret < 0) {
            err_msg = "submitting a packet for bitstream filtering";
            goto fail;
        }

        while (!bsf_eof) {
-            ret = av_bsf_receive_packet(ms->bsf_ctx, ms->bsf_pkt);
+            ret = av_bsf_receive_packet(ms->bsf_ctx, pkt);
            if (ret == AVERROR(EAGAIN))
-                return 0;
+                return;
            else if (ret == AVERROR_EOF)
                bsf_eof = 1;
            else if (ret < 0) {
@@ -380,96 +357,26 @@ int of_output_packet(OutputFile *of, OutputStream *ost, AVPacket *pkt)
                goto fail;
            }

-            if (!bsf_eof)
-                ms->bsf_pkt->time_base = ms->bsf_ctx->time_base_out;
-
-            ret = submit_packet(mux, bsf_eof ? NULL : ms->bsf_pkt, ost);
+            ret = submit_packet(mux, bsf_eof ? NULL : pkt, ost);
            if (ret < 0)
                goto mux_fail;
        }
    } else {
-        ret = submit_packet(mux, pkt, ost);
+        ret = submit_packet(mux, eof ? NULL : pkt, ost);
        if (ret < 0)
            goto mux_fail;
    }

-    return 0;
+    return;

 mux_fail:
    err_msg = "submitting a packet to the muxer";

 fail:
    av_log(ost, AV_LOG_ERROR, "Error %s\n", err_msg);
-    return exit_on_error ? ret : 0;
-}
+    if (exit_on_error)
+        exit_program(1);

-int of_streamcopy(OutputStream *ost, const AVPacket *pkt, int64_t dts)
-{
-    OutputFile *of = output_files[ost->file_index];
-    MuxStream  *ms = ms_from_ost(ost);
-    int64_t start_time = (of->start_time == AV_NOPTS_VALUE) ? 0 : of->start_time;
-    int64_t ts_offset;
-    AVPacket *opkt = ms->pkt;
-    int ret;
-
-    av_packet_unref(opkt);
-
-    if (of->recording_time != INT64_MAX &&
-        dts >= of->recording_time + start_time)
-        pkt = NULL;
-
-    // EOF: flush output bitstream filters.
-    if (!pkt)
-        return of_output_packet(of, ost, NULL);
-
-    if (!ms->streamcopy_started && !(pkt->flags & AV_PKT_FLAG_KEY) &&
-        !ms->copy_initial_nonkeyframes)
-        return 0;
-
-    if (!ms->streamcopy_started) {
-        if (!ms->copy_prior_start &&
-            (pkt->pts == AV_NOPTS_VALUE ?
-             dts < ms->ts_copy_start :
-             pkt->pts < av_rescale_q(ms->ts_copy_start, AV_TIME_BASE_Q, pkt->time_base)))
-            return 0;
-
-        if (of->start_time != AV_NOPTS_VALUE && dts < of->start_time)
-            return 0;
-    }
-
-    ret = av_packet_ref(opkt, pkt);
-    if (ret < 0)
-        return ret;
-
-    ts_offset = av_rescale_q(start_time, AV_TIME_BASE_Q, opkt->time_base);
-
-    if (pkt->pts != AV_NOPTS_VALUE)
-        opkt->pts -= ts_offset;
-
-    if (pkt->dts == AV_NOPTS_VALUE) {
-        opkt->dts = av_rescale_q(dts, AV_TIME_BASE_Q, opkt->time_base);
-    } else if (ost->st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
-        opkt->pts = opkt->dts - ts_offset;
-    }
-    opkt->dts -= ts_offset;
-
-    {
-        int ret = trigger_fix_sub_duration_heartbeat(ost, pkt);
-        if (ret < 0) {
-            av_log(NULL, AV_LOG_ERROR,
-                   "Subtitle heartbeat logic failed in %s! (%s)\n",
-                   __func__, av_err2str(ret));
-            return ret;
-        }
-    }
-
-    ret = of_output_packet(of, ost, opkt);
-    if (ret < 0)
-        return ret;
-
-    ms->streamcopy_started = 1;
-
-    return 0;
 }

 static int thread_stop(Muxer *mux)
@@ -489,6 +396,11 @@ static int thread_stop(Muxer *mux)
    return (int)(intptr_t)ret;
 }

+static void pkt_move(void *dst, void *src)
+{
+    av_packet_move_ref(dst, src);
+}
+
 static int thread_start(Muxer *mux)
 {
    AVFormatContext *fc = mux->fc;
@@ -517,6 +429,10 @@ static int thread_start(Muxer *mux)
        MuxStream     *ms = ms_from_ost(ost);
        AVPacket *pkt;

+        /* try to improve muxing time_base (only possible if nothing has been written yet) */
+        if (!av_fifo_can_read(ms->muxing_queue))
+            ost->mux_timebase = ost->st->time_base;
+
        while (av_fifo_read(ms->muxing_queue, &pkt, 1) >= 0) {
            ret = thread_submit_packet(mux, ost, pkt);
            if (pkt) {
@@ -641,9 +557,9 @@ static int bsf_init(MuxStream *ms)
    int ret;

    if (!ctx)
-        return avcodec_parameters_copy(ost->st->codecpar, ost->par_in);
+        return 0;

-    ret = avcodec_parameters_copy(ctx->par_in, ost->par_in);
+    ret = avcodec_parameters_copy(ctx->par_in, ost->st->codecpar);
    if (ret < 0)
        return ret;

@@ -661,10 +577,6 @@ static int bsf_init(MuxStream *ms)
        return ret;
    ost->st->time_base = ctx->time_base_out;

-    ms->bsf_pkt = av_packet_alloc();
-    if (!ms->bsf_pkt)
-        return AVERROR(ENOMEM);
-
    return 0;
 }

@@ -674,6 +586,9 @@ int of_stream_init(OutputFile *of, OutputStream *ost)
    MuxStream *ms = ms_from_ost(ost);
    int ret;

+    if (ost->sq_idx_mux >= 0)
+        sq_set_tb(mux->sq_mux, ost->sq_idx_mux, ost->mux_timebase);
+
    /* initialize bitstream filters for the output stream
     * needs to be done here, because the codec id for streamcopy is not
     * known until now */
@@ -681,126 +596,16 @@ int of_stream_init(OutputFile *of, OutputStream *ost)
    if (ret < 0)
        return ret;

-    if (ms->stream_duration) {
-        ost->st->duration = av_rescale_q(ms->stream_duration, ms->stream_duration_tb,
-                                         ost->st->time_base);
-    }
-
    ost->initialized = 1;

    return mux_check_init(mux);
 }

-static int check_written(OutputFile *of)
-{
-    int64_t total_packets_written = 0;
-    int pass1_used = 1;
-    int ret = 0;
-
-    for (int i = 0; i < of->nb_streams; i++) {
-        OutputStream *ost = of->streams[i];
-        uint64_t packets_written = atomic_load(&ost->packets_written);
-
-        total_packets_written += packets_written;
-
-        if (ost->enc_ctx &&
-            (ost->enc_ctx->flags & (AV_CODEC_FLAG_PASS1 | AV_CODEC_FLAG_PASS2))
-             != AV_CODEC_FLAG_PASS1)
-            pass1_used = 0;
-
-        if (!packets_written &&
-            (abort_on_flags & ABORT_ON_FLAG_EMPTY_OUTPUT_STREAM)) {
-            av_log(ost, AV_LOG_FATAL, "Empty output stream\n");
-            ret = err_merge(ret, AVERROR(EINVAL));
-        }
-    }
-
-    if (!total_packets_written) {
-        int level = AV_LOG_WARNING;
-
-        if (abort_on_flags & ABORT_ON_FLAG_EMPTY_OUTPUT) {
-            ret = err_merge(ret, AVERROR(EINVAL));
-            level = AV_LOG_FATAL;
-        }
-
-        av_log(of, level, "Output file is empty, nothing was encoded%s\n",
-               pass1_used ? "" : "(check -ss / -t / -frames parameters if used)");
-    }
-
-    return ret;
-}
-
-static void mux_final_stats(Muxer *mux)
-{
-    OutputFile *of = &mux->of;
-    uint64_t total_packets = 0, total_size = 0;
-    uint64_t video_size = 0, audio_size = 0, subtitle_size = 0,
-             extra_size = 0, other_size = 0;
-
-    uint8_t overhead[16] = "unknown";
-    int64_t file_size = of_filesize(of);
-
-    av_log(of, AV_LOG_VERBOSE, "Output file #%d (%s):\n",
-           of->index, of->url);
-
-    for (int j = 0; j < of->nb_streams; j++) {
-        OutputStream *ost = of->streams[j];
-        MuxStream     *ms = ms_from_ost(ost);
-        const AVCodecParameters *par = ost->st->codecpar;
-        const  enum AVMediaType type = par->codec_type;
-        const uint64_t s = ms->data_size_mux;
-
-        switch (type) {
-        case AVMEDIA_TYPE_VIDEO:    video_size    += s; break;
-        case AVMEDIA_TYPE_AUDIO:    audio_size    += s; break;
-        case AVMEDIA_TYPE_SUBTITLE: subtitle_size += s; break;
-        default:                    other_size    += s; break;
-        }
-
-        extra_size    += par->extradata_size;
-        total_size    += s;
-        total_packets += atomic_load(&ost->packets_written);
-
-        av_log(of, AV_LOG_VERBOSE, "  Output stream #%d:%d (%s): ",
-               of->index, j, av_get_media_type_string(type));
-        if (ost->enc) {
-            av_log(of, AV_LOG_VERBOSE, "%"PRIu64" frames encoded",
-                   ost->frames_encoded);
-            if (type == AVMEDIA_TYPE_AUDIO)
-                av_log(of, AV_LOG_VERBOSE, " (%"PRIu64" samples)", ost->samples_encoded);
-            av_log(of, AV_LOG_VERBOSE, "; ");
-        }
-
-        av_log(of, AV_LOG_VERBOSE, "%"PRIu64" packets muxed (%"PRIu64" bytes); ",
-               atomic_load(&ost->packets_written), s);
-
-        av_log(of, AV_LOG_VERBOSE, "\n");
-    }
-
-    av_log(of, AV_LOG_VERBOSE, "  Total: %"PRIu64" packets (%"PRIu64" bytes) muxed\n",
-           total_packets, total_size);
-
-    if (total_size && file_size > 0 && file_size >= total_size) {
-        snprintf(overhead, sizeof(overhead), "%f%%",
-                 100.0 * (file_size - total_size) / total_size);
-    }
-
-    av_log(of, AV_LOG_INFO,
-           "video:%1.0fkB audio:%1.0fkB subtitle:%1.0fkB other streams:%1.0fkB "
-           "global headers:%1.0fkB muxing overhead: %s\n",
-           video_size    / 1024.0,
-           audio_size    / 1024.0,
-           subtitle_size / 1024.0,
-           other_size    / 1024.0,
-           extra_size    / 1024.0,
-           overhead);
-}
-
 int of_write_trailer(OutputFile *of)
 {
    Muxer *mux = mux_from_of(of);
    AVFormatContext *fc = mux->fc;
-    int ret, mux_result = 0;
+    int ret;

    if (!mux->tq) {
        av_log(mux, AV_LOG_ERROR,
@@ -809,12 +614,14 @@ int of_write_trailer(OutputFile *of)
        return AVERROR(EINVAL);
    }

-    mux_result = thread_stop(mux);
+    ret = thread_stop(mux);
+    if (ret < 0)
+        main_return_code = ret;

    ret = av_write_trailer(fc);
    if (ret < 0) {
        av_log(mux, AV_LOG_ERROR, "Error writing trailer: %s\n", av_err2str(ret));
-        mux_result = err_merge(mux_result, ret);
+        return ret;
    }

    mux->last_filesize = filesize(fc->pb);
@@ -823,17 +630,11 @@ int of_write_trailer(OutputFile *of)
        ret = avio_closep(&fc->pb);
        if (ret < 0) {
            av_log(mux, AV_LOG_ERROR, "Error closing file: %s\n", av_err2str(ret));
-            mux_result = err_merge(mux_result, ret);
+            return ret;
        }
    }

-    mux_final_stats(mux);
-
-    // check whether anything was actually written
-    ret = check_written(of);
-    mux_result = err_merge(mux_result, ret);
-
-    return mux_result;
+    return 0;
 }

 static void ost_free(OutputStream **post)
@@ -845,8 +646,6 @@ static void ost_free(OutputStream **post)
        return;
    ms = ms_from_ost(ost);

-    enc_free(&ost->enc);
-
    if (ost->logfile) {
        if (fclose(ost->logfile))
            av_log(ms, AV_LOG_ERROR,
@@ -862,17 +661,18 @@ static void ost_free(OutputStream **post)
        av_fifo_freep2(&ms->muxing_queue);
    }

-    avcodec_parameters_free(&ost->par_in);
-
    av_bsf_free(&ms->bsf_ctx);
-    av_packet_free(&ms->bsf_pkt);

-    av_packet_free(&ms->pkt);
+    av_frame_free(&ost->filtered_frame);
+    av_frame_free(&ost->sq_frame);
+    av_frame_free(&ost->last_frame);
+    av_packet_free(&ost->pkt);
    av_dict_free(&ost->encoder_opts);

    av_freep(&ost->kf.pts);
    av_expr_free(ost->kf.pexpr);

+    av_freep(&ost->avfilter);
    av_freep(&ost->logfile_prefix);
    av_freep(&ost->apad);

@@ -917,7 +717,7 @@ static void fc_close(AVFormatContext **pfc)
    *pfc = NULL;
 }

-void of_free(OutputFile **pof)
+void of_close(OutputFile **pof)
 {
    OutputFile *of = *pof;
    Muxer *mux;
--- a/fftools/ffmpeg_mux.h
+++ b/fftools/ffmpeg_mux.h
@@ -44,9 +44,6 @@ typedef struct MuxStream {
    AVFifo *muxing_queue;

    AVBSFContext *bsf_ctx;
-    AVPacket     *bsf_pkt;
-
-    AVPacket     *pkt;

    EncStats stats;

@@ -63,27 +60,9 @@ typedef struct MuxStream {
    /* Threshold after which max_muxing_queue_size will be in effect */
    size_t muxing_queue_data_threshold;

-    // timestamp from which the streamcopied streams should start,
-    // in AV_TIME_BASE_Q;
-    // everything before it should be discarded
-    int64_t ts_copy_start;
-
    /* dts of the last packet sent to the muxer, in the stream timebase
     * used for making up missing dts values */
    int64_t last_mux_dts;
-
-    int64_t    stream_duration;
-    AVRational stream_duration_tb;
-
-    // state for av_rescale_delta() call for audio in write_packet()
-    int64_t ts_rescale_delta_last;
-
-    // combined size of all the packets sent to the muxer
-    uint64_t data_size_mux;
-
-    int copy_initial_nonkeyframes;
-    int copy_prior_start;
-    int streamcopy_started;
 } MuxStream;

 typedef struct Muxer {
--- a/fftools/ffmpeg_mux_init.c
+++ b/fftools/ffmpeg_mux_init.c
--- a/fftools/ffmpeg_opt.c
+++ b/fftools/ffmpeg_opt.c
@@ -56,9 +56,7 @@
 const char *const opt_name_codec_names[]                      = {"c", "codec", "acodec", "vcodec", "scodec", "dcodec", NULL};
 const char *const opt_name_frame_rates[]                      = {"r", NULL};
 const char *const opt_name_codec_tags[]                       = {"tag", "atag", "vtag", "stag", NULL};
-#if FFMPEG_OPT_TOP
 const char *const opt_name_top_field_first[]                  = {"top", NULL};
-#endif

 HWDevice *filter_hw_device;

@@ -82,6 +80,7 @@ int debug_ts          = 0;
 int exit_on_error     = 0;
 int abort_on_flags    = 0;
 int print_stats       = -1;
+int qp_hist           = 0;
 int stdin_interaction = 1;
 float max_error_rate  = 2.0/3;
 char *filter_nbthreads;
@@ -130,9 +129,8 @@ static void uninit_options(OptionsContext *o)
 #if FFMPEG_OPT_MAP_CHANNEL
    av_freep(&o->audio_channel_maps);
 #endif
+    av_freep(&o->streamid_map);
    av_freep(&o->attachments);
-
-    av_dict_free(&o->streamid);
 }

 static void init_options(OptionsContext *o)
@@ -192,18 +190,11 @@ int parse_and_set_vsync(const char *arg, int *vsync_var, int file_idx, int st_id
    else if (!is_global && !av_strcasecmp(arg, "auto"))  *vsync_var = VSYNC_AUTO;
    else if (!is_global) {
        av_log(NULL, AV_LOG_FATAL, "Invalid value %s specified for fps_mode of #%d:%d.\n", arg, file_idx, st_idx);
-        return AVERROR(EINVAL);
+        exit_program(1);
    }

    if (is_global && *vsync_var == VSYNC_AUTO) {
-        int ret;
-        double num;
-
-        ret = parse_number("vsync", arg, OPT_INT, VSYNC_AUTO, VSYNC_VFR, &num);
-        if (ret < 0)
-            return ret;
-
-        video_sync_method = num;
+        video_sync_method = parse_number_or_die("vsync", arg, OPT_INT, VSYNC_AUTO, VSYNC_VFR);
        av_log(NULL, AV_LOG_WARNING, "Passing a number to -vsync is deprecated,"
               " use a string argument as described in the manual.\n");
    }
@@ -259,12 +250,12 @@ static int apply_sync_offsets(void)
        if (self->input_sync_ref == -1 || self->input_sync_ref == i) continue;
        if (self->input_sync_ref >= nb_input_files || self->input_sync_ref < -1) {
            av_log(NULL, AV_LOG_FATAL, "-isync for input %d references non-existent input %d.\n", i, self->input_sync_ref);
-            return AVERROR(EINVAL);
+            exit_program(1);
        }

        if (copy_ts && !start_at_zero) {
            av_log(NULL, AV_LOG_FATAL, "Use of -isync requires that start_at_zero be set if copyts is set.\n");
-            return AVERROR(EINVAL);
+            exit_program(1);
        }

        ref = input_files[self->input_sync_ref];
@@ -328,10 +319,7 @@ static int opt_abort_on(void *optctx, const char *opt, const char *arg)

 static int opt_stats_period(void *optctx, const char *opt, const char *arg)
 {
-    int64_t user_stats_period;
-    int ret = av_parse_time(&user_stats_period, arg, 1);
-    if (ret < 0)
-        return ret;
+    int64_t user_stats_period = parse_time_or_die(opt, arg, 1);

    if (user_stats_period <= 0) {
        av_log(NULL, AV_LOG_ERROR, "stats_period %s must be positive.\n", arg);
@@ -373,7 +361,9 @@ static int opt_map(void *optctx, const char *opt, const char *arg)
    OptionsContext *o = optctx;
    StreamMap *m = NULL;
    int i, negative = 0, file_idx, disabled = 0;
-    int ret;
+#if FFMPEG_OPT_MAP_SYNC
+    char *sync;
+#endif
    char *map, *p;
    char *allow_unused;

@@ -386,14 +376,10 @@ static int opt_map(void *optctx, const char *opt, const char *arg)
        return AVERROR(ENOMEM);

 #if FFMPEG_OPT_MAP_SYNC
-    {
-        /* parse sync stream first, just pick first matching stream */
-        char *sync = strchr(map, ',');
-
-        if (sync) {
-            *sync = 0;
-            av_log(NULL, AV_LOG_WARNING, "Specifying a sync stream is deprecated and has no effect\n");
-        }
+    /* parse sync stream first, just pick first matching stream */
+    if (sync = strchr(map, ',')) {
+        *sync = 0;
+        av_log(NULL, AV_LOG_WARNING, "Specifying a sync stream is deprecated and has no effect\n");
    }
 #endif

@@ -401,17 +387,12 @@ static int opt_map(void *optctx, const char *opt, const char *arg)
    if (map[0] == '[') {
        /* this mapping refers to lavfi output */
        const char *c = map + 1;
-
-        ret = GROW_ARRAY(o->stream_maps, o->nb_stream_maps);
-        if (ret < 0)
-            goto fail;
-
+        GROW_ARRAY(o->stream_maps, o->nb_stream_maps);
        m = &o->stream_maps[o->nb_stream_maps - 1];
        m->linklabel = av_get_token(&c, "]");
        if (!m->linklabel) {
            av_log(NULL, AV_LOG_ERROR, "Invalid output link label: %s.\n", map);
-            ret = AVERROR(EINVAL);
-            goto fail;
+            exit_program(1);
        }
    } else {
        if (allow_unused = strchr(map, '?'))
@@ -419,8 +400,7 @@ static int opt_map(void *optctx, const char *opt, const char *arg)
        file_idx = strtol(map, &p, 0);
        if (file_idx >= nb_input_files || file_idx < 0) {
            av_log(NULL, AV_LOG_FATAL, "Invalid input file index: %d.\n", file_idx);
-            ret = AVERROR(EINVAL);
-            goto fail;
+            exit_program(1);
        }
        if (negative)
            /* disable some already defined maps */
@@ -441,10 +421,7 @@ static int opt_map(void *optctx, const char *opt, const char *arg)
                    disabled = 1;
                    continue;
                }
-                ret = GROW_ARRAY(o->stream_maps, o->nb_stream_maps);
-                if (ret < 0)
-                    goto fail;
-
+                GROW_ARRAY(o->stream_maps, o->nb_stream_maps);
                m = &o->stream_maps[o->nb_stream_maps - 1];

                m->file_index   = file_idx;
@@ -458,28 +435,22 @@ static int opt_map(void *optctx, const char *opt, const char *arg)
        } else if (disabled) {
            av_log(NULL, AV_LOG_FATAL, "Stream map '%s' matches disabled streams.\n"
                                       "To ignore this, add a trailing '?' to the map.\n", arg);
-            ret = AVERROR(EINVAL);
-            goto fail;
+            exit_program(1);
        } else {
            av_log(NULL, AV_LOG_FATAL, "Stream map '%s' matches no streams.\n"
                                       "To ignore this, add a trailing '?' to the map.\n", arg);
-            ret = AVERROR(EINVAL);
-            goto fail;
+            exit_program(1);
        }
    }
-    ret = 0;
-fail:
+
    av_freep(&map);
-    return ret;
+    return 0;
 }

 static int opt_attach(void *optctx, const char *opt, const char *arg)
 {
    OptionsContext *o = optctx;
-    int ret = GROW_ARRAY(o->attachments, o->nb_attachments);
-    if (ret < 0)
-        return ret;
-
+    GROW_ARRAY(o->attachments, o->nb_attachments);
    o->attachments[o->nb_attachments - 1] = arg;
    return 0;
 }
@@ -488,7 +459,7 @@ static int opt_attach(void *optctx, const char *opt, const char *arg)
 static int opt_map_channel(void *optctx, const char *opt, const char *arg)
 {
    OptionsContext *o = optctx;
-    int n, ret;
+    int n;
    AVStream *st;
    AudioChannelMap *m;
    char *allow_unused;
@@ -503,10 +474,7 @@ static int opt_map_channel(void *optctx, const char *opt, const char *arg)
    if (!mapchan)
        return AVERROR(ENOMEM);

-    ret = GROW_ARRAY(o->audio_channel_maps, o->nb_audio_channel_maps);
-    if (ret < 0)
-        goto end;
-
+    GROW_ARRAY(o->audio_channel_maps, o->nb_audio_channel_maps);
    m = &o->audio_channel_maps[o->nb_audio_channel_maps - 1];

    /* muted channel syntax */
@@ -527,7 +495,7 @@ static int opt_map_channel(void *optctx, const char *opt, const char *arg)
    if (n != 3 && n != 5) {
        av_log(NULL, AV_LOG_FATAL, "Syntax error, mapchan usage: "
               "[file.stream.channel|-1][:syncfile:syncstream]\n");
-        goto fail;
+        exit_program(1);
    }

    if (n != 5) // only file.stream.channel specified
@@ -537,19 +505,19 @@ static int opt_map_channel(void *optctx, const char *opt, const char *arg)
    if (m->file_idx < 0 || m->file_idx >= nb_input_files) {
        av_log(NULL, AV_LOG_FATAL, "mapchan: invalid input file index: %d\n",
               m->file_idx);
-        goto fail;
+        exit_program(1);
    }
    if (m->stream_idx < 0 ||
        m->stream_idx >= input_files[m->file_idx]->nb_streams) {
        av_log(NULL, AV_LOG_FATAL, "mapchan: invalid input file stream index #%d.%d\n",
               m->file_idx, m->stream_idx);
-        goto fail;
+        exit_program(1);
    }
    st = input_files[m->file_idx]->ctx->streams[m->stream_idx];
    if (st->codecpar->codec_type != AVMEDIA_TYPE_AUDIO) {
        av_log(NULL, AV_LOG_FATAL, "mapchan: stream #%d.%d is not an audio stream.\n",
               m->file_idx, m->stream_idx);
-        goto fail;
+        exit_program(1);
    }
    /* allow trailing ? to map_channel */
    if (allow_unused = strchr(mapchan, '?'))
@@ -563,17 +531,12 @@ static int opt_map_channel(void *optctx, const char *opt, const char *arg)
            av_log(NULL, AV_LOG_FATAL,  "mapchan: invalid audio channel #%d.%d.%d\n"
                    "To ignore this, add a trailing '?' to the map_channel.\n",
                    m->file_idx, m->stream_idx, m->channel_idx);
-            goto fail;
+            exit_program(1);
        }

    }
-    ret = 0;
-end:
    av_free(mapchan);
-    return ret;
-fail:
-    ret = AVERROR(EINVAL);
-    goto end;
+    return 0;
 }
 #endif

@@ -625,7 +588,7 @@ static int opt_init_hw_device(void *optctx, const char *opt, const char *arg)
               AV_HWDEVICE_TYPE_NONE)
            printf("%s\n", av_hwdevice_get_type_name(type));
        printf("\n");
-        return AVERROR_EXIT;
+        exit_program(0);
    } else {
        return hw_device_init_from_string(arg, NULL);
    }
@@ -649,16 +612,8 @@ static int opt_recording_timestamp(void *optctx, const char *opt, const char *ar
 {
    OptionsContext *o = optctx;
    char buf[128];
-    int64_t recording_timestamp;
-    int ret;
-    struct tm time;
-
-    ret = av_parse_time(&recording_timestamp, arg, 0);
-    if (ret < 0)
-        return ret;
-
-    recording_timestamp /= 1e6;
-    time = *gmtime((time_t*)&recording_timestamp);
+    int64_t recording_timestamp = parse_time_or_die(opt, arg, 0) / 1E6;
+    struct tm time = *gmtime((time_t*)&recording_timestamp);
    if (!strftime(buf, sizeof(buf), "creation_time=%Y-%m-%dT%H:%M:%S%z", &time))
        return -1;
    parse_option(o, "metadata", buf, options);
@@ -668,8 +623,8 @@ static int opt_recording_timestamp(void *optctx, const char *opt, const char *ar
    return 0;
 }

-int find_codec(void *logctx, const char *name,
-               enum AVMediaType type, int encoder, const AVCodec **pcodec)
+const AVCodec *find_codec_or_die(void *logctx, const char *name,
+                                 enum AVMediaType type, int encoder)
 {
    const AVCodecDescriptor *desc;
    const char *codec_string = encoder ? "encoder" : "decoder";
@@ -689,25 +644,22 @@ int find_codec(void *logctx, const char *name,

    if (!codec) {
        av_log(logctx, AV_LOG_FATAL, "Unknown %s '%s'\n", codec_string, name);
-        return encoder ? AVERROR_ENCODER_NOT_FOUND :
-                         AVERROR_DECODER_NOT_FOUND;
+        exit_program(1);
    }
    if (codec->type != type && !recast_media) {
        av_log(logctx, AV_LOG_FATAL, "Invalid %s type '%s'\n", codec_string, name);
-        return AVERROR(EINVAL);
+        exit_program(1);
    }
-
-    *pcodec = codec;
-    return 0;;
+    return codec;
 }

-int assert_file_overwrite(const char *filename)
+void assert_file_overwrite(const char *filename)
 {
    const char *proto_name = avio_find_protocol_name(filename);

    if (file_overwrite && no_file_overwrite) {
        fprintf(stderr, "Error, both -y and -n supplied. Exiting.\n");
-        return AVERROR(EINVAL);
+        exit_program(1);
    }

    if (!file_overwrite) {
@@ -719,13 +671,13 @@ int assert_file_overwrite(const char *filename)
                signal(SIGINT, SIG_DFL);
                if (!read_yesno()) {
                    av_log(NULL, AV_LOG_FATAL, "Not overwriting - exiting\n");
-                    return AVERROR_EXIT;
+                    exit_program(1);
                }
                term_init();
            }
            else {
                av_log(NULL, AV_LOG_FATAL, "File '%s' already exists. Exiting.\n", filename);
-                return AVERROR_EXIT;
+                exit_program(1);
            }
        }
    }
@@ -738,12 +690,10 @@ int assert_file_overwrite(const char *filename)
             if (!strcmp(filename, file->ctx->url)) {
                 av_log(NULL, AV_LOG_FATAL, "Output %s same as Input #%d - exiting\n", filename, i);
                 av_log(NULL, AV_LOG_WARNING, "FFmpeg cannot edit existing files in-place.\n");
-                 return AVERROR(EINVAL);
+                 exit_program(1);
             }
        }
    }
-
-    return 0;
 }

 /* read file contents into a string */
@@ -776,6 +726,7 @@ char *file_read(const char *filename)
 static int opt_streamid(void *optctx, const char *opt, const char *arg)
 {
    OptionsContext *o = optctx;
+    int idx;
    char *p;
    char idx_str[16];

@@ -785,11 +736,13 @@ static int opt_streamid(void *optctx, const char *opt, const char *arg)
        av_log(NULL, AV_LOG_FATAL,
               "Invalid value '%s' for option '%s', required syntax is 'index:value'\n",
               arg, opt);
-        return AVERROR(EINVAL);
+        exit_program(1);
    }
    *p++ = '\0';
-
-    return av_dict_set(&o->streamid, idx_str, p, 0);
+    idx = parse_number_or_die(opt, idx_str, OPT_INT, 0, MAX_STREAMS-1);
+    o->streamid_map = grow_array(o->streamid_map, sizeof(*o->streamid_map), &o->nb_streamid_map, idx+1);
+    o->streamid_map[idx] = parse_number_or_die(opt, p, OPT_INT, 0, INT_MAX);
+    return 0;
 }

 static int init_complex_filters(void)
@@ -850,7 +803,7 @@ static int opt_target(void *optctx, const char *opt, const char *arg)
        av_log(NULL, AV_LOG_FATAL, "Could not determine norm (PAL/NTSC/NTSC-Film) for target.\n");
        av_log(NULL, AV_LOG_FATAL, "Please prefix target with \"pal-\", \"ntsc-\" or \"film-\",\n");
        av_log(NULL, AV_LOG_FATAL, "or set a framerate with \"-r xxx\".\n");
-        return AVERROR(EINVAL);
+        exit_program(1);
    }

    if (!strcmp(arg, "vcd")) {
@@ -962,7 +915,7 @@ static int opt_vstats(void *optctx, const char *opt, const char *arg)

    if (!today) { // maybe tomorrow
        av_log(NULL, AV_LOG_FATAL, "Unable to get current time: %s\n", strerror(errno));
-        return AVERROR(errno);
+        exit_program(1);
    }

    snprintf(filename, sizeof(filename), "vstats_%02d%02d%02d.log", today->tm_hour, today->tm_min,
@@ -1014,7 +967,6 @@ static int opt_preset(void *optctx, const char *opt, const char *arg)
    FILE *f=NULL;
    char filename[1000], line[1000], tmp_line[1000];
    const char *codec_name = NULL;
-    int ret = 0;

    tmp_line[0] = *opt;
    tmp_line[1] = 0;
@@ -1025,7 +977,7 @@ static int opt_preset(void *optctx, const char *opt, const char *arg)
            av_log(NULL, AV_LOG_FATAL, "Please use -preset <speed> -qp 0\n");
        }else
            av_log(NULL, AV_LOG_FATAL, "File for preset '%s' not found\n", arg);
-        return AVERROR(ENOENT);
+        exit_program(1);
    }

    while (fgets(line, sizeof(line), f)) {
@@ -1037,8 +989,7 @@ static int opt_preset(void *optctx, const char *opt, const char *arg)
        if (!av_strtok(key,   "=",    &value) ||
            !av_strtok(value, "\r\n", &endptr)) {
            av_log(NULL, AV_LOG_FATAL, "%s: Invalid syntax: '%s'\n", filename, line);
-            ret = AVERROR(EINVAL);
-            goto fail;
+            exit_program(1);
        }
        av_log(NULL, AV_LOG_DEBUG, "ffpreset[%s]: set '%s' = '%s'\n", filename, key, value);

@@ -1049,15 +1000,13 @@ static int opt_preset(void *optctx, const char *opt, const char *arg)
        else if (opt_default_new(o, key, value) < 0) {
            av_log(NULL, AV_LOG_FATAL, "%s: Invalid option or argument: '%s', parsed as '%s' = '%s'\n",
                   filename, line, key, value);
-            ret = AVERROR(EINVAL);
-            goto fail;
+            exit_program(1);
        }
    }

-fail:
    fclose(f);

-    return ret;
+    return 0;
 }

 static int opt_old2new(void *optctx, const char *opt, const char *arg)
@@ -1132,7 +1081,8 @@ static int opt_audio_filters(void *optctx, const char *opt, const char *arg)
 static int opt_vsync(void *optctx, const char *opt, const char *arg)
 {
    av_log(NULL, AV_LOG_WARNING, "-vsync is deprecated. Use -fps_mode\n");
-    return parse_and_set_vsync(arg, &video_sync_method, -1, -1, 1);
+    parse_and_set_vsync(arg, &video_sync_method, -1, -1, 1);
+    return 0;
 }

 static int opt_timecode(void *optctx, const char *opt, const char *arg)
@@ -1157,20 +1107,28 @@ static int opt_audio_qscale(void *optctx, const char *opt, const char *arg)

 static int opt_filter_complex(void *optctx, const char *opt, const char *arg)
 {
-    char *graph_desc = av_strdup(arg);
-    if (!graph_desc)
+    FilterGraph *fg = ALLOC_ARRAY_ELEM(filtergraphs, nb_filtergraphs);
+
+    fg->index      = nb_filtergraphs - 1;
+    fg->graph_desc = av_strdup(arg);
+    if (!fg->graph_desc)
        return AVERROR(ENOMEM);

-    return fg_create(NULL, graph_desc);
+    return 0;
 }

 static int opt_filter_complex_script(void *optctx, const char *opt, const char *arg)
 {
+    FilterGraph *fg;
    char *graph_desc = file_read(arg);
    if (!graph_desc)
        return AVERROR(EINVAL);

-    return fg_create(NULL, graph_desc);
+    fg = ALLOC_ARRAY_ELEM(filtergraphs, nb_filtergraphs);
+    fg->index      = nb_filtergraphs - 1;
+    fg->graph_desc = graph_desc;
+
+    return 0;
 }

 void show_help_default(const char *opt, const char *arg)
@@ -1299,7 +1257,6 @@ static int open_files(OptionGroupList *l, const char *inout,
 int ffmpeg_parse_options(int argc, char **argv)
 {
    OptionParseContext octx;
-    const char *errmsg = NULL;
    int ret;

    memset(&octx, 0, sizeof(octx));
@@ -1308,14 +1265,14 @@ int ffmpeg_parse_options(int argc, char **argv)
    ret = split_commandline(&octx, argc, argv, options, groups,
                            FF_ARRAY_ELEMS(groups));
    if (ret < 0) {
-        errmsg = "splitting the argument list";
+        av_log(NULL, AV_LOG_FATAL, "Error splitting the argument list: ");
        goto fail;
    }

    /* apply global options */
    ret = parse_optgroup(NULL, &octx.global_opts);
    if (ret < 0) {
-        errmsg = "parsing global options";
+        av_log(NULL, AV_LOG_FATAL, "Error parsing global options: ");
        goto fail;
    }

@@ -1325,39 +1282,34 @@ int ffmpeg_parse_options(int argc, char **argv)
    /* open input files */
    ret = open_files(&octx.groups[GROUP_INFILE], "input", ifile_open);
    if (ret < 0) {
-        errmsg = "opening input files";
+        av_log(NULL, AV_LOG_FATAL, "Error opening input files: ");
        goto fail;
    }

    /* create the complex filtergraphs */
    ret = init_complex_filters();
    if (ret < 0) {
-        errmsg = "initializing complex filters";
+        av_log(NULL, AV_LOG_FATAL, "Error initializing complex filters.\n");
        goto fail;
    }

    /* open output files */
    ret = open_files(&octx.groups[GROUP_OUTFILE], "output", of_open);
    if (ret < 0) {
-        errmsg = "opening output files";
+        av_log(NULL, AV_LOG_FATAL, "Error opening output files: ");
        goto fail;
    }

    correct_input_start_times();

-    ret = apply_sync_offsets();
-    if (ret < 0)
-        goto fail;
+    apply_sync_offsets();

-    ret = check_filter_outputs();
-    if (ret < 0)
-        goto fail;
+    check_filter_outputs();

 fail:
    uninit_parse_context(&octx);
-    if (ret < 0 && ret != AVERROR_EXIT) {
-        av_log(NULL, AV_LOG_FATAL, "Error %s: %s\n",
-               errmsg ? errmsg : "", av_err2str(ret));
+    if (ret < 0) {
+        av_log(NULL, AV_LOG_FATAL, "%s\n", av_err2str(ret));
    }
    return ret;
 }
@@ -1382,15 +1334,8 @@ static int opt_progress(void *optctx, const char *opt, const char *arg)
 int opt_timelimit(void *optctx, const char *opt, const char *arg)
 {
 #if HAVE_SETRLIMIT
-    int ret;
-    double lim;
-    struct rlimit rl;
-
-    ret = parse_number(opt, arg, OPT_INT64, 0, INT_MAX, &lim);
-    if (ret < 0)
-        return ret;
-
-    rl = (struct rlimit){ lim, lim + 1 };
+    int lim = parse_number_or_die(opt, arg, OPT_INT64, 0, INT_MAX);
+    struct rlimit rl = { lim, lim + 1 };
    if (setrlimit(RLIMIT_CPU, &rl))
        perror("setrlimit");
 #else
@@ -1399,22 +1344,6 @@ int opt_timelimit(void *optctx, const char *opt, const char *arg)
    return 0;
 }

-#if FFMPEG_OPT_QPHIST
-static int opt_qphist(void *optctx, const char *opt, const char *arg)
-{
-    av_log(NULL, AV_LOG_WARNING, "Option -%s is deprecated and has no effect\n", opt);
-    return 0;
-}
-#endif
-
-#if FFMPEG_OPT_ADRIFT_THRESHOLD
-static int opt_adrift_threshold(void *optctx, const char *opt, const char *arg)
-{
-    av_log(NULL, AV_LOG_WARNING, "Option -%s is deprecated and has no effect\n", opt);
-    return 0;
-}
-#endif
-
 #define OFFSET(x) offsetof(OptionsContext, x)
 const OptionDef options[] = {
    /* main options */
@@ -1514,9 +1443,6 @@ const OptionDef options[] = {
    { "readrate",       HAS_ARG | OPT_FLOAT | OPT_OFFSET |
                        OPT_EXPERT | OPT_INPUT,                      { .off = OFFSET(readrate) },
        "read input at specified rate", "speed" },
-    { "readrate_initial_burst", HAS_ARG | OPT_DOUBLE | OPT_OFFSET |
-                                OPT_EXPERT | OPT_INPUT,              { .off = OFFSET(readrate_initial_burst) },
-        "The initial amount of input to burst read before imposing any readrate", "seconds" },
    { "target",         HAS_ARG | OPT_PERFILE | OPT_OUTPUT,          { .func_arg = opt_target },
        "specify target file type (\"vcd\", \"svcd\", \"dvd\", \"dv\" or \"dv50\" "
        "with optional prefixes \"pal-\", \"ntsc-\" or \"film-\")", "type" },
@@ -1524,10 +1450,8 @@ const OptionDef options[] = {
        "set video sync method globally; deprecated, use -fps_mode", "" },
    { "frame_drop_threshold", HAS_ARG | OPT_FLOAT | OPT_EXPERT,      { &frame_drop_threshold },
        "frame drop threshold", "" },
-#if FFMPEG_OPT_ADRIFT_THRESHOLD
-    { "adrift_threshold", HAS_ARG | OPT_EXPERT,                      { .func_arg = opt_adrift_threshold },
-        "deprecated, does nothing", "threshold" },
-#endif
+    { "adrift_threshold", HAS_ARG | OPT_FLOAT | OPT_EXPERT,          { &audio_drift_threshold },
+        "audio drift threshold", "threshold" },
    { "copyts",         OPT_BOOL | OPT_EXPERT,                       { &copy_ts },
        "copy timestamps" },
    { "start_at_zero",  OPT_BOOL | OPT_EXPERT,                       { &start_at_zero },
@@ -1697,18 +1621,14 @@ const OptionDef options[] = {
    { "chroma_intra_matrix", OPT_VIDEO | HAS_ARG | OPT_EXPERT  | OPT_STRING | OPT_SPEC |
                      OPT_OUTPUT,                                                { .off = OFFSET(chroma_intra_matrices) },
        "specify intra matrix coeffs", "matrix" },
-#if FFMPEG_OPT_TOP
    { "top",          OPT_VIDEO | HAS_ARG | OPT_EXPERT  | OPT_INT| OPT_SPEC |
                      OPT_INPUT | OPT_OUTPUT,                                    { .off = OFFSET(top_field_first) },
-        "deprecated, use the setfield video filter", "" },
-#endif
+        "top=1/bottom=0/auto=-1 field first", "" },
    { "vtag",         OPT_VIDEO | HAS_ARG | OPT_EXPERT  | OPT_PERFILE |
                      OPT_INPUT | OPT_OUTPUT,                                    { .func_arg = opt_old2new },
        "force video tag/fourcc", "fourcc/tag" },
-#if FFMPEG_OPT_QPHIST
-    { "qphist",       OPT_VIDEO | OPT_EXPERT ,                        { .func_arg = opt_qphist },
-        "deprecated, does nothing" },
-#endif
+    { "qphist",       OPT_VIDEO | OPT_BOOL | OPT_EXPERT ,                        { &qp_hist },
+        "show QP histogram" },
    { "fps_mode",     OPT_VIDEO | HAS_ARG | OPT_STRING | OPT_EXPERT |
                      OPT_SPEC | OPT_OUTPUT,                                     { .off = OFFSET(fps_mode) },
        "set framerate mode for matching video streams; overrides vsync" },
@@ -1838,7 +1758,7 @@ const OptionDef options[] = {

 #if CONFIG_VAAPI
    { "vaapi_device", HAS_ARG | OPT_EXPERT, { .func_arg = opt_vaapi_device },
-        "set VAAPI hardware device (DirectX adapter index, DRM path or X11 display name)", "device" },
+        "set VAAPI hardware device (DRM path or X11 display name)", "device" },
 #endif

 #if CONFIG_QSV
--- a/fftools/ffplay.c
+++ b/fftools/ffplay.c
@@ -47,12 +47,14 @@
 #include "libavdevice/avdevice.h"
 #include "libswscale/swscale.h"
 #include "libavutil/opt.h"
-#include "libavutil/tx.h"
+#include "libavcodec/avfft.h"
 #include "libswresample/swresample.h"

-#include "libavfilter/avfilter.h"
-#include "libavfilter/buffersink.h"
-#include "libavfilter/buffersrc.h"
+#if CONFIG_AVFILTER
+# include "libavfilter/avfilter.h"
+# include "libavfilter/buffersink.h"
+# include "libavfilter/buffersrc.h"
+#endif

 #include <SDL.h>
 #include <SDL_thread.h>
@@ -107,6 +109,8 @@ const int program_birth_year = 2003;

 #define USE_ONEPASS_SUBTITLE_RENDER 1

+static unsigned sws_flags = SWS_BICUBIC;
+
 typedef struct MyAVPacketList {
    AVPacket *pkt;
    int serial;
@@ -146,10 +150,6 @@ typedef struct Clock {
    int *queue_serial;    /* pointer to the current packet queue serial, used for obsolete clock detection */
 } Clock;

-typedef struct FrameData {
-    int64_t pkt_pos;
-} FrameData;
-
 /* Common struct for handling all types of decoded data and allocated render buffers. */
 typedef struct Frame {
    AVFrame *frame;
@@ -250,7 +250,9 @@ typedef struct VideoState {
    int audio_volume;
    int muted;
    struct AudioParams audio_src;
+#if CONFIG_AVFILTER
    struct AudioParams audio_filter_src;
+#endif
    struct AudioParams audio_tgt;
    struct SwrContext *swr_ctx;
    int frame_drops_early;
@@ -262,11 +264,9 @@ typedef struct VideoState {
    int16_t sample_array[SAMPLE_ARRAY_SIZE];
    int sample_array_index;
    int last_i_start;
-    AVTXContext *rdft;
-    av_tx_fn rdft_fn;
+    RDFTContext *rdft;
    int rdft_bits;
-    float *real_data;
-    AVComplexFloat *rdft_data;
+    FFTSample *rdft_data;
    int xpos;
    double last_vis_time;
    SDL_Texture *vis_texture;
@@ -284,6 +284,7 @@ typedef struct VideoState {
    AVStream *video_st;
    PacketQueue videoq;
    double max_frame_duration;      // maximum duration of a frame - above this, we consider the jump a timestamp discontinuity
+    struct SwsContext *img_convert_ctx;
    struct SwsContext *sub_convert_ctx;
    int eof;

@@ -291,12 +292,14 @@ typedef struct VideoState {
    int width, height, xleft, ytop;
    int step;

+#if CONFIG_AVFILTER
    int vfilter_idx;
    AVFilterContext *in_video_filter;   // the first filter in the video chain
    AVFilterContext *out_video_filter;  // the last filter in the video chain
    AVFilterContext *in_audio_filter;   // the first filter in the audio chain
    AVFilterContext *out_audio_filter;  // the last filter in the audio chain
    AVFilterGraph *agraph;              // audio filter graph
+#endif

    int last_video_stream, last_audio_stream, last_subtitle_stream;

@@ -344,9 +347,11 @@ static const char *video_codec_name;
 double rdftspeed = 0.02;
 static int64_t cursor_last_shown;
 static int cursor_hidden = 0;
+#if CONFIG_AVFILTER
 static const char **vfilters_list = NULL;
 static int nb_vfilters = 0;
 static char *afilters = NULL;
+#endif
 static int autorotate = 1;
 static int find_stream_info = 1;
 static int filter_nbthreads = 0;
@@ -388,15 +393,14 @@ static const struct TextureFormatEntry {
    { AV_PIX_FMT_NONE,           SDL_PIXELFORMAT_UNKNOWN },
 };

+#if CONFIG_AVFILTER
 static int opt_add_vfilter(void *optctx, const char *opt, const char *arg)
 {
-    int ret = GROW_ARRAY(vfilters_list, nb_vfilters);
-    if (ret < 0)
-        return ret;
-
+    GROW_ARRAY(vfilters_list, nb_vfilters);
    vfilters_list[nb_vfilters - 1] = arg;
    return 0;
 }
+#endif

 static inline
 int cmp_audio_fmts(enum AVSampleFormat fmt1, int64_t channel_count1,
@@ -649,16 +653,6 @@ static int decoder_decode_frame(Decoder *d, AVFrame *frame, AVSubtitle *sub) {
            }
            av_packet_unref(d->pkt);
        } else {
-            if (d->pkt->buf && !d->pkt->opaque_ref) {
-                FrameData *fd;
-
-                d->pkt->opaque_ref = av_buffer_allocz(sizeof(*fd));
-                if (!d->pkt->opaque_ref)
-                    return AVERROR(ENOMEM);
-                fd = (FrameData*)d->pkt->opaque_ref->data;
-                fd->pkt_pos = d->pkt->pos;
-            }
-
            if (avcodec_send_packet(d->avctx, d->pkt) == AVERROR(EAGAIN)) {
                av_log(d->avctx, AV_LOG_ERROR, "Receive_frame and send_packet both returned EAGAIN, which is an API violation.\n");
                d->packet_pending = 1;
@@ -701,7 +695,7 @@ static int frame_queue_init(FrameQueue *f, PacketQueue *pktq, int max_size, int
    return 0;
 }

-static void frame_queue_destroy(FrameQueue *f)
+static void frame_queue_destory(FrameQueue *f)
 {
    int i;
    for (i = 0; i < f->max_size; i++) {
@@ -897,8 +891,7 @@ static void get_sdl_pix_fmt_and_blendmode(int format, Uint32 *sdl_pix_fmt, SDL_B
    }
 }

-static int upload_texture(SDL_Texture **tex, AVFrame *frame)
-{
+static int upload_texture(SDL_Texture **tex, AVFrame *frame, struct SwsContext **img_convert_ctx) {
    int ret = 0;
    Uint32 sdl_pix_fmt;
    SDL_BlendMode sdl_blendmode;
@@ -906,6 +899,24 @@ static int upload_texture(SDL_Texture **tex, AVFrame *frame)
    if (realloc_texture(tex, sdl_pix_fmt == SDL_PIXELFORMAT_UNKNOWN ? SDL_PIXELFORMAT_ARGB8888 : sdl_pix_fmt, frame->width, frame->height, sdl_blendmode, 0) < 0)
        return -1;
    switch (sdl_pix_fmt) {
+        case SDL_PIXELFORMAT_UNKNOWN:
+            /* This should only happen if we are not using avfilter... */
+            *img_convert_ctx = sws_getCachedContext(*img_convert_ctx,
+                frame->width, frame->height, frame->format, frame->width, frame->height,
+                AV_PIX_FMT_BGRA, sws_flags, NULL, NULL, NULL);
+            if (*img_convert_ctx != NULL) {
+                uint8_t *pixels[4];
+                int pitch[4];
+                if (!SDL_LockTexture(*tex, NULL, (void **)pixels, pitch)) {
+                    sws_scale(*img_convert_ctx, (const uint8_t * const *)frame->data, frame->linesize,
+                              0, frame->height, pixels, pitch);
+                    SDL_UnlockTexture(*tex);
+                }
+            } else {
+                av_log(NULL, AV_LOG_FATAL, "Cannot initialize the conversion context\n");
+                ret = -1;
+            }
+            break;
        case SDL_PIXELFORMAT_IYUV:
            if (frame->linesize[0] > 0 && frame->linesize[1] > 0 && frame->linesize[2] > 0) {
                ret = SDL_UpdateYUVTexture(*tex, NULL, frame->data[0], frame->linesize[0],
@@ -1003,7 +1014,7 @@ static void video_image_display(VideoState *is)
    set_sdl_yuv_conversion_mode(vp->frame);

    if (!vp->uploaded) {
-        if (upload_texture(&is->vid_texture, vp->frame) < 0) {
+        if (upload_texture(&is->vid_texture, vp->frame, &is->img_convert_ctx) < 0) {
            set_sdl_yuv_conversion_mode(NULL);
            return;
        }
@@ -1122,7 +1133,6 @@ static void video_audio_display(VideoState *s)
            fill_rectangle(s->xleft, y, s->width, 1);
        }
    } else {
-        int err = 0;
        if (realloc_texture(&s->vis_texture, SDL_PIXELFORMAT_ARGB8888, s->width, s->height, SDL_BLENDMODE_NONE, 1) < 0)
            return;

@@ -1130,39 +1140,31 @@ static void video_audio_display(VideoState *s)
            s->xpos = 0;
        nb_display_channels= FFMIN(nb_display_channels, 2);
        if (rdft_bits != s->rdft_bits) {
-            const float rdft_scale = 1.0;
-            av_tx_uninit(&s->rdft);
-            av_freep(&s->real_data);
-            av_freep(&s->rdft_data);
+            av_rdft_end(s->rdft);
+            av_free(s->rdft_data);
+            s->rdft = av_rdft_init(rdft_bits, DFT_R2C);
            s->rdft_bits = rdft_bits;
-            s->real_data = av_malloc_array(nb_freq, 4 *sizeof(*s->real_data));
-            s->rdft_data = av_malloc_array(nb_freq + 1, 2 *sizeof(*s->rdft_data));
-            err = av_tx_init(&s->rdft, &s->rdft_fn, AV_TX_FLOAT_RDFT,
-                             0, 1 << rdft_bits, &rdft_scale, 0);
+            s->rdft_data = av_malloc_array(nb_freq, 4 *sizeof(*s->rdft_data));
        }
-        if (err < 0 || !s->rdft_data) {
+        if (!s->rdft || !s->rdft_data){
            av_log(NULL, AV_LOG_ERROR, "Failed to allocate buffers for RDFT, switching to waves display\n");
            s->show_mode = SHOW_MODE_WAVES;
        } else {
-            float *data_in[2];
-            AVComplexFloat *data[2];
+            FFTSample *data[2];
            SDL_Rect rect = {.x = s->xpos, .y = 0, .w = 1, .h = s->height};
            uint32_t *pixels;
            int pitch;
            for (ch = 0; ch < nb_display_channels; ch++) {
-                data_in[ch] = s->real_data + 2 * nb_freq * ch;
-                data[ch] = s->rdft_data + nb_freq * ch;
+                data[ch] = s->rdft_data + 2 * nb_freq * ch;
                i = i_start + ch;
                for (x = 0; x < 2 * nb_freq; x++) {
                    double w = (x-nb_freq) * (1.0 / nb_freq);
-                    data_in[ch][x] = s->sample_array[i] * (1.0 - w * w);
+                    data[ch][x] = s->sample_array[i] * (1.0 - w * w);
                    i += channels;
                    if (i >= SAMPLE_ARRAY_SIZE)
                        i -= SAMPLE_ARRAY_SIZE;
                }
-                s->rdft_fn(s->rdft, data[ch], data_in[ch], sizeof(float));
-                data[ch][0].im = data[ch][nb_freq].re;
-                data[ch][nb_freq].re = 0;
+                av_rdft_calc(s->rdft, data[ch]);
            }
            /* Least efficient way to do this, we should of course
             * directly access it but it is more than fast enough. */
@@ -1171,8 +1173,8 @@ static void video_audio_display(VideoState *s)
                pixels += pitch * s->height;
                for (y = 0; y < s->height; y++) {
                    double w = 1 / sqrt(nb_freq);
-                    int a = sqrt(w * sqrt(data[0][y].re * data[0][y].re + data[0][y].im * data[0][y].im));
-                    int b = (nb_display_channels == 2 ) ? sqrt(w * hypot(data[1][y].re, data[1][y].im))
+                    int a = sqrt(w * sqrt(data[0][2 * y + 0] * data[0][2 * y + 0] + data[0][2 * y + 1] * data[0][2 * y + 1]));
+                    int b = (nb_display_channels == 2 ) ? sqrt(w * hypot(data[1][2 * y + 0], data[1][2 * y + 1]))
                                                        : a;
                    a = FFMIN(a, 255);
                    b = FFMIN(b, 255);
@@ -1208,8 +1210,7 @@ static void stream_component_close(VideoState *is, int stream_index)
        is->audio_buf = NULL;

        if (is->rdft) {
-            av_tx_uninit(&is->rdft);
-            av_freep(&is->real_data);
+            av_rdft_end(is->rdft);
            av_freep(&is->rdft_data);
            is->rdft = NULL;
            is->rdft_bits = 0;
@@ -1267,10 +1268,11 @@ static void stream_close(VideoState *is)
    packet_queue_destroy(&is->subtitleq);

    /* free all pictures */
-    frame_queue_destroy(&is->pictq);
-    frame_queue_destroy(&is->sampq);
-    frame_queue_destroy(&is->subpq);
+    frame_queue_destory(&is->pictq);
+    frame_queue_destory(&is->sampq);
+    frame_queue_destory(&is->subpq);
    SDL_DestroyCond(is->continue_read_thread);
+    sws_freeContext(is->img_convert_ctx);
    sws_freeContext(is->sub_convert_ctx);
    av_free(is->filename);
    if (is->vis_texture)
@@ -1292,7 +1294,9 @@ static void do_exit(VideoState *is)
    if (window)
        SDL_DestroyWindow(window);
    uninit_opts();
+#if CONFIG_AVFILTER
    av_freep(&vfilters_list);
+#endif
    avformat_network_deinit();
    if (show_status)
        printf("\n");
@@ -1549,8 +1553,7 @@ static double vp_duration(VideoState *is, Frame *vp, Frame *nextvp) {
    }
 }

-static void update_video_pts(VideoState *is, double pts, int serial)
-{
+static void update_video_pts(VideoState *is, double pts, int64_t pos, int serial) {
    /* update current video pts */
    set_clock(&is->vidclk, pts, serial);
    sync_clock_to_slave(&is->extclk, &is->vidclk);
@@ -1615,7 +1618,7 @@ retry:

            SDL_LockMutex(is->pictq.mutex);
            if (!isnan(vp->pts))
-                update_video_pts(is, vp->pts, vp->serial);
+                update_video_pts(is, vp->pts, vp->pos, vp->serial);
            SDL_UnlockMutex(is->pictq.mutex);

            if (frame_queue_nb_remaining(&is->pictq) > 1) {
@@ -1790,6 +1793,7 @@ static int get_video_frame(VideoState *is, AVFrame *frame)
    return got_picture;
 }

+#if CONFIG_AVFILTER
 static int configure_filtergraph(AVFilterGraph *graph, const char *filtergraph,
                                 AVFilterContext *source_ctx, AVFilterContext *sink_ctx)
 {
@@ -1916,13 +1920,8 @@ static int configure_video_filters(AVFilterGraph *graph, VideoState *is, const c
        AVFrameSideData *sd = av_frame_get_side_data(frame, AV_FRAME_DATA_DISPLAYMATRIX);
        if (sd)
            displaymatrix = (int32_t *)sd->data;
-        if (!displaymatrix) {
-            const AVPacketSideData *sd = av_packet_side_data_get(is->video_st->codecpar->coded_side_data,
-                                                                 is->video_st->codecpar->nb_coded_side_data,
-                                                                 AV_PKT_DATA_DISPLAYMATRIX);
-            if (sd)
-                displaymatrix = (int32_t *)sd->data;
-        }
+        if (!displaymatrix)
+            displaymatrix = (int32_t *)av_stream_get_side_data(is->video_st, AV_PKT_DATA_DISPLAYMATRIX, NULL);
        theta = get_rotation(displaymatrix);

        if (fabs(theta - 90) < 1.0) {
@@ -2022,14 +2021,17 @@ end:

    return ret;
 }
+#endif  /* CONFIG_AVFILTER */

 static int audio_thread(void *arg)
 {
    VideoState *is = arg;
    AVFrame *frame = av_frame_alloc();
    Frame *af;
+#if CONFIG_AVFILTER
    int last_serial = -1;
    int reconfigure;
+#endif
    int got_frame = 0;
    AVRational tb;
    int ret = 0;
@@ -2044,6 +2046,7 @@ static int audio_thread(void *arg)
        if (got_frame) {
                tb = (AVRational){1, frame->sample_rate};

+#if CONFIG_AVFILTER
                reconfigure =
                    cmp_audio_fmts(is->audio_filter_src.fmt, is->audio_filter_src.ch_layout.nb_channels,
                                   frame->format, frame->ch_layout.nb_channels)    ||
@@ -2075,28 +2078,32 @@ static int audio_thread(void *arg)
                goto the_end;

            while ((ret = av_buffersink_get_frame_flags(is->out_audio_filter, frame, 0)) >= 0) {
-                FrameData *fd = frame->opaque_ref ? (FrameData*)frame->opaque_ref->data : NULL;
                tb = av_buffersink_get_time_base(is->out_audio_filter);
+#endif
                if (!(af = frame_queue_peek_writable(&is->sampq)))
                    goto the_end;

                af->pts = (frame->pts == AV_NOPTS_VALUE) ? NAN : frame->pts * av_q2d(tb);
-                af->pos = fd ? fd->pkt_pos : -1;
+                af->pos = frame->pkt_pos;
                af->serial = is->auddec.pkt_serial;
                af->duration = av_q2d((AVRational){frame->nb_samples, frame->sample_rate});

                av_frame_move_ref(af->frame, frame);
                frame_queue_push(&is->sampq);

+#if CONFIG_AVFILTER
                if (is->audioq.serial != is->auddec.pkt_serial)
                    break;
            }
            if (ret == AVERROR_EOF)
                is->auddec.finished = is->auddec.pkt_serial;
+#endif
        }
    } while (ret >= 0 || ret == AVERROR(EAGAIN) || ret == AVERROR_EOF);
 the_end:
+#if CONFIG_AVFILTER
    avfilter_graph_free(&is->agraph);
+#endif
    av_frame_free(&frame);
    return ret;
 }
@@ -2122,6 +2129,7 @@ static int video_thread(void *arg)
    AVRational tb = is->video_st->time_base;
    AVRational frame_rate = av_guess_frame_rate(is->ic, is->video_st, NULL);

+#if CONFIG_AVFILTER
    AVFilterGraph *graph = NULL;
    AVFilterContext *filt_out = NULL, *filt_in = NULL;
    int last_w = 0;
@@ -2129,6 +2137,7 @@ static int video_thread(void *arg)
    enum AVPixelFormat last_format = -2;
    int last_serial = -1;
    int last_vfilter_idx = 0;
+#endif

    if (!frame)
        return AVERROR(ENOMEM);
@@ -2140,6 +2149,7 @@ static int video_thread(void *arg)
        if (!ret)
            continue;

+#if CONFIG_AVFILTER
        if (   last_w != frame->width
            || last_h != frame->height
            || last_format != frame->format
@@ -2180,8 +2190,6 @@ static int video_thread(void *arg)
            goto the_end;

        while (ret >= 0) {
-            FrameData *fd;
-
            is->frame_last_returned_time = av_gettime_relative() / 1000000.0;

            ret = av_buffersink_get_frame_flags(filt_out, frame, 0);
@@ -2192,25 +2200,28 @@ static int video_thread(void *arg)
                break;
            }

-            fd = frame->opaque_ref ? (FrameData*)frame->opaque_ref->data : NULL;
-
            is->frame_last_filter_delay = av_gettime_relative() / 1000000.0 - is->frame_last_returned_time;
            if (fabs(is->frame_last_filter_delay) > AV_NOSYNC_THRESHOLD / 10.0)
                is->frame_last_filter_delay = 0;
            tb = av_buffersink_get_time_base(filt_out);
+#endif
            duration = (frame_rate.num && frame_rate.den ? av_q2d((AVRational){frame_rate.den, frame_rate.num}) : 0);
            pts = (frame->pts == AV_NOPTS_VALUE) ? NAN : frame->pts * av_q2d(tb);
-            ret = queue_picture(is, frame, pts, duration, fd ? fd->pkt_pos : -1, is->viddec.pkt_serial);
+            ret = queue_picture(is, frame, pts, duration, frame->pkt_pos, is->viddec.pkt_serial);
            av_frame_unref(frame);
+#if CONFIG_AVFILTER
            if (is->videoq.serial != is->viddec.pkt_serial)
                break;
        }
+#endif

        if (ret < 0)
            goto the_end;
    }
 the_end:
+#if CONFIG_AVFILTER
    avfilter_graph_free(&graph);
+#endif
    av_frame_free(&frame);
    return 0;
 }
@@ -2601,18 +2612,11 @@ static int stream_component_open(VideoState *is, int stream_index)
    if (fast)
        avctx->flags2 |= AV_CODEC_FLAG2_FAST;

-    ret = filter_codec_opts(codec_opts, avctx->codec_id, ic,
-                            ic->streams[stream_index], codec, &opts);
-    if (ret < 0)
-        goto fail;
-
+    opts = filter_codec_opts(codec_opts, avctx->codec_id, ic, ic->streams[stream_index], codec);
    if (!av_dict_get(opts, "threads", NULL, 0))
        av_dict_set(&opts, "threads", "auto", 0);
    if (stream_lowres)
        av_dict_set_int(&opts, "lowres", stream_lowres, 0);
-
-    av_dict_set(&opts, "flags", "+copy_opaque", AV_DICT_MULTIKEY);
-
    if ((ret = avcodec_open2(avctx, codec, &opts)) < 0) {
        goto fail;
    }
@@ -2626,6 +2630,7 @@ static int stream_component_open(VideoState *is, int stream_index)
    ic->streams[stream_index]->discard = AVDISCARD_DEFAULT;
    switch (avctx->codec_type) {
    case AVMEDIA_TYPE_AUDIO:
+#if CONFIG_AVFILTER
        {
            AVFilterContext *sink;

@@ -2642,6 +2647,12 @@ static int stream_component_open(VideoState *is, int stream_index)
            if (ret < 0)
                goto fail;
        }
+#else
+        sample_rate    = avctx->sample_rate;
+        ret = av_channel_layout_copy(&ch_layout, &avctx->ch_layout);
+        if (ret < 0)
+            goto fail;
+#endif

        /* prepare audio output */
        if ((ret = audio_open(is, &ch_layout, sample_rate, &is->audio_tgt)) < 0)
@@ -2663,7 +2674,7 @@ static int stream_component_open(VideoState *is, int stream_index)

        if ((ret = decoder_init(&is->auddec, avctx, &is->audioq, is->continue_read_thread)) < 0)
            goto fail;
-        if (is->ic->iformat->flags & AVFMT_NOTIMESTAMPS) {
+        if ((is->ic->iformat->flags & (AVFMT_NOBINSEARCH | AVFMT_NOGENSEARCH | AVFMT_NO_BYTE_SEEK)) && !is->ic->iformat->read_seek) {
            is->auddec.start_pts = is->audio_st->start_time;
            is->auddec.start_pts_tb = is->audio_st->time_base;
        }
@@ -2794,17 +2805,11 @@ static int read_thread(void *arg)
    if (genpts)
        ic->flags |= AVFMT_FLAG_GENPTS;

-    if (find_stream_info) {
-        AVDictionary **opts;
-        int orig_nb_streams = ic->nb_streams;
+    av_format_inject_global_side_data(ic);

-        err = setup_find_stream_info_opts(ic, codec_opts, &opts);
-        if (err < 0) {
-            av_log(NULL, AV_LOG_ERROR,
-                   "Error setting up avformat_find_stream_info() options\n");
-            ret = err;
-            goto fail;
-        }
+    if (find_stream_info) {
+        AVDictionary **opts = setup_find_stream_info_opts(ic, codec_opts);
+        int orig_nb_streams = ic->nb_streams;

        err = avformat_find_stream_info(ic, opts);

@@ -3321,6 +3326,7 @@ static void event_loop(VideoState *cur_stream)
                stream_cycle_channel(cur_stream, AVMEDIA_TYPE_SUBTITLE);
                break;
            case SDLK_w:
+#if CONFIG_AVFILTER
                if (cur_stream->show_mode == SHOW_MODE_VIDEO && cur_stream->vfilter_idx < nb_vfilters - 1) {
                    if (++cur_stream->vfilter_idx >= nb_vfilters)
                        cur_stream->vfilter_idx = 0;
@@ -3328,6 +3334,9 @@ static void event_loop(VideoState *cur_stream)
                    cur_stream->vfilter_idx = 0;
                    toggle_audio_display(cur_stream);
                }
+#else
+                toggle_audio_display(cur_stream);
+#endif
                break;
            case SDLK_PAGEUP:
                if (cur_stream->ic->nb_chapters <= 1) {
@@ -3463,23 +3472,13 @@ static void event_loop(VideoState *cur_stream)

 static int opt_width(void *optctx, const char *opt, const char *arg)
 {
-    double num;
-    int ret = parse_number(opt, arg, OPT_INT64, 1, INT_MAX, &num);
-    if (ret < 0)
-        return ret;
-
-    screen_width = num;
+    screen_width = parse_number_or_die(opt, arg, OPT_INT64, 1, INT_MAX);
    return 0;
 }

 static int opt_height(void *optctx, const char *opt, const char *arg)
 {
-    double num;
-    int ret = parse_number(opt, arg, OPT_INT64, 1, INT_MAX, &num);
-    if (ret < 0)
-        return ret;
-
-    screen_height = num;
+    screen_height = parse_number_or_die(opt, arg, OPT_INT64, 1, INT_MAX);
    return 0;
 }

@@ -3508,35 +3507,38 @@ static int opt_sync(void *optctx, const char *opt, const char *arg)
    return 0;
 }

+static int opt_seek(void *optctx, const char *opt, const char *arg)
+{
+    start_time = parse_time_or_die(opt, arg, 1);
+    return 0;
+}
+
+static int opt_duration(void *optctx, const char *opt, const char *arg)
+{
+    duration = parse_time_or_die(opt, arg, 1);
+    return 0;
+}
+
 static int opt_show_mode(void *optctx, const char *opt, const char *arg)
 {
    show_mode = !strcmp(arg, "video") ? SHOW_MODE_VIDEO :
                !strcmp(arg, "waves") ? SHOW_MODE_WAVES :
-                !strcmp(arg, "rdft" ) ? SHOW_MODE_RDFT  : SHOW_MODE_NONE;
-
-    if (show_mode == SHOW_MODE_NONE) {
-        double num;
-        int ret = parse_number(opt, arg, OPT_INT, 0, SHOW_MODE_NB-1, &num);
-        if (ret < 0)
-            return ret;
-        show_mode = num;
-    }
+                !strcmp(arg, "rdft" ) ? SHOW_MODE_RDFT  :
+                parse_number_or_die(opt, arg, OPT_INT, 0, SHOW_MODE_NB-1);
    return 0;
 }

-static int opt_input_file(void *optctx, const char *filename)
+static void opt_input_file(void *optctx, const char *filename)
 {
    if (input_filename) {
        av_log(NULL, AV_LOG_FATAL,
               "Argument '%s' provided as input filename, but '%s' was already specified.\n",
                filename, input_filename);
-        return AVERROR(EINVAL);
+        exit(1);
    }
    if (!strcmp(filename, "-"))
        filename = "fd:";
    input_filename = filename;
-
-    return 0;
 }

 static int opt_codec(void *optctx, const char *opt, const char *arg)
@@ -3574,8 +3576,8 @@ static const OptionDef options[] = {
    { "ast", OPT_STRING | HAS_ARG | OPT_EXPERT, { &wanted_stream_spec[AVMEDIA_TYPE_AUDIO] }, "select desired audio stream", "stream_specifier" },
    { "vst", OPT_STRING | HAS_ARG | OPT_EXPERT, { &wanted_stream_spec[AVMEDIA_TYPE_VIDEO] }, "select desired video stream", "stream_specifier" },
    { "sst", OPT_STRING | HAS_ARG | OPT_EXPERT, { &wanted_stream_spec[AVMEDIA_TYPE_SUBTITLE] }, "select desired subtitle stream", "stream_specifier" },
-    { "ss", HAS_ARG | OPT_TIME, { &start_time }, "seek to a given position in seconds", "pos" },
-    { "t",  HAS_ARG | OPT_TIME, { &duration }, "play  \"duration\" seconds of audio/video", "duration" },
+    { "ss", HAS_ARG, { .func_arg = opt_seek }, "seek to a given position in seconds", "pos" },
+    { "t", HAS_ARG, { .func_arg = opt_duration }, "play  \"duration\" seconds of audio/video", "duration" },
    { "bytes", OPT_INT | HAS_ARG, { &seek_by_bytes }, "seek by bytes 0=off 1=on -1=auto", "val" },
    { "seek_interval", OPT_FLOAT | HAS_ARG, { &seek_interval }, "set seek interval for left/right keys, in seconds", "seconds" },
    { "nodisp", OPT_BOOL, { &display_disable }, "disable graphical display" },
@@ -3598,8 +3600,10 @@ static const OptionDef options[] = {
    { "window_title", OPT_STRING | HAS_ARG, { &window_title }, "set window title", "window title" },
    { "left", OPT_INT | HAS_ARG | OPT_EXPERT, { &screen_left }, "set the x position for the left of the window", "x pos" },
    { "top", OPT_INT | HAS_ARG | OPT_EXPERT, { &screen_top }, "set the y position for the top of the window", "y pos" },
+#if CONFIG_AVFILTER
    { "vf", OPT_EXPERT | HAS_ARG, { .func_arg = opt_add_vfilter }, "set video filters", "filter_graph" },
    { "af", OPT_STRING | HAS_ARG, { &afilters }, "set audio filters", "filter_graph" },
+#endif
    { "rdftspeed", OPT_INT | HAS_ARG| OPT_AUDIO | OPT_EXPERT, { &rdftspeed }, "rdft speed", "msecs" },
    { "showmode", HAS_ARG, { .func_arg = opt_show_mode}, "select show mode (0 = video, 1 = waves, 2 = RDFT)", "mode" },
    { "i", OPT_BOOL, { &dummy}, "read specified file", "input_file"},
@@ -3630,7 +3634,11 @@ void show_help_default(const char *opt, const char *arg)
    printf("\n");
    show_help_children(avcodec_get_class(), AV_OPT_FLAG_DECODING_PARAM);
    show_help_children(avformat_get_class(), AV_OPT_FLAG_DECODING_PARAM);
+#if !CONFIG_AVFILTER
+    show_help_children(sws_get_class(), AV_OPT_FLAG_ENCODING_PARAM);
+#else
    show_help_children(avfilter_get_class(), AV_OPT_FLAG_FILTERING_PARAM);
+#endif
    printf("\nWhile playing:\n"
           "q, ESC              quit\n"
           "f                   toggle full screen\n"
@@ -3655,7 +3663,7 @@ void show_help_default(const char *opt, const char *arg)
 /* Called from the main */
 int main(int argc, char **argv)
 {
-    int flags, ret;
+    int flags;
    VideoState *is;

    init_dynload();
@@ -3674,9 +3682,7 @@ int main(int argc, char **argv)

    show_banner(argc, argv, options);

-    ret = parse_options(NULL, argc, argv, options, opt_input_file);
-    if (ret < 0)
-        exit(ret == AVERROR_EXIT ? 0 : 1);
+    parse_options(NULL, argc, argv, options, opt_input_file);

    if (!input_filename) {
        show_usage();
--- a/fftools/ffprobe.c
+++ b/fftools/ffprobe.c
--- a/fftools/opt_common.c
+++ b/fftools/opt_common.c
@@ -291,6 +291,8 @@ static void print_codec(const AVCodec *c)
        printf("delay ");
    if (c->capabilities & AV_CODEC_CAP_SMALL_LAST_FRAME)
        printf("small ");
+    if (c->capabilities & AV_CODEC_CAP_SUBFRAMES)
+        printf("subframes ");
    if (c->capabilities & AV_CODEC_CAP_EXPERIMENTAL)
        printf("exp ");
    if (c->capabilities & AV_CODEC_CAP_CHANNEL_CONF)
@@ -615,10 +617,10 @@ static void print_codecs_for_id(enum AVCodecID id, int encoder)
    void *iter = NULL;
    const AVCodec *codec;

-    printf(" (%s:", encoder ? "encoders" : "decoders");
+    printf(" (%s: ", encoder ? "encoders" : "decoders");

    while ((codec = next_codec_for_id(id, &iter, encoder)))
-        printf(" %s", codec->name);
+        printf("%s ", codec->name);

    printf(")");
 }
@@ -632,7 +634,7 @@ static int compare_codec_desc(const void *a, const void *b)
           strcmp((*da)->name, (*db)->name);
 }

-static int get_codecs_sorted(const AVCodecDescriptor ***rcodecs)
+static unsigned get_codecs_sorted(const AVCodecDescriptor ***rcodecs)
 {
    const AVCodecDescriptor *desc = NULL;
    const AVCodecDescriptor **codecs;
@@ -641,7 +643,7 @@ static int get_codecs_sorted(const AVCodecDescriptor ***rcodecs)
    while ((desc = avcodec_descriptor_next(desc)))
        nb_codecs++;
    if (!(codecs = av_calloc(nb_codecs, sizeof(*codecs))))
-        return AVERROR(ENOMEM);
+        report_and_exit(AVERROR(ENOMEM));
    desc = NULL;
    while ((desc = avcodec_descriptor_next(desc)))
        codecs[i++] = desc;
@@ -666,11 +668,7 @@ static char get_media_type_char(enum AVMediaType type)
 int show_codecs(void *optctx, const char *opt, const char *arg)
 {
    const AVCodecDescriptor **codecs;
-    unsigned i;
-    int nb_codecs = get_codecs_sorted(&codecs);
-
-    if (nb_codecs < 0)
-        return nb_codecs;
+    unsigned i, nb_codecs = get_codecs_sorted(&codecs);

    printf("Codecs:\n"
           " D..... = Decoding supported\n"
@@ -692,13 +690,14 @@ int show_codecs(void *optctx, const char *opt, const char *arg)
        if (strstr(desc->name, "_deprecated"))
            continue;

-        printf(" %c%c%c%c%c%c",
-               avcodec_find_decoder(desc->id) ? 'D' : '.',
-               avcodec_find_encoder(desc->id) ? 'E' : '.',
-               get_media_type_char(desc->type),
-               (desc->props & AV_CODEC_PROP_INTRA_ONLY) ? 'I' : '.',
-               (desc->props & AV_CODEC_PROP_LOSSY)      ? 'L' : '.',
-               (desc->props & AV_CODEC_PROP_LOSSLESS)   ? 'S' : '.');
+        printf(" ");
+        printf(avcodec_find_decoder(desc->id) ? "D" : ".");
+        printf(avcodec_find_encoder(desc->id) ? "E" : ".");
+
+        printf("%c", get_media_type_char(desc->type));
+        printf((desc->props & AV_CODEC_PROP_INTRA_ONLY) ? "I" : ".");
+        printf((desc->props & AV_CODEC_PROP_LOSSY)      ? "L" : ".");
+        printf((desc->props & AV_CODEC_PROP_LOSSLESS)   ? "S" : ".");

        printf(" %-20s %s", desc->name, desc->long_name ? desc->long_name : "");

@@ -746,13 +745,12 @@ static void print_codecs(int encoder)
        void *iter = NULL;

        while ((codec = next_codec_for_id(desc->id, &iter, encoder))) {
-            printf(" %c%c%c%c%c%c",
-                   get_media_type_char(desc->type),
-                   (codec->capabilities & AV_CODEC_CAP_FRAME_THREADS)   ? 'F' : '.',
-                   (codec->capabilities & AV_CODEC_CAP_SLICE_THREADS)   ? 'S' : '.',
-                   (codec->capabilities & AV_CODEC_CAP_EXPERIMENTAL)    ? 'X' : '.',
-                   (codec->capabilities & AV_CODEC_CAP_DRAW_HORIZ_BAND) ? 'B' : '.',
-                   (codec->capabilities & AV_CODEC_CAP_DR1)             ? 'D' : '.');
+            printf(" %c", get_media_type_char(desc->type));
+            printf((codec->capabilities & AV_CODEC_CAP_FRAME_THREADS) ? "F" : ".");
+            printf((codec->capabilities & AV_CODEC_CAP_SLICE_THREADS) ? "S" : ".");
+            printf((codec->capabilities & AV_CODEC_CAP_EXPERIMENTAL)  ? "X" : ".");
+            printf((codec->capabilities & AV_CODEC_CAP_DRAW_HORIZ_BAND)?"B" : ".");
+            printf((codec->capabilities & AV_CODEC_CAP_DR1)           ? "D" : ".");

            printf(" %-20s %s", codec->name, codec->long_name ? codec->long_name : "");
            if (strcmp(codec->name, desc->name))
@@ -1163,10 +1161,7 @@ int init_report(const char *env, FILE **file)
            report_file_level = strtol(val, &tail, 10);
            if (*tail) {
                av_log(NULL, AV_LOG_FATAL, "Invalid report file level\n");
-                av_free(key);
-                av_free(val);
-                av_free(filename_template);
-                return AVERROR(EINVAL);
+                exit_program(1);
            }
            envlevel = 1;
        } else {
@@ -1226,7 +1221,7 @@ int opt_max_alloc(void *optctx, const char *opt, const char *arg)
    max = strtol(arg, &tail, 10);
    if (*tail) {
        av_log(NULL, AV_LOG_FATAL, "Invalid max_alloc \"%s\".\n", arg);
-        return AVERROR(EINVAL);
+        exit_program(1);
    }
    av_max_alloc(max);
    return 0;
@@ -1300,7 +1295,7 @@ int opt_loglevel(void *optctx, const char *opt, const char *arg)
               "Possible levels are numbers or:\n", arg);
        for (i = 0; i < FF_ARRAY_ELEMS(log_levels); i++)
            av_log(NULL, AV_LOG_FATAL, "\"%s\"\n", log_levels[i].name);
-        return AVERROR(EINVAL);
+        exit_program(1);
    }

 end:
--- a/fftools/sync_queue.c
+++ b/fftools/sync_queue.c
@@ -20,59 +20,18 @@
 #include <string.h>

 #include "libavutil/avassert.h"
-#include "libavutil/channel_layout.h"
-#include "libavutil/cpu.h"
 #include "libavutil/error.h"
 #include "libavutil/fifo.h"
 #include "libavutil/mathematics.h"
 #include "libavutil/mem.h"
-#include "libavutil/samplefmt.h"
-#include "libavutil/timestamp.h"

 #include "objpool.h"
 #include "sync_queue.h"

-/*
- * How this works:
- * --------------
- * time:   0    1    2    3    4    5    6    7    8    9    10   11   12   13
- *         -------------------------------------------------------------------
- *         |    |    |    |    |    |    |    |    |    |    |    |    |    |
- *         |    ┌───┐┌────────┐┌───┐┌─────────────┐
- * stream 0|    │d=1││  d=2   ││d=1││    d=3      │
- *         |    └───┘└────────┘└───┘└─────────────┘
- *         ┌───┐               ┌───────────────────────┐
- * stream 1│d=1│               │         d=5           │
- *         └───┘               └───────────────────────┘
- *         |    ┌───┐┌───┐┌───┐┌───┐
- * stream 2|    │d=1││d=1││d=1││d=1│ <- stream 2 is the head stream of the queue
- *         |    └───┘└───┘└───┘└───┘
- *                  ^              ^
- *          [stream 2 tail] [stream 2 head]
- *
- * We have N streams (N=3 in the diagram), each stream is a FIFO. The *tail* of
- * each FIFO is the frame with smallest end time, the *head* is the frame with
- * the largest end time. Frames submitted to the queue with sq_send() are placed
- * after the head, frames returned to the caller with sq_receive() are taken
- * from the tail.
- *
- * The head stream of the whole queue (SyncQueue.head_stream) is the limiting
- * stream with the *smallest* head timestamp, i.e. the stream whose source lags
- * furthest behind all other streams. It determines which frames can be output
- * from the queue.
- *
- * In the diagram, the head stream is 2, because it head time is t=5, while
- * streams 0 and 1 end at t=8 and t=9 respectively. All frames that _end_ at
- * or before t=5 can be output, i.e. the first 3 frames from stream 0, first
- * frame from stream 1, and all 4 frames from stream 2.
- */
-
 typedef struct SyncQueueStream {
    AVFifo          *fifo;
    AVRational       tb;

-    /* number of audio samples in fifo */
-    uint64_t         samples_queued;
    /* stream head: largest timestamp seen */
    int64_t          head_ts;
    int              limiting;
@@ -80,16 +39,12 @@ typedef struct SyncQueueStream {
    int              finished;

    uint64_t         frames_sent;
-    uint64_t         samples_sent;
    uint64_t         frames_max;
-    int              frame_samples;
 } SyncQueueStream;

 struct SyncQueue {
    enum SyncQueueType type;

-    void *logctx;
-
    /* no more frames will be sent for any stream */
    int finished;
    /* sync head: the stream with the _smallest_ head timestamp
@@ -106,10 +61,6 @@ struct SyncQueue {

    // pool of preallocated frames to avoid constant allocations
    ObjPool *pool;
-
-    int have_limiting;
-
-    uintptr_t align_mask;
 };

 static void frame_move(const SyncQueue *sq, SyncQueueFrame dst,
@@ -121,62 +72,22 @@ static void frame_move(const SyncQueue *sq, SyncQueueFrame dst,
        av_frame_move_ref(dst.f, src.f);
 }

-/**
- * Compute the end timestamp of a frame. If nb_samples is provided, consider
- * the frame to have this number of audio samples, otherwise use frame duration.
- */
-static int64_t frame_end(const SyncQueue *sq, SyncQueueFrame frame, int nb_samples)
+static int64_t frame_ts(const SyncQueue *sq, SyncQueueFrame frame)
 {
-    if (nb_samples) {
-        int64_t d = av_rescale_q(nb_samples, (AVRational){ 1, frame.f->sample_rate},
-                                 frame.f->time_base);
-        return frame.f->pts + d;
-    }
-
    return (sq->type == SYNC_QUEUE_PACKETS) ?
           frame.p->pts + frame.p->duration :
           frame.f->pts + frame.f->duration;
 }

-static int frame_samples(const SyncQueue *sq, SyncQueueFrame frame)
-{
-    return (sq->type == SYNC_QUEUE_PACKETS) ? 0 : frame.f->nb_samples;
-}
-
 static int frame_null(const SyncQueue *sq, SyncQueueFrame frame)
 {
    return (sq->type == SYNC_QUEUE_PACKETS) ? (frame.p == NULL) : (frame.f == NULL);
 }

-static void tb_update(const SyncQueue *sq, SyncQueueStream *st,
-                      const SyncQueueFrame frame)
-{
-    AVRational tb = (sq->type == SYNC_QUEUE_PACKETS) ?
-                    frame.p->time_base : frame.f->time_base;
-
-    av_assert0(tb.num > 0 && tb.den > 0);
-
-    if (tb.num == st->tb.num && tb.den == st->tb.den)
-        return;
-
-    // timebase should not change after the first frame
-    av_assert0(!av_fifo_can_read(st->fifo));
-
-    if (st->head_ts != AV_NOPTS_VALUE)
-        st->head_ts = av_rescale_q(st->head_ts, st->tb, tb);
-
-    st->tb = tb;
-}
-
 static void finish_stream(SyncQueue *sq, unsigned int stream_idx)
 {
    SyncQueueStream *st = &sq->streams[stream_idx];

-    if (!st->finished)
-        av_log(sq->logctx, AV_LOG_DEBUG,
-               "sq: finish %u; head ts %s\n", stream_idx,
-               av_ts2timestr(st->head_ts, &st->tb));
-
    st->finished = 1;

    if (st->limiting && st->head_ts != AV_NOPTS_VALUE) {
@@ -194,14 +105,8 @@ static void finish_stream(SyncQueue *sq, unsigned int stream_idx)
        for (unsigned int i = 0; i < sq->nb_streams; i++) {
            SyncQueueStream *st1 = &sq->streams[i];
            if (st != st1 && st1->head_ts != AV_NOPTS_VALUE &&
-                av_compare_ts(st->head_ts, st->tb, st1->head_ts, st1->tb) <= 0) {
-                if (!st1->finished)
-                    av_log(sq->logctx, AV_LOG_DEBUG,
-                           "sq: finish secondary %u; head ts %s\n", i,
-                           av_ts2timestr(st1->head_ts, &st1->tb));
-
+                av_compare_ts(st->head_ts, st->tb, st1->head_ts, st1->tb) <= 0)
                st1->finished = 1;
-            }
        }
    }

@@ -211,32 +116,21 @@ static void finish_stream(SyncQueue *sq, unsigned int stream_idx)
            return;
    }
    sq->finished = 1;
-
-    av_log(sq->logctx, AV_LOG_DEBUG, "sq: finish queue\n");
 }

 static void queue_head_update(SyncQueue *sq)
 {
-    av_assert0(sq->have_limiting);
-
    if (sq->head_stream < 0) {
-        unsigned first_limiting = UINT_MAX;
-
        /* wait for one timestamp in each stream before determining
         * the queue head */
        for (unsigned int i = 0; i < sq->nb_streams; i++) {
            SyncQueueStream *st = &sq->streams[i];
-            if (!st->limiting)
-                continue;
-            if (st->head_ts == AV_NOPTS_VALUE)
+            if (st->limiting && st->head_ts == AV_NOPTS_VALUE)
                return;
-            if (first_limiting == UINT_MAX)
-                first_limiting = i;
        }

        // placeholder value, correct one will be found below
-        av_assert0(first_limiting < UINT_MAX);
-        sq->head_stream = first_limiting;
+        sq->head_stream = 0;
    }

    for (unsigned int i = 0; i < sq->nb_streams; i++) {
@@ -309,7 +203,7 @@ static int overflow_heartbeat(SyncQueue *sq, int stream_idx)
    /* get the chosen stream's tail timestamp */
    for (size_t i = 0; tail_ts == AV_NOPTS_VALUE &&
                       av_fifo_peek(st->fifo, &frame, 1, i) >= 0; i++)
-        tail_ts = frame_end(sq, frame, 0);
+        tail_ts = frame_ts(sq, frame);

    /* overflow triggers when the tail is over specified duration behind the head */
    if (tail_ts == AV_NOPTS_VALUE || tail_ts >= st->head_ts ||
@@ -331,9 +225,6 @@ static int overflow_heartbeat(SyncQueue *sq, int stream_idx)
        if (st1->head_ts != AV_NOPTS_VALUE)
            ts = FFMAX(st1->head_ts + 1, ts);

-        av_log(sq->logctx, AV_LOG_DEBUG, "sq: %u overflow heardbeat %s -> %s\n",
-               i, av_ts2timestr(st1->head_ts, &st1->tb), av_ts2timestr(ts, &st1->tb));
-
        stream_update_ts(sq, i, ts);
    }

@@ -345,39 +236,27 @@ int sq_send(SyncQueue *sq, unsigned int stream_idx, SyncQueueFrame frame)
    SyncQueueStream *st;
    SyncQueueFrame dst;
    int64_t ts;
-    int ret, nb_samples;
+    int ret;

    av_assert0(stream_idx < sq->nb_streams);
    st = &sq->streams[stream_idx];

+    av_assert0(st->tb.num > 0 && st->tb.den > 0);
+
    if (frame_null(sq, frame)) {
-        av_log(sq->logctx, AV_LOG_DEBUG, "sq: %u EOF\n", stream_idx);
        finish_stream(sq, stream_idx);
        return 0;
    }
    if (st->finished)
        return AVERROR_EOF;

-    tb_update(sq, st, frame);
-
    ret = objpool_get(sq->pool, (void**)&dst);
    if (ret < 0)
        return ret;

    frame_move(sq, dst, frame);

-    nb_samples = frame_samples(sq, dst);
-    // make sure frame duration is consistent with sample count
-    if (nb_samples) {
-        av_assert0(dst.f->sample_rate > 0);
-        dst.f->duration = av_rescale_q(nb_samples, (AVRational){ 1, dst.f->sample_rate },
-                                       dst.f->time_base);
-    }
-
-    ts = frame_end(sq, dst, 0);
-
-    av_log(sq->logctx, AV_LOG_DEBUG, "sq: send %u ts %s\n", stream_idx,
-           av_ts2timestr(ts, &st->tb));
+    ts = frame_ts(sq, dst);

    ret = av_fifo_write(st->fifo, &dst, 1);
    if (ret < 0) {
@@ -388,139 +267,13 @@ int sq_send(SyncQueue *sq, unsigned int stream_idx, SyncQueueFrame frame)

    stream_update_ts(sq, stream_idx, ts);

-    st->samples_queued += nb_samples;
-    st->samples_sent   += nb_samples;
-
-    if (st->frame_samples)
-        st->frames_sent = st->samples_sent / st->frame_samples;
-    else
-        st->frames_sent++;
-
-    if (st->frames_sent >= st->frames_max) {
-        av_log(sq->logctx, AV_LOG_DEBUG, "sq: %u frames_max %"PRIu64" reached\n",
-               stream_idx, st->frames_max);
-
+    st->frames_sent++;
+    if (st->frames_sent >= st->frames_max)
        finish_stream(sq, stream_idx);
-    }

    return 0;
 }

-static void offset_audio(AVFrame *f, int nb_samples)
-{
-    const int planar = av_sample_fmt_is_planar(f->format);
-    const int planes = planar ? f->ch_layout.nb_channels : 1;
-    const int    bps = av_get_bytes_per_sample(f->format);
-    const int offset = nb_samples * bps * (planar ? 1 : f->ch_layout.nb_channels);
-
-    av_assert0(bps > 0);
-    av_assert0(nb_samples < f->nb_samples);
-
-    for (int i = 0; i < planes; i++) {
-        f->extended_data[i] += offset;
-        if (i < FF_ARRAY_ELEMS(f->data))
-            f->data[i] = f->extended_data[i];
-    }
-    f->linesize[0] -= offset;
-    f->nb_samples  -= nb_samples;
-    f->duration     = av_rescale_q(f->nb_samples, (AVRational){ 1, f->sample_rate },
-                                   f->time_base);
-    f->pts         += av_rescale_q(nb_samples,    (AVRational){ 1, f->sample_rate },
-                                   f->time_base);
-}
-
-static int frame_is_aligned(const SyncQueue *sq, const AVFrame *frame)
-{
-    // only checks linesize[0], so only works for audio
-    av_assert0(frame->nb_samples > 0);
-    av_assert0(sq->align_mask);
-
-    // only check data[0], because we always offset all data pointers
-    // by the same offset, so if one is aligned, all are
-    if (!((uintptr_t)frame->data[0] & sq->align_mask) &&
-        !(frame->linesize[0]        & sq->align_mask) &&
-        frame->linesize[0] > sq->align_mask)
-        return 1;
-
-    return 0;
-}
-
-static int receive_samples(SyncQueue *sq, SyncQueueStream *st,
-                           AVFrame *dst, int nb_samples)
-{
-    SyncQueueFrame src;
-    int ret;
-
-    av_assert0(st->samples_queued >= nb_samples);
-
-    ret = av_fifo_peek(st->fifo, &src, 1, 0);
-    av_assert0(ret >= 0);
-
-    // peeked frame has enough samples and its data is aligned
-    // -> we can just make a reference and limit its sample count
-    if (src.f->nb_samples > nb_samples && frame_is_aligned(sq, src.f)) {
-        ret = av_frame_ref(dst, src.f);
-        if (ret < 0)
-            return ret;
-
-        dst->nb_samples = nb_samples;
-        offset_audio(src.f, nb_samples);
-        st->samples_queued -= nb_samples;
-
-        goto finish;
-    }
-
-    // otherwise allocate a new frame and copy the data
-    ret = av_channel_layout_copy(&dst->ch_layout, &src.f->ch_layout);
-    if (ret < 0)
-        return ret;
-
-    dst->format     = src.f->format;
-    dst->nb_samples = nb_samples;
-
-    ret = av_frame_get_buffer(dst, 0);
-    if (ret < 0)
-        goto fail;
-
-    ret = av_frame_copy_props(dst, src.f);
-    if (ret < 0)
-        goto fail;
-
-    dst->nb_samples = 0;
-    while (dst->nb_samples < nb_samples) {
-        int to_copy;
-
-        ret = av_fifo_peek(st->fifo, &src, 1, 0);
-        av_assert0(ret >= 0);
-
-        to_copy = FFMIN(nb_samples - dst->nb_samples, src.f->nb_samples);
-
-        av_samples_copy(dst->extended_data, src.f->extended_data, dst->nb_samples,
-                        0, to_copy, dst->ch_layout.nb_channels, dst->format);
-
-        if (to_copy < src.f->nb_samples)
-            offset_audio(src.f, to_copy);
-        else {
-            av_frame_unref(src.f);
-            objpool_release(sq->pool, (void**)&src);
-            av_fifo_drain2(st->fifo, 1);
-        }
-        st->samples_queued -= to_copy;
-
-        dst->nb_samples += to_copy;
-    }
-
-finish:
-    dst->duration   = av_rescale_q(nb_samples, (AVRational){ 1, dst->sample_rate },
-                                   dst->time_base);
-
-    return 0;
-
-fail:
-    av_frame_unref(dst);
-    return ret;
-}
-
 static int receive_for_stream(SyncQueue *sq, unsigned int stream_idx,
                              SyncQueueFrame frame)
 {
@@ -531,18 +284,13 @@ static int receive_for_stream(SyncQueue *sq, unsigned int stream_idx,
    av_assert0(stream_idx < sq->nb_streams);
    st = &sq->streams[stream_idx];

-    if (av_fifo_can_read(st->fifo) &&
-        (st->frame_samples <= st->samples_queued || st->finished)) {
-        int nb_samples = st->frame_samples;
+    if (av_fifo_can_read(st->fifo)) {
        SyncQueueFrame peek;
        int64_t ts;
        int cmp = 1;

-        if (st->finished)
-            nb_samples = FFMIN(nb_samples, st->samples_queued);
-
        av_fifo_peek(st->fifo, &peek, 1, 0);
-        ts = frame_end(sq, peek, nb_samples);
+        ts = frame_ts(sq, peek);

        /* check if this stream's tail timestamp does not overtake
         * the overall queue head */
@@ -551,28 +299,11 @@ static int receive_for_stream(SyncQueue *sq, unsigned int stream_idx,

        /* We can release frames that do not end after the queue head.
         * Frames with no timestamps are just passed through with no conditions.
-         * Frames are also passed through when there are no limiting streams.
         */
-        if (cmp <= 0 || ts == AV_NOPTS_VALUE || !sq->have_limiting) {
-            if (nb_samples &&
-                (nb_samples != peek.f->nb_samples || !frame_is_aligned(sq, peek.f))) {
-                int ret = receive_samples(sq, st, frame.f, nb_samples);
-                if (ret < 0)
-                    return ret;
-            } else {
-                frame_move(sq, frame, peek);
-                objpool_release(sq->pool, (void**)&peek);
-                av_fifo_drain2(st->fifo, 1);
-                av_assert0(st->samples_queued >= frame_samples(sq, frame));
-                st->samples_queued -= frame_samples(sq, frame);
-            }
-
-            av_log(sq->logctx, AV_LOG_DEBUG,
-                   "sq: receive %u ts %s queue head %d ts %s\n", stream_idx,
-                   av_ts2timestr(frame_end(sq, frame, 0), &st->tb),
-                   sq->head_stream,
-                   st_head ? av_ts2timestr(st_head->head_ts, &st_head->tb) : "N/A");
-
+        if (cmp <= 0 || ts == AV_NOPTS_VALUE) {
+            frame_move(sq, frame, peek);
+            objpool_release(sq->pool, (void**)&peek);
+            av_fifo_drain2(st->fifo, 1);
            return 0;
        }
    }
@@ -641,11 +372,24 @@ int sq_add_stream(SyncQueue *sq, int limiting)
    st->frames_max = UINT64_MAX;
    st->limiting   = limiting;

-    sq->have_limiting |= limiting;
-
    return sq->nb_streams++;
 }

+void sq_set_tb(SyncQueue *sq, unsigned int stream_idx, AVRational tb)
+{
+    SyncQueueStream *st;
+
+    av_assert0(stream_idx < sq->nb_streams);
+    st = &sq->streams[stream_idx];
+
+    av_assert0(!av_fifo_can_read(st->fifo));
+
+    if (st->head_ts != AV_NOPTS_VALUE)
+        st->head_ts = av_rescale_q(st->head_ts, st->tb, tb);
+
+    st->tb = tb;
+}
+
 void sq_limit_frames(SyncQueue *sq, unsigned int stream_idx, uint64_t frames)
 {
    SyncQueueStream *st;
@@ -658,21 +402,7 @@ void sq_limit_frames(SyncQueue *sq, unsigned int stream_idx, uint64_t frames)
        finish_stream(sq, stream_idx);
 }

-void sq_frame_samples(SyncQueue *sq, unsigned int stream_idx,
-                      int frame_samples)
-{
-    SyncQueueStream *st;
-
-    av_assert0(sq->type == SYNC_QUEUE_FRAMES);
-    av_assert0(stream_idx < sq->nb_streams);
-    st = &sq->streams[stream_idx];
-
-    st->frame_samples = frame_samples;
-
-    sq->align_mask = av_cpu_max_align() - 1;
-}
-
-SyncQueue *sq_alloc(enum SyncQueueType type, int64_t buf_size_us, void *logctx)
+SyncQueue *sq_alloc(enum SyncQueueType type, int64_t buf_size_us)
 {
    SyncQueue *sq = av_mallocz(sizeof(*sq));

@@ -681,7 +411,6 @@ SyncQueue *sq_alloc(enum SyncQueueType type, int64_t buf_size_us, void *logctx)

    sq->type                 = type;
    sq->buf_size_us          = buf_size_us;
-    sq->logctx               = logctx;

    sq->head_stream          = -1;
    sq->head_finished_stream = -1;
--- a/fftools/sync_queue.h
+++ b/fftools/sync_queue.h
@@ -38,11 +38,6 @@ typedef union SyncQueueFrame {
 #define SQFRAME(frame) ((SyncQueueFrame){ .f = (frame) })
 #define SQPKT(pkt)     ((SyncQueueFrame){ .p = (pkt) })

-/**
- * A sync queue provides timestamp synchronization between multiple streams.
- * Some of these streams are marked as "limiting", then the queue ensures no
- * stream gets ahead of any of the limiting streams.
- */
 typedef struct SyncQueue SyncQueue;

 /**
@@ -50,7 +45,7 @@ typedef struct SyncQueue SyncQueue;
 *
 * @param buf_size_us maximum duration that will be buffered in microseconds
 */
-SyncQueue *sq_alloc(enum SyncQueueType type, int64_t buf_size_us, void *logctx);
+SyncQueue *sq_alloc(enum SyncQueueType type, int64_t buf_size_us);
 void       sq_free(SyncQueue **sq);

 /**
@@ -64,6 +59,12 @@ void       sq_free(SyncQueue **sq);
 */
 int sq_add_stream(SyncQueue *sq, int limiting);

+/**
+ * Set the timebase for the stream with index stream_idx. Should be called
+ * before sending any frames for this stream.
+ */
+void sq_set_tb(SyncQueue *sq, unsigned int stream_idx, AVRational tb);
+
 /**
 * Limit the number of output frames for stream with index stream_idx
 * to max_frames.
@@ -71,16 +72,6 @@ int sq_add_stream(SyncQueue *sq, int limiting);
 void sq_limit_frames(SyncQueue *sq, unsigned int stream_idx,
                     uint64_t max_frames);

-/**
- * Set a constant output audio frame size, in samples. Can only be used with
- * SYNC_QUEUE_FRAMES queues and audio streams.
- *
- * All output frames will have exactly frame_samples audio samples, except
- * possibly for the last one, which may have fewer.
- */
-void sq_frame_samples(SyncQueue *sq, unsigned int stream_idx,
-                      int frame_samples);
-
 /**
 * Submit a frame for the stream with index stream_idx.
 *
--- a/libavcodec/012v.c
+++ b/libavcodec/012v.c
@@ -65,7 +65,7 @@ static int zero12v_decode_frame(AVCodecContext *avctx, AVFrame *pic,
        return ret;

    pic->pict_type = AV_PICTURE_TYPE_I;
-    pic->flags |= AV_FRAME_FLAG_KEY;
+    pic->key_frame = 1;

    line_end = avpkt->data + stride;
    for (line = 0; line < avctx->height; line++) {
--- a/libavcodec/4xm.c
+++ b/libavcodec/4xm.c
@@ -257,10 +257,10 @@ static av_cold void init_vlcs(void)
        for (j = 0; j < 4; j++) {
            block_type_vlc[i][j].table           = table[i][j];
            block_type_vlc[i][j].table_allocated = 32;
-            vlc_init(&block_type_vlc[i][j], BLOCK_TYPE_VLC_BITS, 7,
+            init_vlc(&block_type_vlc[i][j], BLOCK_TYPE_VLC_BITS, 7,
                     &block_type_tab[i][j][0][1], 2, 1,
                     &block_type_tab[i][j][0][0], 2, 1,
-                     VLC_INIT_USE_STATIC);
+                     INIT_VLC_USE_NEW_STATIC);
        }
    }
 }
@@ -706,8 +706,8 @@ static const uint8_t *read_huffman_tables(FourXContext *f,
        len_tab[j]  = len;
    }

-    ff_vlc_free(&f->pre_vlc);
-    if (vlc_init(&f->pre_vlc, ACDC_VLC_BITS, 257, len_tab, 1, 1,
+    ff_free_vlc(&f->pre_vlc);
+    if (init_vlc(&f->pre_vlc, ACDC_VLC_BITS, 257, len_tab, 1, 1,
                 bits_tab, 4, 4, 0))
        return NULL;

@@ -887,6 +887,8 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *picture,
        }

        if (i >= CFRAME_BUFFER_COUNT) {
+            if (free_index < 0)
+                return AVERROR_INVALIDDATA;
            i             = free_index;
            f->cfrm[i].id = id;
        }
@@ -957,10 +959,7 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *picture,
        return AVERROR_INVALIDDATA;
    }

-    if (picture->pict_type == AV_PICTURE_TYPE_I)
-        picture->flags |= AV_FRAME_FLAG_KEY;
-    else
-        picture->flags &= ~AV_FRAME_FLAG_KEY;
+    picture->key_frame = picture->pict_type == AV_PICTURE_TYPE_I;

    av_image_copy_plane(picture->data[0], picture->linesize[0],
                        (const uint8_t*)f->frame_buffer,  avctx->width * 2,
@@ -985,7 +984,7 @@ static av_cold int decode_end(AVCodecContext *avctx)
        av_freep(&f->cfrm[i].data);
        f->cfrm[i].allocated_size = 0;
    }
-    ff_vlc_free(&f->pre_vlc);
+    ff_free_vlc(&f->pre_vlc);

    return 0;
 }
--- a/libavcodec/8bps.c
+++ b/libavcodec/8bps.c
@@ -26,23 +26,29 @@
 *   http://www.pcisys.net/~melanson/codecs/
 *
 * Supports: PAL8 (RGB 8bpp, paletted)
- *         : GBRP (RGB 24bpp)
- *         : GBRAP (RGB 32bpp, 4th plane is alpha)
+ *         : BGR24 (RGB 24bpp) (can also output it as RGB32)
+ *         : RGB32 (RGB 32bpp, 4th plane is alpha)
 */

 #include <string.h>

-#include "libavutil/intreadwrite.h"
+#include "libavutil/bswap.h"
 #include "libavutil/internal.h"
 #include "avcodec.h"
 #include "codec_internal.h"
 #include "decode.h"

+
+static const enum AVPixelFormat pixfmt_rgb24[] = {
+    AV_PIX_FMT_BGR24, AV_PIX_FMT_0RGB32, AV_PIX_FMT_NONE };
+
 typedef struct EightBpsContext {
    AVCodecContext *avctx;

-    uint8_t planes;
-    uint8_t planemap[4];
+    unsigned char planes;
+    unsigned char planemap[4];
+
+    uint32_t pal[256];
 } EightBpsContext;

 static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
@@ -51,14 +57,15 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
    const uint8_t *buf = avpkt->data;
    int buf_size       = avpkt->size;
    EightBpsContext * const c = avctx->priv_data;
-    const uint8_t *encoded = buf;
-    uint8_t *pixptr, *pixptr_end;
+    const unsigned char *encoded = buf;
+    unsigned char *pixptr, *pixptr_end;
    unsigned int height = avctx->height; // Real image height
    unsigned int dlen, p, row;
-    const uint8_t *lp, *dp, *ep;
-    uint8_t count;
-    const uint8_t *planemap = c->planemap;
-    unsigned int planes = c->planes;
+    const unsigned char *lp, *dp, *ep;
+    unsigned char count;
+    unsigned int px_inc;
+    unsigned int planes     = c->planes;
+    unsigned char *planemap = c->planemap;
    int ret;

    if (buf_size < planes * height * 2)
@@ -72,18 +79,19 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
    /* Set data pointer after line lengths */
    dp = encoded + planes * (height << 1);

+    px_inc = planes + (avctx->pix_fmt == AV_PIX_FMT_0RGB32);
+
    for (p = 0; p < planes; p++) {
-        const int pi = planemap[p];
        /* Lines length pointer for this plane */
        lp = encoded + p * (height << 1);

        /* Decode a plane */
        for (row = 0; row < height; row++) {
-            pixptr = frame->data[pi] + row * frame->linesize[pi];
-            pixptr_end = pixptr + frame->linesize[pi];
+            pixptr = frame->data[0] + row * frame->linesize[0] + planemap[p];
+            pixptr_end = pixptr + frame->linesize[0];
            if (ep - lp < row * 2 + 2)
                return AVERROR_INVALIDDATA;
-            dlen = AV_RB16(lp + row * 2);
+            dlen = av_be2ne16(*(const unsigned short *)(lp + row * 2));
            /* Decode a row of this plane */
            while (dlen > 0) {
                if (ep - dp <= 1)
@@ -91,19 +99,22 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
                if ((count = *dp++) <= 127) {
                    count++;
                    dlen -= count + 1;
-                    if (pixptr_end - pixptr < count)
+                    if (pixptr_end - pixptr < count * px_inc)
                        break;
                    if (ep - dp < count)
                        return AVERROR_INVALIDDATA;
-                    memcpy(pixptr, dp, count);
-                    pixptr += count;
-                    dp += count;
+                    while (count--) {
+                        *pixptr = *dp++;
+                        pixptr += px_inc;
+                    }
                } else {
                    count = 257 - count;
-                    if (pixptr_end - pixptr < count)
+                    if (pixptr_end - pixptr < count * px_inc)
                        break;
-                    memset(pixptr, dp[0], count);
-                    pixptr += count;
+                    while (count--) {
+                        *pixptr = *dp;
+                        pixptr += px_inc;
+                    }
                    dp++;
                    dlen -= 2;
                }
@@ -112,14 +123,9 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
    }

    if (avctx->bits_per_coded_sample <= 8) {
-#if FF_API_PALETTE_HAS_CHANGED
-FF_DISABLE_DEPRECATION_WARNINGS
-        frame->palette_has_changed =
-#endif
-        ff_copy_palette(frame->data[1], avpkt, avctx);
-#if FF_API_PALETTE_HAS_CHANGED
-FF_ENABLE_DEPRECATION_WARNINGS
-#endif
+        frame->palette_has_changed = ff_copy_palette(c->pal, avpkt, avctx);
+
+        memcpy (frame->data[1], c->pal, AVPALETTE_SIZE);
    }

    *got_frame = 1;
@@ -141,15 +147,16 @@ static av_cold int decode_init(AVCodecContext *avctx)
        c->planemap[0] = 0; // 1st plane is palette indexes
        break;
    case 24:
-        avctx->pix_fmt = AV_PIX_FMT_GBRP;
+        avctx->pix_fmt = ff_get_format(avctx, pixfmt_rgb24);
        c->planes      = 3;
        c->planemap[0] = 2; // 1st plane is red
-        c->planemap[1] = 0; // 2nd plane is green
-        c->planemap[2] = 1; // 3rd plane is blue
+        c->planemap[1] = 1; // 2nd plane is green
+        c->planemap[2] = 0; // 3rd plane is blue
        break;
    case 32:
-        avctx->pix_fmt = AV_PIX_FMT_GBRAP;
+        avctx->pix_fmt = AV_PIX_FMT_RGB32;
        c->planes      = 4;
+        /* handle planemap setup later for decoding rgb24 data as rbg32 */
        break;
    default:
        av_log(avctx, AV_LOG_ERROR, "Error: Unsupported color depth: %u.\n",
@@ -157,11 +164,11 @@ static av_cold int decode_init(AVCodecContext *avctx)
        return AVERROR_INVALIDDATA;
    }

-    if (avctx->pix_fmt == AV_PIX_FMT_GBRAP) {
-        c->planemap[0] = 2; // 1st plane is red
-        c->planemap[1] = 0; // 2nd plane is green
-        c->planemap[2] = 1; // 3rd plane is blue
-        c->planemap[3] = 3; // 4th plane is alpha
+    if (avctx->pix_fmt == AV_PIX_FMT_RGB32) {
+        c->planemap[0] = HAVE_BIGENDIAN ? 1 : 2; // 1st plane is red
+        c->planemap[1] = HAVE_BIGENDIAN ? 2 : 1; // 2nd plane is green
+        c->planemap[2] = HAVE_BIGENDIAN ? 3 : 0; // 3rd plane is blue
+        c->planemap[3] = HAVE_BIGENDIAN ? 0 : 3; // 4th plane is alpha
    }
    return 0;
 }
--- a/libavcodec/Makefile
+++ b/libavcodec/Makefile
@@ -32,7 +32,6 @@ OBJS = ac3_parser.o                                                     \
       allcodecs.o                                                      \
       avcodec.o                                                        \
       avdct.o                                                          \
-       avfft.o                                                          \
       avpacket.o                                                       \
       bitstream.o                                                      \
       bitstream_filters.o                                              \
@@ -56,7 +55,6 @@ OBJS = ac3_parser.o                                                     \
       profiles.o                                                       \
       qsv_api.o                                                        \
       raw.o                                                            \
-       refstruct.o                                                      \
       utils.o                                                          \
       version.o                                                        \
       vlc.o                                                            \
@@ -78,19 +76,21 @@ OBJS-$(CONFIG_CBS)                     += cbs.o cbs_bsf.o
 OBJS-$(CONFIG_CBS_AV1)                 += cbs_av1.o
 OBJS-$(CONFIG_CBS_H264)                += cbs_h2645.o cbs_sei.o h2645_parse.o
 OBJS-$(CONFIG_CBS_H265)                += cbs_h2645.o cbs_sei.o h2645_parse.o
-OBJS-$(CONFIG_CBS_H266)                += cbs_h2645.o cbs_sei.o h2645_parse.o
 OBJS-$(CONFIG_CBS_JPEG)                += cbs_jpeg.o
 OBJS-$(CONFIG_CBS_MPEG2)               += cbs_mpeg2.o
 OBJS-$(CONFIG_CBS_VP9)                 += cbs_vp9.o
 OBJS-$(CONFIG_CRYSTALHD)               += crystalhd.o
+OBJS-$(CONFIG_DCT)                     += dct.o dct32_fixed.o dct32_float.o
 OBJS-$(CONFIG_DEFLATE_WRAPPER)         += zlib_wrapper.o
 OBJS-$(CONFIG_DOVI_RPU)                += dovi_rpu.o
 OBJS-$(CONFIG_ERROR_RESILIENCE)        += error_resilience.o
-OBJS-$(CONFIG_EVCPARSE)                += evc_parse.o evc_ps.o
 OBJS-$(CONFIG_EXIF)                    += exif.o tiff_common.o
 OBJS-$(CONFIG_FAANDCT)                 += faandct.o
 OBJS-$(CONFIG_FAANIDCT)                += faanidct.o
 OBJS-$(CONFIG_FDCTDSP)                 += fdctdsp.o jfdctfst.o jfdctint.o
+FFT-OBJS-$(CONFIG_HARDCODED_TABLES)    += cos_tables.o
+OBJS-$(CONFIG_FFT)                     += avfft.o fft_float.o fft_fixed_32.o \
+                                          fft_init_table.o $(FFT-OBJS-yes)
 OBJS-$(CONFIG_FMTCONVERT)              += fmtconvert.o
 OBJS-$(CONFIG_GOLOMB)                  += golomb.o
 OBJS-$(CONFIG_H263DSP)                 += h263dsp.o
@@ -104,7 +104,7 @@ OBJS-$(CONFIG_H264_SEI)                += h264_sei.o h2645_sei.o
 OBJS-$(CONFIG_HEVCPARSE)               += hevc_parse.o hevc_ps.o hevc_data.o \
                                          h2645data.o h2645_parse.o h2645_vui.o
 OBJS-$(CONFIG_HEVC_SEI)                += hevc_sei.o h2645_sei.o \
-                                          dynamic_hdr_vivid.o
+                                          dynamic_hdr10_plus.o dynamic_hdr_vivid.o
 OBJS-$(CONFIG_HPELDSP)                 += hpeldsp.o
 OBJS-$(CONFIG_HUFFMAN)                 += huffman.o
 OBJS-$(CONFIG_HUFFYUVDSP)              += huffyuvdsp.o
@@ -123,6 +123,7 @@ OBJS-$(CONFIG_LLVIDENCDSP)             += lossless_videoencdsp.o
 OBJS-$(CONFIG_LPC)                     += lpc.o
 OBJS-$(CONFIG_LSP)                     += lsp.o
 OBJS-$(CONFIG_LZF)                     += lzf.o
+OBJS-$(CONFIG_MDCT)                    += mdct_float.o mdct_fixed_32.o
 OBJS-$(CONFIG_ME_CMP)                  += me_cmp.o
 OBJS-$(CONFIG_MEDIACODEC)              += mediacodecdec_common.o mediacodec_surface.o mediacodec_wrapper.o mediacodec_sw_buffer.o
 OBJS-$(CONFIG_MPEG_ER)                 += mpeg_er.o
@@ -131,8 +132,7 @@ OBJS-$(CONFIG_MPEGAUDIO)               += mpegaudio.o mpegaudiodec_common.o \
 OBJS-$(CONFIG_MPEGAUDIODSP)            += mpegaudiodsp.o                \
                                          mpegaudiodsp_data.o           \
                                          mpegaudiodsp_fixed.o          \
-                                          mpegaudiodsp_float.o          \
-                                          dct32_fixed.o dct32_float.o
+                                          mpegaudiodsp_float.o
 OBJS-$(CONFIG_MPEGAUDIOHEADER)         += mpegaudiodecheader.o mpegaudiotabs.o
 OBJS-$(CONFIG_MPEG4AUDIO)              += mpeg4audio.o mpeg4audio_sample_rates.o
 OBJS-$(CONFIG_MPEGVIDEO)               += mpegvideo.o rl.o \
@@ -154,6 +154,7 @@ OBJS-$(CONFIG_QSV)                     += qsv.o
 OBJS-$(CONFIG_QSVDEC)                  += qsvdec.o
 OBJS-$(CONFIG_QSVENC)                  += qsvenc.o
 OBJS-$(CONFIG_RANGECODER)              += rangecoder.o
+OBJS-$(CONFIG_RDFT)                    += rdft.o
 OBJS-$(CONFIG_RV34DSP)                 += rv34dsp.o
 OBJS-$(CONFIG_SINEWIN)                 += sinewin.o
 OBJS-$(CONFIG_SNAPPY)                  += snappy.o
@@ -252,10 +253,8 @@ OBJS-$(CONFIG_AURA2_DECODER)           += aura.o
 OBJS-$(CONFIG_AV1_DECODER)             += av1dec.o
 OBJS-$(CONFIG_AV1_CUVID_DECODER)       += cuviddec.o
 OBJS-$(CONFIG_AV1_MEDIACODEC_DECODER)  += mediacodecdec.o
-OBJS-$(CONFIG_AV1_MEDIACODEC_ENCODER)  += mediacodecenc.o
 OBJS-$(CONFIG_AV1_NVENC_ENCODER)       += nvenc_av1.o nvenc.o
 OBJS-$(CONFIG_AV1_QSV_ENCODER)         += qsvenc_av1.o
-OBJS-$(CONFIG_AV1_VAAPI_ENCODER)       += vaapi_encode_av1.o av1_levels.o
 OBJS-$(CONFIG_AVRN_DECODER)            += avrndec.o
 OBJS-$(CONFIG_AVRP_DECODER)            += r210dec.o
 OBJS-$(CONFIG_AVRP_ENCODER)            += r210enc.o
@@ -470,7 +469,7 @@ OBJS-$(CONFIG_JACOSUB_DECODER)         += jacosubdec.o ass.o
 OBJS-$(CONFIG_JPEG2000_ENCODER)        += j2kenc.o mqcenc.o mqc.o jpeg2000.o \
                                          jpeg2000dwt.o
 OBJS-$(CONFIG_JPEG2000_DECODER)        += jpeg2000dec.o jpeg2000.o jpeg2000dsp.o \
-                                          jpeg2000dwt.o mqcdec.o mqc.o jpeg2000htdec.o
+                                          jpeg2000dwt.o mqcdec.o mqc.o
 OBJS-$(CONFIG_JPEGLS_DECODER)          += jpeglsdec.o jpegls.o
 OBJS-$(CONFIG_JPEGLS_ENCODER)          += jpeglsenc.o jpegls.o
 OBJS-$(CONFIG_JV_DECODER)              += jvdec.o
@@ -543,7 +542,6 @@ OBJS-$(CONFIG_MPEG4_DECODER)           += mpeg4videodsp.o xvididct.o
 OBJS-$(CONFIG_MPEG4_ENCODER)           += mpeg4videoenc.o
 OBJS-$(CONFIG_MPEG4_CUVID_DECODER)     += cuviddec.o
 OBJS-$(CONFIG_MPEG4_MEDIACODEC_DECODER) += mediacodecdec.o
-OBJS-$(CONFIG_MPEG4_MEDIACODEC_ENCODER) += mediacodecenc.o
 OBJS-$(CONFIG_MPEG4_OMX_ENCODER)       += omx.o
 OBJS-$(CONFIG_MPEG4_V4L2M2M_DECODER)   += v4l2_m2m_dec.o
 OBJS-$(CONFIG_MPEG4_V4L2M2M_ENCODER)   += v4l2_m2m_enc.o
@@ -552,7 +550,6 @@ OBJS-$(CONFIG_MSA1_DECODER)            += mss3.o
 OBJS-$(CONFIG_MSCC_DECODER)            += mscc.o
 OBJS-$(CONFIG_MSNSIREN_DECODER)        += siren.o
 OBJS-$(CONFIG_MSP2_DECODER)            += msp2dec.o
-OBJS-$(CONFIG_MSRLE_ENCODER)           += msrleenc.o
 OBJS-$(CONFIG_MSRLE_DECODER)           += msrle.o msrledec.o
 OBJS-$(CONFIG_MSS1_DECODER)            += mss1.o mss12.o
 OBJS-$(CONFIG_MSS2_DECODER)            += mss2.o mss12.o mss2dsp.o wmv2data.o
@@ -577,7 +574,6 @@ OBJS-$(CONFIG_OPUS_DECODER)            += opusdec.o opusdec_celt.o opus_celt.o \
                                          opusdsp.o opus_parse.o opus_rc.o
 OBJS-$(CONFIG_OPUS_ENCODER)            += opusenc.o opusenc_psy.o opus_celt.o \
                                          opus_pvq.o opus_rc.o opustab.o
-OBJS-$(CONFIG_OSQ_DECODER)             += osq.o
 OBJS-$(CONFIG_PAF_AUDIO_DECODER)       += pafaudio.o
 OBJS-$(CONFIG_PAF_VIDEO_DECODER)       += pafvideo.o
 OBJS-$(CONFIG_PAM_DECODER)             += pnmdec.o pnm.o
@@ -586,7 +582,6 @@ OBJS-$(CONFIG_PBM_DECODER)             += pnmdec.o pnm.o
 OBJS-$(CONFIG_PBM_ENCODER)             += pnmenc.o
 OBJS-$(CONFIG_PCX_DECODER)             += pcx.o
 OBJS-$(CONFIG_PCX_ENCODER)             += pcxenc.o
-OBJS-$(CONFIG_PDV_DECODER)             += pdvdec.o
 OBJS-$(CONFIG_PFM_DECODER)             += pnmdec.o pnm.o
 OBJS-$(CONFIG_PFM_ENCODER)             += pnmenc.o
 OBJS-$(CONFIG_PGM_DECODER)             += pnmdec.o pnm.o
@@ -645,7 +640,6 @@ OBJS-$(CONFIG_ROQ_DPCM_ENCODER)        += roqaudioenc.o
 OBJS-$(CONFIG_RPZA_DECODER)            += rpza.o
 OBJS-$(CONFIG_RPZA_ENCODER)            += rpzaenc.o
 OBJS-$(CONFIG_RSCC_DECODER)            += rscc.o
-OBJS-$(CONFIG_RTV1_DECODER)            += rtv1.o
 OBJS-$(CONFIG_RV10_DECODER)            += rv10.o
 OBJS-$(CONFIG_RV10_ENCODER)            += rv10enc.o
 OBJS-$(CONFIG_RV20_DECODER)            += rv10.o
@@ -755,7 +749,6 @@ OBJS-$(CONFIG_VC2_ENCODER)             += vc2enc.o vc2enc_dwt.o diractab.o
 OBJS-$(CONFIG_VCR1_DECODER)            += vcr1.o
 OBJS-$(CONFIG_VMDAUDIO_DECODER)        += vmdaudio.o
 OBJS-$(CONFIG_VMDVIDEO_DECODER)        += vmdvideo.o
-OBJS-$(CONFIG_VMIX_DECODER)            += vmixdec.o
 OBJS-$(CONFIG_VMNC_DECODER)            += vmnc.o
 OBJS-$(CONFIG_VNULL_DECODER)           += null.o
 OBJS-$(CONFIG_VNULL_ENCODER)           += null.o
@@ -767,11 +760,10 @@ OBJS-$(CONFIG_VP3_DECODER)             += vp3.o jpegquanttables.o
 OBJS-$(CONFIG_VP5_DECODER)             += vp5.o vp56.o vp56data.o vpx_rac.o
 OBJS-$(CONFIG_VP6_DECODER)             += vp6.o vp56.o vp56data.o \
                                          vp6dsp.o vpx_rac.o
-OBJS-$(CONFIG_VP7_DECODER)             += vp8.o vp8data.o vpx_rac.o
-OBJS-$(CONFIG_VP8_DECODER)             += vp8.o vp8data.o vpx_rac.o
+OBJS-$(CONFIG_VP7_DECODER)             += vp8.o vpx_rac.o
+OBJS-$(CONFIG_VP8_DECODER)             += vp8.o vpx_rac.o
 OBJS-$(CONFIG_VP8_CUVID_DECODER)       += cuviddec.o
 OBJS-$(CONFIG_VP8_MEDIACODEC_DECODER)  += mediacodecdec.o
-OBJS-$(CONFIG_VP8_MEDIACODEC_ENCODER)  += mediacodecenc.o
 OBJS-$(CONFIG_VP8_QSV_DECODER)         += qsvdec.o
 OBJS-$(CONFIG_VP8_RKMPP_DECODER)       += rkmppdec.o
 OBJS-$(CONFIG_VP8_VAAPI_ENCODER)       += vaapi_encode_vp8.o
@@ -782,7 +774,6 @@ OBJS-$(CONFIG_VP9_DECODER)             += vp9.o vp9data.o vp9dsp.o vp9lpf.o vp9r
                                          vp9dsp_8bpp.o vp9dsp_10bpp.o vp9dsp_12bpp.o
 OBJS-$(CONFIG_VP9_CUVID_DECODER)       += cuviddec.o
 OBJS-$(CONFIG_VP9_MEDIACODEC_DECODER)  += mediacodecdec.o
-OBJS-$(CONFIG_VP9_MEDIACODEC_ENCODER)  += mediacodecenc.o
 OBJS-$(CONFIG_VP9_RKMPP_DECODER)       += rkmppdec.o
 OBJS-$(CONFIG_VP9_VAAPI_ENCODER)       += vaapi_encode_vp9.o
 OBJS-$(CONFIG_VP9_QSV_ENCODER)         += qsvenc_vp9.o
@@ -986,14 +977,12 @@ OBJS-$(CONFIG_NVDEC)                      += nvdec.o
 OBJS-$(CONFIG_VAAPI)                      += vaapi_decode.o
 OBJS-$(CONFIG_VIDEOTOOLBOX)               += videotoolbox.o
 OBJS-$(CONFIG_VDPAU)                      += vdpau.o
-OBJS-$(CONFIG_VULKAN)                     += vulkan.o vulkan_video.o

 OBJS-$(CONFIG_AV1_D3D11VA_HWACCEL)        += dxva2_av1.o
 OBJS-$(CONFIG_AV1_DXVA2_HWACCEL)          += dxva2_av1.o
 OBJS-$(CONFIG_AV1_NVDEC_HWACCEL)          += nvdec_av1.o
 OBJS-$(CONFIG_AV1_VAAPI_HWACCEL)          += vaapi_av1.o
 OBJS-$(CONFIG_AV1_VDPAU_HWACCEL)          += vdpau_av1.o
-OBJS-$(CONFIG_AV1_VULKAN_HWACCEL)         += vulkan_av1.o
 OBJS-$(CONFIG_H263_VAAPI_HWACCEL)         += vaapi_mpeg4.o
 OBJS-$(CONFIG_H263_VIDEOTOOLBOX_HWACCEL)  += videotoolbox.o
 OBJS-$(CONFIG_H264_D3D11VA_HWACCEL)       += dxva2_h264.o
@@ -1003,14 +992,12 @@ OBJS-$(CONFIG_H264_QSV_HWACCEL)           += qsvdec.o
 OBJS-$(CONFIG_H264_VAAPI_HWACCEL)         += vaapi_h264.o
 OBJS-$(CONFIG_H264_VDPAU_HWACCEL)         += vdpau_h264.o
 OBJS-$(CONFIG_H264_VIDEOTOOLBOX_HWACCEL)  += videotoolbox.o
-OBJS-$(CONFIG_H264_VULKAN_HWACCEL)        += vulkan_decode.o vulkan_h264.o
 OBJS-$(CONFIG_HEVC_D3D11VA_HWACCEL)       += dxva2_hevc.o
 OBJS-$(CONFIG_HEVC_DXVA2_HWACCEL)         += dxva2_hevc.o
 OBJS-$(CONFIG_HEVC_NVDEC_HWACCEL)         += nvdec_hevc.o
 OBJS-$(CONFIG_HEVC_QSV_HWACCEL)           += qsvdec.o
 OBJS-$(CONFIG_HEVC_VAAPI_HWACCEL)         += vaapi_hevc.o h265_profile_level.o
 OBJS-$(CONFIG_HEVC_VDPAU_HWACCEL)         += vdpau_hevc.o h265_profile_level.o
-OBJS-$(CONFIG_HEVC_VULKAN_HWACCEL)        += vulkan_decode.o vulkan_hevc.o
 OBJS-$(CONFIG_MJPEG_NVDEC_HWACCEL)        += nvdec_mjpeg.o
 OBJS-$(CONFIG_MJPEG_VAAPI_HWACCEL)        += vaapi_mjpeg.o
 OBJS-$(CONFIG_MPEG1_NVDEC_HWACCEL)        += nvdec_mpeg12.o
@@ -1055,8 +1042,6 @@ STLIBOBJS-$(CONFIG_AVFORMAT)           += to_upper4.o
 STLIBOBJS-$(CONFIG_ISO_MEDIA)          += mpegaudiotabs.o
 STLIBOBJS-$(CONFIG_FLV_MUXER)          += mpeg4audio_sample_rates.o
 STLIBOBJS-$(CONFIG_HLS_DEMUXER)        += ac3_channel_layout_tab.o
-STLIBOBJS-$(CONFIG_IMAGE_JPEGXL_PIPE_DEMUXER) += jpegxl_parse.o
-STLIBOBJS-$(CONFIG_JPEGXL_ANIM_DEMUXER)       += jpegxl_parse.o
 STLIBOBJS-$(CONFIG_MATROSKA_DEMUXER)   += mpeg4audio_sample_rates.o
 STLIBOBJS-$(CONFIG_MOV_DEMUXER)        += ac3_channel_layout_tab.o
 STLIBOBJS-$(CONFIG_MXF_MUXER)          += golomb.o
@@ -1094,11 +1079,10 @@ OBJS-$(CONFIG_PCM_MULAW_AT_ENCODER)       += audiotoolboxenc.o
 OBJS-$(CONFIG_LIBAOM_AV1_DECODER)         += libaomdec.o libaom.o
 OBJS-$(CONFIG_LIBAOM_AV1_ENCODER)         += libaomenc.o libaom.o
 OBJS-$(CONFIG_LIBARIBB24_DECODER)         += libaribb24.o ass.o
-OBJS-$(CONFIG_LIBARIBCAPTION_DECODER)     += libaribcaption.o ass.o
 OBJS-$(CONFIG_LIBCELT_DECODER)            += libcelt_dec.o
 OBJS-$(CONFIG_LIBCODEC2_DECODER)          += libcodec2.o
 OBJS-$(CONFIG_LIBCODEC2_ENCODER)          += libcodec2.o
-OBJS-$(CONFIG_LIBDAV1D_DECODER)           += libdav1d.o av1_parse.o
+OBJS-$(CONFIG_LIBDAV1D_DECODER)           += libdav1d.o
 OBJS-$(CONFIG_LIBDAVS2_DECODER)           += libdavs2.o
 OBJS-$(CONFIG_LIBFDK_AAC_DECODER)         += libfdk-aacdec.o
 OBJS-$(CONFIG_LIBFDK_AAC_ENCODER)         += libfdk-aacenc.o
@@ -1117,6 +1101,7 @@ OBJS-$(CONFIG_LIBOPENCORE_AMRNB_ENCODER)  += libopencore-amr.o
 OBJS-$(CONFIG_LIBOPENCORE_AMRWB_DECODER)  += libopencore-amr.o
 OBJS-$(CONFIG_LIBOPENH264_DECODER)        += libopenh264dec.o libopenh264.o
 OBJS-$(CONFIG_LIBOPENH264_ENCODER)        += libopenh264enc.o libopenh264.o
+OBJS-$(CONFIG_LIBOPENJPEG_DECODER)        += libopenjpegdec.o
 OBJS-$(CONFIG_LIBOPENJPEG_ENCODER)        += libopenjpegenc.o
 OBJS-$(CONFIG_LIBOPUS_DECODER)            += libopusdec.o libopus.o     \
                                             vorbis_data.o
@@ -1136,8 +1121,8 @@ OBJS-$(CONFIG_LIBVORBIS_ENCODER)          += libvorbisenc.o \
                                             vorbis_data.o
 OBJS-$(CONFIG_LIBVPX_VP8_DECODER)         += libvpxdec.o
 OBJS-$(CONFIG_LIBVPX_VP8_ENCODER)         += libvpxenc.o
-OBJS-$(CONFIG_LIBVPX_VP9_DECODER)         += libvpxdec.o
-OBJS-$(CONFIG_LIBVPX_VP9_ENCODER)         += libvpxenc.o
+OBJS-$(CONFIG_LIBVPX_VP9_DECODER)         += libvpxdec.o libvpx.o
+OBJS-$(CONFIG_LIBVPX_VP9_ENCODER)         += libvpxenc.o libvpx.o
 OBJS-$(CONFIG_LIBWEBP_ENCODER)            += libwebpenc_common.o libwebpenc.o
 OBJS-$(CONFIG_LIBWEBP_ANIM_ENCODER)       += libwebpenc_common.o libwebpenc_animencoder.o
 OBJS-$(CONFIG_LIBX262_ENCODER)            += libx264.o
@@ -1155,7 +1140,7 @@ OBJS-$(CONFIG_AC3_PARSER)              += aac_ac3_parser.o ac3tab.o \
                                          ac3_channel_layout_tab.o
 OBJS-$(CONFIG_ADX_PARSER)              += adx_parser.o
 OBJS-$(CONFIG_AMR_PARSER)              += amr_parser.o
-OBJS-$(CONFIG_AV1_PARSER)              += av1_parser.o av1_parse.o
+OBJS-$(CONFIG_AV1_PARSER)              += av1_parser.o
 OBJS-$(CONFIG_AVS2_PARSER)             += avs2.o avs2_parser.o
 OBJS-$(CONFIG_AVS3_PARSER)             += avs3_parser.o
 OBJS-$(CONFIG_BMP_PARSER)              += bmp_parser.o
@@ -1172,7 +1157,6 @@ OBJS-$(CONFIG_DVAUDIO_PARSER)          += dvaudio_parser.o
 OBJS-$(CONFIG_DVBSUB_PARSER)           += dvbsub_parser.o
 OBJS-$(CONFIG_DVD_NAV_PARSER)          += dvd_nav_parser.o
 OBJS-$(CONFIG_DVDSUB_PARSER)           += dvdsub_parser.o
-OBJS-$(CONFIG_EVC_PARSER)              += evc_parser.o
 OBJS-$(CONFIG_FLAC_PARSER)             += flac_parser.o flacdata.o flac.o
 OBJS-$(CONFIG_FTR_PARSER)              += ftr_parser.o
 OBJS-$(CONFIG_G723_1_PARSER)           += g723_1_parser.o
@@ -1186,7 +1170,6 @@ OBJS-$(CONFIG_HEVC_PARSER)             += hevc_parser.o hevc_data.o
 OBJS-$(CONFIG_HDR_PARSER)              += hdr_parser.o
 OBJS-$(CONFIG_IPU_PARSER)              += ipu_parser.o
 OBJS-$(CONFIG_JPEG2000_PARSER)         += jpeg2000_parser.o
-OBJS-$(CONFIG_JPEGXL_PARSER)           += jpegxl_parser.o jpegxl_parse.o
 OBJS-$(CONFIG_MISC4_PARSER)            += misc4_parser.o
 OBJS-$(CONFIG_MJPEG_PARSER)            += mjpeg_parser.o
 OBJS-$(CONFIG_MLP_PARSER)              += mlp_parse.o mlp_parser.o mlp.o
@@ -1201,7 +1184,8 @@ OBJS-$(CONFIG_OPUS_PARSER)             += opus_parser.o opus_parse.o \
 OBJS-$(CONFIG_PNG_PARSER)              += png_parser.o
 OBJS-$(CONFIG_PNM_PARSER)              += pnm_parser.o pnm.o
 OBJS-$(CONFIG_QOI_PARSER)              += qoi_parser.o
-OBJS-$(CONFIG_RV34_PARSER)             += rv34_parser.o
+OBJS-$(CONFIG_RV30_PARSER)             += rv34_parser.o
+OBJS-$(CONFIG_RV40_PARSER)             += rv34_parser.o
 OBJS-$(CONFIG_SBC_PARSER)              += sbc_parser.o
 OBJS-$(CONFIG_SIPR_PARSER)             += sipr_parser.o
 OBJS-$(CONFIG_TAK_PARSER)              += tak_parser.o tak.o
@@ -1210,7 +1194,6 @@ OBJS-$(CONFIG_VC1_PARSER)              += vc1_parser.o vc1.o vc1data.o  \
 OBJS-$(CONFIG_VP3_PARSER)              += vp3_parser.o
 OBJS-$(CONFIG_VP8_PARSER)              += vp8_parser.o
 OBJS-$(CONFIG_VP9_PARSER)              += vp9_parser.o
-OBJS-$(CONFIG_VVC_PARSER)              += vvc_parser.o
 OBJS-$(CONFIG_WEBP_PARSER)             += webp_parser.o
 OBJS-$(CONFIG_XBM_PARSER)              += xbm_parser.o
 OBJS-$(CONFIG_XMA_PARSER)              += xma_parser.o
@@ -1262,9 +1245,6 @@ OBJS-$(CONFIG_VP9_METADATA_BSF)           += vp9_metadata_bsf.o
 OBJS-$(CONFIG_VP9_RAW_REORDER_BSF)        += vp9_raw_reorder_bsf.o
 OBJS-$(CONFIG_VP9_SUPERFRAME_BSF)         += vp9_superframe_bsf.o
 OBJS-$(CONFIG_VP9_SUPERFRAME_SPLIT_BSF)   += vp9_superframe_split_bsf.o
-OBJS-$(CONFIG_VVC_METADATA_BSF)           += h266_metadata_bsf.o
-OBJS-$(CONFIG_VVC_MP4TOANNEXB_BSF)        += vvc_mp4toannexb_bsf.o
-OBJS-$(CONFIG_EVC_FRAME_MERGE_BSF)        += evc_frame_merge_bsf.o

 # thread libraries
 OBJS-$(HAVE_LIBC_MSVCRT)               += file_open.o
@@ -1284,7 +1264,6 @@ SKIPHEADERS                            += %_tablegen.h                  \
                                          aacenc_quantization.h         \
                                          aacenc_quantization_misc.h    \
                                          bitstream_template.h          \
-                                          vulkan_video_codec_av1std.h   \
                                          $(ARCH)/vpx_arith.h          \

 SKIPHEADERS-$(CONFIG_AMF)              += amfenc.h
@@ -1306,7 +1285,6 @@ SKIPHEADERS-$(CONFIG_XVMC)             += xvmc.h
 SKIPHEADERS-$(CONFIG_VAAPI)            += vaapi_decode.h vaapi_hevc.h vaapi_encode.h
 SKIPHEADERS-$(CONFIG_VDPAU)            += vdpau.h vdpau_internal.h
 SKIPHEADERS-$(CONFIG_VIDEOTOOLBOX)     += videotoolbox.h vt_internal.h
-SKIPHEADERS-$(CONFIG_VULKAN)           += vulkan.h vulkan_video.h vulkan_decode.h vulkan_video_codec_av1std_decode.h
 SKIPHEADERS-$(CONFIG_V4L2_M2M)         += v4l2_buffers.h v4l2_context.h v4l2_m2m.h
 SKIPHEADERS-$(CONFIG_ZLIB)             += zlib_wrapper.h

@@ -1320,8 +1298,9 @@ TESTPROGS = avcodec                                                     \
            jpeg2000dwt                                                 \
            mathops                                                    \

-TESTPROGS-$(CONFIG_AV1_VAAPI_ENCODER)     += av1_levels
 TESTPROGS-$(CONFIG_CABAC)                 += cabac
+TESTPROGS-$(CONFIG_DCT)                   += avfft
+TESTPROGS-$(CONFIG_FFT)                   += fft fft-fixed32
 TESTPROGS-$(CONFIG_GOLOMB)                += golomb
 TESTPROGS-$(CONFIG_IDCTDSP)               += dct
 TESTPROGS-$(CONFIG_IIRFILTER)             += iirfilter
@@ -1341,6 +1320,7 @@ HOSTPROGS = aacps_tablegen                                              \
            aacps_fixed_tablegen                                        \
            cbrt_tablegen                                               \
            cbrt_fixed_tablegen                                         \
+            cos_tablegen                                                \
            dv_tablegen                                                 \
            motionpixels_tablegen                                       \
            mpegaudio_tablegen                                          \
@@ -1355,6 +1335,12 @@ CLEANFILES = *_tables.c *_tables.h *_tablegen$(HOSTEXESUF)
 $(SUBDIR)tests/dct$(EXESUF): $(SUBDIR)dctref.o $(SUBDIR)aandcttab.o
 $(SUBDIR)dv_tablegen$(HOSTEXESUF): $(SUBDIR)dvdata_host.o

+TRIG_TABLES  = cos cos_fixed sin
+TRIG_TABLES := $(TRIG_TABLES:%=$(SUBDIR)%_tables.c)
+
+$(TRIG_TABLES): $(SUBDIR)%_tables.c: $(SUBDIR)cos_tablegen$(HOSTEXESUF)
+	$(M)./$< $* > $@
+
 ifdef CONFIG_SMALL
 $(SUBDIR)%_tablegen$(HOSTEXESUF): HOSTCFLAGS += -DCONFIG_SMALL=1
 else
--- a/libavcodec/aacdec_template.c
+++ b/libavcodec/aacdec_template.c
@@ -1133,14 +1133,14 @@ static av_cold void aac_static_table_init(void)
    for (unsigned i = 0, offset = 0; i < 11; i++) {
        vlc_spectral[i].table           = &vlc_buf[offset];
        vlc_spectral[i].table_allocated = FF_ARRAY_ELEMS(vlc_buf) - offset;
-        ff_vlc_init_sparse(&vlc_spectral[i], 8, ff_aac_spectral_sizes[i],
+        ff_init_vlc_sparse(&vlc_spectral[i], 8, ff_aac_spectral_sizes[i],
                           ff_aac_spectral_bits[i],       sizeof(ff_aac_spectral_bits[i][0]),
                                                          sizeof(ff_aac_spectral_bits[i][0]),
                           ff_aac_spectral_codes[i],      sizeof(ff_aac_spectral_codes[i][0]),
                                                          sizeof(ff_aac_spectral_codes[i][0]),
                           ff_aac_codebook_vector_idx[i], sizeof(ff_aac_codebook_vector_idx[i][0]),
                                                          sizeof(ff_aac_codebook_vector_idx[i][0]),
-                 VLC_INIT_STATIC_OVERLONG);
+                 INIT_VLC_STATIC_OVERLONG);
        offset += vlc_spectral[i].table_size;
    }

@@ -1148,7 +1148,7 @@ static av_cold void aac_static_table_init(void)

    ff_aac_tableinit();

-    VLC_INIT_STATIC(&vlc_scalefactors, 7,
+    INIT_VLC_STATIC(&vlc_scalefactors, 7,
                    FF_ARRAY_ELEMS(ff_aac_scalefactor_code),
                    ff_aac_scalefactor_bits,
                    sizeof(ff_aac_scalefactor_bits[0]),
@@ -1159,8 +1159,8 @@ static av_cold void aac_static_table_init(void)
                    352);

    // window initialization
-    AAC_RENAME(avpriv_kbd_window_init)(AAC_RENAME(aac_kbd_long_960), 4.0, 960);
-    AAC_RENAME(avpriv_kbd_window_init)(AAC_RENAME(aac_kbd_short_120), 6.0, 120);
+    AAC_RENAME(ff_kbd_window_init)(AAC_RENAME(aac_kbd_long_960), 4.0, 960);
+    AAC_RENAME(ff_kbd_window_init)(AAC_RENAME(aac_kbd_short_120), 6.0, 120);

 #if !USE_FIXED
    AAC_RENAME(ff_sine_window_init)(AAC_RENAME(sine_960), 960);
@@ -1168,8 +1168,8 @@ static av_cold void aac_static_table_init(void)
    AAC_RENAME(ff_init_ff_sine_windows)(9);
    ff_aac_float_common_init();
 #else
-    AAC_RENAME(avpriv_kbd_window_init)(AAC_RENAME2(aac_kbd_long_1024), 4.0, 1024);
-    AAC_RENAME(avpriv_kbd_window_init)(AAC_RENAME2(aac_kbd_short_128), 6.0, 128);
+    AAC_RENAME(ff_kbd_window_init)(AAC_RENAME2(aac_kbd_long_1024), 4.0, 1024);
+    AAC_RENAME(ff_kbd_window_init)(AAC_RENAME2(aac_kbd_short_128), 6.0, 128);
    init_sine_windows_fixed();
 #endif

@@ -2486,12 +2486,12 @@ static int decode_extension_payload(AACContext *ac, GetBitContext *gb, int cnt,
                   ac->avctx->ch_layout.nb_channels == 1) {
            ac->oc[1].m4ac.sbr = 1;
            ac->oc[1].m4ac.ps = 1;
-            ac->avctx->profile = AV_PROFILE_AAC_HE_V2;
+            ac->avctx->profile = FF_PROFILE_AAC_HE_V2;
            output_configure(ac, ac->oc[1].layout_map, ac->oc[1].layout_map_tags,
                             ac->oc[1].status, 1);
        } else {
            ac->oc[1].m4ac.sbr = 1;
-            ac->avctx->profile = AV_PROFILE_AAC_HE;
+            ac->avctx->profile = FF_PROFILE_AAC_HE;
        }
        res = AAC_RENAME(ff_decode_sbr_extension)(ac, &che->sbr, gb, crc_flag, cnt, elem_type);
        if (ac->oc[1].m4ac.ps == 1 && !ac->warned_he_aac_mono) {
@@ -3080,7 +3080,7 @@ static int aac_decode_er_frame(AVCodecContext *avctx, void *data,
    if ((err = frame_configure_elements(avctx)) < 0)
        return err;

-    // The AV_PROFILE_AAC_* defines are all object_type - 1
+    // The FF_PROFILE_AAC_* defines are all object_type - 1
    // This may lead to an undefined profile being signaled
    ac->avctx->profile = aot - 1;

@@ -3163,7 +3163,7 @@ static int aac_decode_frame_int(AVCodecContext *avctx, AVFrame *frame,
    if ((err = frame_configure_elements(avctx)) < 0)
        goto fail;

-    // The AV_PROFILE_AAC_* defines are all object_type - 1
+    // The FF_PROFILE_AAC_* defines are all object_type - 1
    // This may lead to an undefined profile being signaled
    ac->avctx->profile = ac->oc[1].m4ac.object_type - 1;

--- a/libavcodec/aacenc.c
+++ b/libavcodec/aacenc.c
@@ -1106,18 +1106,6 @@ static int aac_encode_frame(AVCodecContext *avctx, AVPacket *avpkt,
        too_many_bits = FFMIN(too_many_bits, 6144 * s->channels - 3);
        too_few_bits = FFMIN(FFMAX(rate_bits - rate_bits/4, target_bits), too_many_bits);

-        /* When strict bit-rate control is demanded */
-        if (avctx->bit_rate_tolerance == 0) {
-            if (rate_bits < frame_bits) {
-                float ratio = ((float)rate_bits) / frame_bits;
-                s->lambda *= FFMIN(0.9f, ratio);
-                continue;
-            }
-            /* reset lambda when solution is found */
-            s->lambda = avctx->global_quality > 0 ? avctx->global_quality : 120;
-            break;
-        }
-
        /* When using ABR, be strict (but only for increasing) */
        too_few_bits = too_few_bits - too_few_bits/8;
        too_many_bits = too_many_bits + too_many_bits/2;
@@ -1307,13 +1295,13 @@ static av_cold int aac_encode_init(AVCodecContext *avctx)
                                     avctx->bit_rate);

    /* Profile and option setting */
-    avctx->profile = avctx->profile == AV_PROFILE_UNKNOWN ? AV_PROFILE_AAC_LOW :
+    avctx->profile = avctx->profile == FF_PROFILE_UNKNOWN ? FF_PROFILE_AAC_LOW :
                     avctx->profile;
    for (i = 0; i < FF_ARRAY_ELEMS(aacenc_profiles); i++)
        if (avctx->profile == aacenc_profiles[i])
            break;
-    if (avctx->profile == AV_PROFILE_MPEG2_AAC_LOW) {
-        avctx->profile = AV_PROFILE_AAC_LOW;
+    if (avctx->profile == FF_PROFILE_MPEG2_AAC_LOW) {
+        avctx->profile = FF_PROFILE_AAC_LOW;
        ERROR_IF(s->options.pred,
                 "Main prediction unavailable in the \"mpeg2_aac_low\" profile\n");
        ERROR_IF(s->options.ltp,
@@ -1321,22 +1309,22 @@ static av_cold int aac_encode_init(AVCodecContext *avctx)
        WARN_IF(s->options.pns,
                "PNS unavailable in the \"mpeg2_aac_low\" profile, turning off\n");
        s->options.pns = 0;
-    } else if (avctx->profile == AV_PROFILE_AAC_LTP) {
+    } else if (avctx->profile == FF_PROFILE_AAC_LTP) {
        s->options.ltp = 1;
        ERROR_IF(s->options.pred,
                 "Main prediction unavailable in the \"aac_ltp\" profile\n");
-    } else if (avctx->profile == AV_PROFILE_AAC_MAIN) {
+    } else if (avctx->profile == FF_PROFILE_AAC_MAIN) {
        s->options.pred = 1;
        ERROR_IF(s->options.ltp,
                 "LTP prediction unavailable in the \"aac_main\" profile\n");
    } else if (s->options.ltp) {
-        avctx->profile = AV_PROFILE_AAC_LTP;
+        avctx->profile = FF_PROFILE_AAC_LTP;
        WARN_IF(1,
                "Chainging profile to \"aac_ltp\"\n");
        ERROR_IF(s->options.pred,
                 "Main prediction unavailable in the \"aac_ltp\" profile\n");
    } else if (s->options.pred) {
-        avctx->profile = AV_PROFILE_AAC_MAIN;
+        avctx->profile = FF_PROFILE_AAC_MAIN;
        WARN_IF(1,
                "Chainging profile to \"aac_main\"\n");
        ERROR_IF(s->options.ltp,
--- a/libavcodec/aacenc_ltp.c
+++ b/libavcodec/aacenc_ltp.c
@@ -37,7 +37,7 @@ void ff_aac_encode_ltp_info(AACEncContext *s, SingleChannelElement *sce,
 {
    int i;
    IndividualChannelStream *ics = &sce->ics;
-    if (s->profile != AV_PROFILE_AAC_LTP || !ics->predictor_present)
+    if (s->profile != FF_PROFILE_AAC_LTP || !ics->predictor_present)
        return;
    if (common_window)
        put_bits(&s->pb, 1, 0);
@@ -119,7 +119,7 @@ void ff_aac_update_ltp(AACEncContext *s, SingleChannelElement *sce)
    float *pred_signal = &sce->ltp_state[0];
    const float *samples = &s->planar_samples[s->cur_channel][1024];

-    if (s->profile != AV_PROFILE_AAC_LTP)
+    if (s->profile != FF_PROFILE_AAC_LTP)
        return;

    /* Calculate lag */
--- a/libavcodec/aacenc_pred.c
+++ b/libavcodec/aacenc_pred.c
@@ -335,7 +335,7 @@ void ff_aac_encode_main_pred(AACEncContext *s, SingleChannelElement *sce)
    IndividualChannelStream *ics = &sce->ics;
    const int pmax = FFMIN(ics->max_sfb, ff_aac_pred_sfb_max[s->samplerate_index]);

-    if (s->profile != AV_PROFILE_AAC_MAIN ||
+    if (s->profile != FF_PROFILE_AAC_MAIN ||
        !ics->predictor_present)
        return;

--- a/libavcodec/aacenc_tns.c
+++ b/libavcodec/aacenc_tns.c
@@ -167,7 +167,7 @@ void ff_aac_search_for_tns(AACEncContext *s, SingleChannelElement *sce)
    const int c_bits = is8 ? TNS_Q_BITS_IS8 == 4 : TNS_Q_BITS == 4;
    const int sfb_start = av_clip(tns_min_sfb[is8][s->samplerate_index], 0, mmm);
    const int sfb_end   = av_clip(sce->ics.num_swb, 0, mmm);
-    const int order = is8 ? 7 : s->profile == AV_PROFILE_AAC_LOW ? 12 : TNS_MAX_ORDER;
+    const int order = is8 ? 7 : s->profile == FF_PROFILE_AAC_LOW ? 12 : TNS_MAX_ORDER;
    const int slant = sce->ics.window_sequence[0] == LONG_STOP_SEQUENCE  ? 1 :
                      sce->ics.window_sequence[0] == LONG_START_SEQUENCE ? 0 : 2;
    const int sfb_len = sfb_end - sfb_start;
--- a/libavcodec/aacenctab.h
+++ b/libavcodec/aacenctab.h
@@ -124,10 +124,10 @@ static const unsigned char aac_maxval_cb[] = {
 };

 static const int aacenc_profiles[] = {
-    AV_PROFILE_AAC_MAIN,
-    AV_PROFILE_AAC_LOW,
-    AV_PROFILE_AAC_LTP,
-    AV_PROFILE_MPEG2_AAC_LOW,
+    FF_PROFILE_AAC_MAIN,
+    FF_PROFILE_AAC_LOW,
+    FF_PROFILE_AAC_LTP,
+    FF_PROFILE_MPEG2_AAC_LOW,
 };

 #endif /* AVCODEC_AACENCTAB_H */
--- a/libavcodec/aacps_common.c
+++ b/libavcodec/aacps_common.c
@@ -290,7 +290,7 @@ err:
 }

 #define PS_INIT_VLC_STATIC(num, nb_bits, size)                          \
-    VLC_INIT_STATIC(&vlc_ps[num], nb_bits, ps_tmp[num].table_size / ps_tmp[num].elem_size,    \
+    INIT_VLC_STATIC(&vlc_ps[num], nb_bits, ps_tmp[num].table_size / ps_tmp[num].elem_size,    \
                    ps_tmp[num].ps_bits, 1, 1,                                          \
                    ps_tmp[num].ps_codes, ps_tmp[num].elem_size, ps_tmp[num].elem_size, \
                    size);
--- a/libavcodec/aacpsdsp_template.c
+++ b/libavcodec/aacpsdsp_template.c
@@ -26,25 +26,24 @@
 #include "libavutil/attributes.h"
 #include "aacpsdsp.h"

-static void ps_add_squares_c(INTFLOAT *av_restrict dst,
-                             const INTFLOAT (*src)[2], int n)
+static void ps_add_squares_c(INTFLOAT *dst, const INTFLOAT (*src)[2], int n)
 {
-    for (int i = 0; i < n; i++)
+    int i;
+    for (i = 0; i < n; i++)
        dst[i] += (UINTFLOAT)AAC_MADD28(src[i][0], src[i][0], src[i][1], src[i][1]);
 }

-static void ps_mul_pair_single_c(INTFLOAT (*av_restrict dst)[2],
-                                 INTFLOAT (*src0)[2], INTFLOAT *src1,
+static void ps_mul_pair_single_c(INTFLOAT (*dst)[2], INTFLOAT (*src0)[2], INTFLOAT *src1,
                                 int n)
 {
-    for (int i = 0; i < n; i++) {
+    int i;
+    for (i = 0; i < n; i++) {
        dst[i][0] = AAC_MUL16(src0[i][0], src1[i]);
        dst[i][1] = AAC_MUL16(src0[i][1], src1[i]);
    }
 }

-static void ps_hybrid_analysis_c(INTFLOAT (*av_restrict out)[2],
-                                 INTFLOAT (*in)[2],
+static void ps_hybrid_analysis_c(INTFLOAT (*out)[2], INTFLOAT (*in)[2],
                                 const INTFLOAT (*filter)[8][2],
                                 ptrdiff_t stride, int n)
 {
@@ -77,12 +76,13 @@ static void ps_hybrid_analysis_c(INTFLOAT (*av_restrict out)[2],
    }
 }

-static void ps_hybrid_analysis_ileave_c(INTFLOAT (*av_restrict out)[32][2],
-                                        INTFLOAT L[2][38][64],
-                                        int i, int len)
+static void ps_hybrid_analysis_ileave_c(INTFLOAT (*out)[32][2], INTFLOAT L[2][38][64],
+                                      int i, int len)
 {
+    int j;
+
    for (; i < 64; i++) {
-        for (int j = 0; j < len; j++) {
+        for (j = 0; j < len; j++) {
            out[i][j][0] = L[0][j][i];
            out[i][j][1] = L[1][j][i];
        }
@@ -90,11 +90,13 @@ static void ps_hybrid_analysis_ileave_c(INTFLOAT (*av_restrict out)[32][2],
 }

 static void ps_hybrid_synthesis_deint_c(INTFLOAT out[2][38][64],
-                                        INTFLOAT (*av_restrict in)[32][2],
-                                        int i, int len)
+                                      INTFLOAT (*in)[32][2],
+                                      int i, int len)
 {
+    int n;
+
    for (; i < 64; i++) {
-        for (int n = 0; n < len; n++) {
+        for (n = 0; n < len; n++) {
            out[0][n][i] = in[i][n][0];
            out[1][n][i] = in[i][n][1];
        }
--- a/libavcodec/aacsbr.h
+++ b/libavcodec/aacsbr.h
@@ -70,7 +70,7 @@ static const int8_t vlc_sbr_lav[10] =
    { 60, 60, 24, 24, 31, 31, 12, 12, 31, 12 };

 #define SBR_INIT_VLC_STATIC(num, size) \
-    VLC_INIT_STATIC(&vlc_sbr[num], 9, sbr_tmp[num].table_size / sbr_tmp[num].elem_size,     \
+    INIT_VLC_STATIC(&vlc_sbr[num], 9, sbr_tmp[num].table_size / sbr_tmp[num].elem_size,     \
                    sbr_tmp[num].sbr_bits ,                      1,                      1, \
                    sbr_tmp[num].sbr_codes, sbr_tmp[num].elem_size, sbr_tmp[num].elem_size, \
                    size)
--- a/libavcodec/aacsbr_template.c
+++ b/libavcodec/aacsbr_template.c
@@ -973,7 +973,7 @@ static void read_sbr_extension(AACContext *ac, SpectralBandReplication *sbr,
            *num_bits_left = 0;
        } else {
            *num_bits_left -= ff_ps_read_data(ac->avctx, gb, &sbr->ps.common, *num_bits_left);
-            ac->avctx->profile = AV_PROFILE_AAC_HE_V2;
+            ac->avctx->profile = FF_PROFILE_AAC_HE_V2;
            // ensure the warning is not printed if PS extension is present
            ac->warned_he_aac_mono = 1;
        }
--- a/libavcodec/aacsbrdata.h
+++ b/libavcodec/aacsbrdata.h
@@ -29,6 +29,7 @@
 #define AVCODEC_AACSBRDATA_H

 #include <stdint.h>
+#include "libavutil/attributes_internal.h"
 #include "libavutil/mem_internal.h"
 #include "aac_defines.h"

@@ -267,6 +268,271 @@ static const int8_t sbr_offset[6][16] = {
    {-2, -1,  0,  1,  2,  3,  4,  5,  6,  7,  9, 11, 13, 16, 20, 24}, // 64000 Hz <  fs_sbr
 };

+/* First eight entries repeated at end to simplify SIMD implementations. */
+const attribute_visibility_hidden DECLARE_ALIGNED(16, INTFLOAT, AAC_RENAME(ff_sbr_noise_table))[][2] = {
+{Q31(-0.99948153278296f), Q31(-0.59483417516607f)}, {Q31( 0.97113454393991f), Q31(-0.67528515225647f)},
+{Q31( 0.14130051758487f), Q31(-0.95090983575689f)}, {Q31(-0.47005496701697f), Q31(-0.37340549728647f)},
+{Q31( 0.80705063769351f), Q31( 0.29653668284408f)}, {Q31(-0.38981478896926f), Q31( 0.89572605717087f)},
+{Q31(-0.01053049862020f), Q31(-0.66959058036166f)}, {Q31(-0.91266367957293f), Q31(-0.11522938140034f)},
+{Q31( 0.54840422910309f), Q31( 0.75221367176302f)}, {Q31( 0.40009252867955f), Q31(-0.98929400334421f)},
+{Q31(-0.99867974711855f), Q31(-0.88147068645358f)}, {Q31(-0.95531076805040f), Q31( 0.90908757154593f)},
+{Q31(-0.45725933317144f), Q31(-0.56716323646760f)}, {Q31(-0.72929675029275f), Q31(-0.98008272727324f)},
+{Q31( 0.75622801399036f), Q31( 0.20950329995549f)}, {Q31( 0.07069442601050f), Q31(-0.78247898470706f)},
+{Q31( 0.74496252926055f), Q31(-0.91169004445807f)}, {Q31(-0.96440182703856f), Q31(-0.94739918296622f)},
+{Q31( 0.30424629369539f), Q31(-0.49438267012479f)}, {Q31( 0.66565033746925f), Q31( 0.64652935542491f)},
+{Q31( 0.91697008020594f), Q31( 0.17514097332009f)}, {Q31(-0.70774918760427f), Q31( 0.52548653416543f)},
+{Q31(-0.70051415345560f), Q31(-0.45340028808763f)}, {Q31(-0.99496513054797f), Q31(-0.90071908066973f)},
+{Q31( 0.98164490790123f), Q31(-0.77463155528697f)}, {Q31(-0.54671580548181f), Q31(-0.02570928536004f)},
+{Q31(-0.01689629065389f), Q31( 0.00287506445732f)}, {Q31(-0.86110349531986f), Q31( 0.42548583726477f)},
+{Q31(-0.98892980586032f), Q31(-0.87881132267556f)}, {Q31( 0.51756627678691f), Q31( 0.66926784710139f)},
+{Q31(-0.99635026409640f), Q31(-0.58107730574765f)}, {Q31(-0.99969370862163f), Q31( 0.98369989360250f)},
+{Q31( 0.55266258627194f), Q31( 0.59449057465591f)}, {Q31( 0.34581177741673f), Q31( 0.94879421061866f)},
+{Q31( 0.62664209577999f), Q31(-0.74402970906471f)}, {Q31(-0.77149701404973f), Q31(-0.33883658042801f)},
+{Q31(-0.91592244254432f), Q31( 0.03687901376713f)}, {Q31(-0.76285492357887f), Q31(-0.91371867919124f)},
+{Q31( 0.79788337195331f), Q31(-0.93180971199849f)}, {Q31( 0.54473080610200f), Q31(-0.11919206037186f)},
+{Q31(-0.85639281671058f), Q31( 0.42429854760451f)}, {Q31(-0.92882402971423f), Q31( 0.27871809078609f)},
+{Q31(-0.11708371046774f), Q31(-0.99800843444966f)}, {Q31( 0.21356749817493f), Q31(-0.90716295627033f)},
+{Q31(-0.76191692573909f), Q31( 0.99768118356265f)}, {Q31( 0.98111043100884f), Q31(-0.95854459734407f)},
+{Q31(-0.85913269895572f), Q31( 0.95766566168880f)}, {Q31(-0.93307242253692f), Q31( 0.49431757696466f)},
+{Q31( 0.30485754879632f), Q31(-0.70540034357529f)}, {Q31( 0.85289650925190f), Q31( 0.46766131791044f)},
+{Q31( 0.91328082618125f), Q31(-0.99839597361769f)}, {Q31(-0.05890199924154f), Q31( 0.70741827819497f)},
+{Q31( 0.28398686150148f), Q31( 0.34633555702188f)}, {Q31( 0.95258164539612f), Q31(-0.54893416026939f)},
+{Q31(-0.78566324168507f), Q31(-0.75568541079691f)}, {Q31(-0.95789495447877f), Q31(-0.20423194696966f)},
+{Q31( 0.82411158711197f), Q31( 0.96654618432562f)}, {Q31(-0.65185446735885f), Q31(-0.88734990773289f)},
+{Q31(-0.93643603134666f), Q31( 0.99870790442385f)}, {Q31( 0.91427159529618f), Q31(-0.98290505544444f)},
+{Q31(-0.70395684036886f), Q31( 0.58796798221039f)}, {Q31( 0.00563771969365f), Q31( 0.61768196727244f)},
+{Q31( 0.89065051931895f), Q31( 0.52783352697585f)}, {Q31(-0.68683707712762f), Q31( 0.80806944710339f)},
+{Q31( 0.72165342518718f), Q31(-0.69259857349564f)}, {Q31(-0.62928247730667f), Q31( 0.13627037407335f)},
+{Q31( 0.29938434065514f), Q31(-0.46051329682246f)}, {Q31(-0.91781958879280f), Q31(-0.74012716684186f)},
+{Q31( 0.99298717043688f), Q31( 0.40816610075661f)}, {Q31( 0.82368298622748f), Q31(-0.74036047190173f)},
+{Q31(-0.98512833386833f), Q31(-0.99972330709594f)}, {Q31(-0.95915368242257f), Q31(-0.99237800466040f)},
+{Q31(-0.21411126572790f), Q31(-0.93424819052545f)}, {Q31(-0.68821476106884f), Q31(-0.26892306315457f)},
+{Q31( 0.91851997982317f), Q31( 0.09358228901785f)}, {Q31(-0.96062769559127f), Q31( 0.36099095133739f)},
+{Q31( 0.51646184922287f), Q31(-0.71373332873917f)}, {Q31( 0.61130721139669f), Q31( 0.46950141175917f)},
+{Q31( 0.47336129371299f), Q31(-0.27333178296162f)}, {Q31( 0.90998308703519f), Q31( 0.96715662938132f)},
+{Q31( 0.44844799194357f), Q31( 0.99211574628306f)}, {Q31( 0.66614891079092f), Q31( 0.96590176169121f)},
+{Q31( 0.74922239129237f), Q31(-0.89879858826087f)}, {Q31(-0.99571588506485f), Q31( 0.52785521494349f)},
+{Q31( 0.97401082477563f), Q31(-0.16855870075190f)}, {Q31( 0.72683747733879f), Q31(-0.48060774432251f)},
+{Q31( 0.95432193457128f), Q31( 0.68849603408441f)}, {Q31(-0.72962208425191f), Q31(-0.76608443420917f)},
+{Q31(-0.85359479233537f), Q31( 0.88738125901579f)}, {Q31(-0.81412430338535f), Q31(-0.97480768049637f)},
+{Q31(-0.87930772356786f), Q31( 0.74748307690436f)}, {Q31(-0.71573331064977f), Q31(-0.98570608178923f)},
+{Q31( 0.83524300028228f), Q31( 0.83702537075163f)}, {Q31(-0.48086065601423f), Q31(-0.98848504923531f)},
+{Q31( 0.97139128574778f), Q31( 0.80093621198236f)}, {Q31( 0.51992825347895f), Q31( 0.80247631400510f)},
+{Q31(-0.00848591195325f), Q31(-0.76670128000486f)}, {Q31(-0.70294374303036f), Q31( 0.55359910445577f)},
+{Q31(-0.95894428168140f), Q31(-0.43265504344783f)}, {Q31( 0.97079252950321f), Q31( 0.09325857238682f)},
+{Q31(-0.92404293670797f), Q31( 0.85507704027855f)}, {Q31(-0.69506469500450f), Q31( 0.98633412625459f)},
+{Q31( 0.26559203620024f), Q31( 0.73314307966524f)}, {Q31( 0.28038443336943f), Q31( 0.14537913654427f)},
+{Q31(-0.74138124825523f), Q31( 0.99310339807762f)}, {Q31(-0.01752795995444f), Q31(-0.82616635284178f)},
+{Q31(-0.55126773094930f), Q31(-0.98898543862153f)}, {Q31( 0.97960898850996f), Q31(-0.94021446752851f)},
+{Q31(-0.99196309146936f), Q31( 0.67019017358456f)}, {Q31(-0.67684928085260f), Q31( 0.12631491649378f)},
+{Q31( 0.09140039465500f), Q31(-0.20537731453108f)}, {Q31(-0.71658965751996f), Q31(-0.97788200391224f)},
+{Q31( 0.81014640078925f), Q31( 0.53722648362443f)}, {Q31( 0.40616991671205f), Q31(-0.26469008598449f)},
+{Q31(-0.67680188682972f), Q31( 0.94502052337695f)}, {Q31( 0.86849774348749f), Q31(-0.18333598647899f)},
+{Q31(-0.99500381284851f), Q31(-0.02634122068550f)}, {Q31( 0.84329189340667f), Q31( 0.10406957462213f)},
+{Q31(-0.09215968531446f), Q31( 0.69540012101253f)}, {Q31( 0.99956173327206f), Q31(-0.12358542001404f)},
+{Q31(-0.79732779473535f), Q31(-0.91582524736159f)}, {Q31( 0.96349973642406f), Q31( 0.96640458041000f)},
+{Q31(-0.79942778496547f), Q31( 0.64323902822857f)}, {Q31(-0.11566039853896f), Q31( 0.28587846253726f)},
+{Q31(-0.39922954514662f), Q31( 0.94129601616966f)}, {Q31( 0.99089197565987f), Q31(-0.92062625581587f)},
+{Q31( 0.28631285179909f), Q31(-0.91035047143603f)}, {Q31(-0.83302725605608f), Q31(-0.67330410892084f)},
+{Q31( 0.95404443402072f), Q31( 0.49162765398743f)}, {Q31(-0.06449863579434f), Q31( 0.03250560813135f)},
+{Q31(-0.99575054486311f), Q31( 0.42389784469507f)}, {Q31(-0.65501142790847f), Q31( 0.82546114655624f)},
+{Q31(-0.81254441908887f), Q31(-0.51627234660629f)}, {Q31(-0.99646369485481f), Q31( 0.84490533520752f)},
+{Q31( 0.00287840603348f), Q31( 0.64768261158166f)}, {Q31( 0.70176989408455f), Q31(-0.20453028573322f)},
+{Q31( 0.96361882270190f), Q31( 0.40706967140989f)}, {Q31(-0.68883758192426f), Q31( 0.91338958840772f)},
+{Q31(-0.34875585502238f), Q31( 0.71472290693300f)}, {Q31( 0.91980081243087f), Q31( 0.66507455644919f)},
+{Q31(-0.99009048343881f), Q31( 0.85868021604848f)}, {Q31( 0.68865791458395f), Q31( 0.55660316809678f)},
+{Q31(-0.99484402129368f), Q31(-0.20052559254934f)}, {Q31( 0.94214511408023f), Q31(-0.99696425367461f)},
+{Q31(-0.67414626793544f), Q31( 0.49548221180078f)}, {Q31(-0.47339353684664f), Q31(-0.85904328834047f)},
+{Q31( 0.14323651387360f), Q31(-0.94145598222488f)}, {Q31(-0.29268293575672f), Q31( 0.05759224927952f)},
+{Q31( 0.43793861458754f), Q31(-0.78904969892724f)}, {Q31(-0.36345126374441f), Q31( 0.64874435357162f)},
+{Q31(-0.08750604656825f), Q31( 0.97686944362527f)}, {Q31(-0.96495267812511f), Q31(-0.53960305946511f)},
+{Q31( 0.55526940659947f), Q31( 0.78891523734774f)}, {Q31( 0.73538215752630f), Q31( 0.96452072373404f)},
+{Q31(-0.30889773919437f), Q31(-0.80664389776860f)}, {Q31( 0.03574995626194f), Q31(-0.97325616900959f)},
+{Q31( 0.98720684660488f), Q31( 0.48409133691962f)}, {Q31(-0.81689296271203f), Q31(-0.90827703628298f)},
+{Q31( 0.67866860118215f), Q31( 0.81284503870856f)}, {Q31(-0.15808569732583f), Q31( 0.85279555024382f)},
+{Q31( 0.80723395114371f), Q31(-0.24717418514605f)}, {Q31( 0.47788757329038f), Q31(-0.46333147839295f)},
+{Q31( 0.96367554763201f), Q31( 0.38486749303242f)}, {Q31(-0.99143875716818f), Q31(-0.24945277239809f)},
+{Q31( 0.83081876925833f), Q31(-0.94780851414763f)}, {Q31(-0.58753191905341f), Q31( 0.01290772389163f)},
+{Q31( 0.95538108220960f), Q31(-0.85557052096538f)}, {Q31(-0.96490920476211f), Q31(-0.64020970923102f)},
+{Q31(-0.97327101028521f), Q31( 0.12378128133110f)}, {Q31( 0.91400366022124f), Q31( 0.57972471346930f)},
+{Q31(-0.99925837363824f), Q31( 0.71084847864067f)}, {Q31(-0.86875903507313f), Q31(-0.20291699203564f)},
+{Q31(-0.26240034795124f), Q31(-0.68264554369108f)}, {Q31(-0.24664412953388f), Q31(-0.87642273115183f)},
+{Q31( 0.02416275806869f), Q31( 0.27192914288905f)}, {Q31( 0.82068619590515f), Q31(-0.85087787994476f)},
+{Q31( 0.88547373760759f), Q31(-0.89636802901469f)}, {Q31(-0.18173078152226f), Q31(-0.26152145156800f)},
+{Q31( 0.09355476558534f), Q31( 0.54845123045604f)}, {Q31(-0.54668414224090f), Q31( 0.95980774020221f)},
+{Q31( 0.37050990604091f), Q31(-0.59910140383171f)}, {Q31(-0.70373594262891f), Q31( 0.91227665827081f)},
+{Q31(-0.34600785879594f), Q31(-0.99441426144200f)}, {Q31(-0.68774481731008f), Q31(-0.30238837956299f)},
+{Q31(-0.26843291251234f), Q31( 0.83115668004362f)}, {Q31( 0.49072334613242f), Q31(-0.45359708737775f)},
+{Q31( 0.38975993093975f), Q31( 0.95515358099121f)}, {Q31(-0.97757125224150f), Q31( 0.05305894580606f)},
+{Q31(-0.17325552859616f), Q31(-0.92770672250494f)}, {Q31( 0.99948035025744f), Q31( 0.58285545563426f)},
+{Q31(-0.64946246527458f), Q31( 0.68645507104960f)}, {Q31(-0.12016920576437f), Q31(-0.57147322153312f)},
+{Q31(-0.58947456517751f), Q31(-0.34847132454388f)}, {Q31(-0.41815140454465f), Q31( 0.16276422358861f)},
+{Q31( 0.99885650204884f), Q31( 0.11136095490444f)}, {Q31(-0.56649614128386f), Q31(-0.90494866361587f)},
+{Q31( 0.94138021032330f), Q31( 0.35281916733018f)}, {Q31(-0.75725076534641f), Q31( 0.53650549640587f)},
+{Q31( 0.20541973692630f), Q31(-0.94435144369918f)}, {Q31( 0.99980371023351f), Q31( 0.79835913565599f)},
+{Q31( 0.29078277605775f), Q31( 0.35393777921520f)}, {Q31(-0.62858772103030f), Q31( 0.38765693387102f)},
+{Q31( 0.43440904467688f), Q31(-0.98546330463232f)}, {Q31(-0.98298583762390f), Q31( 0.21021524625209f)},
+{Q31( 0.19513029146934f), Q31(-0.94239832251867f)}, {Q31(-0.95476662400101f), Q31( 0.98364554179143f)},
+{Q31( 0.93379635304810f), Q31(-0.70881994583682f)}, {Q31(-0.85235410573336f), Q31(-0.08342347966410f)},
+{Q31(-0.86425093011245f), Q31(-0.45795025029466f)}, {Q31( 0.38879779059045f), Q31( 0.97274429344593f)},
+{Q31( 0.92045124735495f), Q31(-0.62433652524220f)}, {Q31( 0.89162532251878f), Q31( 0.54950955570563f)},
+{Q31(-0.36834336949252f), Q31( 0.96458298020975f)}, {Q31( 0.93891760988045f), Q31(-0.89968353740388f)},
+{Q31( 0.99267657565094f), Q31(-0.03757034316958f)}, {Q31(-0.94063471614176f), Q31( 0.41332338538963f)},
+{Q31( 0.99740224117019f), Q31(-0.16830494996370f)}, {Q31(-0.35899413170555f), Q31(-0.46633226649613f)},
+{Q31( 0.05237237274947f), Q31(-0.25640361602661f)}, {Q31( 0.36703583957424f), Q31(-0.38653265641875f)},
+{Q31( 0.91653180367913f), Q31(-0.30587628726597f)}, {Q31( 0.69000803499316f), Q31( 0.90952171386132f)},
+{Q31(-0.38658751133527f), Q31( 0.99501571208985f)}, {Q31(-0.29250814029851f), Q31( 0.37444994344615f)},
+{Q31(-0.60182204677608f), Q31( 0.86779651036123f)}, {Q31(-0.97418588163217f), Q31( 0.96468523666475f)},
+{Q31( 0.88461574003963f), Q31( 0.57508405276414f)}, {Q31( 0.05198933055162f), Q31( 0.21269661669964f)},
+{Q31(-0.53499621979720f), Q31( 0.97241553731237f)}, {Q31(-0.49429560226497f), Q31( 0.98183865291903f)},
+{Q31(-0.98935142339139f), Q31(-0.40249159006933f)}, {Q31(-0.98081380091130f), Q31(-0.72856895534041f)},
+{Q31(-0.27338148835532f), Q31( 0.99950922447209f)}, {Q31( 0.06310802338302f), Q31(-0.54539587529618f)},
+{Q31(-0.20461677199539f), Q31(-0.14209977628489f)}, {Q31( 0.66223843141647f), Q31( 0.72528579940326f)},
+{Q31(-0.84764345483665f), Q31( 0.02372316801261f)}, {Q31(-0.89039863483811f), Q31( 0.88866581484602f)},
+{Q31( 0.95903308477986f), Q31( 0.76744927173873f)}, {Q31( 0.73504123909879f), Q31(-0.03747203173192f)},
+{Q31(-0.31744434966056f), Q31(-0.36834111883652f)}, {Q31(-0.34110827591623f), Q31( 0.40211222807691f)},
+{Q31( 0.47803883714199f), Q31(-0.39423219786288f)}, {Q31( 0.98299195879514f), Q31( 0.01989791390047f)},
+{Q31(-0.30963073129751f), Q31(-0.18076720599336f)}, {Q31( 0.99992588229018f), Q31(-0.26281872094289f)},
+{Q31(-0.93149731080767f), Q31(-0.98313162570490f)}, {Q31( 0.99923472302773f), Q31(-0.80142993767554f)},
+{Q31(-0.26024169633417f), Q31(-0.75999759855752f)}, {Q31(-0.35712514743563f), Q31( 0.19298963768574f)},
+{Q31(-0.99899084509530f), Q31( 0.74645156992493f)}, {Q31( 0.86557171579452f), Q31( 0.55593866696299f)},
+{Q31( 0.33408042438752f), Q31( 0.86185953874709f)}, {Q31( 0.99010736374716f), Q31( 0.04602397576623f)},
+{Q31(-0.66694269691195f), Q31(-0.91643611810148f)}, {Q31( 0.64016792079480f), Q31( 0.15649530836856f)},
+{Q31( 0.99570534804836f), Q31( 0.45844586038111f)}, {Q31(-0.63431466947340f), Q31( 0.21079116459234f)},
+{Q31(-0.07706847005931f), Q31(-0.89581437101329f)}, {Q31( 0.98590090577724f), Q31( 0.88241721133981f)},
+{Q31( 0.80099335254678f), Q31(-0.36851896710853f)}, {Q31( 0.78368131392666f), Q31( 0.45506999802597f)},
+{Q31( 0.08707806671691f), Q31( 0.80938994918745f)}, {Q31(-0.86811883080712f), Q31( 0.39347308654705f)},
+{Q31(-0.39466529740375f), Q31(-0.66809432114456f)}, {Q31( 0.97875325649683f), Q31(-0.72467840967746f)},
+{Q31(-0.95038560288864f), Q31( 0.89563219587625f)}, {Q31( 0.17005239424212f), Q31( 0.54683053962658f)},
+{Q31(-0.76910792026848f), Q31(-0.96226617549298f)}, {Q31( 0.99743281016846f), Q31( 0.42697157037567f)},
+{Q31( 0.95437383549973f), Q31( 0.97002324109952f)}, {Q31( 0.99578905365569f), Q31(-0.54106826257356f)},
+{Q31( 0.28058259829990f), Q31(-0.85361420634036f)}, {Q31( 0.85256524470573f), Q31(-0.64567607735589f)},
+{Q31(-0.50608540105128f), Q31(-0.65846015480300f)}, {Q31(-0.97210735183243f), Q31(-0.23095213067791f)},
+{Q31( 0.95424048234441f), Q31(-0.99240147091219f)}, {Q31(-0.96926570524023f), Q31( 0.73775654896574f)},
+{Q31( 0.30872163214726f), Q31( 0.41514960556126f)}, {Q31(-0.24523839572639f), Q31( 0.63206633394807f)},
+{Q31(-0.33813265086024f), Q31(-0.38661779441897f)}, {Q31(-0.05826828420146f), Q31(-0.06940774188029f)},
+{Q31(-0.22898461455054f), Q31( 0.97054853316316f)}, {Q31(-0.18509915019881f), Q31( 0.47565762892084f)},
+{Q31(-0.10488238045009f), Q31(-0.87769947402394f)}, {Q31(-0.71886586182037f), Q31( 0.78030982480538f)},
+{Q31( 0.99793873738654f), Q31( 0.90041310491497f)}, {Q31( 0.57563307626120f), Q31(-0.91034337352097f)},
+{Q31( 0.28909646383717f), Q31( 0.96307783970534f)}, {Q31( 0.42188998312520f), Q31( 0.48148651230437f)},
+{Q31( 0.93335049681047f), Q31(-0.43537023883588f)}, {Q31(-0.97087374418267f), Q31( 0.86636445711364f)},
+{Q31( 0.36722871286923f), Q31( 0.65291654172961f)}, {Q31(-0.81093025665696f), Q31( 0.08778370229363f)},
+{Q31(-0.26240603062237f), Q31(-0.92774095379098f)}, {Q31( 0.83996497984604f), Q31( 0.55839849139647f)},
+{Q31(-0.99909615720225f), Q31(-0.96024605713970f)}, {Q31( 0.74649464155061f), Q31( 0.12144893606462f)},
+{Q31(-0.74774595569805f), Q31(-0.26898062008959f)}, {Q31( 0.95781667469567f), Q31(-0.79047927052628f)},
+{Q31( 0.95472308713099f), Q31(-0.08588776019550f)}, {Q31( 0.48708332746299f), Q31( 0.99999041579432f)},
+{Q31( 0.46332038247497f), Q31( 0.10964126185063f)}, {Q31(-0.76497004940162f), Q31( 0.89210929242238f)},
+{Q31( 0.57397389364339f), Q31( 0.35289703373760f)}, {Q31( 0.75374316974495f), Q31( 0.96705214651335f)},
+{Q31(-0.59174397685714f), Q31(-0.89405370422752f)}, {Q31( 0.75087906691890f), Q31(-0.29612672982396f)},
+{Q31(-0.98607857336230f), Q31( 0.25034911730023f)}, {Q31(-0.40761056640505f), Q31(-0.90045573444695f)},
+{Q31( 0.66929266740477f), Q31( 0.98629493401748f)}, {Q31(-0.97463695257310f), Q31(-0.00190223301301f)},
+{Q31( 0.90145509409859f), Q31( 0.99781390365446f)}, {Q31(-0.87259289048043f), Q31( 0.99233587353666f)},
+{Q31(-0.91529461447692f), Q31(-0.15698707534206f)}, {Q31(-0.03305738840705f), Q31(-0.37205262859764f)},
+{Q31( 0.07223051368337f), Q31(-0.88805001733626f)}, {Q31( 0.99498012188353f), Q31( 0.97094358113387f)},
+{Q31(-0.74904939500519f), Q31( 0.99985483641521f)}, {Q31( 0.04585228574211f), Q31( 0.99812337444082f)},
+{Q31(-0.89054954257993f), Q31(-0.31791913188064f)}, {Q31(-0.83782144651251f), Q31( 0.97637632547466f)},
+{Q31( 0.33454804933804f), Q31(-0.86231516800408f)}, {Q31(-0.99707579362824f), Q31( 0.93237990079441f)},
+{Q31(-0.22827527843994f), Q31( 0.18874759397997f)}, {Q31( 0.67248046289143f), Q31(-0.03646211390569f)},
+{Q31(-0.05146538187944f), Q31(-0.92599700120679f)}, {Q31( 0.99947295749905f), Q31( 0.93625229707912f)},
+{Q31( 0.66951124390363f), Q31( 0.98905825623893f)}, {Q31(-0.99602956559179f), Q31(-0.44654715757688f)},
+{Q31( 0.82104905483590f), Q31( 0.99540741724928f)}, {Q31( 0.99186510988782f), Q31( 0.72023001312947f)},
+{Q31(-0.65284592392918f), Q31( 0.52186723253637f)}, {Q31( 0.93885443798188f), Q31(-0.74895312615259f)},
+{Q31( 0.96735248738388f), Q31( 0.90891816978629f)}, {Q31(-0.22225968841114f), Q31( 0.57124029781228f)},
+{Q31(-0.44132783753414f), Q31(-0.92688840659280f)}, {Q31(-0.85694974219574f), Q31( 0.88844532719844f)},
+{Q31( 0.91783042091762f), Q31(-0.46356892383970f)}, {Q31( 0.72556974415690f), Q31(-0.99899555770747f)},
+{Q31(-0.99711581834508f), Q31( 0.58211560180426f)}, {Q31( 0.77638976371966f), Q31( 0.94321834873819f)},
+{Q31( 0.07717324253925f), Q31( 0.58638399856595f)}, {Q31(-0.56049829194163f), Q31( 0.82522301569036f)},
+{Q31( 0.98398893639988f), Q31( 0.39467440420569f)}, {Q31( 0.47546946844938f), Q31( 0.68613044836811f)},
+{Q31( 0.65675089314631f), Q31( 0.18331637134880f)}, {Q31( 0.03273375457980f), Q31(-0.74933109564108f)},
+{Q31(-0.38684144784738f), Q31( 0.51337349030406f)}, {Q31(-0.97346267944545f), Q31(-0.96549364384098f)},
+{Q31(-0.53282156061942f), Q31(-0.91423265091354f)}, {Q31( 0.99817310731176f), Q31( 0.61133572482148f)},
+{Q31(-0.50254500772635f), Q31(-0.88829338134294f)}, {Q31( 0.01995873238855f), Q31( 0.85223515096765f)},
+{Q31( 0.99930381973804f), Q31( 0.94578896296649f)}, {Q31( 0.82907767600783f), Q31(-0.06323442598128f)},
+{Q31(-0.58660709669728f), Q31( 0.96840773806582f)}, {Q31(-0.17573736667267f), Q31(-0.48166920859485f)},
+{Q31( 0.83434292401346f), Q31(-0.13023450646997f)}, {Q31( 0.05946491307025f), Q31( 0.20511047074866f)},
+{Q31( 0.81505484574602f), Q31(-0.94685947861369f)}, {Q31(-0.44976380954860f), Q31( 0.40894572671545f)},
+{Q31(-0.89746474625671f), Q31( 0.99846578838537f)}, {Q31( 0.39677256130792f), Q31(-0.74854668609359f)},
+{Q31(-0.07588948563079f), Q31( 0.74096214084170f)}, {Q31( 0.76343198951445f), Q31( 0.41746629422634f)},
+{Q31(-0.74490104699626f), Q31( 0.94725911744610f)}, {Q31( 0.64880119792759f), Q31( 0.41336660830571f)},
+{Q31( 0.62319537462542f), Q31(-0.93098313552599f)}, {Q31( 0.42215817594807f), Q31(-0.07712787385208f)},
+{Q31( 0.02704554141885f), Q31(-0.05417518053666f)}, {Q31( 0.80001773566818f), Q31( 0.91542195141039f)},
+{Q31(-0.79351832348816f), Q31(-0.36208897989136f)}, {Q31( 0.63872359151636f), Q31( 0.08128252493444f)},
+{Q31( 0.52890520960295f), Q31( 0.60048872455592f)}, {Q31( 0.74238552914587f), Q31( 0.04491915291044f)},
+{Q31( 0.99096131449250f), Q31(-0.19451182854402f)}, {Q31(-0.80412329643109f), Q31(-0.88513818199457f)},
+{Q31(-0.64612616129736f), Q31( 0.72198674804544f)}, {Q31( 0.11657770663191f), Q31(-0.83662833815041f)},
+{Q31(-0.95053182488101f), Q31(-0.96939905138082f)}, {Q31(-0.62228872928622f), Q31( 0.82767262846661f)},
+{Q31( 0.03004475787316f), Q31(-0.99738896333384f)}, {Q31(-0.97987214341034f), Q31( 0.36526129686425f)},
+{Q31(-0.99986980746200f), Q31(-0.36021610299715f)}, {Q31( 0.89110648599879f), Q31(-0.97894250343044f)},
+{Q31( 0.10407960510582f), Q31( 0.77357793811619f)}, {Q31( 0.95964737821728f), Q31(-0.35435818285502f)},
+{Q31( 0.50843233159162f), Q31( 0.96107691266205f)}, {Q31( 0.17006334670615f), Q31(-0.76854025314829f)},
+{Q31( 0.25872675063360f), Q31( 0.99893303933816f)}, {Q31(-0.01115998681937f), Q31( 0.98496019742444f)},
+{Q31(-0.79598702973261f), Q31( 0.97138411318894f)}, {Q31(-0.99264708948101f), Q31(-0.99542822402536f)},
+{Q31(-0.99829663752818f), Q31( 0.01877138824311f)}, {Q31(-0.70801016548184f), Q31( 0.33680685948117f)},
+{Q31(-0.70467057786826f), Q31( 0.93272777501857f)}, {Q31( 0.99846021905254f), Q31(-0.98725746254433f)},
+{Q31(-0.63364968534650f), Q31(-0.16473594423746f)}, {Q31(-0.16258217500792f), Q31(-0.95939125400802f)},
+{Q31(-0.43645594360633f), Q31(-0.94805030113284f)}, {Q31(-0.99848471702976f), Q31( 0.96245166923809f)},
+{Q31(-0.16796458968998f), Q31(-0.98987511890470f)}, {Q31(-0.87979225745213f), Q31(-0.71725725041680f)},
+{Q31( 0.44183099021786f), Q31(-0.93568974498761f)}, {Q31( 0.93310180125532f), Q31(-0.99913308068246f)},
+{Q31(-0.93941931782002f), Q31(-0.56409379640356f)}, {Q31(-0.88590003188677f), Q31( 0.47624600491382f)},
+{Q31( 0.99971463703691f), Q31(-0.83889954253462f)}, {Q31(-0.75376385639978f), Q31( 0.00814643438625f)},
+{Q31( 0.93887685615875f), Q31(-0.11284528204636f)}, {Q31( 0.85126435782309f), Q31( 0.52349251543547f)},
+{Q31( 0.39701421446381f), Q31( 0.81779634174316f)}, {Q31(-0.37024464187437f), Q31(-0.87071656222959f)},
+{Q31(-0.36024828242896f), Q31( 0.34655735648287f)}, {Q31(-0.93388812549209f), Q31(-0.84476541096429f)},
+{Q31(-0.65298804552119f), Q31(-0.18439575450921f)}, {Q31( 0.11960319006843f), Q31( 0.99899346780168f)},
+{Q31( 0.94292565553160f), Q31( 0.83163906518293f)}, {Q31( 0.75081145286948f), Q31(-0.35533223142265f)},
+{Q31( 0.56721979748394f), Q31(-0.24076836414499f)}, {Q31( 0.46857766746029f), Q31(-0.30140233457198f)},
+{Q31( 0.97312313923635f), Q31(-0.99548191630031f)}, {Q31(-0.38299976567017f), Q31( 0.98516909715427f)},
+{Q31( 0.41025800019463f), Q31( 0.02116736935734f)}, {Q31( 0.09638062008048f), Q31( 0.04411984381457f)},
+{Q31(-0.85283249275397f), Q31( 0.91475563922421f)}, {Q31( 0.88866808958124f), Q31(-0.99735267083226f)},
+{Q31(-0.48202429536989f), Q31(-0.96805608884164f)}, {Q31( 0.27572582416567f), Q31( 0.58634753335832f)},
+{Q31(-0.65889129659168f), Q31( 0.58835634138583f)}, {Q31( 0.98838086953732f), Q31( 0.99994349600236f)},
+{Q31(-0.20651349620689f), Q31( 0.54593044066355f)}, {Q31(-0.62126416356920f), Q31(-0.59893681700392f)},
+{Q31( 0.20320105410437f), Q31(-0.86879180355289f)}, {Q31(-0.97790548600584f), Q31( 0.96290806999242f)},
+{Q31( 0.11112534735126f), Q31( 0.21484763313301f)}, {Q31(-0.41368337314182f), Q31( 0.28216837680365f)},
+{Q31( 0.24133038992960f), Q31( 0.51294362630238f)}, {Q31(-0.66393410674885f), Q31(-0.08249679629081f)},
+{Q31(-0.53697829178752f), Q31(-0.97649903936228f)}, {Q31(-0.97224737889348f), Q31( 0.22081333579837f)},
+{Q31( 0.87392477144549f), Q31(-0.12796173740361f)}, {Q31( 0.19050361015753f), Q31( 0.01602615387195f)},
+{Q31(-0.46353441212724f), Q31(-0.95249041539006f)}, {Q31(-0.07064096339021f), Q31(-0.94479803205886f)},
+{Q31(-0.92444085484466f), Q31(-0.10457590187436f)}, {Q31(-0.83822593578728f), Q31(-0.01695043208885f)},
+{Q31( 0.75214681811150f), Q31(-0.99955681042665f)}, {Q31(-0.42102998829339f), Q31( 0.99720941999394f)},
+{Q31(-0.72094786237696f), Q31(-0.35008961934255f)}, {Q31( 0.78843311019251f), Q31( 0.52851398958271f)},
+{Q31( 0.97394027897442f), Q31(-0.26695944086561f)}, {Q31( 0.99206463477946f), Q31(-0.57010120849429f)},
+{Q31( 0.76789609461795f), Q31(-0.76519356730966f)}, {Q31(-0.82002421836409f), Q31(-0.73530179553767f)},
+{Q31( 0.81924990025724f), Q31( 0.99698425250579f)}, {Q31(-0.26719850873357f), Q31( 0.68903369776193f)},
+{Q31(-0.43311260380975f), Q31( 0.85321815947490f)}, {Q31( 0.99194979673836f), Q31( 0.91876249766422f)},
+{Q31(-0.80692001248487f), Q31(-0.32627540663214f)}, {Q31( 0.43080003649976f), Q31(-0.21919095636638f)},
+{Q31( 0.67709491937357f), Q31(-0.95478075822906f)}, {Q31( 0.56151770568316f), Q31(-0.70693811747778f)},
+{Q31( 0.10831862810749f), Q31(-0.08628837174592f)}, {Q31( 0.91229417540436f), Q31(-0.65987351408410f)},
+{Q31(-0.48972893932274f), Q31( 0.56289246362686f)}, {Q31(-0.89033658689697f), Q31(-0.71656563987082f)},
+{Q31( 0.65269447475094f), Q31( 0.65916004833932f)}, {Q31( 0.67439478141121f), Q31(-0.81684380846796f)},
+{Q31(-0.47770832416973f), Q31(-0.16789556203025f)}, {Q31(-0.99715979260878f), Q31(-0.93565784007648f)},
+{Q31(-0.90889593602546f), Q31( 0.62034397054380f)}, {Q31(-0.06618622548177f), Q31(-0.23812217221359f)},
+{Q31( 0.99430266919728f), Q31( 0.18812555317553f)}, {Q31( 0.97686402381843f), Q31(-0.28664534366620f)},
+{Q31( 0.94813650221268f), Q31(-0.97506640027128f)}, {Q31(-0.95434497492853f), Q31(-0.79607978501983f)},
+{Q31(-0.49104783137150f), Q31( 0.32895214359663f)}, {Q31( 0.99881175120751f), Q31( 0.88993983831354f)},
+{Q31( 0.50449166760303f), Q31(-0.85995072408434f)}, {Q31( 0.47162891065108f), Q31(-0.18680204049569f)},
+{Q31(-0.62081581361840f), Q31( 0.75000676218956f)}, {Q31(-0.43867015250812f), Q31( 0.99998069244322f)},
+{Q31( 0.98630563232075f), Q31(-0.53578899600662f)}, {Q31(-0.61510362277374f), Q31(-0.89515019899997f)},
+{Q31(-0.03841517601843f), Q31(-0.69888815681179f)}, {Q31(-0.30102157304644f), Q31(-0.07667808922205f)},
+{Q31( 0.41881284182683f), Q31( 0.02188098922282f)}, {Q31(-0.86135454941237f), Q31( 0.98947480909359f)},
+{Q31( 0.67226861393788f), Q31(-0.13494389011014f)}, {Q31(-0.70737398842068f), Q31(-0.76547349325992f)},
+{Q31( 0.94044946687963f), Q31( 0.09026201157416f)}, {Q31(-0.82386352534327f), Q31( 0.08924768823676f)},
+{Q31(-0.32070666698656f), Q31( 0.50143421908753f)}, {Q31( 0.57593163224487f), Q31(-0.98966422921509f)},
+{Q31(-0.36326018419965f), Q31( 0.07440243123228f)}, {Q31( 0.99979044674350f), Q31(-0.14130287347405f)},
+{Q31(-0.92366023326932f), Q31(-0.97979298068180f)}, {Q31(-0.44607178518598f), Q31(-0.54233252016394f)},
+{Q31( 0.44226800932956f), Q31( 0.71326756742752f)}, {Q31( 0.03671907158312f), Q31( 0.63606389366675f)},
+{Q31( 0.52175424682195f), Q31(-0.85396826735705f)}, {Q31(-0.94701139690956f), Q31(-0.01826348194255f)},
+{Q31(-0.98759606946049f), Q31( 0.82288714303073f)}, {Q31( 0.87434794743625f), Q31( 0.89399495655433f)},
+{Q31(-0.93412041758744f), Q31( 0.41374052024363f)}, {Q31( 0.96063943315511f), Q31( 0.93116709541280f)},
+{Q31( 0.97534253457837f), Q31( 0.86150930812689f)}, {Q31( 0.99642466504163f), Q31( 0.70190043427512f)},
+{Q31(-0.94705089665984f), Q31(-0.29580042814306f)}, {Q31( 0.91599807087376f), Q31(-0.98147830385781f)},
+// Start of duplicated table
+{Q31(-0.99948153278296f), Q31(-0.59483417516607f)}, {Q31( 0.97113454393991f), Q31(-0.67528515225647f)},
+{Q31( 0.14130051758487f), Q31(-0.95090983575689f)}, {Q31(-0.47005496701697f), Q31(-0.37340549728647f)},
+{Q31( 0.80705063769351f), Q31( 0.29653668284408f)}, {Q31(-0.38981478896926f), Q31( 0.89572605717087f)},
+{Q31(-0.01053049862020f), Q31(-0.66959058036166f)}, {Q31(-0.91266367957293f), Q31(-0.11522938140034f)},
+};
+
 ///< window coefficients for analysis/synthesis QMF banks
 static DECLARE_ALIGNED(32, INTFLOAT, sbr_qmf_window_ds)[320];
 /* This table contains redundancy: It is symmetric about the entry #320
--- a/libavcodec/aactab.c
+++ b/libavcodec/aactab.c
@@ -48,8 +48,8 @@ DECLARE_ALIGNED(32, float,  ff_aac_kbd_short_128)[128];

 static av_cold void aac_float_common_init(void)
 {
-    avpriv_kbd_window_init(ff_aac_kbd_long_1024, 4.0, 1024);
-    avpriv_kbd_window_init(ff_aac_kbd_short_128, 6.0, 128);
+    ff_kbd_window_init(ff_aac_kbd_long_1024, 4.0, 1024);
+    ff_kbd_window_init(ff_aac_kbd_short_128, 6.0, 128);
    ff_init_ff_sine_windows(10);
    ff_init_ff_sine_windows(7);
 }
--- a/libavcodec/aarch64/Makefile
+++ b/libavcodec/aarch64/Makefile
@@ -1,4 +1,5 @@
 # subsystems
+OBJS-$(CONFIG_FFT)                      += aarch64/fft_init_aarch64.o
 OBJS-$(CONFIG_FMTCONVERT)               += aarch64/fmtconvert_init.o
 OBJS-$(CONFIG_H264CHROMA)               += aarch64/h264chroma_init_aarch64.o
 OBJS-$(CONFIG_H264DSP)                  += aarch64/h264dsp_init_aarch64.o
@@ -35,6 +36,7 @@ ARMV8-OBJS-$(CONFIG_VIDEODSP)           += aarch64/videodsp.o

 # subsystems
 NEON-OBJS-$(CONFIG_AAC_DECODER)         += aarch64/sbrdsp_neon.o
+NEON-OBJS-$(CONFIG_FFT)                 += aarch64/fft_neon.o
 NEON-OBJS-$(CONFIG_FMTCONVERT)          += aarch64/fmtconvert_neon.o
 NEON-OBJS-$(CONFIG_H264CHROMA)          += aarch64/h264cmc_neon.o
 NEON-OBJS-$(CONFIG_H264DSP)             += aarch64/h264dsp_neon.o              \
@@ -45,6 +47,7 @@ NEON-OBJS-$(CONFIG_H264QPEL)            += aarch64/h264qpel_neon.o             \
 NEON-OBJS-$(CONFIG_HPELDSP)             += aarch64/hpeldsp_neon.o
 NEON-OBJS-$(CONFIG_IDCTDSP)             += aarch64/idctdsp_neon.o              \
                                           aarch64/simple_idct_neon.o
+NEON-OBJS-$(CONFIG_MDCT)                += aarch64/mdct_neon.o
 NEON-OBJS-$(CONFIG_ME_CMP)              += aarch64/me_cmp_neon.o
 NEON-OBJS-$(CONFIG_MPEGAUDIODSP)        += aarch64/mpegaudiodsp_neon.o
 NEON-OBJS-$(CONFIG_PIXBLOCKDSP)         += aarch64/pixblockdsp_neon.o
@@ -62,9 +65,7 @@ NEON-OBJS-$(CONFIG_VP9_DECODER)         += aarch64/vp9itxfm_16bpp_neon.o       \
                                           aarch64/vp9lpf_neon.o               \
                                           aarch64/vp9mc_16bpp_neon.o          \
                                           aarch64/vp9mc_neon.o
-NEON-OBJS-$(CONFIG_HEVC_DECODER)        += aarch64/hevcdsp_deblock_neon.o      \
-                                           aarch64/hevcdsp_idct_neon.o         \
+NEON-OBJS-$(CONFIG_HEVC_DECODER)        += aarch64/hevcdsp_idct_neon.o         \
                                           aarch64/hevcdsp_init_aarch64.o      \
                                           aarch64/hevcdsp_qpel_neon.o         \
-                                           aarch64/hevcdsp_epel_neon.o         \
                                           aarch64/hevcdsp_sao_neon.o
--- a/libavcodec/aarch64/aacpsdsp_neon.S
+++ b/libavcodec/aarch64/aacpsdsp_neon.S
@@ -19,130 +19,130 @@
 #include "libavutil/aarch64/asm.S"

 function ff_ps_add_squares_neon, export=1
-1:      ld1             {v0.4s,v1.4s}, [x1], #32
-        fmul            v0.4s, v0.4s, v0.4s
-        fmul            v1.4s, v1.4s, v1.4s
-        faddp           v2.4s, v0.4s, v1.4s
-        ld1             {v3.4s}, [x0]
-        fadd            v3.4s, v3.4s, v2.4s
-        st1             {v3.4s}, [x0], #16
-        subs            w2, w2, #4
-        b.gt            1b
+1:      ld1         {v0.4S,v1.4S}, [x1], #32
+        fmul        v0.4S, v0.4S, v0.4S
+        fmul        v1.4S, v1.4S, v1.4S
+        faddp       v2.4S, v0.4S, v1.4S
+        ld1         {v3.4S}, [x0]
+        fadd        v3.4S, v3.4S, v2.4S
+        st1         {v3.4S}, [x0], #16
+        subs        w2, w2, #4
+        b.gt        1b
        ret
 endfunc

 function ff_ps_mul_pair_single_neon, export=1
-1:      ld1             {v0.4s,v1.4s}, [x1], #32
-        ld1             {v2.4s},       [x2], #16
-        zip1            v3.4s, v2.4s, v2.4s
-        zip2            v4.4s, v2.4s, v2.4s
-        fmul            v0.4s, v0.4s, v3.4s
-        fmul            v1.4s, v1.4s, v4.4s
-        st1             {v0.4s,v1.4s}, [x0], #32
-        subs            w3, w3, #4
-        b.gt            1b
+1:      ld1         {v0.4S,v1.4S}, [x1], #32
+        ld1         {v2.4S},       [x2], #16
+        zip1        v3.4S, v2.4S, v2.4S
+        zip2        v4.4S, v2.4S, v2.4S
+        fmul        v0.4S, v0.4S, v3.4S
+        fmul        v1.4S, v1.4S, v4.4S
+        st1         {v0.4S,v1.4S}, [x0], #32
+        subs        w3, w3, #4
+        b.gt        1b
        ret
 endfunc

 function ff_ps_stereo_interpolate_neon, export=1
-        ld1             {v0.4s}, [x2]
-        ld1             {v1.4s}, [x3]
-        zip1            v4.4s, v0.4s, v0.4s
-        zip2            v5.4s, v0.4s, v0.4s
-        zip1            v6.4s, v1.4s, v1.4s
-        zip2            v7.4s, v1.4s, v1.4s
-1:      ld1             {v2.2s}, [x0]
-        ld1             {v3.2s}, [x1]
-        fadd            v4.4s, v4.4s, v6.4s
-        fadd            v5.4s, v5.4s, v7.4s
-        mov             v2.d[1], v2.d[0]
-        mov             v3.d[1], v3.d[0]
-        fmul            v2.4s, v2.4s, v4.4s
-        fmla            v2.4s, v3.4s, v5.4s
-        st1             {v2.d}[0], [x0], #8
-        st1             {v2.d}[1], [x1], #8
-        subs            w4, w4, #1
-        b.gt            1b
+        ld1         {v0.4S}, [x2]
+        ld1         {v1.4S}, [x3]
+        zip1        v4.4S, v0.4S, v0.4S
+        zip2        v5.4S, v0.4S, v0.4S
+        zip1        v6.4S, v1.4S, v1.4S
+        zip2        v7.4S, v1.4S, v1.4S
+1:      ld1         {v2.2S}, [x0]
+        ld1         {v3.2S}, [x1]
+        fadd        v4.4S, v4.4S, v6.4S
+        fadd        v5.4S, v5.4S, v7.4S
+        mov         v2.D[1], v2.D[0]
+        mov         v3.D[1], v3.D[0]
+        fmul        v2.4S, v2.4S, v4.4S
+        fmla        v2.4S, v3.4S, v5.4S
+        st1         {v2.D}[0], [x0], #8
+        st1         {v2.D}[1], [x1], #8
+        subs        w4, w4, #1
+        b.gt        1b
        ret
 endfunc

 function ff_ps_stereo_interpolate_ipdopd_neon, export=1
-        ld1             {v0.4s,v1.4s}, [x2]
-        ld1             {v6.4s,v7.4s}, [x3]
-        fneg            v2.4s, v1.4s
-        fneg            v3.4s, v7.4s
-        zip1            v16.4s, v0.4s, v0.4s
-        zip2            v17.4s, v0.4s, v0.4s
-        zip1            v18.4s, v2.4s, v1.4s
-        zip2            v19.4s, v2.4s, v1.4s
-        zip1            v20.4s, v6.4s, v6.4s
-        zip2            v21.4s, v6.4s, v6.4s
-        zip1            v22.4s, v3.4s, v7.4s
-        zip2            v23.4s, v3.4s, v7.4s
-1:      ld1             {v2.2s}, [x0]
-        ld1             {v3.2s}, [x1]
-        fadd            v16.4s, v16.4s, v20.4s
-        fadd            v17.4s, v17.4s, v21.4s
-        mov             v2.d[1], v2.d[0]
-        mov             v3.d[1], v3.d[0]
-        fmul            v4.4s, v2.4s, v16.4s
-        fmla            v4.4s, v3.4s, v17.4s
-        fadd            v18.4s, v18.4s, v22.4s
-        fadd            v19.4s, v19.4s, v23.4s
-        ext             v2.16b, v2.16b, v2.16b, #4
-        ext             v3.16b, v3.16b, v3.16b, #4
-        fmla            v4.4s, v2.4s, v18.4s
-        fmla            v4.4s, v3.4s, v19.4s
-        st1             {v4.d}[0], [x0], #8
-        st1             {v4.d}[1], [x1], #8
-        subs            w4, w4, #1
-        b.gt            1b
+        ld1         {v0.4S,v1.4S}, [x2]
+        ld1         {v6.4S,v7.4S}, [x3]
+        fneg        v2.4S, v1.4S
+        fneg        v3.4S, v7.4S
+        zip1        v16.4S, v0.4S, v0.4S
+        zip2        v17.4S, v0.4S, v0.4S
+        zip1        v18.4S, v2.4S, v1.4S
+        zip2        v19.4S, v2.4S, v1.4S
+        zip1        v20.4S, v6.4S, v6.4S
+        zip2        v21.4S, v6.4S, v6.4S
+        zip1        v22.4S, v3.4S, v7.4S
+        zip2        v23.4S, v3.4S, v7.4S
+1:      ld1         {v2.2S}, [x0]
+        ld1         {v3.2S}, [x1]
+        fadd        v16.4S, v16.4S, v20.4S
+        fadd        v17.4S, v17.4S, v21.4S
+        mov         v2.D[1], v2.D[0]
+        mov         v3.D[1], v3.D[0]
+        fmul        v4.4S, v2.4S, v16.4S
+        fmla        v4.4S, v3.4S, v17.4S
+        fadd        v18.4S, v18.4S, v22.4S
+        fadd        v19.4S, v19.4S, v23.4S
+        ext         v2.16B, v2.16B, v2.16B, #4
+        ext         v3.16B, v3.16B, v3.16B, #4
+        fmla        v4.4S, v2.4S, v18.4S
+        fmla        v4.4S, v3.4S, v19.4S
+        st1         {v4.D}[0], [x0], #8
+        st1         {v4.D}[1], [x1], #8
+        subs        w4, w4, #1
+        b.gt        1b
        ret
 endfunc

 function ff_ps_hybrid_analysis_neon, export=1
-        lsl             x3, x3, #3
-        ld2             {v0.4s,v1.4s}, [x1], #32
-        ld2             {v2.2s,v3.2s}, [x1], #16
-        ld1             {v24.2s},      [x1], #8
-        ld2             {v4.2s,v5.2s}, [x1], #16
-        ld2             {v6.4s,v7.4s}, [x1]
-        rev64           v6.4s, v6.4s
-        rev64           v7.4s, v7.4s
-        ext             v6.16b, v6.16b, v6.16b, #8
-        ext             v7.16b, v7.16b, v7.16b, #8
-        rev64           v4.2s, v4.2s
-        rev64           v5.2s, v5.2s
-        mov             v2.d[1], v3.d[0]
-        mov             v4.d[1], v5.d[0]
-        mov             v5.d[1], v2.d[0]
-        mov             v3.d[1], v4.d[0]
-        fadd            v16.4s, v0.4s, v6.4s
-        fadd            v17.4s, v1.4s, v7.4s
-        fsub            v18.4s, v1.4s, v7.4s
-        fsub            v19.4s, v0.4s, v6.4s
-        fadd            v22.4s, v2.4s, v4.4s
-        fsub            v23.4s, v5.4s, v3.4s
-        trn1            v20.2d, v22.2d, v23.2d      // {re4+re8, re5+re7, im8-im4, im7-im5}
-        trn2            v21.2d, v22.2d, v23.2d      // {im4+im8, im5+im7, re4-re8, re5-re7}
-1:      ld2             {v2.4s,v3.4s}, [x2], #32
-        ld2             {v4.2s,v5.2s}, [x2], #16
-        ld1             {v6.2s},       [x2], #8
-        add             x2, x2, #8
-        mov             v4.d[1], v5.d[0]
-        mov             v6.s[1], v6.s[0]
-        fmul            v6.2s, v6.2s, v24.2s
-        fmul            v0.4s, v2.4s, v16.4s
-        fmul            v1.4s, v2.4s, v17.4s
-        fmls            v0.4s, v3.4s, v18.4s
-        fmla            v1.4s, v3.4s, v19.4s
-        fmla            v0.4s, v4.4s, v20.4s
-        fmla            v1.4s, v4.4s, v21.4s
-        faddp           v0.4s, v0.4s, v1.4s
-        faddp           v0.4s, v0.4s, v0.4s
-        fadd            v0.2s, v0.2s, v6.2s
-        st1             {v0.2s}, [x0], x3
-        subs            w4, w4, #1
-        b.gt            1b
+        lsl         x3, x3, #3
+        ld2         {v0.4S,v1.4S}, [x1], #32
+        ld2         {v2.2S,v3.2S}, [x1], #16
+        ld1         {v24.2S},      [x1], #8
+        ld2         {v4.2S,v5.2S}, [x1], #16
+        ld2         {v6.4S,v7.4S}, [x1]
+        rev64       v6.4S, v6.4S
+        rev64       v7.4S, v7.4S
+        ext         v6.16B, v6.16B, v6.16B, #8
+        ext         v7.16B, v7.16B, v7.16B, #8
+        rev64       v4.2S, v4.2S
+        rev64       v5.2S, v5.2S
+        mov         v2.D[1], v3.D[0]
+        mov         v4.D[1], v5.D[0]
+        mov         v5.D[1], v2.D[0]
+        mov         v3.D[1], v4.D[0]
+        fadd        v16.4S, v0.4S, v6.4S
+        fadd        v17.4S, v1.4S, v7.4S
+        fsub        v18.4S, v1.4S, v7.4S
+        fsub        v19.4S, v0.4S, v6.4S
+        fadd        v22.4S, v2.4S, v4.4S
+        fsub        v23.4S, v5.4S, v3.4S
+        trn1        v20.2D, v22.2D, v23.2D      // {re4+re8, re5+re7, im8-im4, im7-im5}
+        trn2        v21.2D, v22.2D, v23.2D      // {im4+im8, im5+im7, re4-re8, re5-re7}
+1:      ld2         {v2.4S,v3.4S}, [x2], #32
+        ld2         {v4.2S,v5.2S}, [x2], #16
+        ld1         {v6.2S},       [x2], #8
+        add         x2, x2, #8
+        mov         v4.D[1], v5.D[0]
+        mov         v6.S[1], v6.S[0]
+        fmul        v6.2S, v6.2S, v24.2S
+        fmul        v0.4S, v2.4S, v16.4S
+        fmul        v1.4S, v2.4S, v17.4S
+        fmls        v0.4S, v3.4S, v18.4S
+        fmla        v1.4S, v3.4S, v19.4S
+        fmla        v0.4S, v4.4S, v20.4S
+        fmla        v1.4S, v4.4S, v21.4S
+        faddp       v0.4S, v0.4S, v1.4S
+        faddp       v0.4S, v0.4S, v0.4S
+        fadd        v0.2S, v0.2S, v6.2S
+        st1         {v0.2S}, [x0], x3
+        subs        w4, w4, #1
+        b.gt        1b
        ret
 endfunc
--- a/libavcodec/aarch64/asm-offsets.h
+++ b/libavcodec/aarch64/asm-offsets.h
@@ -0,0 +1,25 @@
+/*
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#ifndef AVCODEC_AARCH64_ASM_OFFSETS_H
+#define AVCODEC_AARCH64_ASM_OFFSETS_H
+
+/* FFTContext */
+#define IMDCT_HALF                      0x48
+
+#endif /* AVCODEC_AARCH64_ASM_OFFSETS_H */
--- a/libavcodec/aarch64/fft_init_aarch64.c
+++ b/libavcodec/aarch64/fft_init_aarch64.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright (c) 2009 Mans Rullgard <mans@mansr.com>
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include "config.h"
+
+#include "libavutil/attributes.h"
+#include "libavutil/cpu.h"
+#include "libavutil/aarch64/cpu.h"
+
+#include "libavcodec/fft.h"
+
+void ff_fft_permute_neon(FFTContext *s, FFTComplex *z);
+void ff_fft_calc_neon(FFTContext *s, FFTComplex *z);
+
+void ff_imdct_calc_neon(FFTContext *s, FFTSample *output, const FFTSample *input);
+void ff_imdct_half_neon(FFTContext *s, FFTSample *output, const FFTSample *input);
+void ff_mdct_calc_neon(FFTContext *s, FFTSample *output, const FFTSample *input);
+
+av_cold void ff_fft_init_aarch64(FFTContext *s)
+{
+    int cpu_flags = av_get_cpu_flags();
+
+    if (have_neon(cpu_flags)) {
+        if (s->nbits < 17) {
+            s->fft_permute = ff_fft_permute_neon;
+            s->fft_calc    = ff_fft_calc_neon;
+        }
+#if CONFIG_MDCT
+        s->imdct_calc   = ff_imdct_calc_neon;
+        s->imdct_half   = ff_imdct_half_neon;
+        s->mdct_calc    = ff_mdct_calc_neon;
+        s->mdct_permutation = FF_MDCT_PERM_INTERLEAVE;
+#endif
+    }
+}
--- a/libavcodec/aarch64/fft_neon.S
+++ b/libavcodec/aarch64/fft_neon.S
@@ -0,0 +1,447 @@
+/*
+ * ARM NEON optimised FFT
+ *
+ * Copyright (c) 2009 Mans Rullgard <mans@mansr.com>
+ * Copyright (c) 2009 Naotoshi Nojiri
+ * Copyright (c) 2014 Janne Grunau <janne-libav@jannau.net>
+ *
+ * This algorithm (though not any of the implementation details) is
+ * based on libdjbfft by D. J. Bernstein.
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include "libavutil/aarch64/asm.S"
+
+#define M_SQRT1_2 0.70710678118654752440
+
+.macro transpose d0, d1, s0, s1
+        trn1            \d0, \s0, \s1
+        trn2            \d1, \s0, \s1
+.endm
+
+
+function fft4_neon
+        AARCH64_VALID_JUMP_TARGET
+        ld1             {v0.2s,v1.2s,v2.2s,v3.2s}, [x0]
+
+        fadd            v4.2s,  v0.2s,  v1.2s   // r0+r1,i0+i1
+        fsub            v6.2s,  v0.2s,  v1.2s   // r0-r1,i0-i1
+
+        ext             v16.8b, v2.8b,  v3.8b,  #4
+        ext             v17.8b, v3.8b,  v2.8b,  #4
+
+        fadd            v5.2s,  v2.2s,  v3.2s   // i2+i3,r2+r3
+        fsub            v7.2s,  v16.2s, v17.2s  // r3-r2,i2-i3
+
+        fadd            v0.2s,  v4.2s,  v5.2s
+        fsub            v2.2s,  v4.2s,  v5.2s
+        fadd            v1.2s,  v6.2s,  v7.2s
+        fsub            v3.2s,  v6.2s,  v7.2s
+
+        st1             {v0.2s,v1.2s,v2.2s,v3.2s}, [x0]
+
+        ret
+endfunc
+
+function fft8_neon
+        AARCH64_VALID_JUMP_TARGET
+        mov             x1,  x0
+        ld1             {v0.2s, v1.2s, v2.2s, v3.2s},  [x0], #32
+        ld1             {v16.2s,v17.2s,v18.2s,v19.2s}, [x0]
+        ext             v22.8b, v2.8b,  v3.8b,  #4
+        ext             v23.8b, v3.8b,  v2.8b,  #4
+        fadd            v4.2s,  v16.2s, v17.2s           // r4+r5,i4+i5
+        fadd            v5.2s,  v18.2s, v19.2s           // r6+r7,i6+i7
+        fsub            v17.2s, v16.2s, v17.2s           // r4-r5,i4-i5
+        fsub            v19.2s, v18.2s, v19.2s           // r6-r7,i6-i7
+        rev64           v27.2s, v28.2s  // ???
+        fadd            v20.2s, v0.2s,  v1.2s            // r0+r1,i0+i1
+        fadd            v21.2s, v2.2s,  v3.2s            // r2+r3,i2+i3
+        fmul            v26.2s, v17.2s, v28.2s           // -a2r*w,a2i*w
+        ext             v6.8b,  v4.8b,  v5.8b,  #4
+        ext             v7.8b,  v5.8b,  v4.8b,  #4
+        fmul            v27.2s, v19.2s, v27.2s           // a3r*w,-a3i*w
+        fsub            v23.2s, v22.2s, v23.2s           // i2-i3,r3-r2
+        fsub            v22.2s, v0.2s,  v1.2s            // r0-r1,i0-i1
+        fmul            v24.2s, v17.2s, v28.s[1]         // a2r*w,a2i*w
+        fmul            v25.2s, v19.2s, v28.s[1]         // a3r*w,a3i*w
+        fadd            v0.2s,  v20.2s, v21.2s
+        fsub            v2.2s,  v20.2s, v21.2s
+        fadd            v1.2s,  v22.2s, v23.2s
+        rev64           v26.2s, v26.2s
+        rev64           v27.2s, v27.2s
+        fsub            v3.2s,  v22.2s, v23.2s
+        fsub            v6.2s,  v6.2s,  v7.2s
+        fadd            v24.2s, v24.2s, v26.2s  // a2r+a2i,a2i-a2r   t1,t2
+        fadd            v25.2s, v25.2s, v27.2s  // a3r-a3i,a3i+a3r   t5,t6
+        fadd            v7.2s,  v4.2s,  v5.2s
+        fsub            v18.2s, v2.2s,  v6.2s
+        ext             v26.8b, v24.8b, v25.8b, #4
+        ext             v27.8b, v25.8b, v24.8b, #4
+        fadd            v2.2s,  v2.2s,  v6.2s
+        fsub            v16.2s, v0.2s,  v7.2s
+        fadd            v5.2s,  v25.2s, v24.2s
+        fsub            v4.2s,  v26.2s, v27.2s
+        fadd            v0.2s,  v0.2s,  v7.2s
+        fsub            v17.2s, v1.2s,  v5.2s
+        fsub            v19.2s, v3.2s,  v4.2s
+        fadd            v3.2s,  v3.2s,  v4.2s
+        fadd            v1.2s,  v1.2s,  v5.2s
+
+        st1             {v16.2s,v17.2s,v18.2s,v19.2s}, [x0]
+        st1             {v0.2s, v1.2s, v2.2s, v3.2s},  [x1]
+
+        ret
+endfunc
+
+function fft16_neon
+        AARCH64_VALID_JUMP_TARGET
+        mov             x1,  x0
+        ld1             {v0.2s, v1.2s, v2.2s, v3.2s},  [x0], #32
+        ld1             {v16.2s,v17.2s,v18.2s,v19.2s}, [x0], #32
+        ext             v22.8b, v2.8b,  v3.8b,  #4
+        ext             v23.8b, v3.8b,  v2.8b,  #4
+        fadd            v4.2s,  v16.2s, v17.2s           // r4+r5,i4+i5
+        fadd            v5.2s,  v18.2s, v19.2s           // r6+r7,i6+i7
+        fsub            v17.2s, v16.2s, v17.2s           // r4-r5,i4-i5
+        fsub            v19.2s, v18.2s, v19.2s           // r6-r7,i6-i7
+        rev64           v27.2s, v28.2s  // ???
+        fadd            v20.2s, v0.2s,  v1.2s            // r0+r1,i0+i1
+        fadd            v21.2s, v2.2s,  v3.2s            // r2+r3,i2+i3
+        fmul            v26.2s, v17.2s, v28.2s           // -a2r*w,a2i*w
+        ext             v6.8b,  v4.8b,  v5.8b,  #4
+        ext             v7.8b,  v5.8b,  v4.8b,  #4
+        fmul            v27.2s, v19.2s, v27.2s           // a3r*w,-a3i*w
+        fsub            v23.2s, v22.2s, v23.2s           // i2-i3,r3-r2
+        fsub            v22.2s, v0.2s,  v1.2s            // r0-r1,i0-i1
+        fmul            v24.2s, v17.2s, v28.s[1]         // a2r*w,a2i*w
+        fmul            v25.2s, v19.2s, v28.s[1]         // a3r*w,a3i*w
+        fadd            v0.2s,  v20.2s, v21.2s
+        fsub            v2.2s,  v20.2s, v21.2s
+        fadd            v1.2s,  v22.2s, v23.2s
+        rev64           v26.2s, v26.2s
+        rev64           v27.2s, v27.2s
+        fsub            v3.2s,  v22.2s, v23.2s
+        fsub            v6.2s,  v6.2s,  v7.2s
+        fadd            v24.2s, v24.2s, v26.2s  // a2r+a2i,a2i-a2r   t1,t2
+        fadd            v25.2s, v25.2s, v27.2s  // a3r-a3i,a3i+a3r   t5,t6
+        fadd            v7.2s,  v4.2s,  v5.2s
+        fsub            v18.2s, v2.2s,  v6.2s
+        ld1             {v20.4s,v21.4s}, [x0], #32
+        ld1             {v22.4s,v23.4s}, [x0], #32
+        ext             v26.8b, v24.8b, v25.8b, #4
+        ext             v27.8b, v25.8b, v24.8b, #4
+        fadd            v2.2s,  v2.2s,  v6.2s
+        fsub            v16.2s, v0.2s,  v7.2s
+        fadd            v5.2s,  v25.2s, v24.2s
+        fsub            v4.2s,  v26.2s, v27.2s
+        transpose       v24.2d, v25.2d, v20.2d, v22.2d
+        transpose       v26.2d, v27.2d, v21.2d, v23.2d
+        fadd            v0.2s,  v0.2s,  v7.2s
+        fsub            v17.2s, v1.2s,  v5.2s
+        fsub            v19.2s, v3.2s,  v4.2s
+        fadd            v3.2s,  v3.2s,  v4.2s
+        fadd            v1.2s,  v1.2s,  v5.2s
+        ext             v20.16b, v21.16b, v21.16b,  #4
+        ext             v21.16b, v23.16b, v23.16b,  #4
+
+        zip1            v0.2d,  v0.2d,  v1.2d   // {z[0],   z[1]}
+        zip1            v1.2d,  v2.2d,  v3.2d   // {z[2],   z[3]}
+        zip1            v2.2d,  v16.2d, v17.2d  // {z[o1],  z[o1+1]}
+        zip1            v3.2d,  v18.2d, v19.2d  // {z[o1+2],z[o1+3]}
+
+        // 2 x fft4
+        transpose       v22.2d, v23.2d, v20.2d, v21.2d
+
+        fadd            v4.4s,  v24.4s, v25.4s
+        fadd            v5.4s,  v26.4s, v27.4s
+        fsub            v6.4s,  v24.4s, v25.4s
+        fsub            v7.4s,  v22.4s, v23.4s
+
+        ld1             {v23.4s},  [x14]
+
+        fadd            v24.4s, v4.4s,  v5.4s   // {z[o2+0],z[o2+1]}
+        fsub            v26.4s, v4.4s,  v5.4s   // {z[o2+2],z[o2+3]}
+        fadd            v25.4s, v6.4s,  v7.4s   // {z[o3+0],z[o3+1]}
+        fsub            v27.4s, v6.4s,  v7.4s   // {z[o3+2],z[o3+3]}
+
+        //fft_pass_neon_16
+        rev64           v7.4s,  v25.4s
+        fmul            v25.4s, v25.4s, v23.s[1]
+        fmul            v7.4s,  v7.4s,  v29.4s
+        fmla            v25.4s, v7.4s,  v23.s[3] // {t1a,t2a,t5a,t6a}
+
+        zip1            v20.4s, v24.4s, v25.4s
+        zip2            v21.4s, v24.4s, v25.4s
+        fneg            v22.4s, v20.4s
+        fadd            v4.4s,  v21.4s, v20.4s
+        fsub            v6.4s,  v20.4s, v21.4s  // just the second half
+        fadd            v5.4s,  v21.4s, v22.4s  // just the first half
+
+        tbl             v4.16b, {v4.16b},        v30.16b // trans4_float
+        tbl             v5.16b, {v5.16b,v6.16b}, v31.16b // trans8_float
+
+        fsub            v20.4s, v0.4s,  v4.4s   // {z[o2],z[o2+1]}
+        fadd            v16.4s, v0.4s,  v4.4s   // {z[0], z[1]}
+        fsub            v22.4s, v2.4s,  v5.4s   // {z[o3],z[o3+1]}
+        fadd            v18.4s, v2.4s,  v5.4s   // {z[o1],z[o1+1]}
+
+//second half
+        rev64           v6.4s,  v26.4s
+        fmul            v26.4s, v26.4s, v23.s[2]
+        rev64           v7.4s,  v27.4s
+        fmul            v27.4s, v27.4s, v23.s[3]
+        fmul            v6.4s,  v6.4s,  v29.4s
+        fmul            v7.4s,  v7.4s,  v29.4s
+        fmla            v26.4s, v6.4s,  v23.s[2] // {t1,t2,t5,t6}
+        fmla            v27.4s, v7.4s,  v23.s[1] // {t1a,t2a,t5a,t6a}
+
+        zip1            v24.4s, v26.4s, v27.4s
+        zip2            v25.4s, v26.4s, v27.4s
+        fneg            v26.4s, v24.4s
+        fadd            v4.4s,  v25.4s, v24.4s
+        fsub            v6.4s,  v24.4s, v25.4s  // just the second half
+        fadd            v5.4s,  v25.4s, v26.4s  // just the first half
+
+        tbl             v4.16b, {v4.16b},        v30.16b // trans4_float
+        tbl             v5.16b, {v5.16b,v6.16b}, v31.16b // trans8_float
+
+        fadd            v17.4s, v1.4s, v4.4s    // {z[2], z[3]}
+        fsub            v21.4s, v1.4s, v4.4s    // {z[o2+2],z[o2+3]}
+        fadd            v19.4s, v3.4s, v5.4s    // {z[o1+2],z[o1+3]}
+        fsub            v23.4s, v3.4s, v5.4s    // {z[o3+2],z[o3+3]}
+
+        st1             {v16.4s,v17.4s}, [x1], #32
+        st1             {v18.4s,v19.4s}, [x1], #32
+        st1             {v20.4s,v21.4s}, [x1], #32
+        st1             {v22.4s,v23.4s}, [x1], #32
+
+        ret
+endfunc
+
+
+const  trans4_float, align=4
+        .byte    0,  1,  2,  3
+        .byte    8,  9, 10, 11
+        .byte    4,  5,  6,  7
+        .byte   12, 13, 14, 15
+endconst
+
+const  trans8_float, align=4
+        .byte   24, 25, 26, 27
+        .byte    0,  1,  2,  3
+        .byte   28, 29, 30, 31
+        .byte    4,  5,  6,  7
+endconst
+
+function fft_pass_neon
+        sub             x6,  x2,  #1            // n - 1, loop counter
+        lsl             x5,  x2,  #3            // 2 * n * sizeof FFTSample
+        lsl             x1,  x2,  #4            // 2 * n * sizeof FFTComplex
+        add             x5,  x4,  x5            // wim
+        add             x3,  x1,  x2,  lsl #5   // 4 * n * sizeof FFTComplex
+        add             x2,  x0,  x2,  lsl #5   // &z[o2]
+        add             x3,  x0,  x3            // &z[o3]
+        add             x1,  x0,  x1            // &z[o1]
+        ld1             {v20.4s},[x2]           // {z[o2],z[o2+1]}
+        ld1             {v22.4s},[x3]           // {z[o3],z[o3+1]}
+        ld1             {v4.2s},  [x4], #8      // {wre[0],wre[1]}
+        trn2            v25.2d, v20.2d, v22.2d
+        sub             x5,  x5,  #4            // wim--
+        trn1            v24.2d, v20.2d, v22.2d
+        ld1             {v5.s}[0],  [x5], x7    // d5[0] = wim[-1]
+        rev64           v7.4s,  v25.4s
+        fmul            v25.4s, v25.4s, v4.s[1]
+        ld1             {v16.4s}, [x0]          // {z[0],z[1]}
+        fmul            v7.4s,  v7.4s,  v29.4s
+        ld1             {v17.4s}, [x1]          // {z[o1],z[o1+1]}
+        prfm            pldl1keep, [x2, #16]
+        prfm            pldl1keep, [x3, #16]
+        fmla            v25.4s, v7.4s,  v5.s[0] // {t1a,t2a,t5a,t6a}
+        prfm            pldl1keep, [x0, #16]
+        prfm            pldl1keep, [x1, #16]
+
+        zip1            v20.4s, v24.4s, v25.4s
+        zip2            v21.4s, v24.4s, v25.4s
+        fneg            v22.4s, v20.4s
+        fadd            v4.4s,  v21.4s, v20.4s
+        fsub            v6.4s,  v20.4s, v21.4s  // just the second half
+        fadd            v5.4s,  v21.4s, v22.4s  // just the first half
+
+        tbl             v4.16b, {v4.16b},        v30.16b // trans4_float
+        tbl             v5.16b, {v5.16b,v6.16b}, v31.16b // trans8_float
+
+        fadd            v20.4s, v16.4s, v4.4s
+        fsub            v22.4s, v16.4s, v4.4s
+        fadd            v21.4s, v17.4s, v5.4s
+        st1             {v20.4s}, [x0], #16     // {z[0], z[1]}
+        fsub            v23.4s, v17.4s, v5.4s
+
+        st1             {v21.4s}, [x1], #16     // {z[o1],z[o1+1]}
+        st1             {v22.4s}, [x2], #16     // {z[o2],z[o2+1]}
+        st1             {v23.4s}, [x3], #16     // {z[o3],z[o3+1]}
+1:
+        ld1             {v20.4s},[x2]    // {z[o2],z[o2+1]}
+        ld1             {v22.4s},[x3]    // {z[o3],z[o3+1]}
+        ld1             {v4.2s}, [x4], #8       // {wre[0],wre[1]}
+        transpose       v26.2d, v27.2d, v20.2d, v22.2d
+        ld1             {v5.2s}, [x5], x7       // {wim[-1],wim[0]}
+        rev64           v6.4s,  v26.4s
+        fmul            v26.4s, v26.4s, v4.s[0]
+        rev64           v7.4s,  v27.4s
+        fmul            v27.4s, v27.4s, v4.s[1]
+        fmul            v6.4s,  v6.4s,  v29.4s
+        fmul            v7.4s,  v7.4s,  v29.4s
+        ld1             {v16.4s},[x0]           // {z[0],z[1]}
+        fmla            v26.4s, v6.4s,  v5.s[1] // {t1,t2,t5,t6}
+        fmla            v27.4s, v7.4s,  v5.s[0] // {t1a,t2a,t5a,t6a}
+        ld1             {v17.4s},[x1]           // {z[o1],z[o1+1]}
+
+        subs            x6,  x6,  #1            // n--
+
+        zip1            v20.4s, v26.4s, v27.4s
+        zip2            v21.4s, v26.4s, v27.4s
+        fneg            v22.4s, v20.4s
+        fadd            v4.4s,  v21.4s, v20.4s
+        fsub            v6.4s,  v20.4s, v21.4s  // just the second half
+        fadd            v5.4s,  v21.4s, v22.4s  // just the first half
+
+        tbl             v4.16b, {v4.16b},        v30.16b // trans4_float
+        tbl             v5.16b, {v5.16b,v6.16b}, v31.16b // trans8_float
+
+        fadd            v20.4s, v16.4s, v4.4s
+        fsub            v22.4s, v16.4s, v4.4s
+        fadd            v21.4s, v17.4s, v5.4s
+        st1             {v20.4s}, [x0], #16     // {z[0], z[1]}
+        fsub            v23.4s, v17.4s, v5.4s
+
+        st1             {v21.4s}, [x1], #16     // {z[o1],z[o1+1]}
+        st1             {v22.4s}, [x2], #16     // {z[o2],z[o2+1]}
+        st1             {v23.4s}, [x3], #16     // {z[o3],z[o3+1]}
+        b.ne            1b
+
+        ret
+endfunc
+
+.macro  def_fft n, n2, n4
+function fft\n\()_neon, align=6
+        AARCH64_VALID_JUMP_TARGET
+        AARCH64_SIGN_LINK_REGISTER
+        stp             x28, x30, [sp, #-16]!
+        add             x28, x0,  #\n4*2*8
+        bl              fft\n2\()_neon
+        mov             x0,  x28
+        bl              fft\n4\()_neon
+        add             x0,  x28, #\n4*1*8
+        bl              fft\n4\()_neon
+        sub             x0,  x28, #\n4*2*8
+        ldp             x28, x30, [sp], #16
+        AARCH64_VALIDATE_LINK_REGISTER
+        movrel          x4,  X(ff_cos_\n)
+        mov             x2,  #\n4>>1
+        b               fft_pass_neon
+endfunc
+.endm
+
+        def_fft    32,    16,     8
+        def_fft    64,    32,    16
+        def_fft   128,    64,    32
+        def_fft   256,   128,    64
+        def_fft   512,   256,   128
+        def_fft  1024,   512,   256
+        def_fft  2048,  1024,   512
+        def_fft  4096,  2048,  1024
+        def_fft  8192,  4096,  2048
+        def_fft 16384,  8192,  4096
+        def_fft 32768, 16384,  8192
+        def_fft 65536, 32768, 16384
+
+function ff_fft_calc_neon, export=1
+        prfm            pldl1keep, [x1]
+        movrel          x10, trans4_float
+        ldr             w2,  [x0]
+        movrel          x11, trans8_float
+        sub             w2,  w2,  #2
+        movrel          x3,  fft_tab_neon
+        ld1             {v30.16b}, [x10]
+        mov             x7,  #-8
+        movrel          x12, pmmp
+        ldr             x3,  [x3, x2, lsl #3]
+        movrel          x13, mppm
+        movrel          x14, X(ff_cos_16)
+        ld1             {v31.16b}, [x11]
+        mov             x0,  x1
+        ld1             {v29.4s},  [x12]         // pmmp
+        ld1             {v28.4s},  [x13]
+        br              x3
+endfunc
+
+function ff_fft_permute_neon, export=1
+        mov             x6,  #1
+        ldr             w2,  [x0]       // nbits
+        ldr             x3,  [x0, #16]  // tmp_buf
+        ldr             x0,  [x0, #8]   // revtab
+        lsl             x6,  x6, x2
+        mov             x2,  x6
+1:
+        ld1             {v0.2s,v1.2s}, [x1], #16
+        ldr             w4,  [x0], #4
+        uxth            w5,  w4
+        lsr             w4,  w4,  #16
+        add             x5,  x3,  x5,  lsl #3
+        add             x4,  x3,  x4,  lsl #3
+        st1             {v0.2s}, [x5]
+        st1             {v1.2s}, [x4]
+        subs            x6,  x6, #2
+        b.gt            1b
+
+        sub             x1,  x1,  x2,  lsl #3
+1:
+        ld1             {v0.4s,v1.4s}, [x3], #32
+        st1             {v0.4s,v1.4s}, [x1], #32
+        subs            x2,  x2,  #4
+        b.gt            1b
+
+        ret
+endfunc
+
+const   fft_tab_neon, relocate=1
+        .quad fft4_neon
+        .quad fft8_neon
+        .quad fft16_neon
+        .quad fft32_neon
+        .quad fft64_neon
+        .quad fft128_neon
+        .quad fft256_neon
+        .quad fft512_neon
+        .quad fft1024_neon
+        .quad fft2048_neon
+        .quad fft4096_neon
+        .quad fft8192_neon
+        .quad fft16384_neon
+        .quad fft32768_neon
+        .quad fft65536_neon
+endconst
+
+const   pmmp, align=4
+        .float          +1.0, -1.0, -1.0, +1.0
+endconst
+
+const   mppm, align=4
+        .float          -M_SQRT1_2, M_SQRT1_2, M_SQRT1_2, -M_SQRT1_2
+endconst
--- a/libavcodec/aarch64/h264cmc_neon.S
+++ b/libavcodec/aarch64/h264cmc_neon.S
@@ -38,11 +38,11 @@ function ff_\type\()_\codec\()_chroma_mc8_neon, export=1
        lsl             w9,  w9,  #3
        lsl             w10, w10, #1
        add             w9,  w9,  w10
-        add             x6,  x6,  w9, uxtw
-        ld1r            {v22.8h}, [x6]
+        add             x6,  x6,  w9, UXTW
+        ld1r            {v22.8H}, [x6]
  .endif
  .ifc \codec,vc1
-        movi            v22.8h,   #28
+        movi            v22.8H,   #28
  .endif
        mul             w7,  w4,  w5
        lsl             w14, w5,  #3
@@ -55,139 +55,139 @@ function ff_\type\()_\codec\()_chroma_mc8_neon, export=1
        add             w4,  w4,  #64
        b.eq            2f

-        dup             v0.8b,  w4
-        dup             v1.8b,  w12
-        ld1             {v4.8b, v5.8b}, [x1], x2
-        dup             v2.8b,  w6
-        dup             v3.8b,  w7
-        ext             v5.8b,  v4.8b,  v5.8b,  #1
-1:      ld1             {v6.8b, v7.8b}, [x1], x2
-        umull           v16.8h, v4.8b,  v0.8b
-        umlal           v16.8h, v5.8b,  v1.8b
-        ext             v7.8b,  v6.8b,  v7.8b,  #1
-        ld1             {v4.8b, v5.8b}, [x1], x2
-        umlal           v16.8h, v6.8b,  v2.8b
+        dup             v0.8B,  w4
+        dup             v1.8B,  w12
+        ld1             {v4.8B, v5.8B}, [x1], x2
+        dup             v2.8B,  w6
+        dup             v3.8B,  w7
+        ext             v5.8B,  v4.8B,  v5.8B,  #1
+1:      ld1             {v6.8B, v7.8B}, [x1], x2
+        umull           v16.8H, v4.8B,  v0.8B
+        umlal           v16.8H, v5.8B,  v1.8B
+        ext             v7.8B,  v6.8B,  v7.8B,  #1
+        ld1             {v4.8B, v5.8B}, [x1], x2
+        umlal           v16.8H, v6.8B,  v2.8B
        prfm            pldl1strm, [x1]
-        ext             v5.8b,  v4.8b,  v5.8b,  #1
-        umlal           v16.8h, v7.8b,  v3.8b
-        umull           v17.8h, v6.8b,  v0.8b
+        ext             v5.8B,  v4.8B,  v5.8B,  #1
+        umlal           v16.8H, v7.8B,  v3.8B
+        umull           v17.8H, v6.8B,  v0.8B
        subs            w3,  w3,  #2
-        umlal           v17.8h, v7.8b, v1.8b
-        umlal           v17.8h, v4.8b, v2.8b
-        umlal           v17.8h, v5.8b, v3.8b
+        umlal           v17.8H, v7.8B, v1.8B
+        umlal           v17.8H, v4.8B, v2.8B
+        umlal           v17.8H, v5.8B, v3.8B
        prfm            pldl1strm, [x1, x2]
  .ifc \codec,h264
-        rshrn           v16.8b, v16.8h, #6
-        rshrn           v17.8b, v17.8h, #6
+        rshrn           v16.8B, v16.8H, #6
+        rshrn           v17.8B, v17.8H, #6
  .else
-        add             v16.8h, v16.8h, v22.8h
-        add             v17.8h, v17.8h, v22.8h
-        shrn            v16.8b, v16.8h, #6
-        shrn            v17.8b, v17.8h, #6
+        add             v16.8H, v16.8H, v22.8H
+        add             v17.8H, v17.8H, v22.8H
+        shrn            v16.8B, v16.8H, #6
+        shrn            v17.8B, v17.8H, #6
  .endif
  .ifc \type,avg
-        ld1             {v20.8b}, [x8], x2
-        ld1             {v21.8b}, [x8], x2
-        urhadd          v16.8b, v16.8b, v20.8b
-        urhadd          v17.8b, v17.8b, v21.8b
+        ld1             {v20.8B}, [x8], x2
+        ld1             {v21.8B}, [x8], x2
+        urhadd          v16.8B, v16.8B, v20.8B
+        urhadd          v17.8B, v17.8B, v21.8B
  .endif
-        st1             {v16.8b}, [x0], x2
-        st1             {v17.8b}, [x0], x2
+        st1             {v16.8B}, [x0], x2
+        st1             {v17.8B}, [x0], x2
        b.gt            1b
        ret

 2:      adds            w12, w12, w6
-        dup             v0.8b, w4
+        dup             v0.8B, w4
        b.eq            5f
        tst             w6,  w6
-        dup             v1.8b, w12
+        dup             v1.8B, w12
        b.eq            4f

-        ld1             {v4.8b}, [x1], x2
-3:      ld1             {v6.8b}, [x1], x2
-        umull           v16.8h, v4.8b,  v0.8b
-        umlal           v16.8h, v6.8b,  v1.8b
-        ld1             {v4.8b}, [x1], x2
-        umull           v17.8h, v6.8b,  v0.8b
-        umlal           v17.8h, v4.8b,  v1.8b
+        ld1             {v4.8B}, [x1], x2
+3:      ld1             {v6.8B}, [x1], x2
+        umull           v16.8H, v4.8B,  v0.8B
+        umlal           v16.8H, v6.8B,  v1.8B
+        ld1             {v4.8B}, [x1], x2
+        umull           v17.8H, v6.8B,  v0.8B
+        umlal           v17.8H, v4.8B,  v1.8B
        prfm            pldl1strm, [x1]
  .ifc \codec,h264
-        rshrn           v16.8b, v16.8h, #6
-        rshrn           v17.8b, v17.8h, #6
+        rshrn           v16.8B, v16.8H, #6
+        rshrn           v17.8B, v17.8H, #6
  .else
-        add             v16.8h, v16.8h, v22.8h
-        add             v17.8h, v17.8h, v22.8h
-        shrn            v16.8b, v16.8h, #6
-        shrn            v17.8b, v17.8h, #6
+        add             v16.8H, v16.8H, v22.8H
+        add             v17.8H, v17.8H, v22.8H
+        shrn            v16.8B, v16.8H, #6
+        shrn            v17.8B, v17.8H, #6
  .endif
        prfm            pldl1strm, [x1, x2]
  .ifc \type,avg
-        ld1             {v20.8b}, [x8], x2
-        ld1             {v21.8b}, [x8], x2
-        urhadd          v16.8b, v16.8b, v20.8b
-        urhadd          v17.8b, v17.8b, v21.8b
+        ld1             {v20.8B}, [x8], x2
+        ld1             {v21.8B}, [x8], x2
+        urhadd          v16.8B, v16.8B, v20.8B
+        urhadd          v17.8B, v17.8B, v21.8B
  .endif
        subs            w3,  w3,  #2
-        st1             {v16.8b}, [x0], x2
-        st1             {v17.8b}, [x0], x2
+        st1             {v16.8B}, [x0], x2
+        st1             {v17.8B}, [x0], x2
        b.gt            3b
        ret

-4:      ld1             {v4.8b, v5.8b}, [x1], x2
-        ld1             {v6.8b, v7.8b}, [x1], x2
-        ext             v5.8b,  v4.8b,  v5.8b,  #1
-        ext             v7.8b,  v6.8b,  v7.8b,  #1
+4:      ld1             {v4.8B, v5.8B}, [x1], x2
+        ld1             {v6.8B, v7.8B}, [x1], x2
+        ext             v5.8B,  v4.8B,  v5.8B,  #1
+        ext             v7.8B,  v6.8B,  v7.8B,  #1
        prfm            pldl1strm, [x1]
        subs            w3,  w3,  #2
-        umull           v16.8h, v4.8b, v0.8b
-        umlal           v16.8h, v5.8b, v1.8b
-        umull           v17.8h, v6.8b, v0.8b
-        umlal           v17.8h, v7.8b, v1.8b
+        umull           v16.8H, v4.8B, v0.8B
+        umlal           v16.8H, v5.8B, v1.8B
+        umull           v17.8H, v6.8B, v0.8B
+        umlal           v17.8H, v7.8B, v1.8B
        prfm            pldl1strm, [x1, x2]
  .ifc \codec,h264
-        rshrn           v16.8b, v16.8h, #6
-        rshrn           v17.8b, v17.8h, #6
+        rshrn           v16.8B, v16.8H, #6
+        rshrn           v17.8B, v17.8H, #6
  .else
-        add             v16.8h, v16.8h, v22.8h
-        add             v17.8h, v17.8h, v22.8h
-        shrn            v16.8b, v16.8h, #6
-        shrn            v17.8b, v17.8h, #6
+        add             v16.8H, v16.8H, v22.8H
+        add             v17.8H, v17.8H, v22.8H
+        shrn            v16.8B, v16.8H, #6
+        shrn            v17.8B, v17.8H, #6
  .endif
  .ifc \type,avg
-        ld1             {v20.8b}, [x8], x2
-        ld1             {v21.8b}, [x8], x2
-        urhadd          v16.8b, v16.8b, v20.8b
-        urhadd          v17.8b, v17.8b, v21.8b
+        ld1             {v20.8B}, [x8], x2
+        ld1             {v21.8B}, [x8], x2
+        urhadd          v16.8B, v16.8B, v20.8B
+        urhadd          v17.8B, v17.8B, v21.8B
  .endif
-        st1             {v16.8b}, [x0], x2
-        st1             {v17.8b}, [x0], x2
+        st1             {v16.8B}, [x0], x2
+        st1             {v17.8B}, [x0], x2
        b.gt            4b
        ret

-5:      ld1             {v4.8b}, [x1], x2
-        ld1             {v5.8b}, [x1], x2
+5:      ld1             {v4.8B}, [x1], x2
+        ld1             {v5.8B}, [x1], x2
        prfm            pldl1strm, [x1]
        subs            w3,  w3,  #2
-        umull           v16.8h, v4.8b, v0.8b
-        umull           v17.8h, v5.8b, v0.8b
+        umull           v16.8H, v4.8B, v0.8B
+        umull           v17.8H, v5.8B, v0.8B
        prfm            pldl1strm, [x1, x2]
  .ifc \codec,h264
-        rshrn           v16.8b, v16.8h, #6
-        rshrn           v17.8b, v17.8h, #6
+        rshrn           v16.8B, v16.8H, #6
+        rshrn           v17.8B, v17.8H, #6
  .else
-        add             v16.8h, v16.8h, v22.8h
-        add             v17.8h, v17.8h, v22.8h
-        shrn            v16.8b, v16.8h, #6
-        shrn            v17.8b, v17.8h, #6
+        add             v16.8H, v16.8H, v22.8H
+        add             v17.8H, v17.8H, v22.8H
+        shrn            v16.8B, v16.8H, #6
+        shrn            v17.8B, v17.8H, #6
  .endif
  .ifc \type,avg
-        ld1             {v20.8b}, [x8], x2
-        ld1             {v21.8b}, [x8], x2
-        urhadd          v16.8b, v16.8b, v20.8b
-        urhadd          v17.8b, v17.8b, v21.8b
+        ld1             {v20.8B}, [x8], x2
+        ld1             {v21.8B}, [x8], x2
+        urhadd          v16.8B, v16.8B, v20.8B
+        urhadd          v17.8B, v17.8B, v21.8B
  .endif
-        st1             {v16.8b}, [x0], x2
-        st1             {v17.8b}, [x0], x2
+        st1             {v16.8B}, [x0], x2
+        st1             {v17.8B}, [x0], x2
        b.gt            5b
        ret
 endfunc
@@ -208,11 +208,11 @@ function ff_\type\()_\codec\()_chroma_mc4_neon, export=1
        lsl             w9,  w9,  #3
        lsl             w10, w10, #1
        add             w9,  w9,  w10
-        add             x6,  x6,  w9, uxtw
-        ld1r            {v22.8h}, [x6]
+        add             x6,  x6,  w9, UXTW
+        ld1r            {v22.8H}, [x6]
  .endif
  .ifc \codec,vc1
-        movi            v22.8h,   #28
+        movi            v22.8H,   #28
  .endif
        mul             w7,  w4,  w5
        lsl             w14, w5,  #3
@@ -225,133 +225,133 @@ function ff_\type\()_\codec\()_chroma_mc4_neon, export=1
        add             w4,  w4,  #64
        b.eq            2f

-        dup             v24.8b,  w4
-        dup             v25.8b,  w12
-        ld1             {v4.8b}, [x1], x2
-        dup             v26.8b,  w6
-        dup             v27.8b,  w7
-        ext             v5.8b,  v4.8b,  v5.8b, #1
-        trn1            v0.2s,  v24.2s, v25.2s
-        trn1            v2.2s,  v26.2s, v27.2s
-        trn1            v4.2s,  v4.2s,  v5.2s
-1:      ld1             {v6.8b}, [x1], x2
-        ext             v7.8b,  v6.8b,  v7.8b, #1
-        trn1            v6.2s,  v6.2s,  v7.2s
-        umull           v18.8h, v4.8b,  v0.8b
-        umlal           v18.8h, v6.8b,  v2.8b
-        ld1             {v4.8b}, [x1], x2
-        ext             v5.8b,  v4.8b,  v5.8b, #1
-        trn1            v4.2s,  v4.2s,  v5.2s
+        dup             v24.8B,  w4
+        dup             v25.8B,  w12
+        ld1             {v4.8B}, [x1], x2
+        dup             v26.8B,  w6
+        dup             v27.8B,  w7
+        ext             v5.8B,  v4.8B,  v5.8B, #1
+        trn1            v0.2S,  v24.2S, v25.2S
+        trn1            v2.2S,  v26.2S, v27.2S
+        trn1            v4.2S,  v4.2S,  v5.2S
+1:      ld1             {v6.8B}, [x1], x2
+        ext             v7.8B,  v6.8B,  v7.8B, #1
+        trn1            v6.2S,  v6.2S,  v7.2S
+        umull           v18.8H, v4.8B,  v0.8B
+        umlal           v18.8H, v6.8B,  v2.8B
+        ld1             {v4.8B}, [x1], x2
+        ext             v5.8B,  v4.8B,  v5.8B, #1
+        trn1            v4.2S,  v4.2S,  v5.2S
        prfm            pldl1strm, [x1]
-        umull           v19.8h, v6.8b,  v0.8b
-        umlal           v19.8h, v4.8b,  v2.8b
-        trn1            v30.2d, v18.2d, v19.2d
-        trn2            v31.2d, v18.2d, v19.2d
-        add             v18.8h, v30.8h, v31.8h
+        umull           v19.8H, v6.8B,  v0.8B
+        umlal           v19.8H, v4.8B,  v2.8B
+        trn1            v30.2D, v18.2D, v19.2D
+        trn2            v31.2D, v18.2D, v19.2D
+        add             v18.8H, v30.8H, v31.8H
  .ifc \codec,h264
-        rshrn           v16.8b, v18.8h, #6
+        rshrn           v16.8B, v18.8H, #6
  .else
-        add             v18.8h, v18.8h, v22.8h
-        shrn            v16.8b, v18.8h, #6
+        add             v18.8H, v18.8H, v22.8H
+        shrn            v16.8B, v18.8H, #6
  .endif
        subs            w3,  w3,  #2
        prfm            pldl1strm, [x1, x2]
  .ifc \type,avg
-        ld1             {v20.s}[0], [x8], x2
-        ld1             {v20.s}[1], [x8], x2
-        urhadd          v16.8b, v16.8b, v20.8b
+        ld1             {v20.S}[0], [x8], x2
+        ld1             {v20.S}[1], [x8], x2
+        urhadd          v16.8B, v16.8B, v20.8B
  .endif
-        st1             {v16.s}[0], [x0], x2
-        st1             {v16.s}[1], [x0], x2
+        st1             {v16.S}[0], [x0], x2
+        st1             {v16.S}[1], [x0], x2
        b.gt            1b
        ret

 2:      adds            w12, w12, w6
-        dup             v30.8b, w4
+        dup             v30.8B, w4
        b.eq            5f
        tst             w6,  w6
-        dup             v31.8b, w12
-        trn1            v0.2s,  v30.2s, v31.2s
-        trn2            v1.2s,  v30.2s, v31.2s
+        dup             v31.8B, w12
+        trn1            v0.2S,  v30.2S, v31.2S
+        trn2            v1.2S,  v30.2S, v31.2S
        b.eq            4f

-        ext             v1.8b,  v0.8b,  v1.8b, #4
-        ld1             {v4.s}[0], [x1], x2
-3:      ld1             {v4.s}[1], [x1], x2
-        umull           v18.8h, v4.8b,  v0.8b
-        ld1             {v4.s}[0], [x1], x2
-        umull           v19.8h, v4.8b,  v1.8b
-        trn1            v30.2d, v18.2d, v19.2d
-        trn2            v31.2d, v18.2d, v19.2d
-        add             v18.8h, v30.8h, v31.8h
+        ext             v1.8B,  v0.8B,  v1.8B, #4
+        ld1             {v4.S}[0], [x1], x2
+3:      ld1             {v4.S}[1], [x1], x2
+        umull           v18.8H, v4.8B,  v0.8B
+        ld1             {v4.S}[0], [x1], x2
+        umull           v19.8H, v4.8B,  v1.8B
+        trn1            v30.2D, v18.2D, v19.2D
+        trn2            v31.2D, v18.2D, v19.2D
+        add             v18.8H, v30.8H, v31.8H
        prfm            pldl1strm, [x1]
  .ifc \codec,h264
-        rshrn           v16.8b, v18.8h, #6
+        rshrn           v16.8B, v18.8H, #6
  .else
-        add             v18.8h, v18.8h, v22.8h
-        shrn            v16.8b, v18.8h, #6
+        add             v18.8H, v18.8H, v22.8H
+        shrn            v16.8B, v18.8H, #6
  .endif
  .ifc \type,avg
-        ld1             {v20.s}[0], [x8], x2
-        ld1             {v20.s}[1], [x8], x2
-        urhadd          v16.8b, v16.8b, v20.8b
+        ld1             {v20.S}[0], [x8], x2
+        ld1             {v20.S}[1], [x8], x2
+        urhadd          v16.8B, v16.8B, v20.8B
  .endif
        subs            w3,  w3,  #2
        prfm            pldl1strm, [x1, x2]
-        st1             {v16.s}[0], [x0], x2
-        st1             {v16.s}[1], [x0], x2
+        st1             {v16.S}[0], [x0], x2
+        st1             {v16.S}[1], [x0], x2
        b.gt            3b
        ret

-4:      ld1             {v4.8b}, [x1], x2
-        ld1             {v6.8b}, [x1], x2
-        ext             v5.8b,  v4.8b,  v5.8b, #1
-        ext             v7.8b,  v6.8b,  v7.8b, #1
-        trn1            v4.2s,  v4.2s,  v5.2s
-        trn1            v6.2s,  v6.2s,  v7.2s
-        umull           v18.8h, v4.8b,  v0.8b
-        umull           v19.8h, v6.8b,  v0.8b
+4:      ld1             {v4.8B}, [x1], x2
+        ld1             {v6.8B}, [x1], x2
+        ext             v5.8B,  v4.8B,  v5.8B, #1
+        ext             v7.8B,  v6.8B,  v7.8B, #1
+        trn1            v4.2S,  v4.2S,  v5.2S
+        trn1            v6.2S,  v6.2S,  v7.2S
+        umull           v18.8H, v4.8B,  v0.8B
+        umull           v19.8H, v6.8B,  v0.8B
        subs            w3,  w3,  #2
-        trn1            v30.2d, v18.2d, v19.2d
-        trn2            v31.2d, v18.2d, v19.2d
-        add             v18.8h, v30.8h, v31.8h
+        trn1            v30.2D, v18.2D, v19.2D
+        trn2            v31.2D, v18.2D, v19.2D
+        add             v18.8H, v30.8H, v31.8H
        prfm            pldl1strm, [x1]
  .ifc \codec,h264
-        rshrn           v16.8b, v18.8h, #6
+        rshrn           v16.8B, v18.8H, #6
  .else
-        add             v18.8h, v18.8h, v22.8h
-        shrn            v16.8b, v18.8h, #6
+        add             v18.8H, v18.8H, v22.8H
+        shrn            v16.8B, v18.8H, #6
  .endif
  .ifc \type,avg
-        ld1             {v20.s}[0], [x8], x2
-        ld1             {v20.s}[1], [x8], x2
-        urhadd          v16.8b, v16.8b, v20.8b
+        ld1             {v20.S}[0], [x8], x2
+        ld1             {v20.S}[1], [x8], x2
+        urhadd          v16.8B, v16.8B, v20.8B
  .endif
        prfm            pldl1strm, [x1]
-        st1             {v16.s}[0], [x0], x2
-        st1             {v16.s}[1], [x0], x2
+        st1             {v16.S}[0], [x0], x2
+        st1             {v16.S}[1], [x0], x2
        b.gt            4b
        ret

-5:      ld1             {v4.s}[0], [x1], x2
-        ld1             {v4.s}[1], [x1], x2
-        umull           v18.8h, v4.8b,  v30.8b
+5:      ld1             {v4.S}[0], [x1], x2
+        ld1             {v4.S}[1], [x1], x2
+        umull           v18.8H, v4.8B,  v30.8B
        subs            w3,  w3,  #2
        prfm            pldl1strm, [x1]
  .ifc \codec,h264
-        rshrn           v16.8b, v18.8h, #6
+        rshrn           v16.8B, v18.8H, #6
  .else
-        add             v18.8h, v18.8h, v22.8h
-        shrn            v16.8b, v18.8h, #6
+        add             v18.8H, v18.8H, v22.8H
+        shrn            v16.8B, v18.8H, #6
  .endif
  .ifc \type,avg
-        ld1             {v20.s}[0], [x8], x2
-        ld1             {v20.s}[1], [x8], x2
-        urhadd          v16.8b, v16.8b, v20.8b
+        ld1             {v20.S}[0], [x8], x2
+        ld1             {v20.S}[1], [x8], x2
+        urhadd          v16.8B, v16.8B, v20.8B
  .endif
        prfm            pldl1strm, [x1]
-        st1             {v16.s}[0], [x0], x2
-        st1             {v16.s}[1], [x0], x2
+        st1             {v16.S}[0], [x0], x2
+        st1             {v16.S}[1], [x0], x2
        b.gt            5b
        ret
 endfunc
@@ -372,51 +372,51 @@ function ff_\type\()_h264_chroma_mc2_neon, export=1
        sub             w4,  w7,  w13
        sub             w4,  w4,  w14
        add             w4,  w4,  #64
-        dup             v0.8b,  w4
-        dup             v2.8b,  w12
-        dup             v1.8b,  w6
-        dup             v3.8b,  w7
-        trn1            v0.4h,  v0.4h,  v2.4h
-        trn1            v1.4h,  v1.4h,  v3.4h
+        dup             v0.8B,  w4
+        dup             v2.8B,  w12
+        dup             v1.8B,  w6
+        dup             v3.8B,  w7
+        trn1            v0.4H,  v0.4H,  v2.4H
+        trn1            v1.4H,  v1.4H,  v3.4H
 1:
-        ld1             {v4.s}[0],  [x1], x2
-        ld1             {v4.s}[1],  [x1], x2
-        rev64           v5.2s,  v4.2s
-        ld1             {v5.s}[1],  [x1]
-        ext             v6.8b,  v4.8b,  v5.8b,  #1
-        ext             v7.8b,  v5.8b,  v4.8b,  #1
-        trn1            v4.4h,  v4.4h,  v6.4h
-        trn1            v5.4h,  v5.4h,  v7.4h
-        umull           v16.8h, v4.8b,  v0.8b
-        umlal           v16.8h, v5.8b,  v1.8b
+        ld1             {v4.S}[0],  [x1], x2
+        ld1             {v4.S}[1],  [x1], x2
+        rev64           v5.2S,  v4.2S
+        ld1             {v5.S}[1],  [x1]
+        ext             v6.8B,  v4.8B,  v5.8B,  #1
+        ext             v7.8B,  v5.8B,  v4.8B,  #1
+        trn1            v4.4H,  v4.4H,  v6.4H
+        trn1            v5.4H,  v5.4H,  v7.4H
+        umull           v16.8H, v4.8B,  v0.8B
+        umlal           v16.8H, v5.8B,  v1.8B
  .ifc \type,avg
-        ld1             {v18.h}[0], [x0], x2
-        ld1             {v18.h}[2], [x0]
+        ld1             {v18.H}[0], [x0], x2
+        ld1             {v18.H}[2], [x0]
        sub             x0,  x0,  x2
  .endif
-        rev64           v17.4s, v16.4s
-        add             v16.8h, v16.8h, v17.8h
-        rshrn           v16.8b, v16.8h, #6
+        rev64           v17.4S, v16.4S
+        add             v16.8H, v16.8H, v17.8H
+        rshrn           v16.8B, v16.8H, #6
  .ifc \type,avg
-        urhadd          v16.8b, v16.8b, v18.8b
+        urhadd          v16.8B, v16.8B, v18.8B
  .endif
-        st1             {v16.h}[0], [x0], x2
-        st1             {v16.h}[2], [x0], x2
+        st1             {v16.H}[0], [x0], x2
+        st1             {v16.H}[2], [x0], x2
        subs            w3,  w3,  #2
        b.gt            1b
        ret

 2:
-        ld1             {v16.h}[0], [x1], x2
-        ld1             {v16.h}[1], [x1], x2
+        ld1             {v16.H}[0], [x1], x2
+        ld1             {v16.H}[1], [x1], x2
  .ifc \type,avg
-        ld1             {v18.h}[0], [x0], x2
-        ld1             {v18.h}[1], [x0]
+        ld1             {v18.H}[0], [x0], x2
+        ld1             {v18.H}[1], [x0]
        sub             x0,  x0,  x2
-        urhadd          v16.8b, v16.8b, v18.8b
+        urhadd          v16.8B, v16.8B, v18.8B
  .endif
-        st1             {v16.h}[0], [x0], x2
-        st1             {v16.h}[1], [x0], x2
+        st1             {v16.H}[0], [x0], x2
+        st1             {v16.H}[1], [x0], x2
        subs            w3,  w3,  #2
        b.gt            2b
        ret
--- a/libavcodec/aarch64/h264dsp_neon.S
+++ b/libavcodec/aarch64/h264dsp_neon.S
@@ -27,7 +27,7 @@
        cmp             w2,  #0
        ldr             w6,  [x4]
        ccmp            w3,  #0, #0, ne
-        mov             v24.s[0], w6
+        mov             v24.S[0], w6
        and             w8,  w6,  w6,  lsl #16
        b.eq            1f
        ands            w8,  w8,  w8,  lsl #8
@@ -38,95 +38,95 @@
 .endm

 .macro  h264_loop_filter_luma
-        dup             v22.16b, w2                     // alpha
-        uxtl            v24.8h,  v24.8b
-        uabd            v21.16b, v16.16b, v0.16b        // abs(p0 - q0)
-        uxtl            v24.4s,  v24.4h
-        uabd            v28.16b, v18.16b, v16.16b       // abs(p1 - p0)
-        sli             v24.8h,  v24.8h,  #8
-        uabd            v30.16b, v2.16b,  v0.16b        // abs(q1 - q0)
-        sli             v24.4s,  v24.4s,  #16
-        cmhi            v21.16b, v22.16b, v21.16b       // < alpha
-        dup             v22.16b, w3                     // beta
-        cmlt            v23.16b, v24.16b, #0
-        cmhi            v28.16b, v22.16b, v28.16b       // < beta
-        cmhi            v30.16b, v22.16b, v30.16b       // < beta
-        bic             v21.16b, v21.16b, v23.16b
-        uabd            v17.16b, v20.16b, v16.16b       // abs(p2 - p0)
-        and             v21.16b, v21.16b, v28.16b
-        uabd            v19.16b,  v4.16b,  v0.16b       // abs(q2 - q0)
-        and             v21.16b, v21.16b, v30.16b      // < beta
+        dup             v22.16B, w2                     // alpha
+        uxtl            v24.8H,  v24.8B
+        uabd            v21.16B, v16.16B, v0.16B        // abs(p0 - q0)
+        uxtl            v24.4S,  v24.4H
+        uabd            v28.16B, v18.16B, v16.16B       // abs(p1 - p0)
+        sli             v24.8H,  v24.8H,  #8
+        uabd            v30.16B, v2.16B,  v0.16B        // abs(q1 - q0)
+        sli             v24.4S,  v24.4S,  #16
+        cmhi            v21.16B, v22.16B, v21.16B       // < alpha
+        dup             v22.16B, w3                     // beta
+        cmlt            v23.16B, v24.16B, #0
+        cmhi            v28.16B, v22.16B, v28.16B       // < beta
+        cmhi            v30.16B, v22.16B, v30.16B       // < beta
+        bic             v21.16B, v21.16B, v23.16B
+        uabd            v17.16B, v20.16B, v16.16B       // abs(p2 - p0)
+        and             v21.16B, v21.16B, v28.16B
+        uabd            v19.16B,  v4.16B,  v0.16B       // abs(q2 - q0)
+        and             v21.16B, v21.16B, v30.16B      // < beta
        shrn            v30.8b,  v21.8h,  #4
        mov             x7, v30.d[0]
-        cmhi            v17.16b, v22.16b, v17.16b       // < beta
-        cmhi            v19.16b, v22.16b, v19.16b       // < beta
+        cmhi            v17.16B, v22.16B, v17.16B       // < beta
+        cmhi            v19.16B, v22.16B, v19.16B       // < beta
        cbz             x7,  9f
-        and             v17.16b, v17.16b, v21.16b
-        and             v19.16b, v19.16b, v21.16b
-        and             v24.16b, v24.16b, v21.16b
-        urhadd          v28.16b, v16.16b,  v0.16b
-        sub             v21.16b, v24.16b, v17.16b
-        uqadd           v23.16b, v18.16b, v24.16b
-        uhadd           v20.16b, v20.16b, v28.16b
-        sub             v21.16b, v21.16b, v19.16b
-        uhadd           v28.16b,  v4.16b, v28.16b
-        umin            v23.16b, v23.16b, v20.16b
-        uqsub           v22.16b, v18.16b, v24.16b
-        uqadd           v4.16b,   v2.16b, v24.16b
-        umax            v23.16b, v23.16b, v22.16b
-        uqsub           v22.16b,  v2.16b, v24.16b
-        umin            v28.16b,  v4.16b, v28.16b
-        uxtl            v4.8h,    v0.8b
-        umax            v28.16b, v28.16b, v22.16b
-        uxtl2           v20.8h,   v0.16b
-        usubw           v4.8h,    v4.8h,  v16.8b
-        usubw2          v20.8h,  v20.8h,  v16.16b
-        shl             v4.8h,    v4.8h,  #2
-        shl             v20.8h,  v20.8h,  #2
-        uaddw           v4.8h,    v4.8h,  v18.8b
-        uaddw2          v20.8h,  v20.8h,  v18.16b
-        usubw           v4.8h,    v4.8h,   v2.8b
-        usubw2          v20.8h,  v20.8h,   v2.16b
-        rshrn           v4.8b,    v4.8h,  #3
-        rshrn2          v4.16b,  v20.8h,  #3
-        bsl             v17.16b, v23.16b, v18.16b
-        bsl             v19.16b, v28.16b,  v2.16b
-        neg             v23.16b, v21.16b
-        uxtl            v28.8h,  v16.8b
-        smin            v4.16b,   v4.16b, v21.16b
-        uxtl2           v21.8h,  v16.16b
-        smax            v4.16b,   v4.16b, v23.16b
-        uxtl            v22.8h,   v0.8b
-        uxtl2           v24.8h,   v0.16b
-        saddw           v28.8h,  v28.8h,  v4.8b
-        saddw2          v21.8h,  v21.8h,  v4.16b
-        ssubw           v22.8h,  v22.8h,  v4.8b
-        ssubw2          v24.8h,  v24.8h,  v4.16b
-        sqxtun          v16.8b,  v28.8h
-        sqxtun2         v16.16b, v21.8h
-        sqxtun          v0.8b,   v22.8h
-        sqxtun2         v0.16b,  v24.8h
+        and             v17.16B, v17.16B, v21.16B
+        and             v19.16B, v19.16B, v21.16B
+        and             v24.16B, v24.16B, v21.16B
+        urhadd          v28.16B, v16.16B,  v0.16B
+        sub             v21.16B, v24.16B, v17.16B
+        uqadd           v23.16B, v18.16B, v24.16B
+        uhadd           v20.16B, v20.16B, v28.16B
+        sub             v21.16B, v21.16B, v19.16B
+        uhadd           v28.16B,  v4.16B, v28.16B
+        umin            v23.16B, v23.16B, v20.16B
+        uqsub           v22.16B, v18.16B, v24.16B
+        uqadd           v4.16B,   v2.16B, v24.16B
+        umax            v23.16B, v23.16B, v22.16B
+        uqsub           v22.16B,  v2.16B, v24.16B
+        umin            v28.16B,  v4.16B, v28.16B
+        uxtl            v4.8H,    v0.8B
+        umax            v28.16B, v28.16B, v22.16B
+        uxtl2           v20.8H,   v0.16B
+        usubw           v4.8H,    v4.8H,  v16.8B
+        usubw2          v20.8H,  v20.8H,  v16.16B
+        shl             v4.8H,    v4.8H,  #2
+        shl             v20.8H,  v20.8H,  #2
+        uaddw           v4.8H,    v4.8H,  v18.8B
+        uaddw2          v20.8H,  v20.8H,  v18.16B
+        usubw           v4.8H,    v4.8H,   v2.8B
+        usubw2          v20.8H,  v20.8H,   v2.16B
+        rshrn           v4.8B,    v4.8H,  #3
+        rshrn2          v4.16B,  v20.8H,  #3
+        bsl             v17.16B, v23.16B, v18.16B
+        bsl             v19.16B, v28.16B,  v2.16B
+        neg             v23.16B, v21.16B
+        uxtl            v28.8H,  v16.8B
+        smin            v4.16B,   v4.16B, v21.16B
+        uxtl2           v21.8H,  v16.16B
+        smax            v4.16B,   v4.16B, v23.16B
+        uxtl            v22.8H,   v0.8B
+        uxtl2           v24.8H,   v0.16B
+        saddw           v28.8H,  v28.8H,  v4.8B
+        saddw2          v21.8H,  v21.8H,  v4.16B
+        ssubw           v22.8H,  v22.8H,  v4.8B
+        ssubw2          v24.8H,  v24.8H,  v4.16B
+        sqxtun          v16.8B,  v28.8H
+        sqxtun2         v16.16B, v21.8H
+        sqxtun          v0.8B,   v22.8H
+        sqxtun2         v0.16B,  v24.8H
 .endm

 function ff_h264_v_loop_filter_luma_neon, export=1
        h264_loop_filter_start

-        ld1             {v0.16b},  [x0], x1
-        ld1             {v2.16b},  [x0], x1
-        ld1             {v4.16b},  [x0], x1
+        ld1             {v0.16B},  [x0], x1
+        ld1             {v2.16B},  [x0], x1
+        ld1             {v4.16B},  [x0], x1
        sub             x0,  x0,  x1, lsl #2
        sub             x0,  x0,  x1, lsl #1
-        ld1             {v20.16b},  [x0], x1
-        ld1             {v18.16b},  [x0], x1
-        ld1             {v16.16b},  [x0], x1
+        ld1             {v20.16B},  [x0], x1
+        ld1             {v18.16B},  [x0], x1
+        ld1             {v16.16B},  [x0], x1

        h264_loop_filter_luma

        sub             x0,  x0,  x1, lsl #1
-        st1             {v17.16b},  [x0], x1
-        st1             {v16.16b}, [x0], x1
-        st1             {v0.16b},  [x0], x1
-        st1             {v19.16b}, [x0]
+        st1             {v17.16B},  [x0], x1
+        st1             {v16.16B}, [x0], x1
+        st1             {v0.16B},  [x0], x1
+        st1             {v19.16B}, [x0]
 9:
        ret
 endfunc
@@ -135,22 +135,22 @@ function ff_h264_h_loop_filter_luma_neon, export=1
        h264_loop_filter_start

        sub             x0,  x0,  #4
-        ld1             {v6.8b},  [x0], x1
-        ld1             {v20.8b}, [x0], x1
-        ld1             {v18.8b}, [x0], x1
-        ld1             {v16.8b}, [x0], x1
-        ld1             {v0.8b},  [x0], x1
-        ld1             {v2.8b},  [x0], x1
-        ld1             {v4.8b},  [x0], x1
-        ld1             {v26.8b}, [x0], x1
-        ld1             {v6.d}[1],  [x0], x1
-        ld1             {v20.d}[1], [x0], x1
-        ld1             {v18.d}[1], [x0], x1
-        ld1             {v16.d}[1], [x0], x1
-        ld1             {v0.d}[1],  [x0], x1
-        ld1             {v2.d}[1],  [x0], x1
-        ld1             {v4.d}[1],  [x0], x1
-        ld1             {v26.d}[1], [x0], x1
+        ld1             {v6.8B},  [x0], x1
+        ld1             {v20.8B}, [x0], x1
+        ld1             {v18.8B}, [x0], x1
+        ld1             {v16.8B}, [x0], x1
+        ld1             {v0.8B},  [x0], x1
+        ld1             {v2.8B},  [x0], x1
+        ld1             {v4.8B},  [x0], x1
+        ld1             {v26.8B}, [x0], x1
+        ld1             {v6.D}[1],  [x0], x1
+        ld1             {v20.D}[1], [x0], x1
+        ld1             {v18.D}[1], [x0], x1
+        ld1             {v16.D}[1], [x0], x1
+        ld1             {v0.D}[1],  [x0], x1
+        ld1             {v2.D}[1],  [x0], x1
+        ld1             {v4.D}[1],  [x0], x1
+        ld1             {v26.D}[1], [x0], x1

        transpose_8x16B v6, v20, v18, v16, v0, v2, v4, v26, v21, v23

@@ -160,22 +160,22 @@ function ff_h264_h_loop_filter_luma_neon, export=1

        sub             x0,  x0,  x1, lsl #4
        add             x0,  x0,  #2
-        st1             {v17.s}[0],  [x0], x1
-        st1             {v16.s}[0], [x0], x1
-        st1             {v0.s}[0],  [x0], x1
-        st1             {v19.s}[0], [x0], x1
-        st1             {v17.s}[1],  [x0], x1
-        st1             {v16.s}[1], [x0], x1
-        st1             {v0.s}[1],  [x0], x1
-        st1             {v19.s}[1], [x0], x1
-        st1             {v17.s}[2],  [x0], x1
-        st1             {v16.s}[2], [x0], x1
-        st1             {v0.s}[2],  [x0], x1
-        st1             {v19.s}[2], [x0], x1
-        st1             {v17.s}[3],  [x0], x1
-        st1             {v16.s}[3], [x0], x1
-        st1             {v0.s}[3],  [x0], x1
-        st1             {v19.s}[3], [x0], x1
+        st1             {v17.S}[0],  [x0], x1
+        st1             {v16.S}[0], [x0], x1
+        st1             {v0.S}[0],  [x0], x1
+        st1             {v19.S}[0], [x0], x1
+        st1             {v17.S}[1],  [x0], x1
+        st1             {v16.S}[1], [x0], x1
+        st1             {v0.S}[1],  [x0], x1
+        st1             {v19.S}[1], [x0], x1
+        st1             {v17.S}[2],  [x0], x1
+        st1             {v16.S}[2], [x0], x1
+        st1             {v0.S}[2],  [x0], x1
+        st1             {v19.S}[2], [x0], x1
+        st1             {v17.S}[3],  [x0], x1
+        st1             {v16.S}[3], [x0], x1
+        st1             {v0.S}[3],  [x0], x1
+        st1             {v19.S}[3], [x0], x1
 9:
        ret
 endfunc
@@ -377,52 +377,52 @@ function ff_h264_h_loop_filter_luma_intra_neon, export=1
 endfunc

 .macro  h264_loop_filter_chroma
-        dup             v22.8b, w2              // alpha
-        dup             v23.8b, w3              // beta
-        uxtl            v24.8h, v24.8b
-        uabd            v26.8b, v16.8b, v0.8b   // abs(p0 - q0)
-        uabd            v28.8b, v18.8b, v16.8b  // abs(p1 - p0)
-        uabd            v30.8b, v2.8b,  v0.8b   // abs(q1 - q0)
-        cmhi            v26.8b, v22.8b, v26.8b  // < alpha
-        cmhi            v28.8b, v23.8b, v28.8b  // < beta
-        cmhi            v30.8b, v23.8b, v30.8b  // < beta
-        uxtl            v4.8h,  v0.8b
-        and             v26.8b, v26.8b, v28.8b
-        usubw           v4.8h,  v4.8h,  v16.8b
-        and             v26.8b, v26.8b, v30.8b
-        shl             v4.8h,  v4.8h,  #2
+        dup             v22.8B, w2              // alpha
+        dup             v23.8B, w3              // beta
+        uxtl            v24.8H, v24.8B
+        uabd            v26.8B, v16.8B, v0.8B   // abs(p0 - q0)
+        uabd            v28.8B, v18.8B, v16.8B  // abs(p1 - p0)
+        uabd            v30.8B, v2.8B,  v0.8B   // abs(q1 - q0)
+        cmhi            v26.8B, v22.8B, v26.8B  // < alpha
+        cmhi            v28.8B, v23.8B, v28.8B  // < beta
+        cmhi            v30.8B, v23.8B, v30.8B  // < beta
+        uxtl            v4.8H,  v0.8B
+        and             v26.8B, v26.8B, v28.8B
+        usubw           v4.8H,  v4.8H,  v16.8B
+        and             v26.8B, v26.8B, v30.8B
+        shl             v4.8H,  v4.8H,  #2
        mov             x8,  v26.d[0]
-        sli             v24.8h, v24.8h, #8
-        uaddw           v4.8h,  v4.8h,  v18.8b
+        sli             v24.8H, v24.8H, #8
+        uaddw           v4.8H,  v4.8H,  v18.8B
        cbz             x8,  9f
-        usubw           v4.8h,  v4.8h,  v2.8b
-        rshrn           v4.8b,  v4.8h,  #3
-        smin            v4.8b,  v4.8b,  v24.8b
-        neg             v25.8b, v24.8b
-        smax            v4.8b,  v4.8b,  v25.8b
-        uxtl            v22.8h, v0.8b
-        and             v4.8b,  v4.8b,  v26.8b
-        uxtl            v28.8h, v16.8b
-        saddw           v28.8h, v28.8h, v4.8b
-        ssubw           v22.8h, v22.8h, v4.8b
-        sqxtun          v16.8b, v28.8h
-        sqxtun          v0.8b,  v22.8h
+        usubw           v4.8H,  v4.8H,  v2.8B
+        rshrn           v4.8B,  v4.8H,  #3
+        smin            v4.8B,  v4.8B,  v24.8B
+        neg             v25.8B, v24.8B
+        smax            v4.8B,  v4.8B,  v25.8B
+        uxtl            v22.8H, v0.8B
+        and             v4.8B,  v4.8B,  v26.8B
+        uxtl            v28.8H, v16.8B
+        saddw           v28.8H, v28.8H, v4.8B
+        ssubw           v22.8H, v22.8H, v4.8B
+        sqxtun          v16.8B, v28.8H
+        sqxtun          v0.8B,  v22.8H
 .endm

 function ff_h264_v_loop_filter_chroma_neon, export=1
        h264_loop_filter_start

        sub             x0,  x0,  x1, lsl #1
-        ld1             {v18.8b}, [x0], x1
-        ld1             {v16.8b}, [x0], x1
-        ld1             {v0.8b},  [x0], x1
-        ld1             {v2.8b},  [x0]
+        ld1             {v18.8B}, [x0], x1
+        ld1             {v16.8B}, [x0], x1
+        ld1             {v0.8B},  [x0], x1
+        ld1             {v2.8B},  [x0]

        h264_loop_filter_chroma

        sub             x0,  x0,  x1, lsl #1
-        st1             {v16.8b}, [x0], x1
-        st1             {v0.8b},  [x0], x1
+        st1             {v16.8B}, [x0], x1
+        st1             {v0.8B},  [x0], x1
 9:
        ret
 endfunc
@@ -432,14 +432,14 @@ function ff_h264_h_loop_filter_chroma_neon, export=1

        sub             x0,  x0,  #2
 h_loop_filter_chroma420:
-        ld1             {v18.s}[0], [x0], x1
-        ld1             {v16.s}[0], [x0], x1
-        ld1             {v0.s}[0],  [x0], x1
-        ld1             {v2.s}[0],  [x0], x1
-        ld1             {v18.s}[1], [x0], x1
-        ld1             {v16.s}[1], [x0], x1
-        ld1             {v0.s}[1],  [x0], x1
-        ld1             {v2.s}[1],  [x0], x1
+        ld1             {v18.S}[0], [x0], x1
+        ld1             {v16.S}[0], [x0], x1
+        ld1             {v0.S}[0],  [x0], x1
+        ld1             {v2.S}[0],  [x0], x1
+        ld1             {v18.S}[1], [x0], x1
+        ld1             {v16.S}[1], [x0], x1
+        ld1             {v0.S}[1],  [x0], x1
+        ld1             {v2.S}[1],  [x0], x1

        transpose_4x8B  v18, v16, v0, v2, v28, v29, v30, v31

@@ -448,14 +448,14 @@ h_loop_filter_chroma420:
        transpose_4x8B  v18, v16, v0, v2, v28, v29, v30, v31

        sub             x0,  x0,  x1, lsl #3
-        st1             {v18.s}[0], [x0], x1
-        st1             {v16.s}[0], [x0], x1
-        st1             {v0.s}[0],  [x0], x1
-        st1             {v2.s}[0],  [x0], x1
-        st1             {v18.s}[1], [x0], x1
-        st1             {v16.s}[1], [x0], x1
-        st1             {v0.s}[1],  [x0], x1
-        st1             {v2.s}[1],  [x0], x1
+        st1             {v18.S}[0], [x0], x1
+        st1             {v16.S}[0], [x0], x1
+        st1             {v0.S}[0],  [x0], x1
+        st1             {v2.S}[0],  [x0], x1
+        st1             {v18.S}[1], [x0], x1
+        st1             {v16.S}[1], [x0], x1
+        st1             {v0.S}[1],  [x0], x1
+        st1             {v2.S}[1],  [x0], x1
 9:
        ret
 endfunc
@@ -526,7 +526,7 @@ function ff_h264_h_loop_filter_chroma_mbaff_intra_neon, export=1
        ld1             {v17.8b}, [x4], x1
        ld1             {v19.8b}, [x4], x1

-        transpose_4x8B  v18, v16, v17, v19, v26, v27, v28, v29
+        transpose_4x8B v18, v16, v17, v19, v26, v27, v28, v29

        h264_loop_filter_chroma_intra

@@ -554,7 +554,7 @@ h_loop_filter_chroma420_intra:
        ld1             {v17.s}[1], [x4], x1
        ld1             {v19.s}[1], [x4], x1

-        transpose_4x8B  v18, v16, v17, v19, v26, v27, v28, v29
+        transpose_4x8B v18, v16, v17, v19, v26, v27, v28, v29

        h264_loop_filter_chroma_intra

@@ -584,102 +584,102 @@ function ff_h264_h_loop_filter_chroma422_intra_neon, export=1
 endfunc

 .macro  biweight_16     macs, macd
-        dup             v0.16b,  w5
-        dup             v1.16b,  w6
-        mov             v4.16b,  v16.16b
-        mov             v6.16b,  v16.16b
+        dup             v0.16B,  w5
+        dup             v1.16B,  w6
+        mov             v4.16B,  v16.16B
+        mov             v6.16B,  v16.16B
 1:      subs            w3,  w3,  #2
-        ld1             {v20.16b}, [x0], x2
-        \macd           v4.8h,   v0.8b,  v20.8b
+        ld1             {v20.16B}, [x0], x2
+        \macd           v4.8H,   v0.8B,  v20.8B
        \macd\()2       v6.8H,   v0.16B, v20.16B
-        ld1             {v22.16b}, [x1], x2
-        \macs           v4.8h,   v1.8b,  v22.8b
+        ld1             {v22.16B}, [x1], x2
+        \macs           v4.8H,   v1.8B,  v22.8B
        \macs\()2       v6.8H,   v1.16B, v22.16B
-        mov             v24.16b, v16.16b
-        ld1             {v28.16b}, [x0], x2
-        mov             v26.16b, v16.16b
-        \macd           v24.8h,  v0.8b,  v28.8b
+        mov             v24.16B, v16.16B
+        ld1             {v28.16B}, [x0], x2
+        mov             v26.16B, v16.16B
+        \macd           v24.8H,  v0.8B,  v28.8B
        \macd\()2       v26.8H,  v0.16B, v28.16B
-        ld1             {v30.16b}, [x1], x2
-        \macs           v24.8h,  v1.8b,  v30.8b
+        ld1             {v30.16B}, [x1], x2
+        \macs           v24.8H,  v1.8B,  v30.8B
        \macs\()2       v26.8H,  v1.16B, v30.16B
-        sshl            v4.8h,   v4.8h,  v18.8h
-        sshl            v6.8h,   v6.8h,  v18.8h
-        sqxtun          v4.8b,   v4.8h
-        sqxtun2         v4.16b,  v6.8h
-        sshl            v24.8h,  v24.8h, v18.8h
-        sshl            v26.8h,  v26.8h, v18.8h
-        sqxtun          v24.8b,  v24.8h
-        sqxtun2         v24.16b, v26.8h
-        mov             v6.16b,  v16.16b
-        st1             {v4.16b},  [x7], x2
-        mov             v4.16b,  v16.16b
-        st1             {v24.16b}, [x7], x2
+        sshl            v4.8H,   v4.8H,  v18.8H
+        sshl            v6.8H,   v6.8H,  v18.8H
+        sqxtun          v4.8B,   v4.8H
+        sqxtun2         v4.16B,  v6.8H
+        sshl            v24.8H,  v24.8H, v18.8H
+        sshl            v26.8H,  v26.8H, v18.8H
+        sqxtun          v24.8B,  v24.8H
+        sqxtun2         v24.16B, v26.8H
+        mov             v6.16B,  v16.16B
+        st1             {v4.16B},  [x7], x2
+        mov             v4.16B,  v16.16B
+        st1             {v24.16B}, [x7], x2
        b.ne            1b
        ret
 .endm

 .macro  biweight_8      macs, macd
-        dup             v0.8b,  w5
-        dup             v1.8b,  w6
-        mov             v2.16b,  v16.16b
-        mov             v20.16b, v16.16b
+        dup             v0.8B,  w5
+        dup             v1.8B,  w6
+        mov             v2.16B,  v16.16B
+        mov             v20.16B, v16.16B
 1:      subs            w3,  w3,  #2
-        ld1             {v4.8b}, [x0], x2
-        \macd           v2.8h,  v0.8b,  v4.8b
-        ld1             {v5.8b}, [x1], x2
-        \macs           v2.8h,  v1.8b,  v5.8b
-        ld1             {v6.8b}, [x0], x2
-        \macd           v20.8h, v0.8b,  v6.8b
-        ld1             {v7.8b}, [x1], x2
-        \macs           v20.8h, v1.8b,  v7.8b
-        sshl            v2.8h,  v2.8h,  v18.8h
-        sqxtun          v2.8b,  v2.8h
-        sshl            v20.8h, v20.8h, v18.8h
-        sqxtun          v4.8b,  v20.8h
-        mov             v20.16b, v16.16b
-        st1             {v2.8b}, [x7], x2
-        mov             v2.16b,  v16.16b
-        st1             {v4.8b}, [x7], x2
+        ld1             {v4.8B}, [x0], x2
+        \macd           v2.8H,  v0.8B,  v4.8B
+        ld1             {v5.8B}, [x1], x2
+        \macs           v2.8H,  v1.8B,  v5.8B
+        ld1             {v6.8B}, [x0], x2
+        \macd           v20.8H, v0.8B,  v6.8B
+        ld1             {v7.8B}, [x1], x2
+        \macs           v20.8H, v1.8B,  v7.8B
+        sshl            v2.8H,  v2.8H,  v18.8H
+        sqxtun          v2.8B,  v2.8H
+        sshl            v20.8H, v20.8H, v18.8H
+        sqxtun          v4.8B,  v20.8H
+        mov             v20.16B, v16.16B
+        st1             {v2.8B}, [x7], x2
+        mov             v2.16B,  v16.16B
+        st1             {v4.8B}, [x7], x2
        b.ne            1b
        ret
 .endm

 .macro  biweight_4      macs, macd
-        dup             v0.8b,  w5
-        dup             v1.8b,  w6
-        mov             v2.16b, v16.16b
-        mov             v20.16b,v16.16b
+        dup             v0.8B,  w5
+        dup             v1.8B,  w6
+        mov             v2.16B, v16.16B
+        mov             v20.16B,v16.16B
 1:      subs            w3,  w3,  #4
-        ld1             {v4.s}[0], [x0], x2
-        ld1             {v4.s}[1], [x0], x2
-        \macd           v2.8h,  v0.8b,  v4.8b
-        ld1             {v5.s}[0], [x1], x2
-        ld1             {v5.s}[1], [x1], x2
-        \macs           v2.8h,  v1.8b,  v5.8b
+        ld1             {v4.S}[0], [x0], x2
+        ld1             {v4.S}[1], [x0], x2
+        \macd           v2.8H,  v0.8B,  v4.8B
+        ld1             {v5.S}[0], [x1], x2
+        ld1             {v5.S}[1], [x1], x2
+        \macs           v2.8H,  v1.8B,  v5.8B
        b.lt            2f
-        ld1             {v6.s}[0], [x0], x2
-        ld1             {v6.s}[1], [x0], x2
-        \macd           v20.8h, v0.8b,  v6.8b
-        ld1             {v7.s}[0], [x1], x2
-        ld1             {v7.s}[1], [x1], x2
-        \macs           v20.8h, v1.8b,  v7.8b
-        sshl            v2.8h,  v2.8h,  v18.8h
-        sqxtun          v2.8b,  v2.8h
-        sshl            v20.8h, v20.8h, v18.8h
-        sqxtun          v4.8b,  v20.8h
-        mov             v20.16b, v16.16b
-        st1             {v2.s}[0], [x7], x2
-        st1             {v2.s}[1], [x7], x2
-        mov             v2.16b,  v16.16b
-        st1             {v4.s}[0], [x7], x2
-        st1             {v4.s}[1], [x7], x2
+        ld1             {v6.S}[0], [x0], x2
+        ld1             {v6.S}[1], [x0], x2
+        \macd           v20.8H, v0.8B,  v6.8B
+        ld1             {v7.S}[0], [x1], x2
+        ld1             {v7.S}[1], [x1], x2
+        \macs           v20.8H, v1.8B,  v7.8B
+        sshl            v2.8H,  v2.8H,  v18.8H
+        sqxtun          v2.8B,  v2.8H
+        sshl            v20.8H, v20.8H, v18.8H
+        sqxtun          v4.8B,  v20.8H
+        mov             v20.16B, v16.16B
+        st1             {v2.S}[0], [x7], x2
+        st1             {v2.S}[1], [x7], x2
+        mov             v2.16B,  v16.16B
+        st1             {v4.S}[0], [x7], x2
+        st1             {v4.S}[1], [x7], x2
        b.ne            1b
        ret
-2:      sshl            v2.8h,  v2.8h,  v18.8h
-        sqxtun          v2.8b,  v2.8h
-        st1             {v2.s}[0], [x7], x2
-        st1             {v2.s}[1], [x7], x2
+2:      sshl            v2.8H,  v2.8H,  v18.8H
+        sqxtun          v2.8B,  v2.8H
+        st1             {v2.S}[0], [x7], x2
+        st1             {v2.S}[1], [x7], x2
        ret
 .endm

@@ -689,10 +689,10 @@ function ff_biweight_h264_pixels_\w\()_neon, export=1
        add             w7,  w7,  #1
        eor             w8,  w8,  w6,  lsr #30
        orr             w7,  w7,  #1
-        dup             v18.8h,   w4
+        dup             v18.8H,   w4
        lsl             w7,  w7,  w4
-        not             v18.16b,  v18.16b
-        dup             v16.8h,   w7
+        not             v18.16B,  v18.16B
+        dup             v16.8H,   w7
        mov             x7,  x0
        cbz             w8,  10f
        subs            w8,  w8,  #1
@@ -716,78 +716,78 @@ endfunc
        biweight_func   4

 .macro  weight_16       add
-        dup             v0.16b,  w4
+        dup             v0.16B,  w4
 1:      subs            w2,  w2,  #2
-        ld1             {v20.16b}, [x0], x1
-        umull           v4.8h,   v0.8b,  v20.8b
-        umull2          v6.8h,   v0.16b, v20.16b
-        ld1             {v28.16b}, [x0], x1
-        umull           v24.8h,  v0.8b,  v28.8b
-        umull2          v26.8h,  v0.16b, v28.16b
-        \add            v4.8h,   v16.8h, v4.8h
-        srshl           v4.8h,   v4.8h,  v18.8h
-        \add            v6.8h,   v16.8h, v6.8h
-        srshl           v6.8h,   v6.8h,  v18.8h
-        sqxtun          v4.8b,   v4.8h
-        sqxtun2         v4.16b,  v6.8h
-        \add            v24.8h,  v16.8h, v24.8h
-        srshl           v24.8h,  v24.8h, v18.8h
-        \add            v26.8h,  v16.8h, v26.8h
-        srshl           v26.8h,  v26.8h, v18.8h
-        sqxtun          v24.8b,  v24.8h
-        sqxtun2         v24.16b, v26.8h
-        st1             {v4.16b},  [x5], x1
-        st1             {v24.16b}, [x5], x1
+        ld1             {v20.16B}, [x0], x1
+        umull           v4.8H,   v0.8B,  v20.8B
+        umull2          v6.8H,   v0.16B, v20.16B
+        ld1             {v28.16B}, [x0], x1
+        umull           v24.8H,  v0.8B,  v28.8B
+        umull2          v26.8H,  v0.16B, v28.16B
+        \add            v4.8H,   v16.8H, v4.8H
+        srshl           v4.8H,   v4.8H,  v18.8H
+        \add            v6.8H,   v16.8H, v6.8H
+        srshl           v6.8H,   v6.8H,  v18.8H
+        sqxtun          v4.8B,   v4.8H
+        sqxtun2         v4.16B,  v6.8H
+        \add            v24.8H,  v16.8H, v24.8H
+        srshl           v24.8H,  v24.8H, v18.8H
+        \add            v26.8H,  v16.8H, v26.8H
+        srshl           v26.8H,  v26.8H, v18.8H
+        sqxtun          v24.8B,  v24.8H
+        sqxtun2         v24.16B, v26.8H
+        st1             {v4.16B},  [x5], x1
+        st1             {v24.16B}, [x5], x1
        b.ne            1b
        ret
 .endm

 .macro  weight_8        add
-        dup             v0.8b,  w4
+        dup             v0.8B,  w4
 1:      subs            w2,  w2,  #2
-        ld1             {v4.8b}, [x0], x1
-        umull           v2.8h,  v0.8b,  v4.8b
-        ld1             {v6.8b}, [x0], x1
-        umull           v20.8h, v0.8b,  v6.8b
-        \add            v2.8h,  v16.8h,  v2.8h
-        srshl           v2.8h,  v2.8h,  v18.8h
-        sqxtun          v2.8b,  v2.8h
-        \add            v20.8h, v16.8h,  v20.8h
-        srshl           v20.8h, v20.8h, v18.8h
-        sqxtun          v4.8b,  v20.8h
-        st1             {v2.8b}, [x5], x1
-        st1             {v4.8b}, [x5], x1
+        ld1             {v4.8B}, [x0], x1
+        umull           v2.8H,  v0.8B,  v4.8B
+        ld1             {v6.8B}, [x0], x1
+        umull           v20.8H, v0.8B,  v6.8B
+        \add            v2.8H,  v16.8H,  v2.8H
+        srshl           v2.8H,  v2.8H,  v18.8H
+        sqxtun          v2.8B,  v2.8H
+        \add            v20.8H, v16.8H,  v20.8H
+        srshl           v20.8H, v20.8H, v18.8H
+        sqxtun          v4.8B,  v20.8H
+        st1             {v2.8B}, [x5], x1
+        st1             {v4.8B}, [x5], x1
        b.ne            1b
        ret
 .endm

 .macro  weight_4        add
-        dup             v0.8b,  w4
+        dup             v0.8B,  w4
 1:      subs            w2,  w2,  #4
-        ld1             {v4.s}[0], [x0], x1
-        ld1             {v4.s}[1], [x0], x1
-        umull           v2.8h,  v0.8b,  v4.8b
+        ld1             {v4.S}[0], [x0], x1
+        ld1             {v4.S}[1], [x0], x1
+        umull           v2.8H,  v0.8B,  v4.8B
        b.lt            2f
-        ld1             {v6.s}[0], [x0], x1
-        ld1             {v6.s}[1], [x0], x1
-        umull           v20.8h, v0.8b,  v6.8b
-        \add            v2.8h,  v16.8h,  v2.8h
-        srshl           v2.8h,  v2.8h,  v18.8h
-        sqxtun          v2.8b,  v2.8h
-        \add            v20.8h, v16.8h,  v20.8h
-        srshl           v20.8h, v20.8h, v18.8h
-        sqxtun          v4.8b,  v20.8h
-        st1             {v2.s}[0], [x5], x1
-        st1             {v2.s}[1], [x5], x1
-        st1             {v4.s}[0], [x5], x1
-        st1             {v4.s}[1], [x5], x1
+        ld1             {v6.S}[0], [x0], x1
+        ld1             {v6.S}[1], [x0], x1
+        umull           v20.8H, v0.8B,  v6.8B
+        \add            v2.8H,  v16.8H,  v2.8H
+        srshl           v2.8H,  v2.8H,  v18.8H
+        sqxtun          v2.8B,  v2.8H
+        \add            v20.8H, v16.8H,  v20.8H
+        srshl           v20.8H, v20.8h, v18.8H
+        sqxtun          v4.8B,  v20.8H
+        st1             {v2.S}[0], [x5], x1
+        st1             {v2.S}[1], [x5], x1
+        st1             {v4.S}[0], [x5], x1
+        st1             {v4.S}[1], [x5], x1
        b.ne            1b
        ret
-2:      \add            v2.8h,  v16.8h,  v2.8h
-        srshl           v2.8h,  v2.8h,  v18.8h
-        sqxtun          v2.8b,  v2.8h
-        st1             {v2.s}[0], [x5], x1
-        st1             {v2.s}[1], [x5], x1
+2:      \add            v2.8H,  v16.8H,  v2.8H
+        srshl           v2.8H,  v2.8H,  v18.8H
+        sqxtun          v2.8B,  v2.8H
+        st1             {v2.S}[0], [x5], x1
+        st1             {v2.S}[1], [x5], x1
        ret
 .endm

@@ -796,18 +796,18 @@ function ff_weight_h264_pixels_\w\()_neon, export=1
        cmp             w3,  #1
        mov             w6,  #1
        lsl             w5,  w5,  w3
-        dup             v16.8h,  w5
+        dup             v16.8H,  w5
        mov             x5,  x0
        b.le            20f
        sub             w6,  w6,  w3
-        dup             v18.8h,  w6
+        dup             v18.8H,  w6
        cmp             w4, #0
        b.lt            10f
        weight_\w       shadd
 10:     neg             w4,  w4
        weight_\w       shsub
 20:     neg             w6,  w3
-        dup             v18.8h,  w6
+        dup             v18.8H,  w6
        cmp             w4,  #0
        b.lt            10f
        weight_\w       add
@@ -825,7 +825,7 @@ endfunc
        ldr             w6,  [x4]
        ccmp            w3,  #0,  #0,  ne
        lsl             w2,  w2,  #2
-        mov             v24.s[0], w6
+        mov             v24.S[0], w6
        lsl             w3,  w3,  #2
        and             w8,  w6,  w6,  lsl #16
        b.eq            1f
@@ -1017,7 +1017,7 @@ function ff_h264_h_loop_filter_chroma_mbaff_intra_neon_10, export=1
        ld1             {v16.8h}, [x4], x1
        ld1             {v19.8h}, [x9], x1

-        transpose_4x8H  v18, v16, v17, v19, v26, v27, v28, v29
+        transpose_4x8H v18, v16, v17, v19, v26, v27, v28, v29

        h264_loop_filter_chroma_intra_10

@@ -1045,7 +1045,7 @@ h_loop_filter_chroma420_intra_10:
        ld1             {v19.4h},   [x4], x1
        ld1             {v19.d}[1], [x9], x1

-        transpose_4x8H  v18, v16, v17, v19, v26, v27, v28, v29
+        transpose_4x8H v18, v16, v17, v19, v26, v27, v28, v29

        h264_loop_filter_chroma_intra_10

--- a/libavcodec/aarch64/h264idct_neon.S
+++ b/libavcodec/aarch64/h264idct_neon.S
@@ -25,54 +25,54 @@
 function ff_h264_idct_add_neon, export=1
 .L_ff_h264_idct_add_neon:
        AARCH64_VALID_CALL_TARGET
-        ld1             {v0.4h, v1.4h, v2.4h, v3.4h},  [x1]
+        ld1             {v0.4H, v1.4H, v2.4H, v3.4H},  [x1]
        sxtw            x2,     w2
-        movi            v30.8h, #0
+        movi            v30.8H, #0

-        add             v4.4h,  v0.4h,  v2.4h
-        sshr            v16.4h, v1.4h,  #1
-        st1             {v30.8h},    [x1], #16
-        sshr            v17.4h, v3.4h,  #1
-        st1             {v30.8h},    [x1], #16
-        sub             v5.4h,  v0.4h,  v2.4h
-        sub             v6.4h,  v16.4h, v3.4h
-        add             v7.4h,  v1.4h,  v17.4h
-        add             v0.4h,  v4.4h,  v7.4h
-        add             v1.4h,  v5.4h,  v6.4h
-        sub             v2.4h,  v5.4h,  v6.4h
-        sub             v3.4h,  v4.4h,  v7.4h
+        add             v4.4H,  v0.4H,  v2.4H
+        sshr            v16.4H, v1.4H,  #1
+        st1             {v30.8H},    [x1], #16
+        sshr            v17.4H, v3.4H,  #1
+        st1             {v30.8H},    [x1], #16
+        sub             v5.4H,  v0.4H,  v2.4H
+        sub             v6.4H,  v16.4H, v3.4H
+        add             v7.4H,  v1.4H,  v17.4H
+        add             v0.4H,  v4.4H,  v7.4H
+        add             v1.4H,  v5.4H,  v6.4H
+        sub             v2.4H,  v5.4H,  v6.4H
+        sub             v3.4H,  v4.4H,  v7.4H

        transpose_4x4H  v0, v1, v2, v3, v4, v5, v6, v7

-        add             v4.4h,  v0.4h,  v2.4h
-        ld1             {v18.s}[0], [x0], x2
-        sshr            v16.4h,  v3.4h,  #1
-        sshr            v17.4h,  v1.4h,  #1
-        ld1             {v18.s}[1], [x0], x2
-        sub             v5.4h,  v0.4h,  v2.4h
-        ld1             {v19.s}[1], [x0], x2
-        add             v6.4h,  v16.4h, v1.4h
-        ins             v4.d[1],  v5.d[0]
-        sub             v7.4h,  v17.4h, v3.4h
-        ld1             {v19.s}[0], [x0], x2
-        ins             v6.d[1],  v7.d[0]
+        add             v4.4H,  v0.4H,  v2.4H
+        ld1             {v18.S}[0], [x0], x2
+        sshr            v16.4H,  v3.4H,  #1
+        sshr            v17.4H,  v1.4H,  #1
+        ld1             {v18.S}[1], [x0], x2
+        sub             v5.4H,  v0.4H,  v2.4H
+        ld1             {v19.S}[1], [x0], x2
+        add             v6.4H,  v16.4H, v1.4H
+        ins             v4.D[1],  v5.D[0]
+        sub             v7.4H,  v17.4H, v3.4H
+        ld1             {v19.S}[0], [x0], x2
+        ins             v6.D[1],  v7.D[0]
        sub             x0,  x0,  x2, lsl #2
-        add             v0.8h,  v4.8h,  v6.8h
-        sub             v1.8h,  v4.8h,  v6.8h
+        add             v0.8H,  v4.8H,  v6.8H
+        sub             v1.8H,  v4.8H,  v6.8H

-        srshr           v0.8h,  v0.8h,  #6
-        srshr           v1.8h,  v1.8h,  #6
+        srshr           v0.8H,  v0.8H,  #6
+        srshr           v1.8H,  v1.8H,  #6

-        uaddw           v0.8h,  v0.8h,  v18.8b
-        uaddw           v1.8h,  v1.8h,  v19.8b
+        uaddw           v0.8H,  v0.8H,  v18.8B
+        uaddw           v1.8H,  v1.8H,  v19.8B

-        sqxtun          v0.8b, v0.8h
-        sqxtun          v1.8b, v1.8h
+        sqxtun          v0.8B, v0.8H
+        sqxtun          v1.8B, v1.8H

-        st1             {v0.s}[0],  [x0], x2
-        st1             {v0.s}[1],  [x0], x2
-        st1             {v1.s}[1],  [x0], x2
-        st1             {v1.s}[0],  [x0], x2
+        st1             {v0.S}[0],  [x0], x2
+        st1             {v0.S}[1],  [x0], x2
+        st1             {v1.S}[1],  [x0], x2
+        st1             {v1.S}[0],  [x0], x2

        sub             x1,  x1,  #32
        ret
@@ -83,22 +83,22 @@ function ff_h264_idct_dc_add_neon, export=1
        AARCH64_VALID_CALL_TARGET
        sxtw            x2,  w2
        mov             w3,       #0
-        ld1r            {v2.8h},  [x1]
+        ld1r            {v2.8H},  [x1]
        strh            w3,       [x1]
-        srshr           v2.8h,  v2.8h,  #6
-        ld1             {v0.s}[0],  [x0], x2
-        ld1             {v0.s}[1],  [x0], x2
-        uaddw           v3.8h,  v2.8h,  v0.8b
-        ld1             {v1.s}[0],  [x0], x2
-        ld1             {v1.s}[1],  [x0], x2
-        uaddw           v4.8h,  v2.8h,  v1.8b
-        sqxtun          v0.8b,  v3.8h
-        sqxtun          v1.8b,  v4.8h
+        srshr           v2.8H,  v2.8H,  #6
+        ld1             {v0.S}[0],  [x0], x2
+        ld1             {v0.S}[1],  [x0], x2
+        uaddw           v3.8H,  v2.8H,  v0.8B
+        ld1             {v1.S}[0],  [x0], x2
+        ld1             {v1.S}[1],  [x0], x2
+        uaddw           v4.8H,  v2.8H,  v1.8B
+        sqxtun          v0.8B,  v3.8H
+        sqxtun          v1.8B,  v4.8H
        sub             x0,  x0,  x2, lsl #2
-        st1             {v0.s}[0],  [x0], x2
-        st1             {v0.s}[1],  [x0], x2
-        st1             {v1.s}[0],  [x0], x2
-        st1             {v1.s}[1],  [x0], x2
+        st1             {v0.S}[0],  [x0], x2
+        st1             {v0.S}[1],  [x0], x2
+        st1             {v1.S}[0],  [x0], x2
+        st1             {v1.S}[1],  [x0], x2
        ret
 endfunc

@@ -194,71 +194,71 @@ endfunc
  .if \pass == 0
        va      .req    v18
        vb      .req    v30
-        sshr            v18.8h, v26.8h, #1
-        add             v16.8h, v24.8h, v28.8h
-        ld1             {v30.8h, v31.8h}, [x1]
-        st1             {v19.8h}, [x1],  #16
-        st1             {v19.8h}, [x1],  #16
-        sub             v17.8h,  v24.8h, v28.8h
-        sshr            v19.8h,  v30.8h, #1
-        sub             v18.8h,  v18.8h,  v30.8h
-        add             v19.8h,  v19.8h,  v26.8h
+        sshr            v18.8H, v26.8H, #1
+        add             v16.8H, v24.8H, v28.8H
+        ld1             {v30.8H, v31.8H}, [x1]
+        st1             {v19.8H}, [x1],  #16
+        st1             {v19.8H}, [x1],  #16
+        sub             v17.8H,  v24.8H, v28.8H
+        sshr            v19.8H,  v30.8H, #1
+        sub             v18.8H,  v18.8H,  v30.8H
+        add             v19.8H,  v19.8H,  v26.8H
  .else
        va      .req    v30
        vb      .req    v18
-        sshr            v30.8h, v26.8h, #1
-        sshr            v19.8h, v18.8h, #1
-        add             v16.8h, v24.8h, v28.8h
-        sub             v17.8h, v24.8h, v28.8h
-        sub             v30.8h, v30.8h, v18.8h
-        add             v19.8h, v19.8h, v26.8h
+        sshr            v30.8H, v26.8H, #1
+        sshr            v19.8H, v18.8H, #1
+        add             v16.8H, v24.8H, v28.8H
+        sub             v17.8H, v24.8H, v28.8H
+        sub             v30.8H, v30.8H, v18.8H
+        add             v19.8H, v19.8H, v26.8H
  .endif
-        add             v26.8h, v17.8h, va.8h
-        sub             v28.8h, v17.8h, va.8h
-        add             v24.8h, v16.8h, v19.8h
-        sub             vb.8h,  v16.8h, v19.8h
-        sub             v16.8h, v29.8h, v27.8h
-        add             v17.8h, v31.8h, v25.8h
-        sub             va.8h,  v31.8h, v25.8h
-        add             v19.8h, v29.8h, v27.8h
-        sub             v16.8h, v16.8h, v31.8h
-        sub             v17.8h, v17.8h, v27.8h
-        add             va.8h,  va.8h,  v29.8h
-        add             v19.8h, v19.8h, v25.8h
-        sshr            v25.8h, v25.8h, #1
-        sshr            v27.8h, v27.8h, #1
-        sshr            v29.8h, v29.8h, #1
-        sshr            v31.8h, v31.8h, #1
-        sub             v16.8h, v16.8h, v31.8h
-        sub             v17.8h, v17.8h, v27.8h
-        add             va.8h,  va.8h,  v29.8h
-        add             v19.8h, v19.8h, v25.8h
-        sshr            v25.8h, v16.8h, #2
-        sshr            v27.8h, v17.8h, #2
-        sshr            v29.8h, va.8h,  #2
-        sshr            v31.8h, v19.8h, #2
-        sub             v19.8h, v19.8h, v25.8h
-        sub             va.8h,  v27.8h, va.8h
-        add             v17.8h, v17.8h, v29.8h
-        add             v16.8h, v16.8h, v31.8h
+        add             v26.8H, v17.8H, va.8H
+        sub             v28.8H, v17.8H, va.8H
+        add             v24.8H, v16.8H, v19.8H
+        sub             vb.8H,  v16.8H, v19.8H
+        sub             v16.8H, v29.8H, v27.8H
+        add             v17.8H, v31.8H, v25.8H
+        sub             va.8H,  v31.8H, v25.8H
+        add             v19.8H, v29.8H, v27.8H
+        sub             v16.8H, v16.8H, v31.8H
+        sub             v17.8H, v17.8H, v27.8H
+        add             va.8H,  va.8H,  v29.8H
+        add             v19.8H, v19.8H, v25.8H
+        sshr            v25.8H, v25.8H, #1
+        sshr            v27.8H, v27.8H, #1
+        sshr            v29.8H, v29.8H, #1
+        sshr            v31.8H, v31.8H, #1
+        sub             v16.8H, v16.8H, v31.8H
+        sub             v17.8H, v17.8H, v27.8H
+        add             va.8H,  va.8H,  v29.8H
+        add             v19.8H, v19.8H, v25.8H
+        sshr            v25.8H, v16.8H, #2
+        sshr            v27.8H, v17.8H, #2
+        sshr            v29.8H, va.8H,  #2
+        sshr            v31.8H, v19.8H, #2
+        sub             v19.8H, v19.8H, v25.8H
+        sub             va.8H,  v27.8H, va.8H
+        add             v17.8H, v17.8H, v29.8H
+        add             v16.8H, v16.8H, v31.8H
  .if \pass == 0
-        sub             v31.8h, v24.8h, v19.8h
-        add             v24.8h, v24.8h, v19.8h
-        add             v25.8h, v26.8h, v18.8h
-        sub             v18.8h, v26.8h, v18.8h
-        add             v26.8h, v28.8h, v17.8h
-        add             v27.8h, v30.8h, v16.8h
-        sub             v29.8h, v28.8h, v17.8h
-        sub             v28.8h, v30.8h, v16.8h
+        sub             v31.8H, v24.8H, v19.8H
+        add             v24.8H, v24.8H, v19.8H
+        add             v25.8H, v26.8H, v18.8H
+        sub             v18.8H, v26.8H, v18.8H
+        add             v26.8H, v28.8H, v17.8H
+        add             v27.8H, v30.8H, v16.8H
+        sub             v29.8H, v28.8H, v17.8H
+        sub             v28.8H, v30.8H, v16.8H
  .else
-        sub             v31.8h, v24.8h, v19.8h
-        add             v24.8h, v24.8h, v19.8h
-        add             v25.8h, v26.8h, v30.8h
-        sub             v30.8h, v26.8h, v30.8h
-        add             v26.8h, v28.8h, v17.8h
-        sub             v29.8h, v28.8h, v17.8h
-        add             v27.8h, v18.8h, v16.8h
-        sub             v28.8h, v18.8h, v16.8h
+        sub             v31.8H, v24.8H, v19.8H
+        add             v24.8H, v24.8H, v19.8H
+        add             v25.8H, v26.8H, v30.8H
+        sub             v30.8H, v26.8H, v30.8H
+        add             v26.8H, v28.8H, v17.8H
+        sub             v29.8H, v28.8H, v17.8H
+        add             v27.8H, v18.8H, v16.8H
+        sub             v28.8H, v18.8H, v16.8H
  .endif
        .unreq          va
        .unreq          vb
@@ -267,63 +267,63 @@ endfunc
 function ff_h264_idct8_add_neon, export=1
 .L_ff_h264_idct8_add_neon:
        AARCH64_VALID_CALL_TARGET
-        movi            v19.8h,   #0
+        movi            v19.8H,   #0
        sxtw            x2,       w2
-        ld1             {v24.8h, v25.8h}, [x1]
-        st1             {v19.8h},  [x1],   #16
-        st1             {v19.8h},  [x1],   #16
-        ld1             {v26.8h, v27.8h}, [x1]
-        st1             {v19.8h},  [x1],   #16
-        st1             {v19.8h},  [x1],   #16
-        ld1             {v28.8h, v29.8h}, [x1]
-        st1             {v19.8h},  [x1],   #16
-        st1             {v19.8h},  [x1],   #16
+        ld1             {v24.8H, v25.8H}, [x1]
+        st1             {v19.8H},  [x1],   #16
+        st1             {v19.8H},  [x1],   #16
+        ld1             {v26.8H, v27.8H}, [x1]
+        st1             {v19.8H},  [x1],   #16
+        st1             {v19.8H},  [x1],   #16
+        ld1             {v28.8H, v29.8H}, [x1]
+        st1             {v19.8H},  [x1],   #16
+        st1             {v19.8H},  [x1],   #16

        idct8x8_cols    0
        transpose_8x8H  v24, v25, v26, v27, v28, v29, v18, v31, v6, v7
        idct8x8_cols    1

        mov             x3,  x0
-        srshr           v24.8h, v24.8h, #6
-        ld1             {v0.8b},     [x0], x2
-        srshr           v25.8h, v25.8h, #6
-        ld1             {v1.8b},     [x0], x2
-        srshr           v26.8h, v26.8h, #6
-        ld1             {v2.8b},     [x0], x2
-        srshr           v27.8h, v27.8h, #6
-        ld1             {v3.8b},     [x0], x2
-        srshr           v28.8h, v28.8h, #6
-        ld1             {v4.8b},     [x0], x2
-        srshr           v29.8h, v29.8h, #6
-        ld1             {v5.8b},     [x0], x2
-        srshr           v30.8h, v30.8h, #6
-        ld1             {v6.8b},     [x0], x2
-        srshr           v31.8h, v31.8h, #6
-        ld1             {v7.8b},     [x0], x2
-        uaddw           v24.8h, v24.8h, v0.8b
-        uaddw           v25.8h, v25.8h, v1.8b
-        uaddw           v26.8h, v26.8h, v2.8b
-        sqxtun          v0.8b,  v24.8h
-        uaddw           v27.8h, v27.8h, v3.8b
-        sqxtun          v1.8b,  v25.8h
-        uaddw           v28.8h, v28.8h, v4.8b
-        sqxtun          v2.8b,  v26.8h
-        st1             {v0.8b},     [x3], x2
-        uaddw           v29.8h, v29.8h, v5.8b
-        sqxtun          v3.8b,  v27.8h
-        st1             {v1.8b},     [x3], x2
-        uaddw           v30.8h, v30.8h, v6.8b
-        sqxtun          v4.8b,  v28.8h
-        st1             {v2.8b},     [x3], x2
-        uaddw           v31.8h, v31.8h, v7.8b
-        sqxtun          v5.8b,  v29.8h
-        st1             {v3.8b},     [x3], x2
-        sqxtun          v6.8b,  v30.8h
-        sqxtun          v7.8b,  v31.8h
-        st1             {v4.8b},     [x3], x2
-        st1             {v5.8b},     [x3], x2
-        st1             {v6.8b},     [x3], x2
-        st1             {v7.8b},     [x3], x2
+        srshr           v24.8H, v24.8H, #6
+        ld1             {v0.8B},     [x0], x2
+        srshr           v25.8H, v25.8H, #6
+        ld1             {v1.8B},     [x0], x2
+        srshr           v26.8H, v26.8H, #6
+        ld1             {v2.8B},     [x0], x2
+        srshr           v27.8H, v27.8H, #6
+        ld1             {v3.8B},     [x0], x2
+        srshr           v28.8H, v28.8H, #6
+        ld1             {v4.8B},     [x0], x2
+        srshr           v29.8H, v29.8H, #6
+        ld1             {v5.8B},     [x0], x2
+        srshr           v30.8H, v30.8H, #6
+        ld1             {v6.8B},     [x0], x2
+        srshr           v31.8H, v31.8H, #6
+        ld1             {v7.8B},     [x0], x2
+        uaddw           v24.8H, v24.8H, v0.8B
+        uaddw           v25.8H, v25.8H, v1.8B
+        uaddw           v26.8H, v26.8H, v2.8B
+        sqxtun          v0.8B,  v24.8H
+        uaddw           v27.8H, v27.8H, v3.8B
+        sqxtun          v1.8B,  v25.8H
+        uaddw           v28.8H, v28.8H, v4.8B
+        sqxtun          v2.8B,  v26.8H
+        st1             {v0.8B},     [x3], x2
+        uaddw           v29.8H, v29.8H, v5.8B
+        sqxtun          v3.8B,  v27.8H
+        st1             {v1.8B},     [x3], x2
+        uaddw           v30.8H, v30.8H, v6.8B
+        sqxtun          v4.8B,  v28.8H
+        st1             {v2.8B},     [x3], x2
+        uaddw           v31.8H, v31.8H, v7.8B
+        sqxtun          v5.8B,  v29.8H
+        st1             {v3.8B},     [x3], x2
+        sqxtun          v6.8B,  v30.8H
+        sqxtun          v7.8B,  v31.8H
+        st1             {v4.8B},     [x3], x2
+        st1             {v5.8B},     [x3], x2
+        st1             {v6.8B},     [x3], x2
+        st1             {v7.8B},     [x3], x2

        sub             x1,  x1,  #128
        ret
@@ -334,42 +334,42 @@ function ff_h264_idct8_dc_add_neon, export=1
        AARCH64_VALID_CALL_TARGET
        mov             w3,       #0
        sxtw            x2,       w2
-        ld1r            {v31.8h}, [x1]
+        ld1r            {v31.8H}, [x1]
        strh            w3,       [x1]
-        ld1             {v0.8b},  [x0], x2
-        srshr           v31.8h, v31.8h, #6
-        ld1             {v1.8b},     [x0], x2
-        ld1             {v2.8b},     [x0], x2
-        uaddw           v24.8h, v31.8h, v0.8b
-        ld1             {v3.8b},     [x0], x2
-        uaddw           v25.8h, v31.8h, v1.8b
-        ld1             {v4.8b},     [x0], x2
-        uaddw           v26.8h, v31.8h, v2.8b
-        ld1             {v5.8b},     [x0], x2
-        uaddw           v27.8h, v31.8h, v3.8b
-        ld1             {v6.8b},     [x0], x2
-        uaddw           v28.8h, v31.8h, v4.8b
-        ld1             {v7.8b},     [x0], x2
-        uaddw           v29.8h, v31.8h, v5.8b
-        uaddw           v30.8h, v31.8h, v6.8b
-        uaddw           v31.8h, v31.8h, v7.8b
-        sqxtun          v0.8b,  v24.8h
-        sqxtun          v1.8b,  v25.8h
-        sqxtun          v2.8b,  v26.8h
-        sqxtun          v3.8b,  v27.8h
+        ld1             {v0.8B},  [x0], x2
+        srshr           v31.8H, v31.8H, #6
+        ld1             {v1.8B},     [x0], x2
+        ld1             {v2.8B},     [x0], x2
+        uaddw           v24.8H, v31.8H, v0.8B
+        ld1             {v3.8B},     [x0], x2
+        uaddw           v25.8H, v31.8H, v1.8B
+        ld1             {v4.8B},     [x0], x2
+        uaddw           v26.8H, v31.8H, v2.8B
+        ld1             {v5.8B},     [x0], x2
+        uaddw           v27.8H, v31.8H, v3.8B
+        ld1             {v6.8B},     [x0], x2
+        uaddw           v28.8H, v31.8H, v4.8B
+        ld1             {v7.8B},     [x0], x2
+        uaddw           v29.8H, v31.8H, v5.8B
+        uaddw           v30.8H, v31.8H, v6.8B
+        uaddw           v31.8H, v31.8H, v7.8B
+        sqxtun          v0.8B,  v24.8H
+        sqxtun          v1.8B,  v25.8H
+        sqxtun          v2.8B,  v26.8H
+        sqxtun          v3.8B,  v27.8H
        sub             x0,  x0,  x2, lsl #3
-        st1             {v0.8b},     [x0], x2
-        sqxtun          v4.8b,  v28.8h
-        st1             {v1.8b},     [x0], x2
-        sqxtun          v5.8b,  v29.8h
-        st1             {v2.8b},     [x0], x2
-        sqxtun          v6.8b,  v30.8h
-        st1             {v3.8b},     [x0], x2
-        sqxtun          v7.8b,  v31.8h
-        st1             {v4.8b},     [x0], x2
-        st1             {v5.8b},     [x0], x2
-        st1             {v6.8b},     [x0], x2
-        st1             {v7.8b},     [x0], x2
+        st1             {v0.8B},     [x0], x2
+        sqxtun          v4.8B,  v28.8H
+        st1             {v1.8B},     [x0], x2
+        sqxtun          v5.8B,  v29.8H
+        st1             {v2.8B},     [x0], x2
+        sqxtun          v6.8B,  v30.8H
+        st1             {v3.8B},     [x0], x2
+        sqxtun          v7.8B,  v31.8H
+        st1             {v4.8B},     [x0], x2
+        st1             {v5.8B},     [x0], x2
+        st1             {v6.8B},     [x0], x2
+        st1             {v7.8B},     [x0], x2
        ret
 endfunc

@@ -385,7 +385,7 @@ function ff_h264_idct8_add4_neon, export=1
        movrel          x14, .L_ff_h264_idct8_add_neon
 1:      ldrb            w9,  [x7], #4
        ldrsw           x0,  [x5], #16
-        ldrb            w9,  [x4, w9, uxtw]
+        ldrb            w9,  [x4, w9, UXTW]
        subs            w9,  w9,  #1
        b.lt            2f
        ldrsh           w11,  [x1]
--- a/libavcodec/aarch64/h264qpel_neon.S
+++ b/libavcodec/aarch64/h264qpel_neon.S
@@ -27,127 +27,127 @@
 .macro  lowpass_const   r
        movz            \r, #20, lsl #16
        movk            \r, #5
-        mov             v6.s[0], \r
+        mov             v6.S[0], \r
 .endm

 //trashes v0-v5
 .macro  lowpass_8       r0,  r1,  r2,  r3,  d0,  d1,  narrow=1
-        ext             v2.8b,      \r0\().8b, \r1\().8b, #2
-        ext             v3.8b,      \r0\().8b, \r1\().8b, #3
-        uaddl           v2.8h,      v2.8b,     v3.8b
-        ext             v4.8b,      \r0\().8b, \r1\().8b, #1
-        ext             v5.8b,      \r0\().8b, \r1\().8b, #4
-        uaddl           v4.8h,      v4.8b,     v5.8b
-        ext             v1.8b,      \r0\().8b, \r1\().8b, #5
-        uaddl           \d0\().8h,  \r0\().8b, v1.8b
-        ext             v0.8b,      \r2\().8b, \r3\().8b, #2
-        mla             \d0\().8h,  v2.8h,     v6.h[1]
-        ext             v1.8b,      \r2\().8b, \r3\().8b, #3
-        uaddl           v0.8h,      v0.8b,     v1.8b
-        ext             v1.8b,      \r2\().8b, \r3\().8b, #1
-        mls             \d0\().8h,  v4.8h,     v6.h[0]
-        ext             v3.8b,      \r2\().8b, \r3\().8b, #4
-        uaddl           v1.8h,      v1.8b,     v3.8b
-        ext             v2.8b,      \r2\().8b, \r3\().8b, #5
-        uaddl           \d1\().8h,  \r2\().8b, v2.8b
-        mla             \d1\().8h,  v0.8h,     v6.h[1]
-        mls             \d1\().8h,  v1.8h,     v6.h[0]
+        ext             v2.8B,      \r0\().8B, \r1\().8B, #2
+        ext             v3.8B,      \r0\().8B, \r1\().8B, #3
+        uaddl           v2.8H,      v2.8B,     v3.8B
+        ext             v4.8B,      \r0\().8B, \r1\().8B, #1
+        ext             v5.8B,      \r0\().8B, \r1\().8B, #4
+        uaddl           v4.8H,      v4.8B,     v5.8B
+        ext             v1.8B,      \r0\().8B, \r1\().8B, #5
+        uaddl           \d0\().8H,  \r0\().8B, v1.8B
+        ext             v0.8B,      \r2\().8B, \r3\().8B, #2
+        mla             \d0\().8H,  v2.8H,     v6.H[1]
+        ext             v1.8B,      \r2\().8B, \r3\().8B, #3
+        uaddl           v0.8H,      v0.8B,     v1.8B
+        ext             v1.8B,      \r2\().8B, \r3\().8B, #1
+        mls             \d0\().8H,  v4.8H,     v6.H[0]
+        ext             v3.8B,      \r2\().8B, \r3\().8B, #4
+        uaddl           v1.8H,      v1.8B,     v3.8B
+        ext             v2.8B,      \r2\().8B, \r3\().8B, #5
+        uaddl           \d1\().8H,  \r2\().8B, v2.8B
+        mla             \d1\().8H,  v0.8H,     v6.H[1]
+        mls             \d1\().8H,  v1.8H,     v6.H[0]
  .if \narrow
-        sqrshrun        \d0\().8b,  \d0\().8h, #5
-        sqrshrun        \d1\().8b,  \d1\().8h, #5
+        sqrshrun        \d0\().8B,  \d0\().8H, #5
+        sqrshrun        \d1\().8B,  \d1\().8H, #5
  .endif
 .endm

 //trashes v0-v4
 .macro  lowpass_8_v     r0,  r1,  r2,  r3,  r4,  r5,  r6,  d0,  d1,  narrow=1
-        uaddl           v2.8h,      \r2\().8b, \r3\().8b
-        uaddl           v0.8h,      \r3\().8b, \r4\().8b
-        uaddl           v4.8h,      \r1\().8b, \r4\().8b
-        uaddl           v1.8h,      \r2\().8b, \r5\().8b
-        uaddl           \d0\().8h,  \r0\().8b, \r5\().8b
-        uaddl           \d1\().8h,  \r1\().8b, \r6\().8b
-        mla             \d0\().8h,  v2.8h,     v6.h[1]
-        mls             \d0\().8h,  v4.8h,     v6.h[0]
-        mla             \d1\().8h,  v0.8h,     v6.h[1]
-        mls             \d1\().8h,  v1.8h,     v6.h[0]
+        uaddl           v2.8H,      \r2\().8B, \r3\().8B
+        uaddl           v0.8H,      \r3\().8B, \r4\().8B
+        uaddl           v4.8H,      \r1\().8B, \r4\().8B
+        uaddl           v1.8H,      \r2\().8B, \r5\().8B
+        uaddl           \d0\().8H,  \r0\().8B, \r5\().8B
+        uaddl           \d1\().8H,  \r1\().8B, \r6\().8B
+        mla             \d0\().8H,  v2.8H,     v6.H[1]
+        mls             \d0\().8H,  v4.8H,     v6.H[0]
+        mla             \d1\().8H,  v0.8H,     v6.H[1]
+        mls             \d1\().8H,  v1.8H,     v6.H[0]
  .if \narrow
-        sqrshrun        \d0\().8b,  \d0\().8h, #5
-        sqrshrun        \d1\().8b,  \d1\().8h, #5
+        sqrshrun        \d0\().8B,  \d0\().8H, #5
+        sqrshrun        \d1\().8B,  \d1\().8H, #5
  .endif
 .endm

 //trashes v0-v5, v7, v30-v31
 .macro  lowpass_8H      r0,  r1
-        ext             v0.16b,     \r0\().16b, \r0\().16b, #2
-        ext             v1.16b,     \r0\().16b, \r0\().16b, #3
-        uaddl           v0.8h,      v0.8b,      v1.8b
-        ext             v2.16b,     \r0\().16b, \r0\().16b, #1
-        ext             v3.16b,     \r0\().16b, \r0\().16b, #4
-        uaddl           v2.8h,      v2.8b,      v3.8b
-        ext             v30.16b,    \r0\().16b, \r0\().16b, #5
-        uaddl           \r0\().8h,  \r0\().8b,  v30.8b
-        ext             v4.16b,     \r1\().16b, \r1\().16b, #2
-        mla             \r0\().8h,  v0.8h,      v6.h[1]
-        ext             v5.16b,     \r1\().16b, \r1\().16b, #3
-        uaddl           v4.8h,      v4.8b,      v5.8b
-        ext             v7.16b,     \r1\().16b, \r1\().16b, #1
-        mls             \r0\().8h,  v2.8h,      v6.h[0]
-        ext             v0.16b,     \r1\().16b, \r1\().16b, #4
-        uaddl           v7.8h,      v7.8b,      v0.8b
-        ext             v31.16b,    \r1\().16b, \r1\().16b, #5
-        uaddl           \r1\().8h,  \r1\().8b,  v31.8b
-        mla             \r1\().8h,  v4.8h,      v6.h[1]
-        mls             \r1\().8h,  v7.8h,      v6.h[0]
+        ext             v0.16B,     \r0\().16B, \r0\().16B, #2
+        ext             v1.16B,     \r0\().16B, \r0\().16B, #3
+        uaddl           v0.8H,      v0.8B,      v1.8B
+        ext             v2.16B,     \r0\().16B, \r0\().16B, #1
+        ext             v3.16B,     \r0\().16B, \r0\().16B, #4
+        uaddl           v2.8H,      v2.8B,      v3.8B
+        ext             v30.16B,    \r0\().16B, \r0\().16B, #5
+        uaddl           \r0\().8H,  \r0\().8B,  v30.8B
+        ext             v4.16B,     \r1\().16B, \r1\().16B, #2
+        mla             \r0\().8H,  v0.8H,      v6.H[1]
+        ext             v5.16B,     \r1\().16B, \r1\().16B, #3
+        uaddl           v4.8H,      v4.8B,      v5.8B
+        ext             v7.16B,     \r1\().16B, \r1\().16B, #1
+        mls             \r0\().8H,  v2.8H,      v6.H[0]
+        ext             v0.16B,     \r1\().16B, \r1\().16B, #4
+        uaddl           v7.8H,      v7.8B,      v0.8B
+        ext             v31.16B,    \r1\().16B, \r1\().16B, #5
+        uaddl           \r1\().8H,  \r1\().8B,  v31.8B
+        mla             \r1\().8H,  v4.8H,      v6.H[1]
+        mls             \r1\().8H,  v7.8H,      v6.H[0]
 .endm

 // trashes v2-v5, v30
 .macro  lowpass_8_1     r0,  r1,  d0,  narrow=1
-        ext             v2.8b,     \r0\().8b, \r1\().8b, #2
-        ext             v3.8b,     \r0\().8b, \r1\().8b, #3
-        uaddl           v2.8h,     v2.8b,     v3.8b
-        ext             v4.8b,     \r0\().8b, \r1\().8b, #1
-        ext             v5.8b,     \r0\().8b, \r1\().8b, #4
-        uaddl           v4.8h,     v4.8b,     v5.8b
-        ext             v30.8b,    \r0\().8b, \r1\().8b, #5
-        uaddl           \d0\().8h, \r0\().8b, v30.8b
-        mla             \d0\().8h, v2.8h,     v6.h[1]
-        mls             \d0\().8h, v4.8h,     v6.h[0]
+        ext             v2.8B,     \r0\().8B, \r1\().8B, #2
+        ext             v3.8B,     \r0\().8B, \r1\().8B, #3
+        uaddl           v2.8H,     v2.8B,     v3.8B
+        ext             v4.8B,     \r0\().8B, \r1\().8B, #1
+        ext             v5.8B,     \r0\().8B, \r1\().8B, #4
+        uaddl           v4.8H,     v4.8B,     v5.8B
+        ext             v30.8B,    \r0\().8B, \r1\().8B, #5
+        uaddl           \d0\().8H, \r0\().8B, v30.8B
+        mla             \d0\().8H, v2.8H,     v6.H[1]
+        mls             \d0\().8H, v4.8H,     v6.H[0]
  .if \narrow
-        sqrshrun        \d0\().8b, \d0\().8h, #5
+        sqrshrun        \d0\().8B, \d0\().8H, #5
  .endif
 .endm

 // trashed v0-v7
 .macro  lowpass_8.16    r0,  r1,  r2,  r3,  r4,  r5
-        saddl           v5.4s,      \r2\().4h,  \r3\().4h
-        saddl2          v1.4s,      \r2\().8h,  \r3\().8h
-        saddl           v6.4s,      \r1\().4h,  \r4\().4h
-        saddl2          v2.4s,      \r1\().8h,  \r4\().8h
-        saddl           v0.4s,      \r0\().4h,  \r5\().4h
-        saddl2          v4.4s,      \r0\().8h,  \r5\().8h
+        saddl           v5.4S,      \r2\().4H,  \r3\().4H
+        saddl2          v1.4S,      \r2\().8H,  \r3\().8H
+        saddl           v6.4S,      \r1\().4H,  \r4\().4H
+        saddl2          v2.4S,      \r1\().8H,  \r4\().8H
+        saddl           v0.4S,      \r0\().4H,  \r5\().4H
+        saddl2          v4.4S,      \r0\().8H,  \r5\().8H

-        shl             v3.4s,  v5.4s,  #4
-        shl             v5.4s,  v5.4s,  #2
-        shl             v7.4s,  v6.4s,  #2
-        add             v5.4s,  v5.4s,  v3.4s
-        add             v6.4s,  v6.4s,  v7.4s
+        shl             v3.4S,  v5.4S,  #4
+        shl             v5.4S,  v5.4S,  #2
+        shl             v7.4S,  v6.4S,  #2
+        add             v5.4S,  v5.4S,  v3.4S
+        add             v6.4S,  v6.4S,  v7.4S

-        shl             v3.4s,  v1.4s,  #4
-        shl             v1.4s,  v1.4s,  #2
-        shl             v7.4s,  v2.4s,  #2
-        add             v1.4s,  v1.4s,  v3.4s
-        add             v2.4s,  v2.4s,  v7.4s
+        shl             v3.4S,  v1.4S,  #4
+        shl             v1.4S,  v1.4S,  #2
+        shl             v7.4S,  v2.4S,  #2
+        add             v1.4S,  v1.4S,  v3.4S
+        add             v2.4S,  v2.4S,  v7.4S

-        add             v5.4s,  v5.4s,  v0.4s
-        sub             v5.4s,  v5.4s,  v6.4s
+        add             v5.4S,  v5.4S,  v0.4S
+        sub             v5.4S,  v5.4S,  v6.4S

-        add             v1.4s,  v1.4s,  v4.4s
-        sub             v1.4s,  v1.4s,  v2.4s
+        add             v1.4S,  v1.4S,  v4.4S
+        sub             v1.4S,  v1.4S,  v2.4S

-        rshrn           v5.4h,  v5.4s,  #10
-        rshrn2          v5.8h,  v1.4s,  #10
+        rshrn           v5.4H,  v5.4S,  #10
+        rshrn2          v5.8H,  v1.4S,  #10

-        sqxtun          \r0\().8b,  v5.8h
+        sqxtun          \r0\().8B,  v5.8H
 .endm

 function put_h264_qpel16_h_lowpass_neon_packed
@@ -176,19 +176,19 @@ function \type\()_h264_qpel16_h_lowpass_neon
 endfunc

 function \type\()_h264_qpel8_h_lowpass_neon
-1:      ld1             {v28.8b, v29.8b}, [x1], x2
-        ld1             {v16.8b, v17.8b}, [x1], x2
+1:      ld1             {v28.8B, v29.8B}, [x1], x2
+        ld1             {v16.8B, v17.8B}, [x1], x2
        subs            x12, x12, #2
        lowpass_8       v28, v29, v16, v17, v28, v16
  .ifc \type,avg
-        ld1             {v2.8b},    [x0], x3
-        ld1             {v3.8b},    [x0]
-        urhadd          v28.8b, v28.8b,  v2.8b
-        urhadd          v16.8b, v16.8b, v3.8b
+        ld1             {v2.8B},    [x0], x3
+        ld1             {v3.8B},    [x0]
+        urhadd          v28.8B, v28.8B,  v2.8B
+        urhadd          v16.8B, v16.8B, v3.8B
        sub             x0,  x0,  x3
  .endif
-        st1             {v28.8b},    [x0], x3
-        st1             {v16.8b},    [x0], x3
+        st1             {v28.8B},    [x0], x3
+        st1             {v16.8B},    [x0], x3
        b.ne            1b
        ret
 endfunc
@@ -213,23 +213,23 @@ function \type\()_h264_qpel16_h_lowpass_l2_neon
 endfunc

 function \type\()_h264_qpel8_h_lowpass_l2_neon
-1:      ld1             {v26.8b, v27.8b}, [x1], x2
-        ld1             {v16.8b, v17.8b}, [x1], x2
-        ld1             {v28.8b},     [x3], x2
-        ld1             {v29.8b},     [x3], x2
+1:      ld1             {v26.8B, v27.8B}, [x1], x2
+        ld1             {v16.8B, v17.8B}, [x1], x2
+        ld1             {v28.8B},     [x3], x2
+        ld1             {v29.8B},     [x3], x2
        subs            x12, x12, #2
        lowpass_8       v26, v27, v16, v17, v26, v27
-        urhadd          v26.8b, v26.8b, v28.8b
-        urhadd          v27.8b, v27.8b, v29.8b
+        urhadd          v26.8B, v26.8B, v28.8B
+        urhadd          v27.8B, v27.8B, v29.8B
  .ifc \type,avg
-        ld1             {v2.8b},      [x0], x2
-        ld1             {v3.8b},      [x0]
-        urhadd          v26.8b, v26.8b, v2.8b
-        urhadd          v27.8b, v27.8b, v3.8b
+        ld1             {v2.8B},      [x0], x2
+        ld1             {v3.8B},      [x0]
+        urhadd          v26.8B, v26.8B, v2.8B
+        urhadd          v27.8B, v27.8B, v3.8B
        sub             x0,  x0,  x2
  .endif
-        st1             {v26.8b},     [x0], x2
-        st1             {v27.8b},     [x0], x2
+        st1             {v26.8B},     [x0], x2
+        st1             {v27.8B},     [x0], x2
        b.ne            1b
        ret
 endfunc
@@ -270,52 +270,52 @@ function \type\()_h264_qpel16_v_lowpass_neon
 endfunc

 function \type\()_h264_qpel8_v_lowpass_neon
-        ld1             {v16.8b}, [x1], x3
-        ld1             {v17.8b}, [x1], x3
-        ld1             {v18.8b}, [x1], x3
-        ld1             {v19.8b}, [x1], x3
-        ld1             {v20.8b}, [x1], x3
-        ld1             {v21.8b}, [x1], x3
-        ld1             {v22.8b}, [x1], x3
-        ld1             {v23.8b}, [x1], x3
-        ld1             {v24.8b}, [x1], x3
-        ld1             {v25.8b}, [x1], x3
-        ld1             {v26.8b}, [x1], x3
-        ld1             {v27.8b}, [x1], x3
-        ld1             {v28.8b}, [x1]
+        ld1             {v16.8B}, [x1], x3
+        ld1             {v17.8B}, [x1], x3
+        ld1             {v18.8B}, [x1], x3
+        ld1             {v19.8B}, [x1], x3
+        ld1             {v20.8B}, [x1], x3
+        ld1             {v21.8B}, [x1], x3
+        ld1             {v22.8B}, [x1], x3
+        ld1             {v23.8B}, [x1], x3
+        ld1             {v24.8B}, [x1], x3
+        ld1             {v25.8B}, [x1], x3
+        ld1             {v26.8B}, [x1], x3
+        ld1             {v27.8B}, [x1], x3
+        ld1             {v28.8B}, [x1]

        lowpass_8_v     v16, v17, v18, v19, v20, v21, v22, v16, v17
        lowpass_8_v     v18, v19, v20, v21, v22, v23, v24, v18, v19
        lowpass_8_v     v20, v21, v22, v23, v24, v25, v26, v20, v21
        lowpass_8_v     v22, v23, v24, v25, v26, v27, v28, v22, v23
  .ifc \type,avg
-        ld1             {v24.8b},  [x0], x2
-        ld1             {v25.8b}, [x0], x2
-        ld1             {v26.8b}, [x0], x2
-        urhadd          v16.8b, v16.8b, v24.8b
-        ld1             {v27.8b}, [x0], x2
-        urhadd          v17.8b, v17.8b, v25.8b
-        ld1             {v28.8b}, [x0], x2
-        urhadd          v18.8b, v18.8b, v26.8b
-        ld1             {v29.8b}, [x0], x2
-        urhadd          v19.8b, v19.8b, v27.8b
-        ld1             {v30.8b}, [x0], x2
-        urhadd          v20.8b, v20.8b, v28.8b
-        ld1             {v31.8b}, [x0], x2
-        urhadd          v21.8b, v21.8b, v29.8b
-        urhadd          v22.8b, v22.8b, v30.8b
-        urhadd          v23.8b, v23.8b, v31.8b
+        ld1             {v24.8B},  [x0], x2
+        ld1             {v25.8B}, [x0], x2
+        ld1             {v26.8B}, [x0], x2
+        urhadd          v16.8B, v16.8B, v24.8B
+        ld1             {v27.8B}, [x0], x2
+        urhadd          v17.8B, v17.8B, v25.8B
+        ld1             {v28.8B}, [x0], x2
+        urhadd          v18.8B, v18.8B, v26.8B
+        ld1             {v29.8B}, [x0], x2
+        urhadd          v19.8B, v19.8B, v27.8B
+        ld1             {v30.8B}, [x0], x2
+        urhadd          v20.8B, v20.8B, v28.8B
+        ld1             {v31.8B}, [x0], x2
+        urhadd          v21.8B, v21.8B, v29.8B
+        urhadd          v22.8B, v22.8B, v30.8B
+        urhadd          v23.8B, v23.8B, v31.8B
        sub             x0,  x0,  x2,  lsl #3
  .endif

-        st1             {v16.8b}, [x0], x2
-        st1             {v17.8b}, [x0], x2
-        st1             {v18.8b}, [x0], x2
-        st1             {v19.8b}, [x0], x2
-        st1             {v20.8b}, [x0], x2
-        st1             {v21.8b}, [x0], x2
-        st1             {v22.8b}, [x0], x2
-        st1             {v23.8b}, [x0], x2
+        st1             {v16.8B}, [x0], x2
+        st1             {v17.8B}, [x0], x2
+        st1             {v18.8B}, [x0], x2
+        st1             {v19.8B}, [x0], x2
+        st1             {v20.8B}, [x0], x2
+        st1             {v21.8B}, [x0], x2
+        st1             {v22.8B}, [x0], x2
+        st1             {v23.8B}, [x0], x2

        ret
 endfunc
@@ -343,70 +343,70 @@ function \type\()_h264_qpel16_v_lowpass_l2_neon
 endfunc

 function \type\()_h264_qpel8_v_lowpass_l2_neon
-        ld1             {v16.8b}, [x1], x3
-        ld1             {v17.8b}, [x1], x3
-        ld1             {v18.8b}, [x1], x3
-        ld1             {v19.8b}, [x1], x3
-        ld1             {v20.8b}, [x1], x3
-        ld1             {v21.8b}, [x1], x3
-        ld1             {v22.8b}, [x1], x3
-        ld1             {v23.8b}, [x1], x3
-        ld1             {v24.8b}, [x1], x3
-        ld1             {v25.8b}, [x1], x3
-        ld1             {v26.8b}, [x1], x3
-        ld1             {v27.8b}, [x1], x3
-        ld1             {v28.8b}, [x1]
+        ld1             {v16.8B}, [x1], x3
+        ld1             {v17.8B}, [x1], x3
+        ld1             {v18.8B}, [x1], x3
+        ld1             {v19.8B}, [x1], x3
+        ld1             {v20.8B}, [x1], x3
+        ld1             {v21.8B}, [x1], x3
+        ld1             {v22.8B}, [x1], x3
+        ld1             {v23.8B}, [x1], x3
+        ld1             {v24.8B}, [x1], x3
+        ld1             {v25.8B}, [x1], x3
+        ld1             {v26.8B}, [x1], x3
+        ld1             {v27.8B}, [x1], x3
+        ld1             {v28.8B}, [x1]

        lowpass_8_v     v16, v17, v18, v19, v20, v21, v22, v16, v17
        lowpass_8_v     v18, v19, v20, v21, v22, v23, v24, v18, v19
        lowpass_8_v     v20, v21, v22, v23, v24, v25, v26, v20, v21
        lowpass_8_v     v22, v23, v24, v25, v26, v27, v28, v22, v23

-        ld1             {v24.8b},  [x12], x2
-        ld1             {v25.8b},  [x12], x2
-        ld1             {v26.8b},  [x12], x2
-        ld1             {v27.8b},  [x12], x2
-        ld1             {v28.8b},  [x12], x2
-        urhadd          v16.8b, v24.8b, v16.8b
-        urhadd          v17.8b, v25.8b, v17.8b
-        ld1             {v29.8b},  [x12], x2
-        urhadd          v18.8b, v26.8b, v18.8b
-        urhadd          v19.8b, v27.8b, v19.8b
-        ld1             {v30.8b}, [x12], x2
-        urhadd          v20.8b, v28.8b, v20.8b
-        urhadd          v21.8b, v29.8b, v21.8b
-        ld1             {v31.8b}, [x12], x2
-        urhadd          v22.8b, v30.8b, v22.8b
-        urhadd          v23.8b, v31.8b, v23.8b
+        ld1             {v24.8B},  [x12], x2
+        ld1             {v25.8B},  [x12], x2
+        ld1             {v26.8B},  [x12], x2
+        ld1             {v27.8B},  [x12], x2
+        ld1             {v28.8B},  [x12], x2
+        urhadd          v16.8B, v24.8B, v16.8B
+        urhadd          v17.8B, v25.8B, v17.8B
+        ld1             {v29.8B},  [x12], x2
+        urhadd          v18.8B, v26.8B, v18.8B
+        urhadd          v19.8B, v27.8B, v19.8B
+        ld1             {v30.8B}, [x12], x2
+        urhadd          v20.8B, v28.8B, v20.8B
+        urhadd          v21.8B, v29.8B, v21.8B
+        ld1             {v31.8B}, [x12], x2
+        urhadd          v22.8B, v30.8B, v22.8B
+        urhadd          v23.8B, v31.8B, v23.8B

  .ifc \type,avg
-        ld1             {v24.8b}, [x0], x3
-        ld1             {v25.8b}, [x0], x3
-        ld1             {v26.8b}, [x0], x3
-        urhadd          v16.8b, v16.8b, v24.8b
-        ld1             {v27.8b}, [x0], x3
-        urhadd          v17.8b, v17.8b, v25.8b
-        ld1             {v28.8b}, [x0], x3
-        urhadd          v18.8b, v18.8b, v26.8b
-        ld1             {v29.8b}, [x0], x3
-        urhadd          v19.8b, v19.8b, v27.8b
-        ld1             {v30.8b}, [x0], x3
-        urhadd          v20.8b, v20.8b, v28.8b
-        ld1             {v31.8b}, [x0], x3
-        urhadd          v21.8b, v21.8b, v29.8b
-        urhadd          v22.8b, v22.8b, v30.8b
-        urhadd          v23.8b, v23.8b, v31.8b
+        ld1             {v24.8B}, [x0], x3
+        ld1             {v25.8B}, [x0], x3
+        ld1             {v26.8B}, [x0], x3
+        urhadd          v16.8B, v16.8B, v24.8B
+        ld1             {v27.8B}, [x0], x3
+        urhadd          v17.8B, v17.8B, v25.8B
+        ld1             {v28.8B}, [x0], x3
+        urhadd          v18.8B, v18.8B, v26.8B
+        ld1             {v29.8B}, [x0], x3
+        urhadd          v19.8B, v19.8B, v27.8B
+        ld1             {v30.8B}, [x0], x3
+        urhadd          v20.8B, v20.8B, v28.8B
+        ld1             {v31.8B}, [x0], x3
+        urhadd          v21.8B, v21.8B, v29.8B
+        urhadd          v22.8B, v22.8B, v30.8B
+        urhadd          v23.8B, v23.8B, v31.8B
        sub             x0,  x0,  x3,  lsl #3
  .endif

-        st1             {v16.8b}, [x0], x3
-        st1             {v17.8b}, [x0], x3
-        st1             {v18.8b}, [x0], x3
-        st1             {v19.8b}, [x0], x3
-        st1             {v20.8b}, [x0], x3
-        st1             {v21.8b}, [x0], x3
-        st1             {v22.8b}, [x0], x3
-        st1             {v23.8b}, [x0], x3
+        st1             {v16.8B}, [x0], x3
+        st1             {v17.8B}, [x0], x3
+        st1             {v18.8B}, [x0], x3
+        st1             {v19.8B}, [x0], x3
+        st1             {v20.8B}, [x0], x3
+        st1             {v21.8B}, [x0], x3
+        st1             {v22.8B}, [x0], x3
+        st1             {v23.8B}, [x0], x3

        ret
 endfunc
@@ -417,19 +417,19 @@ endfunc

 function put_h264_qpel8_hv_lowpass_neon_top
        lowpass_const   w12
-        ld1             {v16.8h}, [x1], x3
-        ld1             {v17.8h}, [x1], x3
-        ld1             {v18.8h}, [x1], x3
-        ld1             {v19.8h}, [x1], x3
-        ld1             {v20.8h}, [x1], x3
-        ld1             {v21.8h}, [x1], x3
-        ld1             {v22.8h}, [x1], x3
-        ld1             {v23.8h}, [x1], x3
-        ld1             {v24.8h}, [x1], x3
-        ld1             {v25.8h}, [x1], x3
-        ld1             {v26.8h}, [x1], x3
-        ld1             {v27.8h}, [x1], x3
-        ld1             {v28.8h}, [x1]
+        ld1             {v16.8H}, [x1], x3
+        ld1             {v17.8H}, [x1], x3
+        ld1             {v18.8H}, [x1], x3
+        ld1             {v19.8H}, [x1], x3
+        ld1             {v20.8H}, [x1], x3
+        ld1             {v21.8H}, [x1], x3
+        ld1             {v22.8H}, [x1], x3
+        ld1             {v23.8H}, [x1], x3
+        ld1             {v24.8H}, [x1], x3
+        ld1             {v25.8H}, [x1], x3
+        ld1             {v26.8H}, [x1], x3
+        ld1             {v27.8H}, [x1], x3
+        ld1             {v28.8H}, [x1]
        lowpass_8H      v16, v17
        lowpass_8H      v18, v19
        lowpass_8H      v20, v21
@@ -458,33 +458,33 @@ function \type\()_h264_qpel8_hv_lowpass_neon
        mov             x10, x30
        bl              put_h264_qpel8_hv_lowpass_neon_top
  .ifc \type,avg
-        ld1             {v0.8b},      [x0], x2
-        ld1             {v1.8b},      [x0], x2
-        ld1             {v2.8b},      [x0], x2
-        urhadd          v16.8b, v16.8b, v0.8b
-        ld1             {v3.8b},      [x0], x2
-        urhadd          v17.8b, v17.8b, v1.8b
-        ld1             {v4.8b},      [x0], x2
-        urhadd          v18.8b, v18.8b, v2.8b
-        ld1             {v5.8b},      [x0], x2
-        urhadd          v19.8b, v19.8b, v3.8b
-        ld1             {v6.8b},      [x0], x2
-        urhadd          v20.8b, v20.8b, v4.8b
-        ld1             {v7.8b},      [x0], x2
-        urhadd          v21.8b, v21.8b, v5.8b
-        urhadd          v22.8b, v22.8b, v6.8b
-        urhadd          v23.8b, v23.8b, v7.8b
+        ld1             {v0.8B},      [x0], x2
+        ld1             {v1.8B},      [x0], x2
+        ld1             {v2.8B},      [x0], x2
+        urhadd          v16.8B, v16.8B, v0.8B
+        ld1             {v3.8B},      [x0], x2
+        urhadd          v17.8B, v17.8B, v1.8B
+        ld1             {v4.8B},      [x0], x2
+        urhadd          v18.8B, v18.8B, v2.8B
+        ld1             {v5.8B},      [x0], x2
+        urhadd          v19.8B, v19.8B, v3.8B
+        ld1             {v6.8B},      [x0], x2
+        urhadd          v20.8B, v20.8B, v4.8B
+        ld1             {v7.8B},      [x0], x2
+        urhadd          v21.8B, v21.8B, v5.8B
+        urhadd          v22.8B, v22.8B, v6.8B
+        urhadd          v23.8B, v23.8B, v7.8B
        sub             x0,  x0,  x2,  lsl #3
  .endif

-        st1             {v16.8b},     [x0], x2
-        st1             {v17.8b},     [x0], x2
-        st1             {v18.8b},     [x0], x2
-        st1             {v19.8b},     [x0], x2
-        st1             {v20.8b},     [x0], x2
-        st1             {v21.8b},     [x0], x2
-        st1             {v22.8b},     [x0], x2
-        st1             {v23.8b},     [x0], x2
+        st1             {v16.8B},     [x0], x2
+        st1             {v17.8B},     [x0], x2
+        st1             {v18.8B},     [x0], x2
+        st1             {v19.8B},     [x0], x2
+        st1             {v20.8B},     [x0], x2
+        st1             {v21.8B},     [x0], x2
+        st1             {v22.8B},     [x0], x2
+        st1             {v23.8B},     [x0], x2

        ret             x10
 endfunc
@@ -498,45 +498,45 @@ function \type\()_h264_qpel8_hv_lowpass_l2_neon
        mov             x10, x30
        bl              put_h264_qpel8_hv_lowpass_neon_top

-        ld1             {v0.8b, v1.8b},  [x2], #16
-        ld1             {v2.8b, v3.8b},  [x2], #16
-        urhadd          v0.8b,  v0.8b,  v16.8b
-        urhadd          v1.8b,  v1.8b,  v17.8b
-        ld1             {v4.8b, v5.8b},  [x2], #16
-        urhadd          v2.8b,  v2.8b,  v18.8b
-        urhadd          v3.8b,  v3.8b,  v19.8b
-        ld1             {v6.8b, v7.8b},  [x2], #16
-        urhadd          v4.8b,  v4.8b,  v20.8b
-        urhadd          v5.8b,  v5.8b,  v21.8b
-        urhadd          v6.8b,  v6.8b,  v22.8b
-        urhadd          v7.8b,  v7.8b,  v23.8b
+        ld1             {v0.8B, v1.8B},  [x2], #16
+        ld1             {v2.8B, v3.8B},  [x2], #16
+        urhadd          v0.8B,  v0.8B,  v16.8B
+        urhadd          v1.8B,  v1.8B,  v17.8B
+        ld1             {v4.8B, v5.8B},  [x2], #16
+        urhadd          v2.8B,  v2.8B,  v18.8B
+        urhadd          v3.8B,  v3.8B,  v19.8B
+        ld1             {v6.8B, v7.8B},  [x2], #16
+        urhadd          v4.8B,  v4.8B,  v20.8B
+        urhadd          v5.8B,  v5.8B,  v21.8B
+        urhadd          v6.8B,  v6.8B,  v22.8B
+        urhadd          v7.8B,  v7.8B,  v23.8B
  .ifc \type,avg
-        ld1             {v16.8b},     [x0], x3
-        ld1             {v17.8b},     [x0], x3
-        ld1             {v18.8b},     [x0], x3
-        urhadd          v0.8b,  v0.8b,  v16.8b
-        ld1             {v19.8b},     [x0], x3
-        urhadd          v1.8b,  v1.8b,  v17.8b
-        ld1             {v20.8b},     [x0], x3
-        urhadd          v2.8b,  v2.8b,  v18.8b
-        ld1             {v21.8b},     [x0], x3
-        urhadd          v3.8b,  v3.8b,  v19.8b
-        ld1             {v22.8b},     [x0], x3
-        urhadd          v4.8b,  v4.8b,  v20.8b
-        ld1             {v23.8b},     [x0], x3
-        urhadd          v5.8b,  v5.8b,  v21.8b
-        urhadd          v6.8b,  v6.8b,  v22.8b
-        urhadd          v7.8b,  v7.8b,  v23.8b
+        ld1             {v16.8B},     [x0], x3
+        ld1             {v17.8B},     [x0], x3
+        ld1             {v18.8B},     [x0], x3
+        urhadd          v0.8B,  v0.8B,  v16.8B
+        ld1             {v19.8B},     [x0], x3
+        urhadd          v1.8B,  v1.8B,  v17.8B
+        ld1             {v20.8B},     [x0], x3
+        urhadd          v2.8B,  v2.8B,  v18.8B
+        ld1             {v21.8B},     [x0], x3
+        urhadd          v3.8B,  v3.8B,  v19.8B
+        ld1             {v22.8B},     [x0], x3
+        urhadd          v4.8B,  v4.8B,  v20.8B
+        ld1             {v23.8B},     [x0], x3
+        urhadd          v5.8B,  v5.8B,  v21.8B
+        urhadd          v6.8B,  v6.8B,  v22.8B
+        urhadd          v7.8B,  v7.8B,  v23.8B
        sub             x0,  x0,  x3,  lsl #3
  .endif
-        st1             {v0.8b},      [x0], x3
-        st1             {v1.8b},      [x0], x3
-        st1             {v2.8b},      [x0], x3
-        st1             {v3.8b},      [x0], x3
-        st1             {v4.8b},      [x0], x3
-        st1             {v5.8b},      [x0], x3
-        st1             {v6.8b},      [x0], x3
-        st1             {v7.8b},      [x0], x3
+        st1             {v0.8B},      [x0], x3
+        st1             {v1.8B},      [x0], x3
+        st1             {v2.8B},      [x0], x3
+        st1             {v3.8B},      [x0], x3
+        st1             {v4.8B},      [x0], x3
+        st1             {v5.8B},      [x0], x3
+        st1             {v6.8B},      [x0], x3
+        st1             {v7.8B},      [x0], x3

        ret             x10
 endfunc
@@ -580,8 +580,8 @@ function \type\()_h264_qpel16_hv_lowpass_l2_neon
 endfunc
 .endm

-        h264_qpel16_hv  put
-        h264_qpel16_hv  avg
+        h264_qpel16_hv put
+        h264_qpel16_hv avg

 .macro  h264_qpel8      type
 function ff_\type\()_h264_qpel8_mc10_neon, export=1
@@ -759,8 +759,8 @@ function ff_\type\()_h264_qpel8_mc33_neon, export=1
 endfunc
 .endm

-        h264_qpel8      put
-        h264_qpel8      avg
+        h264_qpel8 put
+        h264_qpel8 avg

 .macro  h264_qpel16     type
 function ff_\type\()_h264_qpel16_mc10_neon, export=1
@@ -931,5 +931,5 @@ function ff_\type\()_h264_qpel16_mc33_neon, export=1
 endfunc
 .endm

-        h264_qpel16     put
-        h264_qpel16     avg
+        h264_qpel16 put
+        h264_qpel16 avg
--- a/libavcodec/aarch64/hevcdsp_deblock_neon.S
+++ b/libavcodec/aarch64/hevcdsp_deblock_neon.S
@@ -1,183 +0,0 @@
-/* -*-arm64-*-
- * vim: syntax=arm64asm
- *
- * Copyright (c) 2014 Seppo Tomperi <seppo.tomperi@vtt.fi>
- * Copyright (c) 2023 J. Dekker <jdek@itanimul.li>
- *
- * This file is part of FFmpeg.
- *
- * FFmpeg is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2.1 of the License, or (at your option) any later version.
- *
- * FFmpeg is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with FFmpeg; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
-
-#include "libavutil/aarch64/asm.S"
-#include "neon.S"
-
-.macro hevc_loop_filter_chroma_start bitdepth
-        mov             x4, x30
-        ldr             w14, [x2]
-        ldr             w15, [x2, #4]
-.if \bitdepth > 8
-        lsl             w14, w14, #(\bitdepth - 8)
-        lsl             w15, w15, #(\bitdepth - 8)
-.endif
-        adds            w2, w14, w15
-        b.eq            1f
-        dup             v16.4h, w14
-        dup             v17.4h, w15
-        trn1            v16.2d, v16.2d, v17.2d
-.if \bitdepth > 8
-        mvni            v19.8h, #((0xff << (\bitdepth - 8)) & 0xff), lsl #8
-        movi            v18.8h, #0
-.endif
-        neg             v17.8h, v16.8h
-.endm
-
-.macro hevc_loop_filter_chroma_body bitdepth
-.if \bitdepth <= 8
-        uxtl            v20.8h, v0.8b // p1
-        uxtl            v1.8h,  v1.8b // p0
-        uxtl            v2.8h,  v2.8b // q0
-        uxtl            v23.8h, v3.8b // q1
-        va              .req v20
-        vb              .req v23
-.else   // required to specify both cases as we are unable to do: v0 .req v20
-        va              .req v0
-        vb              .req v3
-.endif
-        sub             v5.8h, v2.8h, v1.8h // q0 - p0
-        sub             v6.8h, va.8h, vb.8h // p1 - q1
-        shl             v5.8h, v5.8h, #2
-        add             v5.8h, v6.8h, v5.8h
-        srshr           v5.8h, v5.8h, #3
-        clip            v17.8h, v16.8h, v5.8h
-        sqadd           v1.8h, v1.8h, v5.8h // p0 + delta
-        sqsub           v2.8h, v2.8h, v5.8h // q0 - delta
-.if \bitdepth <= 8
-        sqxtun          v1.8b, v1.8h
-        sqxtun          v2.8b, v2.8h
-.else
-        clip            v18.8h, v19.8h, v1.8h, v2.8h
-.endif
-.unreq  va
-.unreq  vb
-.endm
-
-function hevc_loop_filter_chroma_body_8_neon, export=0
-        hevc_loop_filter_chroma_body 8
-        ret
-endfunc
-
-function hevc_loop_filter_chroma_body_10_neon, export=0
-hevc_loop_filter_chroma_body_12_neon:
-        hevc_loop_filter_chroma_body 10
-        ret
-endfunc
-
-// void ff_hevc_h_loop_filter_chroma_8_neon(uint8_t *_pix, ptrdiff_t _stride, int *_tc, uint8_t *_no_p, uint8_t *_no_q);
-
-.macro hevc_h_loop_filter_chroma bitdepth
-function ff_hevc_h_loop_filter_chroma_\bitdepth\()_neon, export=1
-        hevc_loop_filter_chroma_start \bitdepth
-        sub             x0, x0, x1, lsl #1
-.if \bitdepth > 8
-        ld1             {v0.8h}, [x0], x1
-        ld1             {v1.8h}, [x0], x1
-        ld1             {v2.8h}, [x0], x1
-        ld1             {v3.8h}, [x0]
-.else
-        ld1             {v0.8b}, [x0], x1
-        ld1             {v1.8b}, [x0], x1
-        ld1             {v2.8b}, [x0], x1
-        ld1             {v3.8b}, [x0]
-.endif
-        sub             x0, x0, x1, lsl #1
-        bl              hevc_loop_filter_chroma_body_\bitdepth\()_neon
-.if \bitdepth > 8
-        st1             {v1.8h}, [x0], x1
-        st1             {v2.8h}, [x0]
-.else
-        st1             {v1.8b}, [x0], x1
-        st1             {v2.8b}, [x0]
-.endif
-1:      ret             x4
-endfunc
-.endm
-
-.macro hevc_v_loop_filter_chroma bitdepth
-function ff_hevc_v_loop_filter_chroma_\bitdepth\()_neon, export=1
-        hevc_loop_filter_chroma_start \bitdepth
-.if \bitdepth > 8
-        sub             x0, x0, #4
-        add             x3, x0, x1
-        lsl             x1, x1, #1
-        ld1             {v0.d}[0], [x0], x1
-        ld1             {v1.d}[0], [x3], x1
-        ld1             {v2.d}[0], [x0], x1
-        ld1             {v3.d}[0], [x3], x1
-        ld1             {v0.d}[1], [x0], x1
-        ld1             {v1.d}[1], [x3], x1
-        ld1             {v2.d}[1], [x0], x1
-        ld1             {v3.d}[1], [x3], x1
-        transpose_4x8H  v0, v1, v2, v3, v28, v29, v30, v31
-.else
-        sub             x0, x0, #2
-        add             x3, x0, x1
-        lsl             x1, x1, #1
-        ld1             {v0.s}[0], [x0], x1
-        ld1             {v1.s}[0], [x3], x1
-        ld1             {v2.s}[0], [x0], x1
-        ld1             {v3.s}[0], [x3], x1
-        ld1             {v0.s}[1], [x0], x1
-        ld1             {v1.s}[1], [x3], x1
-        ld1             {v2.s}[1], [x0], x1
-        ld1             {v3.s}[1], [x3], x1
-        transpose_4x8B  v0, v1, v2, v3, v28, v29, v30, v31
-.endif
-        sub             x0, x0, x1, lsl #2
-        sub             x3, x3, x1, lsl #2
-        bl              hevc_loop_filter_chroma_body_\bitdepth\()_neon
-.if \bitdepth > 8
-        transpose_4x8H  v0, v1, v2, v3, v28, v29, v30, v31
-        st1             {v0.d}[0], [x0], x1
-        st1             {v1.d}[0], [x3], x1
-        st1             {v2.d}[0], [x0], x1
-        st1             {v3.d}[0], [x3], x1
-        st1             {v0.d}[1], [x0], x1
-        st1             {v1.d}[1], [x3], x1
-        st1             {v2.d}[1], [x0], x1
-        st1             {v3.d}[1], [x3]
-.else
-        transpose_4x8B  v0, v1, v2, v3, v28, v29, v30, v31
-        st1             {v0.s}[0], [x0], x1
-        st1             {v1.s}[0], [x3], x1
-        st1             {v2.s}[0], [x0], x1
-        st1             {v3.s}[0], [x3], x1
-        st1             {v0.s}[1], [x0], x1
-        st1             {v1.s}[1], [x3], x1
-        st1             {v2.s}[1], [x0], x1
-        st1             {v3.s}[1], [x3]
-.endif
-1:      ret             x4
-endfunc
-.endm
-
-hevc_h_loop_filter_chroma 8
-hevc_h_loop_filter_chroma 10
-hevc_h_loop_filter_chroma 12
-
-hevc_v_loop_filter_chroma 8
-hevc_v_loop_filter_chroma 10
-hevc_v_loop_filter_chroma 12
--- a/libavcodec/aarch64/hevcdsp_epel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_epel_neon.S
--- a/libavcodec/aarch64/hevcdsp_idct_neon.S
+++ b/libavcodec/aarch64/hevcdsp_idct_neon.S
@@ -5,8 +5,7 @@
 *
 * Ported from arm/hevcdsp_idct_neon.S by
 * Copyright (c) 2020 Reimar Döffinger
- * Copyright (c) 2023 J. Dekker <jdek@itanimul.li>
- * Copyright (c) 2023 xu fulong <839789740@qq.com>
+ * Copyright (c) 2020 J. Dekker
 *
 * This file is part of FFmpeg.
 *
@@ -26,7 +25,6 @@
 */

 #include "libavutil/aarch64/asm.S"
-#include "neon.S"

 const trans, align=4
        .short          64, 83, 64, 36
@@ -39,6 +37,13 @@ const trans, align=4
        .short          31, 22, 13, 4
 endconst

+.macro clip2 in1, in2, min, max
+        smax            \in1, \in1, \min
+        smax            \in2, \in2, \min
+        smin            \in1, \in1, \max
+        smin            \in2, \in2, \max
+.endm
+
 function ff_hevc_add_residual_4x4_8_neon, export=1
        ld1             {v0.8h-v1.8h}, [x1]
        ld1             {v2.s}[0], [x0], x2
@@ -176,7 +181,7 @@ function hevc_add_residual_4x4_16_neon, export=0
        ld1             {v3.d}[1], [x12], x2
        movi            v4.8h, #0
        sqadd           v1.8h, v1.8h, v3.8h
-        clip            v4.8h, v21.8h, v0.8h, v1.8h
+        clip2           v0.8h, v1.8h, v4.8h, v21.8h
        st1             {v0.d}[0], [x0],  x2
        st1             {v0.d}[1], [x0],  x2
        st1             {v1.d}[0], [x0],  x2
@@ -195,7 +200,7 @@ function hevc_add_residual_8x8_16_neon, export=0
        sqadd           v0.8h, v0.8h, v2.8h
        ld1             {v3.8h}, [x12]
        sqadd           v1.8h, v1.8h, v3.8h
-        clip            v4.8h, v21.8h, v0.8h, v1.8h
+        clip2           v0.8h, v1.8h, v4.8h, v21.8h
        st1             {v0.8h}, [x0],  x2
        st1             {v1.8h}, [x12], x2
        bne             1b
@@ -215,7 +220,8 @@ function hevc_add_residual_16x16_16_neon, export=0
        sqadd           v1.8h, v1.8h, v17.8h
        sqadd           v2.8h, v2.8h, v18.8h
        sqadd           v3.8h, v3.8h, v19.8h
-        clip            v20.8h, v21.8h, v0.8h, v1.8h, v2.8h, v3.8h
+        clip2           v0.8h, v1.8h, v20.8h, v21.8h
+        clip2           v2.8h, v3.8h, v20.8h, v21.8h
        st1             {v0.8h-v1.8h}, [x0],  x2
        st1             {v2.8h-v3.8h}, [x12], x2
        bne             1b
@@ -232,49 +238,13 @@ function hevc_add_residual_32x32_16_neon, export=0
        sqadd           v1.8h, v1.8h, v17.8h
        sqadd           v2.8h, v2.8h, v18.8h
        sqadd           v3.8h, v3.8h, v19.8h
-        clip            v20.8h, v21.8h, v0.8h, v1.8h, v2.8h, v3.8h
+        clip2           v0.8h, v1.8h, v20.8h, v21.8h
+        clip2           v2.8h, v3.8h, v20.8h, v21.8h
        st1             {v0.8h-v3.8h}, [x0], x2
        bne             1b
        ret
 endfunc

-.macro tr_4x4 in0, in1, in2, in3, out0, out1, out2, out3, shift
-        sshll           v20.4s, \in0, #6
-        sshll           v21.4s, \in0, #6
-        smull           v22.4s, \in1, v4.h[1]
-        smull           v23.4s, \in1, v4.h[3]
-        smlal           v20.4s, \in2, v4.h[0] //e0
-        smlsl           v21.4s, \in2, v4.h[0] //e1
-        smlal           v22.4s, \in3, v4.h[3] //o0
-        smlsl           v23.4s, \in3, v4.h[1] //o1
-
-        add             v24.4s, v20.4s, v22.4s
-        sub             v20.4s, v20.4s, v22.4s
-        add             v22.4s, v21.4s, v23.4s
-        sub             v21.4s, v21.4s, v23.4s
-        sqrshrn         \out0, v24.4s, #\shift
-        sqrshrn         \out3, v20.4s, #\shift
-        sqrshrn         \out1, v22.4s, #\shift
-        sqrshrn         \out2, v21.4s, #\shift
-.endm
-
-.macro idct_4x4 bitdepth
-function ff_hevc_idct_4x4_\bitdepth\()_neon, export=1
-        ld1             {v0.4h-v3.4h}, [x0]
-
-        movrel          x1, trans
-        ld1             {v4.4h}, [x1]
-
-        tr_4x4          v0.4h, v1.4h, v2.4h, v3.4h, v16.4h, v17.4h, v18.4h, v19.4h, 7
-        transpose_4x8H  v16, v17, v18, v19, v26, v27, v28, v29
-
-        tr_4x4          v16.4h, v17.4h, v18.4h, v19.4h, v0.4h, v1.4h, v2.4h, v3.4h, 20 - \bitdepth
-        transpose_4x8H  v0, v1, v2, v3, v26, v27, v28, v29
-        st1             {v0.4h-v3.4h}, [x0]
-        ret
-endfunc
-.endm
-
 .macro sum_sub out, in, c, op, p
  .ifc \op, +
        smlal\p         \out, \in, \c
@@ -294,24 +264,35 @@ endfunc

 // uses and clobbers v28-v31 as temp registers
 .macro tr_4x4_8 in0, in1, in2, in3, out0, out1, out2, out3, p1, p2
-        sshll\p1        v28.4s, \in0, #6
-        mov             v29.16b, v28.16b
-        smull\p1        v30.4s, \in1, v0.h[1]
-        smull\p1        v31.4s, \in1, v0.h[3]
-        smlal\p2        v28.4s, \in2, v0.h[0] //e0
-        smlsl\p2        v29.4s, \in2, v0.h[0] //e1
-        smlal\p2        v30.4s, \in3, v0.h[3] //o0
-        smlsl\p2        v31.4s, \in3, v0.h[1] //o1
+         sshll\p1       v28.4s, \in0, #6
+         mov            v29.16b, v28.16b
+         smull\p1       v30.4s, \in1, v0.h[1]
+         smull\p1       v31.4s, \in1, v0.h[3]
+         smlal\p2       v28.4s, \in2, v0.h[0] //e0
+         smlsl\p2       v29.4s, \in2, v0.h[0] //e1
+         smlal\p2       v30.4s, \in3, v0.h[3] //o0
+         smlsl\p2       v31.4s, \in3, v0.h[1] //o1

-        add             \out0, v28.4s, v30.4s
-        add             \out1, v29.4s, v31.4s
-        sub             \out2, v29.4s, v31.4s
-        sub             \out3, v28.4s, v30.4s
+         add            \out0, v28.4s, v30.4s
+         add            \out1, v29.4s, v31.4s
+         sub            \out2, v29.4s, v31.4s
+         sub            \out3, v28.4s, v30.4s
+.endm
+
+.macro transpose8_4x4 r0, r1, r2, r3
+        trn1            v2.8h, \r0\().8h, \r1\().8h
+        trn2            v3.8h, \r0\().8h, \r1\().8h
+        trn1            v4.8h, \r2\().8h, \r3\().8h
+        trn2            v5.8h, \r2\().8h, \r3\().8h
+        trn1            \r0\().4s, v2.4s, v4.4s
+        trn2            \r2\().4s, v2.4s, v4.4s
+        trn1            \r1\().4s, v3.4s, v5.4s
+        trn2            \r3\().4s, v3.4s, v5.4s
 .endm

 .macro transpose_8x8 r0, r1, r2, r3, r4, r5, r6, r7
-        transpose_4x8H  \r0, \r1, \r2, \r3, v2, v3, v4, v5
-        transpose_4x8H  \r4, \r5, \r6, \r7, v2, v3, v4, v5
+        transpose8_4x4  \r0, \r1, \r2, \r3
+        transpose8_4x4  \r4, \r5, \r6, \r7
 .endm

 .macro tr_8x4 shift, in0,in0t, in1,in1t, in2,in2t, in3,in3t, in4,in4t, in5,in5t, in6,in6t, in7,in7t, p1, p2
@@ -362,11 +343,11 @@ endfunc
 .macro idct_8x8 bitdepth
 function ff_hevc_idct_8x8_\bitdepth\()_neon, export=1
 //x0 - coeffs
-        mov             x1,  x0
+        mov              x1,  x0
        ld1             {v16.8h-v19.8h}, [x1], #64
        ld1             {v20.8h-v23.8h}, [x1]

-        movrel          x1, trans
+        movrel           x1, trans
        ld1             {v0.8h}, [x1]

        tr_8x4          7, v16,.4h, v17,.4h, v18,.4h, v19,.4h, v20,.4h, v21,.4h, v22,.4h, v23,.4h
@@ -379,7 +360,7 @@ function ff_hevc_idct_8x8_\bitdepth\()_neon, export=1

        transpose_8x8   v16, v17, v18, v19, v20, v21, v22, v23

-        mov             x1,  x0
+        mov              x1,  x0
        st1             {v16.8h-v19.8h}, [x1], #64
        st1             {v20.8h-v23.8h}, [x1]

@@ -388,8 +369,8 @@ endfunc
 .endm

 .macro butterfly e, o, tmp_p, tmp_m
-        add             \tmp_p, \e, \o
-        sub             \tmp_m, \e, \o
+        add        \tmp_p, \e, \o
+        sub        \tmp_m, \e, \o
 .endm

 .macro tr16_8x4 in0, in1, in2, in3, offset
@@ -418,7 +399,7 @@ endfunc
        butterfly       v25.4s, v29.4s, v17.4s, v22.4s
        butterfly       v26.4s, v30.4s, v18.4s, v21.4s
        butterfly       v27.4s, v31.4s, v19.4s, v20.4s
-        add             x4,  sp,  #\offset
+        add              x4,  sp,  #\offset
        st1             {v16.4s-v19.4s}, [x4], #64
        st1             {v20.4s-v23.4s}, [x4]
 .endm
@@ -435,14 +416,14 @@ endfunc
 .endm

 .macro add_member in, t0, t1, t2, t3, t4, t5, t6, t7, op0, op1, op2, op3, op4, op5, op6, op7, p
-        sum_sub         v21.4s, \in, \t0, \op0, \p
-        sum_sub         v22.4s, \in, \t1, \op1, \p
-        sum_sub         v23.4s, \in, \t2, \op2, \p
-        sum_sub         v24.4s, \in, \t3, \op3, \p
-        sum_sub         v25.4s, \in, \t4, \op4, \p
-        sum_sub         v26.4s, \in, \t5, \op5, \p
-        sum_sub         v27.4s, \in, \t6, \op6, \p
-        sum_sub         v28.4s, \in, \t7, \op7, \p
+        sum_sub v21.4s, \in, \t0, \op0, \p
+        sum_sub v22.4s, \in, \t1, \op1, \p
+        sum_sub v23.4s, \in, \t2, \op2, \p
+        sum_sub v24.4s, \in, \t3, \op3, \p
+        sum_sub v25.4s, \in, \t4, \op4, \p
+        sum_sub v26.4s, \in, \t5, \op5, \p
+        sum_sub v27.4s, \in, \t6, \op6, \p
+        sum_sub v28.4s, \in, \t7, \op7, \p
 .endm

 .macro butterfly16 in0, in1, in2, in3, in4, in5, in6, in7
@@ -478,70 +459,52 @@ endfunc
        sqrshrn2        \out3\().8h, \in7, \shift
 .endm

-// use temp register to transpose, then we can reuse it
-.macro transpose16_4x4_2 r0, r1, r2, r3, tmp0, tmp1, tmp2, tmp3, tmp4, tmp5
+.macro transpose16_4x4_2 r0, r1, r2, r3
        // lower halves
-        trn1            \tmp0\().4h, \r0\().4h, \r1\().4h
-        trn2            \tmp1\().4h, \r0\().4h, \r1\().4h
-        trn1            \tmp2\().4h, \r2\().4h, \r3\().4h
-        trn2            \tmp3\().4h, \r2\().4h, \r3\().4h
-        trn1            \tmp4\().2s, \tmp0\().2s, \tmp2\().2s
-        trn2            \tmp5\().2s, \tmp0\().2s, \tmp2\().2s
-        trn1            \tmp0\().2s, \tmp1\().2s, \tmp3\().2s
-        trn2            \tmp2\().2s, \tmp1\().2s, \tmp3\().2s
-        mov             \r0\().d[0], \tmp4\().d[0]
-        mov             \r2\().d[0], \tmp5\().d[0]
-        mov             \r1\().d[0], \tmp0\().d[0]
-        mov             \r3\().d[0], \tmp2\().d[0]
+        trn1            v2.4h, \r0\().4h, \r1\().4h
+        trn2            v3.4h, \r0\().4h, \r1\().4h
+        trn1            v4.4h, \r2\().4h, \r3\().4h
+        trn2            v5.4h, \r2\().4h, \r3\().4h
+        trn1            v6.2s, v2.2s, v4.2s
+        trn2            v7.2s, v2.2s, v4.2s
+        trn1            v2.2s, v3.2s, v5.2s
+        trn2            v4.2s, v3.2s, v5.2s
+        mov             \r0\().d[0], v6.d[0]
+        mov             \r2\().d[0], v7.d[0]
+        mov             \r1\().d[0], v2.d[0]
+        mov             \r3\().d[0], v4.d[0]

        // upper halves in reverse order
-        trn1            \tmp0\().8h, \r3\().8h, \r2\().8h
-        trn2            \tmp1\().8h, \r3\().8h, \r2\().8h
-        trn1            \tmp2\().8h, \r1\().8h, \r0\().8h
-        trn2            \tmp3\().8h, \r1\().8h, \r0\().8h
-        trn1            \tmp4\().4s, \tmp0\().4s, \tmp2\().4s
-        trn2            \tmp5\().4s, \tmp0\().4s, \tmp2\().4s
-        trn1            \tmp0\().4s, \tmp1\().4s, \tmp3\().4s
-        trn2            \tmp2\().4s, \tmp1\().4s, \tmp3\().4s
-        mov             \r3\().d[1], \tmp4\().d[1]
-        mov             \r1\().d[1], \tmp5\().d[1]
-        mov             \r2\().d[1], \tmp0\().d[1]
-        mov             \r0\().d[1], \tmp2\().d[1]
-.endm
-
-// stores in0, in2, in4, in6 ascending from off1 and
-// stores in1, in3, in5, in7 descending from off2
-.macro store_to_stack off1, off2, in0, in2, in4, in6, in7, in5, in3, in1
-        add             x1, sp, #\off1
-        add             x3, sp, #\off2
-        mov             x2, #-16
-        mov             x4, #16
-        st1             {\in0}, [x1], x4
-        st1             {\in1}, [x3], x2
-        st1             {\in2}, [x1], x4
-        st1             {\in3}, [x3], x2
-        st1             {\in4}, [x1], x4
-        st1             {\in5}, [x3], x2
-        st1             {\in6}, [x1]
-        st1             {\in7}, [x3]
+        trn1            v2.8h, \r3\().8h, \r2\().8h
+        trn2            v3.8h, \r3\().8h, \r2\().8h
+        trn1            v4.8h, \r1\().8h, \r0\().8h
+        trn2            v5.8h, \r1\().8h, \r0\().8h
+        trn1            v6.4s, v2.4s, v4.4s
+        trn2            v7.4s, v2.4s, v4.4s
+        trn1            v2.4s, v3.4s, v5.4s
+        trn2            v4.4s, v3.4s, v5.4s
+        mov             \r3\().d[1], v6.d[1]
+        mov             \r1\().d[1], v7.d[1]
+        mov             \r2\().d[1], v2.d[1]
+        mov             \r0\().d[1], v4.d[1]
 .endm

 .macro tr_16x4 name, shift, offset, step
 function func_tr_16x4_\name
-        mov             x1,  x5
-        add             x3,  x5, #(\step * 64)
-        mov             x2,  #(\step * 128)
+        mov              x1,  x5
+        add              x3,  x5, #(\step * 64)
+        mov              x2,  #(\step * 128)
        load16          v16.d, v17.d, v18.d, v19.d
-        movrel          x1,  trans
+        movrel           x1,  trans
        ld1             {v0.8h}, [x1]

        tr16_8x4        v16, v17, v18, v19, \offset

-        add             x1,  x5, #(\step * 32)
-        add             x3,  x5, #(\step * 3 *32)
-        mov             x2,  #(\step * 128)
+        add              x1,  x5, #(\step * 32)
+        add              x3,  x5, #(\step * 3 *32)
+        mov              x2,  #(\step * 128)
        load16          v20.d, v17.d, v18.d, v19.d
-        movrel          x1, trans, 16
+        movrel           x1, trans, 16
        ld1             {v1.8h}, [x1]
        smull           v21.4s, v20.4h, v1.h[0]
        smull           v22.4s, v20.4h, v1.h[1]
@@ -560,36 +523,29 @@ function func_tr_16x4_\name
        add_member      v19.4h, v1.h[6], v1.h[3], v1.h[0], v1.h[2], v1.h[5], v1.h[7], v1.h[4], v1.h[1], +, -, +, -, +, +, -, +
        add_member      v19.8h, v1.h[7], v1.h[6], v1.h[5], v1.h[4], v1.h[3], v1.h[2], v1.h[1], v1.h[0], +, -, +, -, +, -, +, -, 2

-        add             x4, sp, #\offset
+        add              x4, sp, #\offset
        ld1             {v16.4s-v19.4s}, [x4], #64
+
        butterfly16     v16.4s, v21.4s, v17.4s, v22.4s, v18.4s, v23.4s, v19.4s, v24.4s
-    .if \shift > 0
        scale           v29, v30, v31, v24, v20.4s, v16.4s, v21.4s, v17.4s, v22.4s, v18.4s, v23.4s, v19.4s, \shift
-        transpose16_4x4_2 v29, v30, v31, v24, v2, v3, v4, v5, v6, v7
-        mov             x1,  x6
-        add             x3,  x6, #(24 +3*32)
-        mov             x2, #32
-        mov             x4, #-32
+        transpose16_4x4_2 v29, v30, v31, v24
+        mov              x1,  x6
+        add              x3,  x6, #(24 +3*32)
+        mov              x2, #32
+        mov              x4, #-32
        store16         v29.d, v30.d, v31.d, v24.d, x4
-    .else
-        store_to_stack  \offset, (\offset + 240), v20.4s, v21.4s, v22.4s, v23.4s, v19.4s, v18.4s, v17.4s, v16.4s
-    .endif

        add             x4, sp, #(\offset + 64)
        ld1             {v16.4s-v19.4s}, [x4]
        butterfly16     v16.4s, v25.4s, v17.4s, v26.4s, v18.4s, v27.4s, v19.4s, v28.4s
-   .if \shift > 0
        scale           v29, v30, v31, v20, v20.4s, v16.4s, v25.4s, v17.4s, v26.4s, v18.4s, v27.4s, v19.4s, \shift
-        transpose16_4x4_2 v29, v30, v31, v20, v2, v3, v4, v5, v6, v7
+        transpose16_4x4_2 v29, v30, v31, v20

-        add             x1,  x6, #8
-        add             x3,  x6, #(16 + 3 * 32)
-        mov             x2, #32
-        mov             x4, #-32
+        add              x1,  x6, #8
+        add              x3,  x6, #(16 + 3 * 32)
+        mov              x2, #32
+        mov              x4, #-32
        store16         v29.d, v30.d, v31.d, v20.d, x4
-   .else
-        store_to_stack  (\offset + 64), (\offset + 176), v20.4s, v25.4s, v26.4s, v27.4s, v19.4s, v18.4s, v17.4s, v16.4s
-   .endif

        ret
 endfunc
@@ -601,325 +557,69 @@ function ff_hevc_idct_16x16_\bitdepth\()_neon, export=1
        mov             x15, x30

        // allocate a temp buffer
-        sub             sp,  sp,  #640
+        sub              sp,  sp,  #640

 .irp i, 0, 1, 2, 3
-        add             x5,  x0, #(8 * \i)
-        add             x6,  sp, #(8 * \i * 16)
+        add              x5,  x0, #(8 * \i)
+        add              x6,  sp, #(8 * \i * 16)
        bl              func_tr_16x4_firstpass
 .endr

 .irp i, 0, 1, 2, 3
-        add             x5,  sp, #(8 * \i)
-        add             x6,  x0, #(8 * \i * 16)
+        add              x5,  sp, #(8 * \i)
+        add              x6,  x0, #(8 * \i * 16)
        bl              func_tr_16x4_secondpass_\bitdepth
 .endr

-        add             sp,  sp,  #640
+        add              sp,  sp,  #640

-        ret             x15
-endfunc
-.endm
-
-.macro load32
-        add             x1,  x5, #64
-        add             x3,  x1, #128
-        mov             x2,  #256
-        ld1             {v4.d}[0],  [x1], x2
-        ld1             {v4.d}[1],  [x3], x2
-        ld1             {v5.d}[0],  [x1], x2
-        ld1             {v5.d}[1],  [x3], x2
-        ld1             {v6.d}[0],  [x1], x2
-        ld1             {v6.d}[1],  [x3], x2
-        ld1             {v7.d}[0],  [x1], x2
-        ld1             {v7.d}[1],  [x3], x2
-        ld1             {v16.d}[0], [x1], x2
-        ld1             {v16.d}[1], [x3], x2
-        ld1             {v17.d}[0], [x1], x2
-        ld1             {v17.d}[1], [x3], x2
-        ld1             {v18.d}[0], [x1], x2
-        ld1             {v18.d}[1], [x3], x2
-        ld1             {v19.d}[0], [x1], x2
-        ld1             {v19.d}[1], [x3], x2
-.endm
-
-.macro add_member32 in, t0, t1, t2, t3, op0, op1, op2, op3, p
-        sum_sub         v24.4s, \in, \t0, \op0, \p
-        sum_sub         v25.4s, \in, \t1, \op1, \p
-        sum_sub         v26.4s, \in, \t2, \op2, \p
-        sum_sub         v27.4s, \in, \t3, \op3, \p
-.endm
-
-.macro butterfly32 in0, in1, in2, in3, out
-        add             \out, \in0, \in1
-        sub             \in0, \in0, \in1
-        add             \in1, \in2, \in3
-        sub             \in2, \in2, \in3
-.endm
-
-.macro multiply in
-        smull           v24.4s, v4.4h, \in\().h[0]
-        smull           v25.4s, v4.4h, \in\().h[1]
-        smull           v26.4s, v4.4h, \in\().h[2]
-        smull           v27.4s, v4.4h, \in\().h[3]
-.endm
-
-.macro scale_store shift
-        ld1             {v28.8h-v31.8h}, [x4], #64
-        butterfly32     v28.4s, v24.4s, v29.4s, v25.4s, v2.4s
-        butterfly32     v30.4s, v26.4s, v31.4s, v27.4s, v3.4s
-        scale           v20, v21, v22, v23, v2.4s, v28.4s, v24.4s, v29.4s, v3.4s, v30.4s, v26.4s, v31.4s, \shift
-
-        transpose16_4x4_2 v20, v21, v22, v23, v24, v25, v26, v27, v28, v29
-        store16         v20.d, v21.d, v22.d, v23.d, x8
-
-        // reload coefficients
-        ld1             {v2.4h-v3.4h}, [x9]
-.endm
-
-function tr_block1
-        multiply        v0
-        add_member32    v4.8h,  v0.h[1], v1.h[0], v1.h[3], v2.h[2], +, +, +, +, 2
-        add_member32    v5.4h,  v0.h[2], v1.h[3], v3.h[0], v3.h[2], +, +, +, -
-        add_member32    v5.8h,  v0.h[3], v2.h[2], v3.h[2], v1.h[3], +, +, -, -, 2
-        add_member32    v6.4h,  v1.h[0], v3.h[1], v2.h[1], v0.h[0], +, +, -, -
-        add_member32    v6.8h,  v1.h[1], v3.h[3], v1.h[0], v1.h[2], +, -, -, -, 2
-        add_member32    v7.4h,  v1.h[2], v3.h[0], v0.h[0], v3.h[1], +, -, -, -
-        add_member32    v7.8h,  v1.h[3], v2.h[1], v1.h[1], v2.h[3], +, -, -, +, 2
-        add_member32    v16.4h, v2.h[0], v1.h[2], v2.h[2], v1.h[0], +, -, -, +
-        add_member32    v16.8h, v2.h[1], v0.h[3], v3.h[3], v0.h[2], +, -, -, +, 2
-        add_member32    v17.4h, v2.h[2], v0.h[1], v2.h[3], v2.h[1], +, -, +, +
-        add_member32    v17.8h, v2.h[3], v0.h[2], v1.h[2], v3.h[3], +, -, +, -, 2
-        add_member32    v18.4h, v3.h[0], v1.h[1], v0.h[1], v2.h[0], +, -, +, -
-        add_member32    v18.8h, v3.h[1], v2.h[0], v0.h[3], v0.h[1], +, -, +, -, 2
-        add_member32    v19.4h, v3.h[2], v2.h[3], v2.h[0], v1.h[1], +, -, +, -
-        add_member32    v19.8h, v3.h[3], v3.h[2], v3.h[1], v3.h[0], +, -, +, -, 2
+        mov             x30, x15
        ret
 endfunc
-
-function tr_block2
-        multiply        v1
-        add_member32    v4.8h,  v3.h[1], v3.h[3], v3.h[0], v2.h[1], +, -, -, -, 2
-        add_member32    v5.4h,  v2.h[1], v1.h[0], v0.h[0], v1.h[1], -, -, -, -
-        add_member32    v5.8h,  v0.h[0], v1.h[2], v3.h[1], v2.h[3], -, -, -, +, 2
-        add_member32    v6.4h,  v2.h[0], v3.h[2], v1.h[1], v0.h[3], -, +, +, +
-        add_member32    v6.8h,  v3.h[2], v0.h[3], v1.h[3], v3.h[1], +, +, +, -, 2
-        add_member32    v7.4h,  v1.h[1], v1.h[3], v2.h[3], v0.h[0], +, +, -, -
-        add_member32    v7.8h,  v0.h[3], v3.h[1], v0.h[1], v3.h[3], +, -, -, +, 2
-        add_member32    v16.4h, v3.h[0], v0.h[2], v3.h[2], v0.h[1], +, -, -, +
-        add_member32    v16.8h, v2.h[2], v2.h[0], v1.h[0], v3.h[2], -, -, +, +, 2
-        add_member32    v17.4h, v0.h[1], v3.h[0], v2.h[0], v0.h[2], -, +, +, -
-        add_member32    v17.8h, v1.h[3], v0.h[1], v2.h[2], v3.h[0], -, +, -, -, 2
-        add_member32    v18.4h, v3.h[3], v2.h[1], v0.h[2], v1.h[0], +, +, -, +
-        add_member32    v18.8h, v1.h[2], v2.h[3], v3.h[3], v2.h[2], +, -, -, +, 2
-        add_member32    v19.4h, v0.h[2], v0.h[1], v0.h[3], v1.h[2], +, -, +, -
-        add_member32    v19.8h, v2.h[3], v2.h[2], v2.h[1], v2.h[0], +, -, +, -, 2
-        ret
-endfunc
-
-function tr_block3
-        multiply        v2
-        add_member32    v4.8h,  v1.h[2], v0.h[3], v0.h[0], v0.h[2], -, -, -, -, 2
-        add_member32    v5.4h,  v2.h[2], v3.h[3], v2.h[3], v1.h[2], -, -, +, +
-        add_member32    v5.8h,  v1.h[0], v0.h[2], v2.h[1], v3.h[3], +, +, +, -, 2
-        add_member32    v6.4h,  v3.h[0], v2.h[2], v0.h[1], v1.h[3], +, -, -, -
-        add_member32    v6.8h,  v0.h[2], v2.h[0], v3.h[0], v0.h[0], -, -, +, +, 2
-        add_member32    v7.4h,  v3.h[2], v1.h[0], v2.h[0], v2.h[2], -, +, +, -
-        add_member32    v7.8h,  v0.h[0], v3.h[2], v0.h[2], v3.h[0], +, +, -, -, 2
-        add_member32    v16.4h, v3.h[3], v0.h[1], v3.h[1], v0.h[3], -, -, +, +
-        add_member32    v16.8h, v0.h[1], v2.h[3], v1.h[3], v1.h[1], -, +, +, -, 2
-        add_member32    v17.4h, v3.h[1], v1.h[3], v0.h[3], v3.h[2], +, +, -, +
-        add_member32    v17.8h, v0.h[3], v1.h[1], v3.h[2], v2.h[0], +, -, +, +, 2
-        add_member32    v18.4h, v2.h[3], v3.h[1], v1.h[2], v0.h[1], -, -, +, -
-        add_member32    v18.8h, v1.h[1], v0.h[0], v1.h[0], v2.h[1], -, +, -, +, 2
-        add_member32    v19.4h, v2.h[1], v3.h[0], v3.h[3], v3.h[1], +, -, +, +
-        add_member32    v19.8h, v1.h[3], v1.h[2], v1.h[1], v1.h[0], +, -, +, -, 2
-        ret
-endfunc
-
-function tr_block4
-        multiply        v3
-        add_member32    v4.8h,  v1.h[1], v2.h[0], v2.h[3], v3.h[2], -, -, -, -, 2
-        add_member32    v5.4h,  v0.h[0], v0.h[3], v2.h[0], v3.h[1], +, +, +, +
-        add_member32    v5.8h,  v2.h[0], v0.h[0], v1.h[1], v3.h[0], -, -, -, -, 2
-        add_member32    v6.4h,  v3.h[3], v1.h[2], v0.h[2], v2.h[3], +, +, +, +
-        add_member32    v6.8h,  v2.h[1], v2.h[3], v0.h[0], v2.h[2], +, -, -, -, 2
-        add_member32    v7.4h,  v0.h[2], v3.h[3], v0.h[3], v2.h[1], -, -, +, +
-        add_member32    v7.8h,  v1.h[0], v2.h[2], v1.h[2], v2.h[0], +, +, -, -, 2
-        add_member32    v16.4h, v2.h[3], v1.h[1], v2.h[1], v1.h[3], -, -, +, +
-        add_member32    v16.8h, v3.h[1], v0.h[1], v3.h[0], v1.h[2], -, +, -, -, 2
-        add_member32    v17.4h, v1.h[2], v1.h[0], v3.h[3], v1.h[1], +, -, +, +
-        add_member32    v17.8h, v0.h[1], v2.h[1], v3.h[1], v1.h[0], -, +, +, -, 2
-        add_member32    v18.4h, v1.h[3], v3.h[2], v2.h[2], v0.h[3], +, -, -, +
-        add_member32    v18.8h, v3.h[2], v3.h[0], v1.h[3], v0.h[2], -, -, +, -, 2
-        add_member32    v19.4h, v2.h[2], v1.h[3], v1.h[0], v0.h[1], -, +, -, +
-        add_member32    v19.8h, v0.h[3], v0.h[2], v0.h[1], v0.h[0], +, -, +, -, 2
-        ret
-endfunc
-
-.macro tr_32x4 name, shift
-function func_tr_32x4_\name
-        mov             x10, x30
-        bl              func_tr_16x4_noscale
-
-        load32
-        movrel          x9, trans, 32
-        ld1             {v0.4h-v1.4h}, [x9], #16
-        ld1             {v2.4h-v3.4h}, [x9]
-        add             x4, sp, #2048
-        mov             x2, #64
-        mov             x8, #-64
-
-        bl              tr_block1
-        mov             x1, x11
-        add             x3, x11, #(56 + 3 * 64)
-        scale_store     \shift
-
-        bl              tr_block2
-        add             x1, x11, #8
-        add             x3, x11, #(48 + 3 * 64)
-        scale_store     \shift
-
-        bl              tr_block3
-        add             x1, x11, #16
-        add             x3, x11, #(40 + 3 * 64)
-        scale_store     \shift
-
-        bl              tr_block4
-        add             x1, x11, #24
-        add             x3, x11, #(32 + 3 * 64)
-        scale_store     \shift
-
-        ret             x10
-endfunc
 .endm

-.macro idct_32x32 bitdepth
-function ff_hevc_idct_32x32_\bitdepth\()_neon, export=1
-        mov             x15, x30
-        // allocate a temp buffer
-        sub             sp,  sp,  #2432
-
-.irp i, 0, 1, 2, 3, 4, 5, 6, 7
-        add             x5, x0, #(8 * \i)
-        add             x11, sp, #(8 * \i * 32)
-        bl              func_tr_32x4_firstpass
-.endr
-
-.irp i, 0, 1, 2, 3, 4, 5, 6, 7
-        add             x5, sp, #(8 * \i)
-        add             x11, x0, #(8 * \i * 32)
-        bl              func_tr_32x4_secondpass_\bitdepth
-.endr
-
-        add             sp,  sp,  #2432
-        ret             x15
-endfunc
-.endm
-
-idct_4x4 8
-idct_4x4 10
-
 idct_8x8 8
 idct_8x8 10

 tr_16x4 firstpass, 7, 512, 1
 tr_16x4 secondpass_8, 20 - 8, 512, 1
 tr_16x4 secondpass_10, 20 - 10, 512, 1
-tr_16x4 noscale, 0, 2048, 4

 idct_16x16 8
 idct_16x16 10

-.ltorg
-tr_32x4 firstpass, 7
-tr_32x4 secondpass_8, 20 - 8
-tr_32x4 secondpass_10, 20 - 10
-.ltorg
-
-idct_32x32 8
-idct_32x32 10
-
-.macro tr4_luma_shift r0, r1, r2, r3, shift
-        saddl           v0.4s, \r0, \r2         // c0 = src0 + src2
-        saddl           v1.4s, \r2, \r3         // c1 = src2 + src3
-        ssubl           v2.4s, \r0, \r3         // c2 = src0 - src3
-        smull           v3.4s, \r1, v21.4h      // c3 = 74 * src1
-
-        saddl           v7.4s, \r0, \r3         // src0 + src3
-        ssubw           v7.4s, v7.4s, \r2       // src0 - src2 + src3
-        mul             v7.4s, v7.4s, v18.4s    // dst2 = 74 * (src0 - src2 + src3)
-
-        mul             v5.4s, v0.4s, v19.4s    // 29 * c0
-        mul             v6.4s, v1.4s, v20.4s    // 55 * c1
-        add             v5.4s, v5.4s, v6.4s     // 29 * c0 + 55 * c1
-        add             v5.4s, v5.4s, v3.4s     // dst0 = 29 * c0 + 55 * c1 + c3
-
-        mul             v1.4s, v1.4s, v19.4s    // 29 * c1
-        mul             v6.4s, v2.4s, v20.4s    // 55 * c2
-        sub             v6.4s, v6.4s, v1.4s     // 55 * c2 - 29 * c1
-        add             v6.4s, v6.4s, v3.4s     // dst1 = 55 * c2 - 29 * c1 + c3
-
-        mul             v0.4s, v0.4s, v20.4s    // 55 * c0
-        mul             v2.4s, v2.4s, v19.4s    // 29 * c2
-        add             v0.4s, v0.4s, v2.4s     // 55 * c0 + 29 * c2
-        sub             v0.4s, v0.4s, v3.4s     // dst3 = 55 * c0 + 29 * c2 - c3
-
-        sqrshrn         \r0, v5.4s, \shift
-        sqrshrn         \r1, v6.4s, \shift
-        sqrshrn         \r2, v7.4s, \shift
-        sqrshrn         \r3, v0.4s, \shift
-.endm
-
-function ff_hevc_transform_luma_4x4_neon_8, export=1
-        ld1             {v28.4h-v31.4h}, [x0]
-        movi            v18.4s, #74
-        movi            v19.4s, #29
-        movi            v20.4s, #55
-        movi            v21.4h, #74
-
-        tr4_luma_shift  v28.4h, v29.4h, v30.4h, v31.4h, #7
-        transpose_4x4H  v28, v29, v30, v31, v22, v23, v24, v25
-
-        tr4_luma_shift  v28.4h, v29.4h, v30.4h, v31.4h, #12
-        transpose_4x4H  v28, v29, v30, v31, v22, v23, v24, v25
-
-        st1             {v28.4h-v31.4h}, [x0]
-        ret
-endfunc
-
 // void ff_hevc_idct_NxN_dc_DEPTH_neon(int16_t *coeffs)
 .macro idct_dc size, bitdepth
 function ff_hevc_idct_\size\()x\size\()_dc_\bitdepth\()_neon, export=1
-        ld1r            {v4.8h}, [x0]
-        srshr           v4.8h,  v4.8h,  #1
-        srshr           v0.8h,  v4.8h,  #(14 - \bitdepth)
-        srshr           v1.8h,  v4.8h,  #(14 - \bitdepth)
+        ld1r         {v4.8h}, [x0]
+        srshr         v4.8h,  v4.8h,  #1
+        srshr         v0.8h,  v4.8h,  #(14 - \bitdepth)
+        srshr         v1.8h,  v4.8h,  #(14 - \bitdepth)
 .if \size > 4
-        srshr           v2.8h,  v4.8h,  #(14 - \bitdepth)
-        srshr           v3.8h,  v4.8h,  #(14 - \bitdepth)
+        srshr         v2.8h,  v4.8h,  #(14 - \bitdepth)
+        srshr         v3.8h,  v4.8h,  #(14 - \bitdepth)
 .if \size > 16 /* dc 32x32 */
-        mov             x2,  #4
+        mov              x2,  #4
 1:
-        subs            x2,  x2, #1
+        subs             x2,  x2, #1
 .endif
        add             x12,  x0, #64
        mov             x13,  #128
 .if \size > 8 /* dc 16x16 */
-        st1             {v0.8h-v3.8h},  [x0], x13
-        st1             {v0.8h-v3.8h}, [x12], x13
-        st1             {v0.8h-v3.8h},  [x0], x13
-        st1             {v0.8h-v3.8h}, [x12], x13
-        st1             {v0.8h-v3.8h},  [x0], x13
-        st1             {v0.8h-v3.8h}, [x12], x13
+        st1            {v0.8h-v3.8h},  [x0], x13
+        st1            {v0.8h-v3.8h}, [x12], x13
+        st1            {v0.8h-v3.8h},  [x0], x13
+        st1            {v0.8h-v3.8h}, [x12], x13
+        st1            {v0.8h-v3.8h},  [x0], x13
+        st1            {v0.8h-v3.8h}, [x12], x13
 .endif /* dc 8x8 */
-        st1             {v0.8h-v3.8h},  [x0], x13
-        st1             {v0.8h-v3.8h}, [x12], x13
+        st1            {v0.8h-v3.8h},  [x0], x13
+        st1            {v0.8h-v3.8h}, [x12], x13
 .if \size > 16 /* dc 32x32 */
        bne             1b
 .endif
 .else /* dc 4x4 */
-        st1             {v0.8h-v1.8h},  [x0]
+        st1            {v0.8h-v1.8h},  [x0]
 .endif
        ret
 endfunc
--- a/libavcodec/aarch64/hevcdsp_init_aarch64.c
+++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c
@@ -1,6 +1,5 @@
 /*
 * Copyright (c) 2020 Reimar Döffinger
- * Copyright (c) 2023 xu fulong <839789740@qq.com>
 *
 * This file is part of FFmpeg.
 *
@@ -26,18 +25,6 @@
 #include "libavutil/aarch64/cpu.h"
 #include "libavcodec/hevcdsp.h"

-void ff_hevc_v_loop_filter_chroma_8_neon(uint8_t *_pix, ptrdiff_t _stride,
-                                         const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q);
-void ff_hevc_v_loop_filter_chroma_10_neon(uint8_t *_pix, ptrdiff_t _stride,
-                                          const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q);
-void ff_hevc_v_loop_filter_chroma_12_neon(uint8_t *_pix, ptrdiff_t _stride,
-                                          const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q);
-void ff_hevc_h_loop_filter_chroma_8_neon(uint8_t *_pix, ptrdiff_t _stride,
-                                         const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q);
-void ff_hevc_h_loop_filter_chroma_10_neon(uint8_t *_pix, ptrdiff_t _stride,
-                                          const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q);
-void ff_hevc_h_loop_filter_chroma_12_neon(uint8_t *_pix, ptrdiff_t _stride,
-                                          const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q);
 void ff_hevc_add_residual_4x4_8_neon(uint8_t *_dst, const int16_t *coeffs,
                                     ptrdiff_t stride);
 void ff_hevc_add_residual_4x4_10_neon(uint8_t *_dst, const int16_t *coeffs,
@@ -62,14 +49,10 @@ void ff_hevc_add_residual_32x32_10_neon(uint8_t *_dst, const int16_t *coeffs,
                                        ptrdiff_t stride);
 void ff_hevc_add_residual_32x32_12_neon(uint8_t *_dst, const int16_t *coeffs,
                                        ptrdiff_t stride);
-void ff_hevc_idct_4x4_8_neon(int16_t *coeffs, int col_limit);
-void ff_hevc_idct_4x4_10_neon(int16_t *coeffs, int col_limit);
 void ff_hevc_idct_8x8_8_neon(int16_t *coeffs, int col_limit);
 void ff_hevc_idct_8x8_10_neon(int16_t *coeffs, int col_limit);
 void ff_hevc_idct_16x16_8_neon(int16_t *coeffs, int col_limit);
 void ff_hevc_idct_16x16_10_neon(int16_t *coeffs, int col_limit);
-void ff_hevc_idct_32x32_8_neon(int16_t *coeffs, int col_limit);
-void ff_hevc_idct_32x32_10_neon(int16_t *coeffs, int col_limit);
 void ff_hevc_idct_4x4_dc_8_neon(int16_t *coeffs);
 void ff_hevc_idct_8x8_dc_8_neon(int16_t *coeffs);
 void ff_hevc_idct_16x16_dc_8_neon(int16_t *coeffs);
@@ -78,7 +61,6 @@ void ff_hevc_idct_4x4_dc_10_neon(int16_t *coeffs);
 void ff_hevc_idct_8x8_dc_10_neon(int16_t *coeffs);
 void ff_hevc_idct_16x16_dc_10_neon(int16_t *coeffs);
 void ff_hevc_idct_32x32_dc_10_neon(int16_t *coeffs);
-void ff_hevc_transform_luma_4x4_neon_8(int16_t *coeffs);
 void ff_hevc_sao_band_filter_8x8_8_neon(uint8_t *_dst, const uint8_t *_src,
                                  ptrdiff_t stride_dst, ptrdiff_t stride_src,
                                  const int16_t *sao_offset_val, int sao_left_class,
@@ -128,140 +110,21 @@ void ff_hevc_put_hevc_qpel_bi_h16_8_neon(uint8_t *_dst, ptrdiff_t _dststride, co
                                         ptrdiff_t _srcstride, const int16_t *src2, int height, intptr_t
                                         mx, intptr_t my, int width);

-#define NEON8_FNPROTO(fn, args, ext) \
-    void ff_hevc_put_hevc_##fn##4_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##6_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##8_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##12_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##16_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##24_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##32_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##48_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##64_8_neon##ext args
-
-#define NEON8_FNPROTO_PARTIAL_4(fn, args, ext) \
-    void ff_hevc_put_hevc_##fn##4_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##8_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##16_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##64_8_neon##ext args
-
-#define NEON8_FNPROTO_PARTIAL_5(fn, args, ext) \
-    void ff_hevc_put_hevc_##fn##4_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##8_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##16_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##32_8_neon##ext args; \
-    void ff_hevc_put_hevc_##fn##64_8_neon##ext args
-
-NEON8_FNPROTO(pel_uni_pixels, (uint8_t *_dst, ptrdiff_t _dststride,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, intptr_t mx, intptr_t my, int width),);
-
-NEON8_FNPROTO(pel_uni_w_pixels, (uint8_t *_dst, ptrdiff_t _dststride,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, int denom, int wx, int ox,
-        intptr_t mx, intptr_t my, int width),);
-
-NEON8_FNPROTO(epel_uni_v, (uint8_t *dst,  ptrdiff_t dststride,
-        const uint8_t *src, ptrdiff_t srcstride,
-        int height, intptr_t mx, intptr_t my, int width),);
-
-NEON8_FNPROTO(epel_uni_hv, (uint8_t *dst, ptrdiff_t _dststride,
-        const uint8_t *src, ptrdiff_t srcstride,
-        int height, intptr_t mx, intptr_t my, int width), _i8mm);
-
-NEON8_FNPROTO(epel_uni_w_v, (uint8_t *_dst,  ptrdiff_t _dststride,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, int denom, int wx, int ox,
-        intptr_t mx, intptr_t my, int width),);
-
-NEON8_FNPROTO_PARTIAL_4(qpel_uni_w_v, (uint8_t *_dst,  ptrdiff_t _dststride,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, int denom, int wx, int ox,
-        intptr_t mx, intptr_t my, int width),);
-
-NEON8_FNPROTO(epel_h, (int16_t *dst,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, intptr_t mx, intptr_t my, int width), _i8mm);
-
-NEON8_FNPROTO(epel_uni_w_h, (uint8_t *_dst,  ptrdiff_t _dststride,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, int denom, int wx, int ox,
-        intptr_t mx, intptr_t my, int width), _i8mm);
-
-NEON8_FNPROTO(qpel_h, (int16_t *dst,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, intptr_t mx, intptr_t my, int width), _i8mm);
-
-NEON8_FNPROTO(qpel_uni_v, (uint8_t *dst,  ptrdiff_t dststride,
-        const uint8_t *src, ptrdiff_t srcstride,
-        int height, intptr_t mx, intptr_t my, int width),);
-
-NEON8_FNPROTO(qpel_uni_hv, (uint8_t *dst,  ptrdiff_t dststride,
-        const uint8_t *src, ptrdiff_t srcstride,
-        int height, intptr_t mx, intptr_t my, int width), _i8mm);
-
-NEON8_FNPROTO(qpel_uni_w_h, (uint8_t *_dst,  ptrdiff_t _dststride,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, int denom, int wx, int ox,
-        intptr_t mx, intptr_t my, int width), _i8mm);
-
-NEON8_FNPROTO(epel_uni_w_hv, (uint8_t *_dst,  ptrdiff_t _dststride,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, int denom, int wx, int ox,
-        intptr_t mx, intptr_t my, int width), _i8mm);
-
-NEON8_FNPROTO_PARTIAL_5(qpel_uni_w_hv, (uint8_t *_dst,  ptrdiff_t _dststride,
-        const uint8_t *_src, ptrdiff_t _srcstride,
-        int height, int denom, int wx, int ox,
-        intptr_t mx, intptr_t my, int width), _i8mm);
-
-#define NEON8_FNASSIGN(member, v, h, fn, ext) \
-        member[1][v][h] = ff_hevc_put_hevc_##fn##4_8_neon##ext;  \
-        member[2][v][h] = ff_hevc_put_hevc_##fn##6_8_neon##ext;  \
-        member[3][v][h] = ff_hevc_put_hevc_##fn##8_8_neon##ext;  \
-        member[4][v][h] = ff_hevc_put_hevc_##fn##12_8_neon##ext; \
-        member[5][v][h] = ff_hevc_put_hevc_##fn##16_8_neon##ext; \
-        member[6][v][h] = ff_hevc_put_hevc_##fn##24_8_neon##ext; \
-        member[7][v][h] = ff_hevc_put_hevc_##fn##32_8_neon##ext; \
-        member[8][v][h] = ff_hevc_put_hevc_##fn##48_8_neon##ext; \
-        member[9][v][h] = ff_hevc_put_hevc_##fn##64_8_neon##ext;
-
-#define NEON8_FNASSIGN_PARTIAL_4(member, v, h, fn, ext) \
-        member[1][v][h] = ff_hevc_put_hevc_##fn##4_8_neon##ext;  \
-        member[3][v][h] = ff_hevc_put_hevc_##fn##8_8_neon##ext;  \
-        member[5][v][h] = ff_hevc_put_hevc_##fn##16_8_neon##ext; \
-        member[7][v][h] = ff_hevc_put_hevc_##fn##64_8_neon##ext; \
-        member[8][v][h] = ff_hevc_put_hevc_##fn##64_8_neon##ext; \
-        member[9][v][h] = ff_hevc_put_hevc_##fn##64_8_neon##ext;
-
-#define NEON8_FNASSIGN_PARTIAL_5(member, v, h, fn, ext) \
-        member[1][v][h] = ff_hevc_put_hevc_##fn##4_8_neon##ext;  \
-        member[3][v][h] = ff_hevc_put_hevc_##fn##8_8_neon##ext;  \
-        member[5][v][h] = ff_hevc_put_hevc_##fn##16_8_neon##ext; \
-        member[7][v][h] = ff_hevc_put_hevc_##fn##32_8_neon##ext; \
-        member[9][v][h] = ff_hevc_put_hevc_##fn##64_8_neon##ext;
-
 av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth)
 {
-    int cpu_flags = av_get_cpu_flags();
-    if (!have_neon(cpu_flags)) return;
+    if (!have_neon(av_get_cpu_flags())) return;

    if (bit_depth == 8) {
-        c->hevc_h_loop_filter_chroma   = ff_hevc_h_loop_filter_chroma_8_neon;
-        c->hevc_v_loop_filter_chroma   = ff_hevc_v_loop_filter_chroma_8_neon;
        c->add_residual[0]             = ff_hevc_add_residual_4x4_8_neon;
        c->add_residual[1]             = ff_hevc_add_residual_8x8_8_neon;
        c->add_residual[2]             = ff_hevc_add_residual_16x16_8_neon;
        c->add_residual[3]             = ff_hevc_add_residual_32x32_8_neon;
-        c->idct[0]                     = ff_hevc_idct_4x4_8_neon;
        c->idct[1]                     = ff_hevc_idct_8x8_8_neon;
        c->idct[2]                     = ff_hevc_idct_16x16_8_neon;
-        c->idct[3]                     = ff_hevc_idct_32x32_8_neon;
        c->idct_dc[0]                  = ff_hevc_idct_4x4_dc_8_neon;
        c->idct_dc[1]                  = ff_hevc_idct_8x8_dc_8_neon;
        c->idct_dc[2]                  = ff_hevc_idct_16x16_dc_8_neon;
        c->idct_dc[3]                  = ff_hevc_idct_32x32_dc_8_neon;
-        c->transform_4x4_luma          = ff_hevc_transform_luma_4x4_neon_8;
        c->sao_band_filter[0]          =
        c->sao_band_filter[1]          =
        c->sao_band_filter[2]          =
@@ -299,47 +162,20 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth)
        c->put_hevc_qpel_bi[7][0][1]   =
        c->put_hevc_qpel_bi[8][0][1]   =
        c->put_hevc_qpel_bi[9][0][1]   = ff_hevc_put_hevc_qpel_bi_h16_8_neon;
-
-        NEON8_FNASSIGN(c->put_hevc_epel_uni, 0, 0, pel_uni_pixels,);
-        NEON8_FNASSIGN(c->put_hevc_epel_uni, 1, 0, epel_uni_v,);
-        NEON8_FNASSIGN(c->put_hevc_qpel_uni, 0, 0, pel_uni_pixels,);
-        NEON8_FNASSIGN(c->put_hevc_qpel_uni, 1, 0, qpel_uni_v,);
-        NEON8_FNASSIGN(c->put_hevc_epel_uni_w, 0, 0, pel_uni_w_pixels,);
-        NEON8_FNASSIGN(c->put_hevc_qpel_uni_w, 0, 0, pel_uni_w_pixels,);
-        NEON8_FNASSIGN(c->put_hevc_epel_uni_w, 1, 0, epel_uni_w_v,);
-        NEON8_FNASSIGN_PARTIAL_4(c->put_hevc_qpel_uni_w, 1, 0, qpel_uni_w_v,);
-
-        if (have_i8mm(cpu_flags)) {
-            NEON8_FNASSIGN(c->put_hevc_epel, 0, 1, epel_h, _i8mm);
-            NEON8_FNASSIGN(c->put_hevc_epel_uni, 1, 1, epel_uni_hv, _i8mm);
-            NEON8_FNASSIGN(c->put_hevc_epel_uni_w, 0, 1, epel_uni_w_h ,_i8mm);
-            NEON8_FNASSIGN(c->put_hevc_qpel, 0, 1, qpel_h, _i8mm);
-            NEON8_FNASSIGN(c->put_hevc_qpel_uni, 1, 1, qpel_uni_hv, _i8mm);
-            NEON8_FNASSIGN(c->put_hevc_qpel_uni_w, 0, 1, qpel_uni_w_h, _i8mm);
-            NEON8_FNASSIGN(c->put_hevc_epel_uni_w, 1, 1, epel_uni_w_hv, _i8mm);
-            NEON8_FNASSIGN_PARTIAL_5(c->put_hevc_qpel_uni_w, 1, 1, qpel_uni_w_hv, _i8mm);
-        }
-
    }
    if (bit_depth == 10) {
-        c->hevc_h_loop_filter_chroma   = ff_hevc_h_loop_filter_chroma_10_neon;
-        c->hevc_v_loop_filter_chroma   = ff_hevc_v_loop_filter_chroma_10_neon;
        c->add_residual[0]             = ff_hevc_add_residual_4x4_10_neon;
        c->add_residual[1]             = ff_hevc_add_residual_8x8_10_neon;
        c->add_residual[2]             = ff_hevc_add_residual_16x16_10_neon;
        c->add_residual[3]             = ff_hevc_add_residual_32x32_10_neon;
-        c->idct[0]                     = ff_hevc_idct_4x4_10_neon;
        c->idct[1]                     = ff_hevc_idct_8x8_10_neon;
        c->idct[2]                     = ff_hevc_idct_16x16_10_neon;
-        c->idct[3]                     = ff_hevc_idct_32x32_10_neon;
        c->idct_dc[0]                  = ff_hevc_idct_4x4_dc_10_neon;
        c->idct_dc[1]                  = ff_hevc_idct_8x8_dc_10_neon;
        c->idct_dc[2]                  = ff_hevc_idct_16x16_dc_10_neon;
        c->idct_dc[3]                  = ff_hevc_idct_32x32_dc_10_neon;
    }
    if (bit_depth == 12) {
-        c->hevc_h_loop_filter_chroma   = ff_hevc_h_loop_filter_chroma_12_neon;
-        c->hevc_v_loop_filter_chroma   = ff_hevc_v_loop_filter_chroma_12_neon;
        c->add_residual[0]             = ff_hevc_add_residual_4x4_12_neon;
        c->add_residual[1]             = ff_hevc_add_residual_8x8_12_neon;
        c->add_residual[2]             = ff_hevc_add_residual_16x16_12_neon;
--- a/libavcodec/aarch64/hevcdsp_qpel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_qpel_neon.S
--- a/libavcodec/aarch64/hpeldsp_neon.S
+++ b/libavcodec/aarch64/hpeldsp_neon.S
@@ -26,295 +26,295 @@
  .if \avg
        mov             x12, x0
  .endif
-1:      ld1             {v0.16b},  [x1], x2
-        ld1             {v1.16b},  [x1], x2
-        ld1             {v2.16b},  [x1], x2
-        ld1             {v3.16b},  [x1], x2
+1:      ld1             {v0.16B},  [x1], x2
+        ld1             {v1.16B},  [x1], x2
+        ld1             {v2.16B},  [x1], x2
+        ld1             {v3.16B},  [x1], x2
  .if \avg
-        ld1             {v4.16b},  [x12], x2
-        urhadd          v0.16b,  v0.16b,  v4.16b
-        ld1             {v5.16b},  [x12], x2
-        urhadd          v1.16b,  v1.16b,  v5.16b
-        ld1             {v6.16b},  [x12], x2
-        urhadd          v2.16b,  v2.16b,  v6.16b
-        ld1             {v7.16b},  [x12], x2
-        urhadd          v3.16b,  v3.16b,  v7.16b
+        ld1             {v4.16B},  [x12], x2
+        urhadd          v0.16B,  v0.16B,  v4.16B
+        ld1             {v5.16B},  [x12], x2
+        urhadd          v1.16B,  v1.16B,  v5.16B
+        ld1             {v6.16B},  [x12], x2
+        urhadd          v2.16B,  v2.16B,  v6.16B
+        ld1             {v7.16B},  [x12], x2
+        urhadd          v3.16B,  v3.16B,  v7.16B
  .endif
        subs            w3,  w3,  #4
-        st1             {v0.16b},  [x0], x2
-        st1             {v1.16b},  [x0], x2
-        st1             {v2.16b},  [x0], x2
-        st1             {v3.16b},  [x0], x2
+        st1             {v0.16B},  [x0], x2
+        st1             {v1.16B},  [x0], x2
+        st1             {v2.16B},  [x0], x2
+        st1             {v3.16B},  [x0], x2
        b.ne            1b
        ret
 .endm

 .macro  pixels16_x2     rnd=1, avg=0
-1:      ld1             {v0.16b, v1.16b}, [x1], x2
-        ld1             {v2.16b, v3.16b}, [x1], x2
+1:      ld1             {v0.16B, v1.16B}, [x1], x2
+        ld1             {v2.16B, v3.16B}, [x1], x2
        subs            w3,  w3,  #2
-        ext             v1.16b,  v0.16b,  v1.16b,  #1
-        avg             v0.16b,  v0.16b,  v1.16b
-        ext             v3.16b,  v2.16b,  v3.16b,  #1
-        avg             v2.16b,  v2.16b,  v3.16b
+        ext             v1.16B,  v0.16B,  v1.16B,  #1
+        avg             v0.16B,  v0.16B,  v1.16B
+        ext             v3.16B,  v2.16B,  v3.16B,  #1
+        avg             v2.16B,  v2.16B,  v3.16B
  .if \avg
-        ld1             {v1.16b}, [x0], x2
-        ld1             {v3.16b}, [x0]
-        urhadd          v0.16b,  v0.16b,  v1.16b
-        urhadd          v2.16b,  v2.16b,  v3.16b
+        ld1             {v1.16B}, [x0], x2
+        ld1             {v3.16B}, [x0]
+        urhadd          v0.16B,  v0.16B,  v1.16B
+        urhadd          v2.16B,  v2.16B,  v3.16B
        sub             x0,  x0,  x2
  .endif
-        st1             {v0.16b}, [x0], x2
-        st1             {v2.16b}, [x0], x2
+        st1             {v0.16B}, [x0], x2
+        st1             {v2.16B}, [x0], x2
        b.ne            1b
        ret
 .endm

 .macro  pixels16_y2     rnd=1, avg=0
        sub             w3,  w3,  #2
-        ld1             {v0.16b}, [x1], x2
-        ld1             {v1.16b}, [x1], x2
+        ld1             {v0.16B}, [x1], x2
+        ld1             {v1.16B}, [x1], x2
 1:      subs            w3,  w3,  #2
-        avg             v2.16b,  v0.16b,  v1.16b
-        ld1             {v0.16b}, [x1], x2
-        avg             v3.16b,  v0.16b,  v1.16b
-        ld1             {v1.16b}, [x1], x2
+        avg             v2.16B,  v0.16B,  v1.16B
+        ld1             {v0.16B}, [x1], x2
+        avg             v3.16B,  v0.16B,  v1.16B
+        ld1             {v1.16B}, [x1], x2
  .if \avg
-        ld1             {v4.16b}, [x0], x2
-        ld1             {v5.16b}, [x0]
-        urhadd          v2.16b,  v2.16b,  v4.16b
-        urhadd          v3.16b,  v3.16b,  v5.16b
+        ld1             {v4.16B}, [x0], x2
+        ld1             {v5.16B}, [x0]
+        urhadd          v2.16B,  v2.16B,  v4.16B
+        urhadd          v3.16B,  v3.16B,  v5.16B
        sub             x0,  x0,  x2
  .endif
-        st1             {v2.16b}, [x0], x2
-        st1             {v3.16b}, [x0], x2
+        st1             {v2.16B}, [x0], x2
+        st1             {v3.16B}, [x0], x2
        b.ne            1b

-        avg             v2.16b,  v0.16b,  v1.16b
-        ld1             {v0.16b}, [x1], x2
-        avg             v3.16b,  v0.16b,  v1.16b
+        avg             v2.16B,  v0.16B,  v1.16B
+        ld1             {v0.16B}, [x1], x2
+        avg             v3.16B,  v0.16B,  v1.16B
  .if \avg
-        ld1             {v4.16b}, [x0], x2
-        ld1             {v5.16b}, [x0]
-        urhadd          v2.16b,  v2.16b,  v4.16b
-        urhadd          v3.16b,  v3.16b,  v5.16b
+        ld1             {v4.16B}, [x0], x2
+        ld1             {v5.16B}, [x0]
+        urhadd          v2.16B,  v2.16B,  v4.16B
+        urhadd          v3.16B,  v3.16B,  v5.16B
        sub             x0,  x0,  x2
  .endif
-        st1             {v2.16b},     [x0], x2
-        st1             {v3.16b},     [x0], x2
+        st1             {v2.16B},     [x0], x2
+        st1             {v3.16B},     [x0], x2

        ret
 .endm

 .macro  pixels16_xy2    rnd=1, avg=0
        sub             w3,  w3,  #2
-        ld1             {v0.16b, v1.16b}, [x1], x2
-        ld1             {v4.16b, v5.16b}, [x1], x2
+        ld1             {v0.16B, v1.16B}, [x1], x2
+        ld1             {v4.16B, v5.16B}, [x1], x2
 NRND    movi            v26.8H, #1
-        ext             v1.16b,  v0.16b,  v1.16b,  #1
-        ext             v5.16b,  v4.16b,  v5.16b,  #1
-        uaddl           v16.8h,  v0.8b,   v1.8b
-        uaddl2          v20.8h,  v0.16b,  v1.16b
-        uaddl           v18.8h,  v4.8b,   v5.8b
-        uaddl2          v22.8h,  v4.16b,  v5.16b
+        ext             v1.16B,  v0.16B,  v1.16B,  #1
+        ext             v5.16B,  v4.16B,  v5.16B,  #1
+        uaddl           v16.8H,  v0.8B,   v1.8B
+        uaddl2          v20.8H,  v0.16B,  v1.16B
+        uaddl           v18.8H,  v4.8B,   v5.8B
+        uaddl2          v22.8H,  v4.16B,  v5.16B
 1:      subs            w3,  w3,  #2
-        ld1             {v0.16b, v1.16b}, [x1], x2
-        add             v24.8h,  v16.8h,  v18.8h
+        ld1             {v0.16B, v1.16B}, [x1], x2
+        add             v24.8H,  v16.8H,  v18.8H
 NRND    add             v24.8H,  v24.8H,  v26.8H
-        ext             v30.16b, v0.16b,  v1.16b,  #1
-        add             v1.8h,   v20.8h,  v22.8h
-        mshrn           v28.8b,  v24.8h,  #2
+        ext             v30.16B, v0.16B,  v1.16B,  #1
+        add             v1.8H,   v20.8H,  v22.8H
+        mshrn           v28.8B,  v24.8H,  #2
 NRND    add             v1.8H,   v1.8H,   v26.8H
-        mshrn2          v28.16b, v1.8h,   #2
+        mshrn2          v28.16B, v1.8H,   #2
  .if \avg
-        ld1             {v16.16b},        [x0]
-        urhadd          v28.16b, v28.16b, v16.16b
+        ld1             {v16.16B},        [x0]
+        urhadd          v28.16B, v28.16B, v16.16B
  .endif
-        uaddl           v16.8h,  v0.8b,   v30.8b
-        ld1             {v2.16b, v3.16b}, [x1], x2
-        uaddl2          v20.8h,  v0.16b,  v30.16b
-        st1             {v28.16b},        [x0], x2
-        add             v24.8h,  v16.8h,  v18.8h
+        uaddl           v16.8H,  v0.8B,   v30.8B
+        ld1             {v2.16B, v3.16B}, [x1], x2
+        uaddl2          v20.8H,  v0.16B,  v30.16B
+        st1             {v28.16B},        [x0], x2
+        add             v24.8H,  v16.8H,  v18.8H
 NRND    add             v24.8H,  v24.8H,  v26.8H
-        ext             v3.16b,  v2.16b,  v3.16b,  #1
-        add             v0.8h,   v20.8h,  v22.8h
-        mshrn           v30.8b,  v24.8h,  #2
+        ext             v3.16B,  v2.16B,  v3.16B,  #1
+        add             v0.8H,   v20.8H,  v22.8H
+        mshrn           v30.8B,  v24.8H,  #2
 NRND    add             v0.8H,   v0.8H,   v26.8H
-        mshrn2          v30.16b, v0.8h,   #2
+        mshrn2          v30.16B, v0.8H,   #2
  .if \avg
-        ld1             {v18.16b},        [x0]
-        urhadd          v30.16b, v30.16b, v18.16b
+        ld1             {v18.16B},        [x0]
+        urhadd          v30.16B, v30.16B, v18.16B
  .endif
-        uaddl           v18.8h,   v2.8b,  v3.8b
-        uaddl2          v22.8h,   v2.16b, v3.16b
-        st1             {v30.16b},        [x0], x2
+        uaddl           v18.8H,   v2.8B,  v3.8B
+        uaddl2          v22.8H,   v2.16B, v3.16B
+        st1             {v30.16B},        [x0], x2
        b.gt            1b

-        ld1             {v0.16b, v1.16b}, [x1], x2
-        add             v24.8h,  v16.8h,  v18.8h
+        ld1             {v0.16B, v1.16B}, [x1], x2
+        add             v24.8H,  v16.8H,  v18.8H
 NRND    add             v24.8H,  v24.8H,  v26.8H
-        ext             v30.16b, v0.16b,  v1.16b,  #1
-        add             v1.8h,   v20.8h,  v22.8h
-        mshrn           v28.8b,  v24.8h,  #2
+        ext             v30.16B, v0.16B,  v1.16B,  #1
+        add             v1.8H,   v20.8H,  v22.8H
+        mshrn           v28.8B,  v24.8H,  #2
 NRND    add             v1.8H,   v1.8H,   v26.8H
-        mshrn2          v28.16b, v1.8h,   #2
+        mshrn2          v28.16B, v1.8H,   #2
  .if \avg
-        ld1             {v16.16b},        [x0]
-        urhadd          v28.16b, v28.16b, v16.16b
+        ld1             {v16.16B},        [x0]
+        urhadd          v28.16B, v28.16B, v16.16B
  .endif
-        uaddl           v16.8h,  v0.8b,   v30.8b
-        uaddl2          v20.8h,  v0.16b,  v30.16b
-        st1             {v28.16b},        [x0], x2
-        add             v24.8h,  v16.8h,  v18.8h
+        uaddl           v16.8H,  v0.8B,   v30.8B
+        uaddl2          v20.8H,  v0.16B,  v30.16B
+        st1             {v28.16B},        [x0], x2
+        add             v24.8H,  v16.8H,  v18.8H
 NRND    add             v24.8H,  v24.8H,  v26.8H
-        add             v0.8h,   v20.8h,  v22.8h
-        mshrn           v30.8b,  v24.8h,  #2
+        add             v0.8H,   v20.8H,  v22.8H
+        mshrn           v30.8B,  v24.8H,  #2
 NRND    add             v0.8H,   v0.8H,   v26.8H
-        mshrn2          v30.16b, v0.8h,   #2
+        mshrn2          v30.16B, v0.8H,   #2
  .if \avg
-        ld1             {v18.16b},        [x0]
-        urhadd          v30.16b, v30.16b, v18.16b
+        ld1             {v18.16B},        [x0]
+        urhadd          v30.16B, v30.16B, v18.16B
  .endif
-        st1             {v30.16b},        [x0], x2
+        st1             {v30.16B},        [x0], x2

        ret
 .endm

 .macro  pixels8         rnd=1, avg=0
-1:      ld1             {v0.8b}, [x1], x2
-        ld1             {v1.8b}, [x1], x2
-        ld1             {v2.8b}, [x1], x2
-        ld1             {v3.8b}, [x1], x2
+1:      ld1             {v0.8B}, [x1], x2
+        ld1             {v1.8B}, [x1], x2
+        ld1             {v2.8B}, [x1], x2
+        ld1             {v3.8B}, [x1], x2
  .if \avg
-        ld1             {v4.8b}, [x0], x2
-        urhadd          v0.8b,  v0.8b,  v4.8b
-        ld1             {v5.8b}, [x0], x2
-        urhadd          v1.8b,  v1.8b,  v5.8b
-        ld1             {v6.8b}, [x0], x2
-        urhadd          v2.8b,  v2.8b,  v6.8b
-        ld1             {v7.8b}, [x0], x2
-        urhadd          v3.8b,  v3.8b,  v7.8b
+        ld1             {v4.8B}, [x0], x2
+        urhadd          v0.8B,  v0.8B,  v4.8B
+        ld1             {v5.8B}, [x0], x2
+        urhadd          v1.8B,  v1.8B,  v5.8B
+        ld1             {v6.8B}, [x0], x2
+        urhadd          v2.8B,  v2.8B,  v6.8B
+        ld1             {v7.8B}, [x0], x2
+        urhadd          v3.8B,  v3.8B,  v7.8B
        sub             x0,  x0,  x2,  lsl #2
  .endif
        subs            w3,  w3,  #4
-        st1             {v0.8b}, [x0], x2
-        st1             {v1.8b}, [x0], x2
-        st1             {v2.8b}, [x0], x2
-        st1             {v3.8b}, [x0], x2
+        st1             {v0.8B}, [x0], x2
+        st1             {v1.8B}, [x0], x2
+        st1             {v2.8B}, [x0], x2
+        st1             {v3.8B}, [x0], x2
        b.ne            1b
        ret
 .endm

 .macro  pixels8_x2      rnd=1, avg=0
-1:      ld1             {v0.8b, v1.8b}, [x1], x2
-        ext             v1.8b,  v0.8b,  v1.8b,  #1
-        ld1             {v2.8b, v3.8b}, [x1], x2
-        ext             v3.8b,  v2.8b,  v3.8b,  #1
+1:      ld1             {v0.8B, v1.8B}, [x1], x2
+        ext             v1.8B,  v0.8B,  v1.8B,  #1
+        ld1             {v2.8B, v3.8B}, [x1], x2
+        ext             v3.8B,  v2.8B,  v3.8B,  #1
        subs            w3,  w3,  #2
-        avg             v0.8b,   v0.8b,   v1.8b
-        avg             v2.8b,   v2.8b,   v3.8b
+        avg             v0.8B,   v0.8B,   v1.8B
+        avg             v2.8B,   v2.8B,   v3.8B
  .if \avg
-        ld1             {v4.8b},     [x0], x2
-        ld1             {v5.8b},     [x0]
-        urhadd          v0.8b,   v0.8b,   v4.8b
-        urhadd          v2.8b,   v2.8b,   v5.8b
+        ld1             {v4.8B},     [x0], x2
+        ld1             {v5.8B},     [x0]
+        urhadd          v0.8B,   v0.8B,   v4.8B
+        urhadd          v2.8B,   v2.8B,   v5.8B
        sub             x0,  x0,  x2
  .endif
-        st1             {v0.8b}, [x0], x2
-        st1             {v2.8b}, [x0], x2
+        st1             {v0.8B}, [x0], x2
+        st1             {v2.8B}, [x0], x2
        b.ne            1b
        ret
 .endm

 .macro  pixels8_y2      rnd=1, avg=0
        sub             w3,  w3,  #2
-        ld1             {v0.8b},  [x1], x2
-        ld1             {v1.8b},  [x1], x2
+        ld1             {v0.8B},  [x1], x2
+        ld1             {v1.8B},  [x1], x2
 1:      subs            w3,  w3,  #2
-        avg             v4.8b,  v0.8b,  v1.8b
-        ld1             {v0.8b},  [x1], x2
-        avg             v5.8b,  v0.8b,  v1.8b
-        ld1             {v1.8b},  [x1], x2
+        avg             v4.8B,  v0.8B,  v1.8B
+        ld1             {v0.8B},  [x1], x2
+        avg             v5.8B,  v0.8B,  v1.8B
+        ld1             {v1.8B},  [x1], x2
  .if \avg
-        ld1             {v2.8b},     [x0], x2
-        ld1             {v3.8b},     [x0]
-        urhadd          v4.8b,  v4.8b,  v2.8b
-        urhadd          v5.8b,  v5.8b,  v3.8b
+        ld1             {v2.8B},     [x0], x2
+        ld1             {v3.8B},     [x0]
+        urhadd          v4.8B,  v4.8B,  v2.8B
+        urhadd          v5.8B,  v5.8B,  v3.8B
        sub             x0,  x0,  x2
  .endif
-        st1             {v4.8b},     [x0], x2
-        st1             {v5.8b},     [x0], x2
+        st1             {v4.8B},     [x0], x2
+        st1             {v5.8B},     [x0], x2
        b.ne            1b

-        avg             v4.8b,  v0.8b,  v1.8b
-        ld1             {v0.8b},  [x1], x2
-        avg             v5.8b,  v0.8b,  v1.8b
+        avg             v4.8B,  v0.8B,  v1.8B
+        ld1             {v0.8B},  [x1], x2
+        avg             v5.8B,  v0.8B,  v1.8B
  .if \avg
-        ld1             {v2.8b},     [x0], x2
-        ld1             {v3.8b},     [x0]
-        urhadd          v4.8b,  v4.8b,  v2.8b
-        urhadd          v5.8b,  v5.8b,  v3.8b
+        ld1             {v2.8B},     [x0], x2
+        ld1             {v3.8B},     [x0]
+        urhadd          v4.8B,  v4.8B,  v2.8B
+        urhadd          v5.8B,  v5.8B,  v3.8B
        sub             x0,  x0,  x2
  .endif
-        st1             {v4.8b},     [x0], x2
-        st1             {v5.8b},     [x0], x2
+        st1             {v4.8B},     [x0], x2
+        st1             {v5.8B},     [x0], x2

        ret
 .endm

 .macro  pixels8_xy2     rnd=1, avg=0
        sub             w3,  w3,  #2
-        ld1             {v0.16b},     [x1], x2
-        ld1             {v1.16b},     [x1], x2
+        ld1             {v0.16B},     [x1], x2
+        ld1             {v1.16B},     [x1], x2
 NRND    movi            v19.8H, #1
-        ext             v4.16b,  v0.16b,  v4.16b,  #1
-        ext             v6.16b,  v1.16b,  v6.16b,  #1
-        uaddl           v16.8h,  v0.8b,  v4.8b
-        uaddl           v17.8h,  v1.8b,  v6.8b
+        ext             v4.16B,  v0.16B,  v4.16B,  #1
+        ext             v6.16B,  v1.16B,  v6.16B,  #1
+        uaddl           v16.8H,  v0.8B,  v4.8B
+        uaddl           v17.8H,  v1.8B,  v6.8B
 1:      subs            w3,  w3,  #2
-        ld1             {v0.16b},     [x1], x2
-        add             v18.8h, v16.8h,  v17.8h
-        ext             v4.16b,  v0.16b,  v4.16b,  #1
+        ld1             {v0.16B},     [x1], x2
+        add             v18.8H, v16.8H,  v17.8H
+        ext             v4.16B,  v0.16B,  v4.16B,  #1
 NRND    add             v18.8H, v18.8H, v19.8H
-        uaddl           v16.8h,  v0.8b,  v4.8b
-        mshrn           v5.8b,  v18.8h, #2
-        ld1             {v1.16b},     [x1], x2
-        add             v18.8h, v16.8h,  v17.8h
+        uaddl           v16.8H,  v0.8B,  v4.8B
+        mshrn           v5.8B,  v18.8H, #2
+        ld1             {v1.16B},     [x1], x2
+        add             v18.8H, v16.8H,  v17.8H
  .if \avg
-        ld1             {v7.8b},     [x0]
-        urhadd          v5.8b,  v5.8b,  v7.8b
+        ld1             {v7.8B},     [x0]
+        urhadd          v5.8B,  v5.8B,  v7.8B
  .endif
 NRND    add             v18.8H, v18.8H, v19.8H
-        st1             {v5.8b},     [x0], x2
-        mshrn           v7.8b,  v18.8h, #2
+        st1             {v5.8B},     [x0], x2
+        mshrn           v7.8B,  v18.8H, #2
  .if \avg
-        ld1             {v5.8b},     [x0]
-        urhadd          v7.8b,  v7.8b,  v5.8b
+        ld1             {v5.8B},     [x0]
+        urhadd          v7.8B,  v7.8B,  v5.8B
  .endif
-        ext             v6.16b,  v1.16b,  v6.16b,  #1
-        uaddl           v17.8h,  v1.8b,   v6.8b
-        st1             {v7.8b},     [x0], x2
+        ext             v6.16B,  v1.16B,  v6.16B,  #1
+        uaddl           v17.8H,  v1.8B,   v6.8B
+        st1             {v7.8B},     [x0], x2
        b.gt            1b

-        ld1             {v0.16b},     [x1], x2
-        add             v18.8h, v16.8h, v17.8h
-        ext             v4.16b, v0.16b, v4.16b,  #1
+        ld1             {v0.16B},     [x1], x2
+        add             v18.8H, v16.8H, v17.8H
+        ext             v4.16B, v0.16B, v4.16B,  #1
 NRND    add             v18.8H, v18.8H, v19.8H
-        uaddl           v16.8h,  v0.8b, v4.8b
-        mshrn           v5.8b,  v18.8h, #2
-        add             v18.8h, v16.8h, v17.8h
+        uaddl           v16.8H,  v0.8B, v4.8B
+        mshrn           v5.8B,  v18.8H, #2
+        add             v18.8H, v16.8H, v17.8H
  .if \avg
-        ld1             {v7.8b},     [x0]
-        urhadd          v5.8b,  v5.8b,  v7.8b
+        ld1             {v7.8B},     [x0]
+        urhadd          v5.8B,  v5.8B,  v7.8B
  .endif
 NRND    add             v18.8H, v18.8H, v19.8H
-        st1             {v5.8b},     [x0], x2
-        mshrn           v7.8b,  v18.8h, #2
+        st1             {v5.8B},     [x0], x2
+        mshrn           v7.8B,  v18.8H, #2
  .if \avg
-        ld1             {v5.8b},     [x0]
-        urhadd          v7.8b,  v7.8b,  v5.8b
+        ld1             {v5.8B},     [x0]
+        urhadd          v7.8B,  v7.8B,  v5.8B
  .endif
-        st1             {v7.8b},     [x0], x2
+        st1             {v7.8B},     [x0], x2

        ret
 .endm
--- a/libavcodec/aarch64/mdct_neon.S
+++ b/libavcodec/aarch64/mdct_neon.S
@@ -0,0 +1,326 @@
+/*
+ * AArch64 NEON optimised MDCT
+ * Copyright (c) 2009 Mans Rullgard <mans@mansr.com>
+ * Copyright (c) 2014 Janne Grunau <janne-libav@jannau.net>
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include "libavutil/aarch64/asm.S"
+
+function ff_imdct_half_neon, export=1
+        stp             x19, x20, [sp, #-32]!
+        AARCH64_SIGN_LINK_REGISTER
+        str             x30, [sp, #16]
+        mov             x12, #1
+        ldr             w14, [x0, #28]          // mdct_bits
+        ldr             x4,  [x0, #32]          // tcos
+        ldr             x3,  [x0, #8]           // revtab
+        lsl             x12, x12, x14           // n  = 1 << nbits
+        lsr             x14, x12, #2            // n4 = n >> 2
+        add             x7,  x2,  x12,  lsl #1
+        mov             x12, #-16
+        sub             x7,  x7,  #16
+
+        ld2             {v16.2s,v17.2s}, [x7], x12 // d16=x,n1 d17=x,n0
+        ld2             {v0.2s,v1.2s},   [x2], #16 // d0 =m0,x d1 =m1,x
+        rev64           v17.2s, v17.2s
+        ld2             {v2.2s,v3.2s},   [x4], #16 // d2=c0,c1 d3=s0,s2
+        fmul            v6.2s,  v17.2s, v2.2s
+        fmul            v7.2s,  v0.2s,  v2.2s
+1:
+        subs            x14, x14, #2
+        ldr             w6,  [x3], #4
+        fmul            v4.2s,  v0.2s,  v3.2s
+        fmul            v5.2s,  v17.2s, v3.2s
+        fsub            v4.2s,  v6.2s,  v4.2s
+        fadd            v5.2s,  v5.2s,  v7.2s
+        ubfm            x8,  x6,  #16, #31
+        ubfm            x6,  x6,  #0,  #15
+        add             x8,  x1,  x8,  lsl #3
+        add             x6,  x1,  x6,  lsl #3
+        b.eq            2f
+        ld2             {v16.2s,v17.2s}, [x7], x12
+        ld2             {v0.2s,v1.2s},   [x2], #16
+        rev64           v17.2s, v17.2s
+        ld2             {v2.2s,v3.2s},   [x4], #16    // d2=c0,c1 d3=s0,s2
+        fmul            v6.2s,  v17.2s, v2.2s
+        fmul            v7.2s,  v0.2s,  v2.2s
+        st2             {v4.s,v5.s}[0], [x6]
+        st2             {v4.s,v5.s}[1], [x8]
+        b               1b
+2:
+        st2             {v4.s,v5.s}[0], [x6]
+        st2             {v4.s,v5.s}[1], [x8]
+
+        mov             x19, x0
+        mov             x20, x1
+        bl              X(ff_fft_calc_neon)
+
+        mov             x12, #1
+        ldr             w14, [x19, #28]          // mdct_bits
+        ldr             x4,  [x19, #32]          // tcos
+        lsl             x12, x12, x14            // n  = 1 << nbits
+        lsr             x14, x12, #3             // n8 = n >> 3
+
+        add             x4,  x4,  x14, lsl #3
+        add             x6,  x20, x14, lsl #3
+        sub             x1,  x4,  #16
+        sub             x3,  x6,  #16
+
+        mov             x7,  #-16
+        mov             x8,  x6
+        mov             x0,  x3
+
+        ld2             {v0.2s,v1.2s},  [x3], x7 // d0 =i1,r1 d1 =i0,r0
+        ld2             {v20.2s,v21.2s},[x6], #16 // d20=i2,r2 d21=i3,r3
+        ld2             {v16.2s,v17.2s},[x1], x7 // d16=c1,c0 d18=s1,s0
+3:
+        subs            x14, x14, #2
+        fmul            v7.2s,  v0.2s,  v17.2s
+        ld2             {v18.2s,v19.2s},[x4], #16    // d17=c2,c3 d19=s2,s3
+        fmul            v4.2s,  v1.2s,  v17.2s
+        fmul            v6.2s,  v21.2s, v19.2s
+        fmul            v5.2s,  v20.2s, v19.2s
+        fmul            v22.2s, v1.2s,  v16.2s
+        fmul            v23.2s, v21.2s, v18.2s
+        fmul            v24.2s, v0.2s,  v16.2s
+        fmul            v25.2s, v20.2s, v18.2s
+        fadd            v7.2s,  v7.2s,  v22.2s
+        fadd            v5.2s,  v5.2s,  v23.2s
+        fsub            v4.2s,  v4.2s,  v24.2s
+        fsub            v6.2s,  v6.2s,  v25.2s
+        b.eq            4f
+        ld2             {v0.2s,v1.2s},  [x3], x7
+        ld2             {v20.2s,v21.2s},[x6], #16
+        ld2             {v16.2s,v17.2s},[x1], x7 // d16=c1,c0 d18=s1,s0
+        rev64           v5.2s,  v5.2s
+        rev64           v7.2s,  v7.2s
+        st2             {v4.2s,v5.2s},  [x0], x7
+        st2             {v6.2s,v7.2s},  [x8], #16
+        b               3b
+4:
+        rev64           v5.2s,  v5.2s
+        rev64           v7.2s,  v7.2s
+        st2             {v4.2s,v5.2s},  [x0]
+        st2             {v6.2s,v7.2s},  [x8]
+
+        ldr             x30, [sp, #16]
+        AARCH64_VALIDATE_LINK_REGISTER
+        ldp             x19, x20, [sp], #32
+
+        ret
+endfunc
+
+function ff_imdct_calc_neon, export=1
+        stp             x19, x20, [sp, #-32]!
+        AARCH64_SIGN_LINK_REGISTER
+        str             x30, [sp, #16]
+        ldr             w3,  [x0, #28]          // mdct_bits
+        mov             x19, #1
+        mov             x20, x1
+        lsl             x19, x19, x3
+        add             x1,  x1,  x19
+
+        bl              X(ff_imdct_half_neon)
+
+        add             x0,  x20, x19,  lsl #2
+        add             x1,  x20, x19,  lsl #1
+        sub             x0,  x0,  #8
+        sub             x2,  x1,  #16
+        mov             x3,  #-16
+        mov             x6,  #-8
+1:
+        ld1             {v0.4s}, [x2], x3
+        prfum           pldl1keep, [x0, #-16]
+        rev64           v0.4s, v0.4s
+        ld1             {v2.2s,v3.2s}, [x1], #16
+        fneg            v4.4s,  v0.4s
+        prfum           pldl1keep, [x2, #-16]
+        rev64           v2.2s, v2.2s
+        rev64           v3.2s, v3.2s
+        ext             v4.16b, v4.16b, v4.16b, #8
+        st1             {v2.2s}, [x0], x6
+        st1             {v3.2s}, [x0], x6
+        st1             {v4.4s}, [x20], #16
+        subs            x19, x19,  #16
+        b.gt            1b
+
+        ldr             x30, [sp, #16]
+        AARCH64_VALIDATE_LINK_REGISTER
+        ldp             x19, x20, [sp], #32
+
+        ret
+endfunc
+
+
+function ff_mdct_calc_neon, export=1
+        stp             x19, x20, [sp, #-32]!
+        AARCH64_SIGN_LINK_REGISTER
+        str             x30, [sp, #16]
+
+        mov             x12, #1
+        ldr             w14, [x0, #28]          // mdct_bits
+        ldr             x4,  [x0, #32]          // tcos
+        ldr             x3,  [x0, #8]           // revtab
+        lsl             x14, x12, x14           // n  = 1 << nbits
+        add             x7,  x2,  x14           // in4u
+        sub             x9,  x7,  #16           // in4d
+        add             x2,  x7,  x14, lsl #1   // in3u
+        add             x8,  x9,  x14, lsl #1   // in3d
+        add             x5,  x4,  x14, lsl #1
+        sub             x5,  x5,  #16
+        sub             x3,  x3,  #4
+        mov             x12, #-16
+        lsr             x13, x14, #1
+
+        ld2             {v16.2s,v17.2s}, [x9], x12  // in0u0,in0u1 in4d1,in4d0
+        ld2             {v18.2s,v19.2s}, [x8], x12  // in2u0,in2u1 in3d1,in3d0
+        ld2             {v0.2s, v1.2s},  [x7], #16  // in4u0,in4u1 in2d1,in2d0
+        rev64           v17.2s, v17.2s              // in4d0,in4d1 in3d0,in3d1
+        rev64           v19.2s, v19.2s              // in4d0,in4d1 in3d0,in3d1
+        ld2             {v2.2s, v3.2s},  [x2], #16  // in3u0,in3u1 in1d1,in1d0
+        fsub            v0.2s,  v17.2s, v0.2s       // in4d-in4u      I
+        ld2             {v20.2s,v21.2s}, [x4], #16  // c0,c1 s0,s1
+        rev64           v1.2s,  v1.2s               // in2d0,in2d1 in1d0,in1d1
+        rev64           v3.2s,  v3.2s               // in2d0,in2d1 in1d0,in1d1
+        ld2             {v30.2s,v31.2s}, [x5], x12  // c2,c3 s2,s3
+        fadd            v2.2s,  v2.2s,  v19.2s      // in3u+in3d     -R
+        fsub            v16.2s, v16.2s, v1.2s       // in0u-in2d      R
+        fadd            v18.2s, v18.2s, v3.2s       // in2u+in1d     -I
+1:
+        fmul            v7.2s,  v0.2s,  v21.2s      //  I*s
+        ldr             w10, [x3, x13]
+        fmul            v6.2s,  v2.2s,  v20.2s      // -R*c
+        ldr             w6,  [x3, #4]!
+        fmul            v4.2s,  v2.2s,  v21.2s      // -R*s
+        fmul            v5.2s,  v0.2s,  v20.2s      //  I*c
+        fmul            v24.2s, v16.2s, v30.2s      //  R*c
+        fmul            v25.2s, v18.2s, v31.2s      // -I*s
+        fmul            v22.2s, v16.2s, v31.2s      //  R*s
+        fmul            v23.2s, v18.2s, v30.2s      //  I*c
+        subs            x14, x14, #16
+        subs            x13, x13, #8
+        fsub            v6.2s,  v6.2s,  v7.2s       // -R*c-I*s
+        fadd            v7.2s,  v4.2s,  v5.2s       // -R*s+I*c
+        fsub            v24.2s, v25.2s, v24.2s      // I*s-R*c
+        fadd            v25.2s, v22.2s, v23.2s      // R*s-I*c
+        b.eq            1f
+        mov             x12, #-16
+        ld2             {v16.2s,v17.2s}, [x9], x12  // in0u0,in0u1 in4d1,in4d0
+        ld2             {v18.2s,v19.2s}, [x8], x12  // in2u0,in2u1 in3d1,in3d0
+        fneg            v7.2s,  v7.2s               //  R*s-I*c
+        ld2             {v0.2s, v1.2s},  [x7], #16  // in4u0,in4u1 in2d1,in2d0
+        rev64           v17.2s, v17.2s              // in4d0,in4d1 in3d0,in3d1
+        rev64           v19.2s, v19.2s              // in4d0,in4d1 in3d0,in3d1
+        ld2             {v2.2s, v3.2s},  [x2], #16  // in3u0,in3u1 in1d1,in1d0
+        fsub            v0.2s,  v17.2s, v0.2s       // in4d-in4u      I
+        ld2             {v20.2s,v21.2s}, [x4], #16  // c0,c1 s0,s1
+        rev64           v1.2s,  v1.2s               // in2d0,in2d1 in1d0,in1d1
+        rev64           v3.2s,  v3.2s               // in2d0,in2d1 in1d0,in1d1
+        ld2             {v30.2s,v31.2s}, [x5], x12  // c2,c3 s2,s3
+        fadd            v2.2s,  v2.2s,  v19.2s      // in3u+in3d     -R
+        fsub            v16.2s, v16.2s, v1.2s       // in0u-in2d      R
+        fadd            v18.2s, v18.2s, v3.2s       // in2u+in1d     -I
+        ubfm            x12, x6,  #16, #31
+        ubfm            x6,  x6,  #0,  #15
+        add             x12, x1,  x12, lsl #3
+        add             x6,  x1,  x6,  lsl #3
+        st2             {v6.s,v7.s}[0],   [x6]
+        st2             {v6.s,v7.s}[1],   [x12]
+        ubfm            x6,  x10, #16, #31
+        ubfm            x10, x10, #0,  #15
+        add             x6 , x1,  x6,  lsl #3
+        add             x10, x1,  x10, lsl #3
+        st2             {v24.s,v25.s}[0], [x10]
+        st2             {v24.s,v25.s}[1], [x6]
+        b               1b
+1:
+        fneg            v7.2s,  v7.2s           //  R*s-I*c
+        ubfm            x12, x6,  #16, #31
+        ubfm            x6,  x6,  #0,  #15
+        add             x12, x1,  x12, lsl #3
+        add             x6,  x1,  x6,  lsl #3
+        st2             {v6.s,v7.s}[0],   [x6]
+        st2             {v6.s,v7.s}[1],   [x12]
+        ubfm            x6,  x10, #16, #31
+        ubfm            x10, x10, #0,  #15
+        add             x6 , x1,  x6,  lsl #3
+        add             x10, x1,  x10, lsl #3
+        st2             {v24.s,v25.s}[0], [x10]
+        st2             {v24.s,v25.s}[1], [x6]
+
+        mov             x19, x0
+        mov             x20, x1
+        bl              X(ff_fft_calc_neon)
+
+        mov             x12, #1
+        ldr             w14, [x19, #28]         // mdct_bits
+        ldr             x4,  [x19, #32]         // tcos
+        lsl             x12, x12, x14           // n  = 1 << nbits
+        lsr             x14, x12, #3            // n8 = n >> 3
+
+        add             x4,  x4,  x14, lsl #3
+        add             x6,  x20, x14, lsl #3
+        sub             x1,  x4,  #16
+        sub             x3,  x6,  #16
+
+        mov             x7,  #-16
+        mov             x8,  x6
+        mov             x0,  x3
+
+        ld2             {v0.2s,v1.2s},   [x3], x7   // d0 =r1,i1 d1 =r0,i0
+        ld2             {v20.2s,v21.2s}, [x6], #16  // d20=r2,i2 d21=r3,i3
+        ld2             {v16.2s,v17.2s}, [x1], x7   // c1,c0 s1,s0
+1:
+        subs            x14, x14, #2
+        fmul            v7.2s,  v0.2s,  v17.2s      // r1*s1,r0*s0
+        ld2             {v18.2s,v19.2s}, [x4], #16  // c2,c3 s2,s3
+        fmul            v4.2s,  v1.2s,  v17.2s      // i1*s1,i0*s0
+        fmul            v6.2s,  v21.2s, v19.2s      // i2*s2,i3*s3
+        fmul            v5.2s,  v20.2s, v19.2s      // r2*s2,r3*s3
+        fmul            v24.2s, v0.2s,  v16.2s      // r1*c1,r0*c0
+        fmul            v25.2s, v20.2s, v18.2s      // r2*c2,r3*c3
+        fmul            v22.2s, v21.2s, v18.2s      // i2*c2,i3*c3
+        fmul            v23.2s, v1.2s,  v16.2s      // i1*c1,i0*c0
+        fadd            v4.2s,  v4.2s,  v24.2s      // i1*s1+r1*c1,i0*s0+r0*c0
+        fadd            v6.2s,  v6.2s,  v25.2s      // i2*s2+r2*c2,i3*s3+r3*c3
+        fsub            v5.2s,  v22.2s, v5.2s       // i2*c2-r2*s2,i3*c3-r3*s3
+        fsub            v7.2s,  v23.2s, v7.2s       // i1*c1-r1*s1,i0*c0-r0*s0
+        fneg            v4.2s,  v4.2s
+        fneg            v6.2s,  v6.2s
+        b.eq            1f
+        ld2             {v0.2s, v1.2s},  [x3], x7
+        ld2             {v20.2s,v21.2s}, [x6], #16
+        ld2             {v16.2s,v17.2s}, [x1], x7   // c1,c0 s1,s0
+        rev64           v5.2s,  v5.2s
+        rev64           v7.2s,  v7.2s
+        st2             {v4.2s,v5.2s},  [x0], x7
+        st2             {v6.2s,v7.2s},  [x8], #16
+        b               1b
+1:
+        rev64           v5.2s,  v5.2s
+        rev64           v7.2s,  v7.2s
+        st2             {v4.2s,v5.2s},  [x0]
+        st2             {v6.2s,v7.2s},  [x8]
+
+        ldr             x30, [sp, #16]
+        AARCH64_VALIDATE_LINK_REGISTER
+        ldp             x19, x20, [sp], #32
+
+        ret
+endfunc
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -1099,7 +1099,7 @@ function vsse_intra16_neon, export=1
        cbnz            w4, 2b

 3:
-        add             v16.4s, v16.4s, v17.4s
+        add             v16.4s, v16.4s, v17.4S
        uaddlv          d17, v16.4s
        fmov            w0, s17

--- a/libavcodec/aarch64/neon.S
+++ b/libavcodec/aarch64/neon.S
@@ -1,8 +1,6 @@
 /*
 * This file is part of FFmpeg.
 *
- * Copyright (c) 2023 J. Dekker <jdek@itanimul.li>
- *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
@@ -18,156 +16,147 @@
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

-.macro clip min, max, regs:vararg
-.irp x, \regs
-        smax            \x, \x, \min
-.endr
-.irp x, \regs
-        smin            \x, \x, \max
-.endr
-.endm
-
 .macro  transpose_8x8B  r0, r1, r2, r3, r4, r5, r6, r7, r8, r9
-        trn1            \r8\().8b,  \r0\().8b,  \r1\().8b
-        trn2            \r9\().8b,  \r0\().8b,  \r1\().8b
-        trn1            \r1\().8b,  \r2\().8b,  \r3\().8b
-        trn2            \r3\().8b,  \r2\().8b,  \r3\().8b
-        trn1            \r0\().8b,  \r4\().8b,  \r5\().8b
-        trn2            \r5\().8b,  \r4\().8b,  \r5\().8b
-        trn1            \r2\().8b,  \r6\().8b,  \r7\().8b
-        trn2            \r7\().8b,  \r6\().8b,  \r7\().8b
+        trn1            \r8\().8B,  \r0\().8B,  \r1\().8B
+        trn2            \r9\().8B,  \r0\().8B,  \r1\().8B
+        trn1            \r1\().8B,  \r2\().8B,  \r3\().8B
+        trn2            \r3\().8B,  \r2\().8B,  \r3\().8B
+        trn1            \r0\().8B,  \r4\().8B,  \r5\().8B
+        trn2            \r5\().8B,  \r4\().8B,  \r5\().8B
+        trn1            \r2\().8B,  \r6\().8B,  \r7\().8B
+        trn2            \r7\().8B,  \r6\().8B,  \r7\().8B

-        trn1            \r4\().4h,  \r0\().4h,  \r2\().4h
-        trn2            \r2\().4h,  \r0\().4h,  \r2\().4h
-        trn1            \r6\().4h,  \r5\().4h,  \r7\().4h
-        trn2            \r7\().4h,  \r5\().4h,  \r7\().4h
-        trn1            \r5\().4h,  \r9\().4h,  \r3\().4h
-        trn2            \r9\().4h,  \r9\().4h,  \r3\().4h
-        trn1            \r3\().4h,  \r8\().4h,  \r1\().4h
-        trn2            \r8\().4h,  \r8\().4h,  \r1\().4h
+        trn1            \r4\().4H,  \r0\().4H,  \r2\().4H
+        trn2            \r2\().4H,  \r0\().4H,  \r2\().4H
+        trn1            \r6\().4H,  \r5\().4H,  \r7\().4H
+        trn2            \r7\().4H,  \r5\().4H,  \r7\().4H
+        trn1            \r5\().4H,  \r9\().4H,  \r3\().4H
+        trn2            \r9\().4H,  \r9\().4H,  \r3\().4H
+        trn1            \r3\().4H,  \r8\().4H,  \r1\().4H
+        trn2            \r8\().4H,  \r8\().4H,  \r1\().4H

-        trn1            \r0\().2s,  \r3\().2s,  \r4\().2s
-        trn2            \r4\().2s,  \r3\().2s,  \r4\().2s
+        trn1            \r0\().2S,  \r3\().2S,  \r4\().2S
+        trn2            \r4\().2S,  \r3\().2S,  \r4\().2S

-        trn1            \r1\().2s,  \r5\().2s,  \r6\().2s
-        trn2            \r5\().2s,  \r5\().2s,  \r6\().2s
+        trn1            \r1\().2S,  \r5\().2S,  \r6\().2S
+        trn2            \r5\().2S,  \r5\().2S,  \r6\().2S

-        trn2            \r6\().2s,  \r8\().2s,  \r2\().2s
-        trn1            \r2\().2s,  \r8\().2s,  \r2\().2s
+        trn2            \r6\().2S,  \r8\().2S,  \r2\().2S
+        trn1            \r2\().2S,  \r8\().2S,  \r2\().2S

-        trn1            \r3\().2s,  \r9\().2s,  \r7\().2s
-        trn2            \r7\().2s,  \r9\().2s,  \r7\().2s
+        trn1            \r3\().2S,  \r9\().2S,  \r7\().2S
+        trn2            \r7\().2S,  \r9\().2S,  \r7\().2S
 .endm

 .macro  transpose_8x16B r0, r1, r2, r3, r4, r5, r6, r7, t0, t1
-        trn1            \t0\().16b, \r0\().16b, \r1\().16b
-        trn2            \t1\().16b, \r0\().16b, \r1\().16b
-        trn1            \r1\().16b, \r2\().16b, \r3\().16b
-        trn2            \r3\().16b, \r2\().16b, \r3\().16b
-        trn1            \r0\().16b, \r4\().16b, \r5\().16b
-        trn2            \r5\().16b, \r4\().16b, \r5\().16b
-        trn1            \r2\().16b, \r6\().16b, \r7\().16b
-        trn2            \r7\().16b, \r6\().16b, \r7\().16b
+        trn1            \t0\().16B, \r0\().16B, \r1\().16B
+        trn2            \t1\().16B, \r0\().16B, \r1\().16B
+        trn1            \r1\().16B, \r2\().16B, \r3\().16B
+        trn2            \r3\().16B, \r2\().16B, \r3\().16B
+        trn1            \r0\().16B, \r4\().16B, \r5\().16B
+        trn2            \r5\().16B, \r4\().16B, \r5\().16B
+        trn1            \r2\().16B, \r6\().16B, \r7\().16B
+        trn2            \r7\().16B, \r6\().16B, \r7\().16B

-        trn1            \r4\().8h,  \r0\().8h,  \r2\().8h
-        trn2            \r2\().8h,  \r0\().8h,  \r2\().8h
-        trn1            \r6\().8h,  \r5\().8h,  \r7\().8h
-        trn2            \r7\().8h,  \r5\().8h,  \r7\().8h
-        trn1            \r5\().8h,  \t1\().8h,  \r3\().8h
-        trn2            \t1\().8h,  \t1\().8h,  \r3\().8h
-        trn1            \r3\().8h,  \t0\().8h,  \r1\().8h
-        trn2            \t0\().8h,  \t0\().8h,  \r1\().8h
+        trn1            \r4\().8H,  \r0\().8H,  \r2\().8H
+        trn2            \r2\().8H,  \r0\().8H,  \r2\().8H
+        trn1            \r6\().8H,  \r5\().8H,  \r7\().8H
+        trn2            \r7\().8H,  \r5\().8H,  \r7\().8H
+        trn1            \r5\().8H,  \t1\().8H,  \r3\().8H
+        trn2            \t1\().8H,  \t1\().8H,  \r3\().8H
+        trn1            \r3\().8H,  \t0\().8H,  \r1\().8H
+        trn2            \t0\().8H,  \t0\().8H,  \r1\().8H

-        trn1            \r0\().4s,  \r3\().4s,  \r4\().4s
-        trn2            \r4\().4s,  \r3\().4s,  \r4\().4s
+        trn1            \r0\().4S,  \r3\().4S,  \r4\().4S
+        trn2            \r4\().4S,  \r3\().4S,  \r4\().4S

-        trn1            \r1\().4s,  \r5\().4s,  \r6\().4s
-        trn2            \r5\().4s,  \r5\().4s,  \r6\().4s
+        trn1            \r1\().4S,  \r5\().4S,  \r6\().4S
+        trn2            \r5\().4S,  \r5\().4S,  \r6\().4S

-        trn2            \r6\().4s,  \t0\().4s,  \r2\().4s
-        trn1            \r2\().4s,  \t0\().4s,  \r2\().4s
+        trn2            \r6\().4S,  \t0\().4S,  \r2\().4S
+        trn1            \r2\().4S,  \t0\().4S,  \r2\().4S

-        trn1            \r3\().4s,  \t1\().4s,  \r7\().4s
-        trn2            \r7\().4s,  \t1\().4s,  \r7\().4s
+        trn1            \r3\().4S,  \t1\().4S,  \r7\().4S
+        trn2            \r7\().4S,  \t1\().4S,  \r7\().4S
 .endm

 .macro  transpose_4x16B r0, r1, r2, r3, t4, t5, t6, t7
-        trn1            \t4\().16b, \r0\().16b,  \r1\().16b
-        trn2            \t5\().16b, \r0\().16b,  \r1\().16b
-        trn1            \t6\().16b, \r2\().16b,  \r3\().16b
-        trn2            \t7\().16b, \r2\().16b,  \r3\().16b
+        trn1            \t4\().16B, \r0\().16B,  \r1\().16B
+        trn2            \t5\().16B, \r0\().16B,  \r1\().16B
+        trn1            \t6\().16B, \r2\().16B,  \r3\().16B
+        trn2            \t7\().16B, \r2\().16B,  \r3\().16B

-        trn1            \r0\().8h,  \t4\().8h,  \t6\().8h
-        trn2            \r2\().8h,  \t4\().8h,  \t6\().8h
-        trn1            \r1\().8h,  \t5\().8h,  \t7\().8h
-        trn2            \r3\().8h,  \t5\().8h,  \t7\().8h
+        trn1            \r0\().8H,  \t4\().8H,  \t6\().8H
+        trn2            \r2\().8H,  \t4\().8H,  \t6\().8H
+        trn1            \r1\().8H,  \t5\().8H,  \t7\().8H
+        trn2            \r3\().8H,  \t5\().8H,  \t7\().8H
 .endm

 .macro  transpose_4x8B  r0, r1, r2, r3, t4, t5, t6, t7
-        trn1            \t4\().8b,  \r0\().8b,  \r1\().8b
-        trn2            \t5\().8b,  \r0\().8b,  \r1\().8b
-        trn1            \t6\().8b,  \r2\().8b,  \r3\().8b
-        trn2            \t7\().8b,  \r2\().8b,  \r3\().8b
+        trn1            \t4\().8B,  \r0\().8B,  \r1\().8B
+        trn2            \t5\().8B,  \r0\().8B,  \r1\().8B
+        trn1            \t6\().8B,  \r2\().8B,  \r3\().8B
+        trn2            \t7\().8B,  \r2\().8B,  \r3\().8B

-        trn1            \r0\().4h,  \t4\().4h,  \t6\().4h
-        trn2            \r2\().4h,  \t4\().4h,  \t6\().4h
-        trn1            \r1\().4h,  \t5\().4h,  \t7\().4h
-        trn2            \r3\().4h,  \t5\().4h,  \t7\().4h
+        trn1            \r0\().4H,  \t4\().4H,  \t6\().4H
+        trn2            \r2\().4H,  \t4\().4H,  \t6\().4H
+        trn1            \r1\().4H,  \t5\().4H,  \t7\().4H
+        trn2            \r3\().4H,  \t5\().4H,  \t7\().4H
 .endm

 .macro  transpose_4x4H  r0, r1, r2, r3, r4, r5, r6, r7
-        trn1            \r4\().4h,  \r0\().4h,  \r1\().4h
-        trn2            \r5\().4h,  \r0\().4h,  \r1\().4h
-        trn1            \r6\().4h,  \r2\().4h,  \r3\().4h
-        trn2            \r7\().4h,  \r2\().4h,  \r3\().4h
+        trn1            \r4\().4H,  \r0\().4H,  \r1\().4H
+        trn2            \r5\().4H,  \r0\().4H,  \r1\().4H
+        trn1            \r6\().4H,  \r2\().4H,  \r3\().4H
+        trn2            \r7\().4H,  \r2\().4H,  \r3\().4H

-        trn1            \r0\().2s,  \r4\().2s,  \r6\().2s
-        trn2            \r2\().2s,  \r4\().2s,  \r6\().2s
-        trn1            \r1\().2s,  \r5\().2s,  \r7\().2s
-        trn2            \r3\().2s,  \r5\().2s,  \r7\().2s
+        trn1            \r0\().2S,  \r4\().2S,  \r6\().2S
+        trn2            \r2\().2S,  \r4\().2S,  \r6\().2S
+        trn1            \r1\().2S,  \r5\().2S,  \r7\().2S
+        trn2            \r3\().2S,  \r5\().2S,  \r7\().2S
 .endm

 .macro transpose_4x8H r0, r1, r2, r3, t4, t5, t6, t7
-        trn1            \t4\().8h,  \r0\().8h,  \r1\().8h
-        trn2            \t5\().8h,  \r0\().8h,  \r1\().8h
-        trn1            \t6\().8h,  \r2\().8h,  \r3\().8h
-        trn2            \t7\().8h,  \r2\().8h,  \r3\().8h
+        trn1            \t4\().8H,  \r0\().8H,  \r1\().8H
+        trn2            \t5\().8H,  \r0\().8H,  \r1\().8H
+        trn1            \t6\().8H,  \r2\().8H,  \r3\().8H
+        trn2            \t7\().8H,  \r2\().8H,  \r3\().8H

-        trn1            \r0\().4s,  \t4\().4s,  \t6\().4s
-        trn2            \r2\().4s,  \t4\().4s,  \t6\().4s
-        trn1            \r1\().4s,  \t5\().4s,  \t7\().4s
-        trn2            \r3\().4s,  \t5\().4s,  \t7\().4s
+        trn1            \r0\().4S,  \t4\().4S,  \t6\().4S
+        trn2            \r2\().4S,  \t4\().4S,  \t6\().4S
+        trn1            \r1\().4S,  \t5\().4S,  \t7\().4S
+        trn2            \r3\().4S,  \t5\().4S,  \t7\().4S
 .endm

 .macro  transpose_8x8H  r0, r1, r2, r3, r4, r5, r6, r7, r8, r9
-        trn1            \r8\().8h,  \r0\().8h,  \r1\().8h
-        trn2            \r9\().8h,  \r0\().8h,  \r1\().8h
-        trn1            \r1\().8h,  \r2\().8h,  \r3\().8h
-        trn2            \r3\().8h,  \r2\().8h,  \r3\().8h
-        trn1            \r0\().8h,  \r4\().8h,  \r5\().8h
-        trn2            \r5\().8h,  \r4\().8h,  \r5\().8h
-        trn1            \r2\().8h,  \r6\().8h,  \r7\().8h
-        trn2            \r7\().8h,  \r6\().8h,  \r7\().8h
+        trn1            \r8\().8H,  \r0\().8H,  \r1\().8H
+        trn2            \r9\().8H,  \r0\().8H,  \r1\().8H
+        trn1            \r1\().8H,  \r2\().8H,  \r3\().8H
+        trn2            \r3\().8H,  \r2\().8H,  \r3\().8H
+        trn1            \r0\().8H,  \r4\().8H,  \r5\().8H
+        trn2            \r5\().8H,  \r4\().8H,  \r5\().8H
+        trn1            \r2\().8H,  \r6\().8H,  \r7\().8H
+        trn2            \r7\().8H,  \r6\().8H,  \r7\().8H

-        trn1            \r4\().4s,  \r0\().4s,  \r2\().4s
-        trn2            \r2\().4s,  \r0\().4s,  \r2\().4s
-        trn1            \r6\().4s,  \r5\().4s,  \r7\().4s
-        trn2            \r7\().4s,  \r5\().4s,  \r7\().4s
-        trn1            \r5\().4s,  \r9\().4s,  \r3\().4s
-        trn2            \r9\().4s,  \r9\().4s,  \r3\().4s
-        trn1            \r3\().4s,  \r8\().4s,  \r1\().4s
-        trn2            \r8\().4s,  \r8\().4s,  \r1\().4s
+        trn1            \r4\().4S,  \r0\().4S,  \r2\().4S
+        trn2            \r2\().4S,  \r0\().4S,  \r2\().4S
+        trn1            \r6\().4S,  \r5\().4S,  \r7\().4S
+        trn2            \r7\().4S,  \r5\().4S,  \r7\().4S
+        trn1            \r5\().4S,  \r9\().4S,  \r3\().4S
+        trn2            \r9\().4S,  \r9\().4S,  \r3\().4S
+        trn1            \r3\().4S,  \r8\().4S,  \r1\().4S
+        trn2            \r8\().4S,  \r8\().4S,  \r1\().4S

-        trn1            \r0\().2d,  \r3\().2d,  \r4\().2d
-        trn2            \r4\().2d,  \r3\().2d,  \r4\().2d
+        trn1            \r0\().2D,  \r3\().2D,  \r4\().2D
+        trn2            \r4\().2D,  \r3\().2D,  \r4\().2D

-        trn1            \r1\().2d,  \r5\().2d,  \r6\().2d
-        trn2            \r5\().2d,  \r5\().2d,  \r6\().2d
+        trn1            \r1\().2D,  \r5\().2D,  \r6\().2D
+        trn2            \r5\().2D,  \r5\().2D,  \r6\().2D

-        trn2            \r6\().2d,  \r8\().2d,  \r2\().2d
-        trn1            \r2\().2d,  \r8\().2d,  \r2\().2d
+        trn2            \r6\().2D,  \r8\().2D,  \r2\().2D
+        trn1            \r2\().2D,  \r8\().2D,  \r2\().2D

-        trn1            \r3\().2d,  \r9\().2d,  \r7\().2d
-        trn2            \r7\().2d,  \r9\().2d,  \r7\().2d
+        trn1            \r3\().2D,  \r9\().2D,  \r7\().2D
+        trn2            \r7\().2D,  \r9\().2D,  \r7\().2D

 .endm
--- a/libavcodec/aarch64/opusdsp_neon.S
+++ b/libavcodec/aarch64/opusdsp_neon.S
@@ -33,81 +33,81 @@ const tab_x2, align=4
 endconst

 function ff_opus_deemphasis_neon, export=1
-        movrel          x4, tab_st
-        ld1             {v4.4s}, [x4]
-        movrel          x4, tab_x0
-        ld1             {v5.4s}, [x4]
-        movrel          x4, tab_x1
-        ld1             {v6.4s}, [x4]
-        movrel          x4, tab_x2
-        ld1             {v7.4s}, [x4]
+        movrel  x4, tab_st
+        ld1    {v4.4s}, [x4]
+        movrel  x4, tab_x0
+        ld1    {v5.4s}, [x4]
+        movrel  x4, tab_x1
+        ld1    {v6.4s}, [x4]
+        movrel  x4, tab_x2
+        ld1    {v7.4s}, [x4]

-        fmul            v0.4s, v4.4s, v0.s[0]
+        fmul v0.4s, v4.4s, v0.s[0]

-1:      ld1             {v1.4s, v2.4s}, [x1], #32
+1:      ld1  {v1.4s, v2.4s}, [x1], #32

-        fmla            v0.4s, v5.4s, v1.s[0]
-        fmul            v3.4s, v7.4s, v2.s[2]
+        fmla v0.4s, v5.4s, v1.s[0]
+        fmul v3.4s, v7.4s, v2.s[2]

-        fmla            v0.4s, v6.4s, v1.s[1]
-        fmla            v3.4s, v6.4s, v2.s[1]
+        fmla v0.4s, v6.4s, v1.s[1]
+        fmla v3.4s, v6.4s, v2.s[1]

-        fmla            v0.4s, v7.4s, v1.s[2]
-        fmla            v3.4s, v5.4s, v2.s[0]
+        fmla v0.4s, v7.4s, v1.s[2]
+        fmla v3.4s, v5.4s, v2.s[0]

-        fadd            v1.4s, v1.4s, v0.4s
-        fadd            v2.4s, v2.4s, v3.4s
+        fadd v1.4s, v1.4s, v0.4s
+        fadd v2.4s, v2.4s, v3.4s

-        fmla            v2.4s, v4.4s, v1.s[3]
+        fmla v2.4s, v4.4s, v1.s[3]

-        st1             {v1.4s, v2.4s}, [x0], #32
-        fmul            v0.4s, v4.4s, v2.s[3]
+        st1  {v1.4s, v2.4s}, [x0], #32
+        fmul v0.4s, v4.4s, v2.s[3]

-        subs            w2, w2, #8
-        b.gt            1b
+        subs w2, w2, #8
+        b.gt 1b

-        mov             s0, v2.s[3]
+        mov s0, v2.s[3]

        ret
 endfunc

 function ff_opus_postfilter_neon, export=1
-        ld1             {v0.4s}, [x2]
-        dup             v1.4s, v0.s[1]
-        dup             v2.4s, v0.s[2]
-        dup             v0.4s, v0.s[0]
+        ld1 {v0.4s}, [x2]
+        dup v1.4s, v0.s[1]
+        dup v2.4s, v0.s[2]
+        dup v0.4s, v0.s[0]

-        add             w1, w1, #2
-        sub             x1, x0, x1, lsl #2
+        add w1, w1, #2
+        sub x1, x0, x1, lsl #2

-        ld1             {v3.4s}, [x1]
-        fmul            v3.4s, v3.4s, v2.4s
+        ld1 {v3.4s}, [x1]
+        fmul v3.4s, v3.4s, v2.4s

-1:      add             x1, x1, #4
-        ld1             {v4.4s}, [x1]
-        add             x1, x1, #4
-        ld1             {v5.4s}, [x1]
-        add             x1, x1, #4
-        ld1             {v6.4s}, [x1]
-        add             x1, x1, #4
-        ld1             {v7.4s}, [x1]
+1:      add x1, x1, #4
+        ld1 {v4.4s}, [x1]
+        add x1, x1, #4
+        ld1 {v5.4s}, [x1]
+        add x1, x1, #4
+        ld1 {v6.4s}, [x1]
+        add x1, x1, #4
+        ld1 {v7.4s}, [x1]

-        fmla            v3.4s, v7.4s, v2.4s
-        fadd            v6.4s, v6.4s, v4.4s
+        fmla v3.4s, v7.4s, v2.4s
+        fadd v6.4s, v6.4s, v4.4s

-        ld1             {v4.4s}, [x0]
-        fmla            v4.4s, v5.4s, v0.4s
+        ld1 {v4.4s}, [x0]
+        fmla v4.4s, v5.4s, v0.4s

-        fmul            v6.4s, v6.4s, v1.4s
-        fadd            v6.4s, v6.4s, v3.4s
+        fmul v6.4s, v6.4s, v1.4s
+        fadd v6.4s, v6.4s, v3.4s

-        fadd            v4.4s, v4.4s, v6.4s
-        fmul            v3.4s, v7.4s, v2.4s
+        fadd v4.4s, v4.4s, v6.4s
+        fmul v3.4s, v7.4s, v2.4s

-        st1             {v4.4s}, [x0], #16
+        st1  {v4.4s}, [x0], #16

-        subs            w3, w3, #4
-        b.gt            1b
+        subs w3, w3, #4
+        b.gt 1b

        ret
 endfunc
--- a/libavcodec/aarch64/sbrdsp_neon.S
+++ b/libavcodec/aarch64/sbrdsp_neon.S
@@ -46,49 +46,49 @@ function ff_sbr_sum64x5_neon, export=1
        add             x3, x0, #192*4
        add             x4, x0, #256*4
        mov             x5, #64
-1:      ld1             {v0.4s}, [x0]
-        ld1             {v1.4s}, [x1], #16
-        fadd            v0.4s, v0.4s, v1.4s
-        ld1             {v2.4s}, [x2], #16
-        fadd            v0.4s, v0.4s, v2.4s
-        ld1             {v3.4s}, [x3], #16
-        fadd            v0.4s, v0.4s, v3.4s
-        ld1             {v4.4s}, [x4], #16
-        fadd            v0.4s, v0.4s, v4.4s
-        st1             {v0.4s}, [x0], #16
+1:      ld1             {v0.4S}, [x0]
+        ld1             {v1.4S}, [x1], #16
+        fadd            v0.4S, v0.4S, v1.4S
+        ld1             {v2.4S}, [x2], #16
+        fadd            v0.4S, v0.4S, v2.4S
+        ld1             {v3.4S}, [x3], #16
+        fadd            v0.4S, v0.4S, v3.4S
+        ld1             {v4.4S}, [x4], #16
+        fadd            v0.4S, v0.4S, v4.4S
+        st1             {v0.4S}, [x0], #16
        subs            x5, x5, #4
        b.gt            1b
        ret
 endfunc

 function ff_sbr_sum_square_neon, export=1
-        movi            v0.4s, #0
-1:      ld1             {v1.4s}, [x0], #16
-        fmla            v0.4s, v1.4s, v1.4s
+        movi            v0.4S, #0
+1:      ld1             {v1.4S}, [x0], #16
+        fmla            v0.4S, v1.4S, v1.4S
        subs            w1, w1, #2
        b.gt            1b
-        faddp           v0.4s, v0.4s, v0.4s
-        faddp           v0.4s, v0.4s, v0.4s
+        faddp           v0.4S, v0.4S, v0.4S
+        faddp           v0.4S, v0.4S, v0.4S
        ret
 endfunc

 function ff_sbr_neg_odd_64_neon, export=1
        mov             x1, x0
-        movi            v5.4s, #1<<7, lsl #24
-        ld2             {v0.4s, v1.4s}, [x0], #32
-        eor             v1.16b, v1.16b, v5.16b
-        ld2             {v2.4s, v3.4s}, [x0], #32
+        movi            v5.4S, #1<<7, lsl #24
+        ld2             {v0.4S, v1.4S}, [x0], #32
+        eor             v1.16B, v1.16B, v5.16B
+        ld2             {v2.4S, v3.4S}, [x0], #32
 .rept 3
-        st2             {v0.4s, v1.4s}, [x1], #32
-        eor             v3.16b, v3.16b, v5.16b
-        ld2             {v0.4s, v1.4s}, [x0], #32
-        st2             {v2.4s, v3.4s}, [x1], #32
-        eor             v1.16b, v1.16b, v5.16b
-        ld2             {v2.4s, v3.4s}, [x0], #32
+        st2             {v0.4S, v1.4S}, [x1], #32
+        eor             v3.16B, v3.16B, v5.16B
+        ld2             {v0.4S, v1.4S}, [x0], #32
+        st2             {v2.4S, v3.4S}, [x1], #32
+        eor             v1.16B, v1.16B, v5.16B
+        ld2             {v2.4S, v3.4S}, [x0], #32
 .endr
-        eor             v3.16b, v3.16b, v5.16b
-        st2             {v0.4s, v1.4s}, [x1], #32
-        st2             {v2.4s, v3.4s}, [x1], #32
+        eor             v3.16B, v3.16B, v5.16B
+        st2             {v0.4S, v1.4S}, [x1], #32
+        st2             {v2.4S, v3.4S}, [x1], #32
        ret
 endfunc

@@ -97,26 +97,26 @@ function ff_sbr_qmf_pre_shuffle_neon, export=1
        add             x2, x0, #64*4
        mov             x3, #-16
        mov             x4, #-4
-        movi            v6.4s, #1<<7, lsl #24
-        ld1             {v0.2s}, [x0], #8
-        st1             {v0.2s}, [x2], #8
+        movi            v6.4S, #1<<7, lsl #24
+        ld1             {v0.2S}, [x0], #8
+        st1             {v0.2S}, [x2], #8
 .rept 7
-        ld1             {v1.4s}, [x1], x3
-        ld1             {v2.4s}, [x0], #16
-        eor             v1.16b, v1.16b, v6.16b
-        rev64           v1.4s, v1.4s
-        ext             v1.16b, v1.16b, v1.16b, #8
-        st2             {v1.4s, v2.4s}, [x2], #32
+        ld1             {v1.4S}, [x1], x3
+        ld1             {v2.4S}, [x0], #16
+        eor             v1.16B, v1.16B, v6.16B
+        rev64           v1.4S, v1.4S
+        ext             v1.16B, v1.16B, v1.16B, #8
+        st2             {v1.4S, v2.4S}, [x2], #32
 .endr
        add             x1, x1, #8
-        ld1             {v1.2s}, [x1], x4
-        ld1             {v2.2s}, [x0], #8
-        ld1             {v1.s}[3], [x1]
-        ld1             {v2.s}[2], [x0]
-        eor             v1.16b, v1.16b, v6.16b
-        rev64           v1.4s, v1.4s
-        st2             {v1.2s, v2.2s}, [x2], #16
-        st2             {v1.s, v2.s}[2], [x2]
+        ld1             {v1.2S}, [x1], x4
+        ld1             {v2.2S}, [x0], #8
+        ld1             {v1.S}[3], [x1]
+        ld1             {v2.S}[2], [x0]
+        eor             v1.16B, v1.16B, v6.16B
+        rev64           v1.4S, v1.4S
+        st2             {v1.2S, v2.2S}, [x2], #16
+        st2             {v1.S, v2.S}[2], [x2]
        ret
 endfunc

@@ -124,13 +124,13 @@ function ff_sbr_qmf_post_shuffle_neon, export=1
        add             x2, x1, #60*4
        mov             x3, #-16
        mov             x4, #32
-        movi            v6.4s, #1<<7, lsl #24
-1:      ld1             {v0.4s}, [x2], x3
-        ld1             {v1.4s}, [x1], #16
-        eor             v0.16b, v0.16b, v6.16b
-        rev64           v0.4s, v0.4s
-        ext             v0.16b, v0.16b, v0.16b, #8
-        st2             {v0.4s, v1.4s}, [x0], #32
+        movi            v6.4S, #1<<7, lsl #24
+1:      ld1             {v0.4S}, [x2], x3
+        ld1             {v1.4S}, [x1], #16
+        eor             v0.16B, v0.16B, v6.16B
+        rev64           v0.4S, v0.4S
+        ext             v0.16B, v0.16B, v0.16B, #8
+        st2             {v0.4S, v1.4S}, [x0], #32
        subs            x4, x4, #4
        b.gt            1b
        ret
@@ -141,13 +141,13 @@ function ff_sbr_qmf_deint_neg_neon, export=1
        add             x2, x0, #60*4
        mov             x3, #-32
        mov             x4, #32
-        movi            v2.4s, #1<<7, lsl #24
-1:      ld2             {v0.4s, v1.4s}, [x1], x3
-        eor             v0.16b, v0.16b, v2.16b
-        rev64           v1.4s, v1.4s
-        ext             v1.16b, v1.16b, v1.16b, #8
-        st1             {v0.4s}, [x2]
-        st1             {v1.4s}, [x0], #16
+        movi            v2.4S, #1<<7, lsl #24
+1:      ld2             {v0.4S, v1.4S}, [x1], x3
+        eor             v0.16B, v0.16B, v2.16B
+        rev64           v1.4S, v1.4S
+        ext             v1.16B, v1.16B, v1.16B, #8
+        st1             {v0.4S}, [x2]
+        st1             {v1.4S}, [x0], #16
        sub             x2, x2, #16
        subs            x4, x4, #4
        b.gt            1b
@@ -159,16 +159,16 @@ function ff_sbr_qmf_deint_bfly_neon, export=1
        add             x3, x0, #124*4
        mov             x4, #64
        mov             x5, #-16
-1:      ld1             {v0.4s}, [x1], #16
-        ld1             {v1.4s}, [x2], x5
-        rev64           v2.4s, v0.4s
-        ext             v2.16b, v2.16b, v2.16b, #8
-        rev64           v3.4s, v1.4s
-        ext             v3.16b, v3.16b, v3.16b, #8
-        fadd            v1.4s, v1.4s, v2.4s
-        fsub            v0.4s, v0.4s, v3.4s
-        st1             {v0.4s}, [x0], #16
-        st1             {v1.4s}, [x3], x5
+1:      ld1             {v0.4S}, [x1], #16
+        ld1             {v1.4S}, [x2], x5
+        rev64           v2.4S, v0.4S
+        ext             v2.16B, v2.16B, v2.16B, #8
+        rev64           v3.4S, v1.4S
+        ext             v3.16B, v3.16B, v3.16B, #8
+        fadd            v1.4S, v1.4S, v2.4S
+        fsub            v0.4S, v0.4S, v3.4S
+        st1             {v0.4S}, [x0], #16
+        st1             {v1.4S}, [x3], x5
        subs            x4, x4, #4
        b.gt            1b
        ret
@@ -178,32 +178,32 @@ function ff_sbr_hf_gen_neon, export=1
        sxtw            x4, w4
        sxtw            x5, w5
        movrel          x6, factors
-        ld1             {v7.4s}, [x6]
-        dup             v1.4s, v0.s[0]
-        mov             v2.8b, v1.8b
-        mov             v2.s[2], v7.s[0]
-        mov             v2.s[3], v7.s[0]
-        fmul            v1.4s, v1.4s, v2.4s
-        ld1             {v0.d}[0], [x3]
-        ld1             {v0.d}[1], [x2]
-        fmul            v0.4s, v0.4s, v1.4s
-        fmul            v1.4s, v0.4s, v7.4s
-        rev64           v0.4s, v0.4s
+        ld1             {v7.4S}, [x6]
+        dup             v1.4S, v0.S[0]
+        mov             v2.8B, v1.8B
+        mov             v2.S[2], v7.S[0]
+        mov             v2.S[3], v7.S[0]
+        fmul            v1.4S, v1.4S, v2.4S
+        ld1             {v0.D}[0], [x3]
+        ld1             {v0.D}[1], [x2]
+        fmul            v0.4S, v0.4S, v1.4S
+        fmul            v1.4S, v0.4S, v7.4S
+        rev64           v0.4S, v0.4S
        sub             x7, x5, x4
        add             x0, x0, x4, lsl #3
        add             x1, x1, x4, lsl #3
        sub             x1, x1, #16
-1:      ld1             {v2.4s}, [x1], #16
-        ld1             {v3.2s}, [x1]
-        fmul            v4.4s, v2.4s, v1.4s
-        fmul            v5.4s, v2.4s, v0.4s
-        faddp           v4.4s, v4.4s, v4.4s
-        faddp           v5.4s, v5.4s, v5.4s
-        faddp           v4.4s, v4.4s, v4.4s
-        faddp           v5.4s, v5.4s, v5.4s
-        mov             v4.s[1], v5.s[0]
-        fadd            v4.2s, v4.2s, v3.2s
-        st1             {v4.2s}, [x0], #8
+1:      ld1             {v2.4S}, [x1], #16
+        ld1             {v3.2S}, [x1]
+        fmul            v4.4S, v2.4S, v1.4S
+        fmul            v5.4S, v2.4S, v0.4S
+        faddp           v4.4S, v4.4S, v4.4S
+        faddp           v5.4S, v5.4S, v5.4S
+        faddp           v4.4S, v4.4S, v4.4S
+        faddp           v5.4S, v5.4S, v5.4S
+        mov             v4.S[1], v5.S[0]
+        fadd            v4.2S, v4.2S, v3.2S
+        st1             {v4.2S}, [x0], #8
        sub             x1, x1, #8
        subs            x7, x7, #1
        b.gt            1b
@@ -215,10 +215,10 @@ function ff_sbr_hf_g_filt_neon, export=1
        sxtw            x4, w4
        mov             x5, #40*2*4
        add             x1, x1, x4, lsl #3
-1:      ld1             {v0.2s}, [x1], x5
-        ld1             {v1.s}[0], [x2], #4
-        fmul            v2.4s, v0.4s, v1.s[0]
-        st1             {v2.2s}, [x0], #8
+1:      ld1             {v0.2S}, [x1], x5
+        ld1             {v1.S}[0], [x2], #4
+        fmul            v2.4S, v0.4S, v1.S[0]
+        st1             {v2.2S}, [x0], #8
        subs            x3, x3, #1
        b.gt            1b
        ret
@@ -227,46 +227,46 @@ endfunc
 function ff_sbr_autocorrelate_neon, export=1
        mov             x2, #38
        movrel          x3, factors
-        ld1             {v0.4s}, [x3]
-        movi            v1.4s, #0
-        movi            v2.4s, #0
-        movi            v3.4s, #0
-        ld1             {v4.2s}, [x0], #8
-        ld1             {v5.2s}, [x0], #8
-        fmul            v16.2s, v4.2s, v4.2s
-        fmul            v17.2s, v5.2s, v4.s[0]
-        fmul            v18.2s, v5.2s, v4.s[1]
-1:      ld1             {v5.d}[1], [x0], #8
-        fmla            v1.2s, v4.2s, v4.2s
-        fmla            v2.4s, v5.4s, v4.s[0]
-        fmla            v3.4s, v5.4s, v4.s[1]
-        mov             v4.d[0], v5.d[0]
-        mov             v5.d[0], v5.d[1]
+        ld1             {v0.4S}, [x3]
+        movi            v1.4S, #0
+        movi            v2.4S, #0
+        movi            v3.4S, #0
+        ld1             {v4.2S}, [x0], #8
+        ld1             {v5.2S}, [x0], #8
+        fmul            v16.2S, v4.2S, v4.2S
+        fmul            v17.2S, v5.2S, v4.S[0]
+        fmul            v18.2S, v5.2S, v4.S[1]
+1:      ld1             {v5.D}[1], [x0], #8
+        fmla            v1.2S, v4.2S, v4.2S
+        fmla            v2.4S, v5.4S, v4.S[0]
+        fmla            v3.4S, v5.4S, v4.S[1]
+        mov             v4.D[0], v5.D[0]
+        mov             v5.D[0], v5.D[1]
        subs            x2, x2, #1
        b.gt            1b
-        fmul            v19.2s, v4.2s, v4.2s
-        fmul            v20.2s, v5.2s, v4.s[0]
-        fmul            v21.2s, v5.2s, v4.s[1]
-        fadd            v22.4s, v2.4s, v20.4s
-        fsub            v22.4s, v22.4s, v17.4s
-        fadd            v23.4s, v3.4s, v21.4s
-        fsub            v23.4s, v23.4s, v18.4s
-        rev64           v23.4s, v23.4s
-        fmul            v23.4s, v23.4s, v0.4s
-        fadd            v22.4s, v22.4s, v23.4s
-        st1             {v22.4s}, [x1], #16
-        fadd            v23.2s, v1.2s, v19.2s
-        fsub            v23.2s, v23.2s, v16.2s
-        faddp           v23.2s, v23.2s, v23.2s
-        st1             {v23.s}[0], [x1]
+        fmul            v19.2S, v4.2S, v4.2S
+        fmul            v20.2S, v5.2S, v4.S[0]
+        fmul            v21.2S, v5.2S, v4.S[1]
+        fadd            v22.4S, v2.4S, v20.4S
+        fsub            v22.4S, v22.4S, v17.4S
+        fadd            v23.4S, v3.4S, v21.4S
+        fsub            v23.4S, v23.4S, v18.4S
+        rev64           v23.4S, v23.4S
+        fmul            v23.4S, v23.4S, v0.4S
+        fadd            v22.4S, v22.4S, v23.4S
+        st1             {v22.4S}, [x1], #16
+        fadd            v23.2S, v1.2S, v19.2S
+        fsub            v23.2S, v23.2S, v16.2S
+        faddp           v23.2S, v23.2S, v23.2S
+        st1             {v23.S}[0], [x1]
        add             x1, x1, #8
-        rev64           v3.2s, v3.2s
-        fmul            v3.2s, v3.2s, v0.2s
-        fadd            v2.2s, v2.2s, v3.2s
-        st1             {v2.2s}, [x1]
+        rev64           v3.2S, v3.2S
+        fmul            v3.2S, v3.2S, v0.2S
+        fadd            v2.2S, v2.2S, v3.2S
+        st1             {v2.2S}, [x1]
        add             x1, x1, #16
-        faddp           v1.2s, v1.2s, v1.2s
-        st1             {v1.s}[0], [x1]
+        faddp           v1.2S, v1.2S, v1.2S
+        st1             {v1.S}[0], [x1]
        ret
 endfunc

@@ -278,25 +278,25 @@ endfunc
 1:      and             x3, x3, #0x1ff
        add             x8, x7, x3, lsl #3
        add             x3, x3, #2
-        ld1             {v2.4s}, [x0]
-        ld1             {v3.2s}, [x1], #8
-        ld1             {v4.2s}, [x2], #8
-        ld1             {v5.4s}, [x8]
-        mov             v6.16b, v2.16b
-        zip1            v3.4s, v3.4s, v3.4s
-        zip1            v4.4s, v4.4s, v4.4s
-        fmla            v6.4s, v1.4s, v3.4s
-        fmla            v2.4s, v5.4s, v4.4s
-        fcmeq           v7.4s, v3.4s, #0
-        bif             v2.16b, v6.16b, v7.16b
-        st1             {v2.4s}, [x0], #16
+        ld1             {v2.4S}, [x0]
+        ld1             {v3.2S}, [x1], #8
+        ld1             {v4.2S}, [x2], #8
+        ld1             {v5.4S}, [x8]
+        mov             v6.16B, v2.16B
+        zip1            v3.4S, v3.4S, v3.4S
+        zip1            v4.4S, v4.4S, v4.4S
+        fmla            v6.4S, v1.4S, v3.4S
+        fmla            v2.4S, v5.4S, v4.4S
+        fcmeq           v7.4S, v3.4S, #0
+        bif             v2.16B, v6.16B, v7.16B
+        st1             {v2.4S}, [x0], #16
        subs            x5, x5, #2
        b.gt            1b
 .endm

 function ff_sbr_hf_apply_noise_0_neon, export=1
        movrel          x9, phi_noise_0
-        ld1             {v1.4s}, [x9]
+        ld1             {v1.4S}, [x9]
        apply_noise_common
        ret
 endfunc
@@ -305,14 +305,14 @@ function ff_sbr_hf_apply_noise_1_neon, export=1
        movrel          x9, phi_noise_1
        and             x4, x4, #1
        add             x9, x9, x4, lsl #4
-        ld1             {v1.4s}, [x9]
+        ld1             {v1.4S}, [x9]
        apply_noise_common
        ret
 endfunc

 function ff_sbr_hf_apply_noise_2_neon, export=1
        movrel          x9, phi_noise_2
-        ld1             {v1.4s}, [x9]
+        ld1             {v1.4S}, [x9]
        apply_noise_common
        ret
 endfunc
@@ -321,7 +321,7 @@ function ff_sbr_hf_apply_noise_3_neon, export=1
        movrel          x9, phi_noise_3
        and             x4, x4, #1
        add             x9, x9, x4, lsl #4
-        ld1             {v1.4s}, [x9]
+        ld1             {v1.4S}, [x9]
        apply_noise_common
        ret
 endfunc
--- a/libavcodec/aarch64/simple_idct_neon.S
+++ b/libavcodec/aarch64/simple_idct_neon.S
@@ -54,7 +54,7 @@ endconst
        prfm            pldl1keep, [\data]
        mov             x10, x30
        movrel          x3, idct_coeff_neon
-        ld1             {v0.2d}, [x3]
+        ld1             {v0.2D}, [x3]
 .endm

 .macro idct_end
@@ -74,146 +74,146 @@ endconst
 .endm

 .macro idct_col4_top y1, y2, y3, y4, i, l
-        smull\i         v7.4s,  \y3\l, z2
-        smull\i         v16.4s, \y3\l, z6
-        smull\i         v17.4s, \y2\l, z1
-        add             v19.4s, v23.4s, v7.4s
-        smull\i         v18.4s, \y2\l, z3
-        add             v20.4s, v23.4s, v16.4s
-        smull\i         v5.4s,  \y2\l, z5
-        sub             v21.4s, v23.4s, v16.4s
-        smull\i         v6.4s,  \y2\l, z7
-        sub             v22.4s, v23.4s, v7.4s
+        smull\i         v7.4S,  \y3\l, z2
+        smull\i         v16.4S, \y3\l, z6
+        smull\i         v17.4S, \y2\l, z1
+        add             v19.4S, v23.4S, v7.4S
+        smull\i         v18.4S, \y2\l, z3
+        add             v20.4S, v23.4S, v16.4S
+        smull\i         v5.4S,  \y2\l, z5
+        sub             v21.4S, v23.4S, v16.4S
+        smull\i         v6.4S,  \y2\l, z7
+        sub             v22.4S, v23.4S, v7.4S

-        smlal\i         v17.4s, \y4\l, z3
-        smlsl\i         v18.4s, \y4\l, z7
-        smlsl\i         v5.4s,  \y4\l, z1
-        smlsl\i         v6.4s,  \y4\l, z5
+        smlal\i         v17.4S, \y4\l, z3
+        smlsl\i         v18.4S, \y4\l, z7
+        smlsl\i         v5.4S,  \y4\l, z1
+        smlsl\i         v6.4S,  \y4\l, z5
 .endm

 .macro idct_row4_neon y1, y2, y3, y4, pass
-        ld1             {\y1\().2d,\y2\().2d}, [x2], #32
-        movi            v23.4s, #1<<2, lsl #8
-        orr             v5.16b, \y1\().16b, \y2\().16b
-        ld1             {\y3\().2d,\y4\().2d}, [x2], #32
-        orr             v6.16b, \y3\().16b, \y4\().16b
-        orr             v5.16b, v5.16b, v6.16b
-        mov             x3, v5.d[1]
-        smlal           v23.4s, \y1\().4h, z4
+        ld1             {\y1\().2D,\y2\().2D}, [x2], #32
+        movi            v23.4S, #1<<2, lsl #8
+        orr             v5.16B, \y1\().16B, \y2\().16B
+        ld1             {\y3\().2D,\y4\().2D}, [x2], #32
+        orr             v6.16B, \y3\().16B, \y4\().16B
+        orr             v5.16B, v5.16B, v6.16B
+        mov             x3, v5.D[1]
+        smlal           v23.4S, \y1\().4H, z4

-        idct_col4_top   \y1, \y2, \y3, \y4, 1, .4h
+        idct_col4_top   \y1, \y2, \y3, \y4, 1, .4H

        cmp             x3, #0
        b.eq            \pass\()f

-        smull2          v7.4s, \y1\().8h, z4
-        smlal2          v17.4s, \y2\().8h, z5
-        smlsl2          v18.4s, \y2\().8h, z1
-        smull2          v16.4s, \y3\().8h, z2
-        smlal2          v5.4s, \y2\().8h, z7
-        add             v19.4s, v19.4s, v7.4s
-        sub             v20.4s, v20.4s, v7.4s
-        sub             v21.4s, v21.4s, v7.4s
-        add             v22.4s, v22.4s, v7.4s
-        smlal2          v6.4s, \y2\().8h, z3
-        smull2          v7.4s, \y3\().8h, z6
-        smlal2          v17.4s, \y4\().8h, z7
-        smlsl2          v18.4s, \y4\().8h, z5
-        smlal2          v5.4s, \y4\().8h, z3
-        smlsl2          v6.4s, \y4\().8h, z1
-        add             v19.4s, v19.4s, v7.4s
-        sub             v20.4s, v20.4s, v16.4s
-        add             v21.4s, v21.4s, v16.4s
-        sub             v22.4s, v22.4s, v7.4s
+        smull2          v7.4S, \y1\().8H, z4
+        smlal2          v17.4S, \y2\().8H, z5
+        smlsl2          v18.4S, \y2\().8H, z1
+        smull2          v16.4S, \y3\().8H, z2
+        smlal2          v5.4S, \y2\().8H, z7
+        add             v19.4S, v19.4S, v7.4S
+        sub             v20.4S, v20.4S, v7.4S
+        sub             v21.4S, v21.4S, v7.4S
+        add             v22.4S, v22.4S, v7.4S
+        smlal2          v6.4S, \y2\().8H, z3
+        smull2          v7.4S, \y3\().8H, z6
+        smlal2          v17.4S, \y4\().8H, z7
+        smlsl2          v18.4S, \y4\().8H, z5
+        smlal2          v5.4S, \y4\().8H, z3
+        smlsl2          v6.4S, \y4\().8H, z1
+        add             v19.4S, v19.4S, v7.4S
+        sub             v20.4S, v20.4S, v16.4S
+        add             v21.4S, v21.4S, v16.4S
+        sub             v22.4S, v22.4S, v7.4S

 \pass:  add             \y3\().4S, v19.4S, v17.4S
-        add             \y4\().4s, v20.4s, v18.4s
-        shrn            \y1\().4h, \y3\().4s, #ROW_SHIFT
-        shrn            \y2\().4h, \y4\().4s, #ROW_SHIFT
-        add             v7.4s, v21.4s, v5.4s
-        add             v16.4s, v22.4s, v6.4s
-        shrn            \y3\().4h, v7.4s, #ROW_SHIFT
-        shrn            \y4\().4h, v16.4s, #ROW_SHIFT
-        sub             v22.4s, v22.4s, v6.4s
-        sub             v19.4s, v19.4s, v17.4s
-        sub             v21.4s, v21.4s, v5.4s
-        shrn2           \y1\().8h, v22.4s, #ROW_SHIFT
-        sub             v20.4s, v20.4s, v18.4s
-        shrn2           \y2\().8h, v21.4s, #ROW_SHIFT
-        shrn2           \y3\().8h, v20.4s, #ROW_SHIFT
-        shrn2           \y4\().8h, v19.4s, #ROW_SHIFT
+        add             \y4\().4S, v20.4S, v18.4S
+        shrn            \y1\().4H, \y3\().4S, #ROW_SHIFT
+        shrn            \y2\().4H, \y4\().4S, #ROW_SHIFT
+        add             v7.4S, v21.4S, v5.4S
+        add             v16.4S, v22.4S, v6.4S
+        shrn            \y3\().4H, v7.4S, #ROW_SHIFT
+        shrn            \y4\().4H, v16.4S, #ROW_SHIFT
+        sub             v22.4S, v22.4S, v6.4S
+        sub             v19.4S, v19.4S, v17.4S
+        sub             v21.4S, v21.4S, v5.4S
+        shrn2           \y1\().8H, v22.4S, #ROW_SHIFT
+        sub             v20.4S, v20.4S, v18.4S
+        shrn2           \y2\().8H, v21.4S, #ROW_SHIFT
+        shrn2           \y3\().8H, v20.4S, #ROW_SHIFT
+        shrn2           \y4\().8H, v19.4S, #ROW_SHIFT

-        trn1            v16.8h, \y1\().8h, \y2\().8h
-        trn2            v17.8h, \y1\().8h, \y2\().8h
-        trn1            v18.8h, \y3\().8h, \y4\().8h
-        trn2            v19.8h, \y3\().8h, \y4\().8h
-        trn1            \y1\().4s, v16.4s, v18.4s
-        trn1            \y2\().4s, v17.4s, v19.4s
-        trn2            \y3\().4s, v16.4s, v18.4s
-        trn2            \y4\().4s, v17.4s, v19.4s
+        trn1            v16.8H, \y1\().8H, \y2\().8H
+        trn2            v17.8H, \y1\().8H, \y2\().8H
+        trn1            v18.8H, \y3\().8H, \y4\().8H
+        trn2            v19.8H, \y3\().8H, \y4\().8H
+        trn1            \y1\().4S, v16.4S, v18.4S
+        trn1            \y2\().4S, v17.4S, v19.4S
+        trn2            \y3\().4S, v16.4S, v18.4S
+        trn2            \y4\().4S, v17.4S, v19.4S
 .endm

 .macro declare_idct_col4_neon i, l
 function idct_col4_neon\i
-        dup             v23.4h, z4c
+        dup             v23.4H, z4c
 .if \i == 1
-        add             v23.4h, v23.4h, v24.4h
+        add             v23.4H, v23.4H, v24.4H
 .else
-        mov             v5.d[0], v24.d[1]
-        add             v23.4h, v23.4h, v5.4h
+        mov             v5.D[0], v24.D[1]
+        add             v23.4H, v23.4H, v5.4H
 .endif
-        smull           v23.4s, v23.4h, z4
+        smull           v23.4S, v23.4H, z4

        idct_col4_top   v24, v25, v26, v27, \i, \l

-        mov             x4, v28.d[\i - 1]
-        mov             x5, v29.d[\i - 1]
+        mov             x4, v28.D[\i - 1]
+        mov             x5, v29.D[\i - 1]
        cmp             x4, #0
        b.eq            1f

-        smull\i         v7.4s,  v28\l,  z4
-        add             v19.4s, v19.4s, v7.4s
-        sub             v20.4s, v20.4s, v7.4s
-        sub             v21.4s, v21.4s, v7.4s
-        add             v22.4s, v22.4s, v7.4s
+        smull\i         v7.4S,  v28\l,  z4
+        add             v19.4S, v19.4S, v7.4S
+        sub             v20.4S, v20.4S, v7.4S
+        sub             v21.4S, v21.4S, v7.4S
+        add             v22.4S, v22.4S, v7.4S

-1:      mov             x4, v30.d[\i - 1]
+1:      mov             x4, v30.D[\i - 1]
        cmp             x5, #0
        b.eq            2f

-        smlal\i         v17.4s, v29\l, z5
-        smlsl\i         v18.4s, v29\l, z1
-        smlal\i         v5.4s,  v29\l, z7
-        smlal\i         v6.4s,  v29\l, z3
+        smlal\i         v17.4S, v29\l, z5
+        smlsl\i         v18.4S, v29\l, z1
+        smlal\i         v5.4S,  v29\l, z7
+        smlal\i         v6.4S,  v29\l, z3

-2:      mov             x5, v31.d[\i - 1]
+2:      mov             x5, v31.D[\i - 1]
        cmp             x4, #0
        b.eq            3f

-        smull\i         v7.4s,  v30\l, z6
-        smull\i         v16.4s, v30\l, z2
-        add             v19.4s, v19.4s, v7.4s
-        sub             v22.4s, v22.4s, v7.4s
-        sub             v20.4s, v20.4s, v16.4s
-        add             v21.4s, v21.4s, v16.4s
+        smull\i         v7.4S,  v30\l, z6
+        smull\i         v16.4S, v30\l, z2
+        add             v19.4S, v19.4S, v7.4S
+        sub             v22.4S, v22.4S, v7.4S
+        sub             v20.4S, v20.4S, v16.4S
+        add             v21.4S, v21.4S, v16.4S

 3:      cmp             x5, #0
        b.eq            4f

-        smlal\i         v17.4s, v31\l, z7
-        smlsl\i         v18.4s, v31\l, z5
-        smlal\i         v5.4s,  v31\l, z3
-        smlsl\i         v6.4s,  v31\l, z1
+        smlal\i         v17.4S, v31\l, z7
+        smlsl\i         v18.4S, v31\l, z5
+        smlal\i         v5.4S,  v31\l, z3
+        smlsl\i         v6.4S,  v31\l, z1

-4:      addhn           v7.4h, v19.4s, v17.4s
-        addhn2          v7.8h, v20.4s, v18.4s
-        subhn           v18.4h, v20.4s, v18.4s
-        subhn2          v18.8h, v19.4s, v17.4s
+4:      addhn           v7.4H, v19.4S, v17.4S
+        addhn2          v7.8H, v20.4S, v18.4S
+        subhn           v18.4H, v20.4S, v18.4S
+        subhn2          v18.8H, v19.4S, v17.4S

-        addhn           v16.4h, v21.4s, v5.4s
-        addhn2          v16.8h, v22.4s, v6.4s
-        subhn           v17.4h, v22.4s, v6.4s
-        subhn2          v17.8h, v21.4s, v5.4s
+        addhn           v16.4H, v21.4S, v5.4S
+        addhn2          v16.8H, v22.4S, v6.4S
+        subhn           v17.4H, v22.4S, v6.4S
+        subhn2          v17.8H, v21.4S, v5.4S

        ret
 endfunc
@@ -229,33 +229,33 @@ function ff_simple_idct_put_neon, export=1
        idct_row4_neon  v28, v29, v30, v31, 2
        bl              idct_col4_neon1

-        sqshrun         v1.8b,  v7.8h, #COL_SHIFT-16
-        sqshrun2        v1.16b, v16.8h, #COL_SHIFT-16
-        sqshrun         v3.8b,  v17.8h, #COL_SHIFT-16
-        sqshrun2        v3.16b, v18.8h, #COL_SHIFT-16
+        sqshrun         v1.8B,  v7.8H, #COL_SHIFT-16
+        sqshrun2        v1.16B, v16.8H, #COL_SHIFT-16
+        sqshrun         v3.8B,  v17.8H, #COL_SHIFT-16
+        sqshrun2        v3.16B, v18.8H, #COL_SHIFT-16

        bl              idct_col4_neon2

-        sqshrun         v2.8b,  v7.8h, #COL_SHIFT-16
-        sqshrun2        v2.16b, v16.8h, #COL_SHIFT-16
-        sqshrun         v4.8b,  v17.8h, #COL_SHIFT-16
-        sqshrun2        v4.16b, v18.8h, #COL_SHIFT-16
+        sqshrun         v2.8B,  v7.8H, #COL_SHIFT-16
+        sqshrun2        v2.16B, v16.8H, #COL_SHIFT-16
+        sqshrun         v4.8B,  v17.8H, #COL_SHIFT-16
+        sqshrun2        v4.16B, v18.8H, #COL_SHIFT-16

-        zip1            v16.4s, v1.4s, v2.4s
-        zip2            v17.4s, v1.4s, v2.4s
+        zip1            v16.4S, v1.4S, v2.4S
+        zip2            v17.4S, v1.4S, v2.4S

-        st1             {v16.d}[0], [x0], x1
-        st1             {v16.d}[1], [x0], x1
+        st1             {v16.D}[0], [x0], x1
+        st1             {v16.D}[1], [x0], x1

-        zip1            v18.4s, v3.4s, v4.4s
-        zip2            v19.4s, v3.4s, v4.4s
+        zip1            v18.4S, v3.4S, v4.4S
+        zip2            v19.4S, v3.4S, v4.4S

-        st1             {v17.d}[0], [x0], x1
-        st1             {v17.d}[1], [x0], x1
-        st1             {v18.d}[0], [x0], x1
-        st1             {v18.d}[1], [x0], x1
-        st1             {v19.d}[0], [x0], x1
-        st1             {v19.d}[1], [x0], x1
+        st1             {v17.D}[0], [x0], x1
+        st1             {v17.D}[1], [x0], x1
+        st1             {v18.D}[0], [x0], x1
+        st1             {v18.D}[1], [x0], x1
+        st1             {v19.D}[0], [x0], x1
+        st1             {v19.D}[1], [x0], x1

        idct_end
 endfunc
@@ -267,59 +267,59 @@ function ff_simple_idct_add_neon, export=1
        idct_row4_neon  v28, v29, v30, v31, 2
        bl              idct_col4_neon1

-        sshr            v1.8h, v7.8h, #COL_SHIFT-16
-        sshr            v2.8h, v16.8h, #COL_SHIFT-16
-        sshr            v3.8h, v17.8h, #COL_SHIFT-16
-        sshr            v4.8h, v18.8h, #COL_SHIFT-16
+        sshr            v1.8H, v7.8H, #COL_SHIFT-16
+        sshr            v2.8H, v16.8H, #COL_SHIFT-16
+        sshr            v3.8H, v17.8H, #COL_SHIFT-16
+        sshr            v4.8H, v18.8H, #COL_SHIFT-16

        bl              idct_col4_neon2

-        sshr            v7.8h, v7.8h, #COL_SHIFT-16
-        sshr            v16.8h, v16.8h, #COL_SHIFT-16
-        sshr            v17.8h, v17.8h, #COL_SHIFT-16
-        sshr            v18.8h, v18.8h, #COL_SHIFT-16
+        sshr            v7.8H, v7.8H, #COL_SHIFT-16
+        sshr            v16.8H, v16.8H, #COL_SHIFT-16
+        sshr            v17.8H, v17.8H, #COL_SHIFT-16
+        sshr            v18.8H, v18.8H, #COL_SHIFT-16

        mov             x9,  x0
-        ld1             {v19.d}[0], [x0], x1
-        zip1            v23.2d, v1.2d, v7.2d
-        zip2            v24.2d, v1.2d, v7.2d
-        ld1             {v19.d}[1], [x0], x1
-        zip1            v25.2d, v2.2d, v16.2d
-        zip2            v26.2d, v2.2d, v16.2d
-        ld1             {v20.d}[0], [x0], x1
-        zip1            v27.2d, v3.2d, v17.2d
-        zip2            v28.2d, v3.2d, v17.2d
-        ld1             {v20.d}[1], [x0], x1
-        zip1            v29.2d, v4.2d, v18.2d
-        zip2            v30.2d, v4.2d, v18.2d
-        ld1             {v21.d}[0], [x0], x1
-        uaddw           v23.8h, v23.8h, v19.8b
-        uaddw2          v24.8h, v24.8h, v19.16b
-        ld1             {v21.d}[1], [x0], x1
-        sqxtun          v23.8b, v23.8h
-        sqxtun2         v23.16b, v24.8h
-        ld1             {v22.d}[0], [x0], x1
-        uaddw           v24.8h, v25.8h, v20.8b
-        uaddw2          v25.8h, v26.8h, v20.16b
-        ld1             {v22.d}[1], [x0], x1
-        sqxtun          v24.8b, v24.8h
-        sqxtun2         v24.16b, v25.8h
-        st1             {v23.d}[0], [x9], x1
-        uaddw           v25.8h, v27.8h, v21.8b
-        uaddw2          v26.8h, v28.8h, v21.16b
-        st1             {v23.d}[1], [x9], x1
-        sqxtun          v25.8b, v25.8h
-        sqxtun2         v25.16b, v26.8h
-        st1             {v24.d}[0], [x9], x1
-        uaddw           v26.8h, v29.8h, v22.8b
-        uaddw2          v27.8h, v30.8h, v22.16b
-        st1             {v24.d}[1], [x9], x1
-        sqxtun          v26.8b, v26.8h
-        sqxtun2         v26.16b, v27.8h
-        st1             {v25.d}[0], [x9], x1
-        st1             {v25.d}[1], [x9], x1
-        st1             {v26.d}[0], [x9], x1
-        st1             {v26.d}[1], [x9], x1
+        ld1             {v19.D}[0], [x0], x1
+        zip1            v23.2D, v1.2D, v7.2D
+        zip2            v24.2D, v1.2D, v7.2D
+        ld1             {v19.D}[1], [x0], x1
+        zip1            v25.2D, v2.2D, v16.2D
+        zip2            v26.2D, v2.2D, v16.2D
+        ld1             {v20.D}[0], [x0], x1
+        zip1            v27.2D, v3.2D, v17.2D
+        zip2            v28.2D, v3.2D, v17.2D
+        ld1             {v20.D}[1], [x0], x1
+        zip1            v29.2D, v4.2D, v18.2D
+        zip2            v30.2D, v4.2D, v18.2D
+        ld1             {v21.D}[0], [x0], x1
+        uaddw           v23.8H, v23.8H, v19.8B
+        uaddw2          v24.8H, v24.8H, v19.16B
+        ld1             {v21.D}[1], [x0], x1
+        sqxtun          v23.8B, v23.8H
+        sqxtun2         v23.16B, v24.8H
+        ld1             {v22.D}[0], [x0], x1
+        uaddw           v24.8H, v25.8H, v20.8B
+        uaddw2          v25.8H, v26.8H, v20.16B
+        ld1             {v22.D}[1], [x0], x1
+        sqxtun          v24.8B, v24.8H
+        sqxtun2         v24.16B, v25.8H
+        st1             {v23.D}[0], [x9], x1
+        uaddw           v25.8H, v27.8H, v21.8B
+        uaddw2          v26.8H, v28.8H, v21.16B
+        st1             {v23.D}[1], [x9], x1
+        sqxtun          v25.8B, v25.8H
+        sqxtun2         v25.16B, v26.8H
+        st1             {v24.D}[0], [x9], x1
+        uaddw           v26.8H, v29.8H, v22.8B
+        uaddw2          v27.8H, v30.8H, v22.16B
+        st1             {v24.D}[1], [x9], x1
+        sqxtun          v26.8B, v26.8H
+        sqxtun2         v26.16B, v27.8H
+        st1             {v25.D}[0], [x9], x1
+        st1             {v25.D}[1], [x9], x1
+        st1             {v26.D}[0], [x9], x1
+        st1             {v26.D}[1], [x9], x1

        idct_end
 endfunc
@@ -333,30 +333,30 @@ function ff_simple_idct_neon, export=1
        sub             x2, x2, #128
        bl              idct_col4_neon1

-        sshr            v1.8h, v7.8h, #COL_SHIFT-16
-        sshr            v2.8h, v16.8h, #COL_SHIFT-16
-        sshr            v3.8h, v17.8h, #COL_SHIFT-16
-        sshr            v4.8h, v18.8h, #COL_SHIFT-16
+        sshr            v1.8H, v7.8H, #COL_SHIFT-16
+        sshr            v2.8H, v16.8H, #COL_SHIFT-16
+        sshr            v3.8H, v17.8H, #COL_SHIFT-16
+        sshr            v4.8H, v18.8H, #COL_SHIFT-16

        bl              idct_col4_neon2

-        sshr            v7.8h, v7.8h, #COL_SHIFT-16
-        sshr            v16.8h, v16.8h, #COL_SHIFT-16
-        sshr            v17.8h, v17.8h, #COL_SHIFT-16
-        sshr            v18.8h, v18.8h, #COL_SHIFT-16
+        sshr            v7.8H, v7.8H, #COL_SHIFT-16
+        sshr            v16.8H, v16.8H, #COL_SHIFT-16
+        sshr            v17.8H, v17.8H, #COL_SHIFT-16
+        sshr            v18.8H, v18.8H, #COL_SHIFT-16

-        zip1            v23.2d, v1.2d, v7.2d
-        zip2            v24.2d, v1.2d, v7.2d
-        st1             {v23.2d,v24.2d}, [x2], #32
-        zip1            v25.2d, v2.2d, v16.2d
-        zip2            v26.2d, v2.2d, v16.2d
-        st1             {v25.2d,v26.2d}, [x2], #32
-        zip1            v27.2d, v3.2d, v17.2d
-        zip2            v28.2d, v3.2d, v17.2d
-        st1             {v27.2d,v28.2d}, [x2], #32
-        zip1            v29.2d, v4.2d, v18.2d
-        zip2            v30.2d, v4.2d, v18.2d
-        st1             {v29.2d,v30.2d}, [x2], #32
+        zip1            v23.2D, v1.2D, v7.2D
+        zip2            v24.2D, v1.2D, v7.2D
+        st1             {v23.2D,v24.2D}, [x2], #32
+        zip1            v25.2D, v2.2D, v16.2D
+        zip2            v26.2D, v2.2D, v16.2D
+        st1             {v25.2D,v26.2D}, [x2], #32
+        zip1            v27.2D, v3.2D, v17.2D
+        zip2            v28.2D, v3.2D, v17.2D
+        st1             {v27.2D,v28.2D}, [x2], #32
+        zip1            v29.2D, v4.2D, v18.2D
+        zip2            v30.2D, v4.2D, v18.2D
+        st1             {v29.2D,v30.2D}, [x2], #32

        idct_end
 endfunc
--- a/libavcodec/aarch64/synth_filter_init.c
+++ b/libavcodec/aarch64/synth_filter_init.c
@@ -23,8 +23,15 @@
 #include "libavutil/aarch64/cpu.h"
 #include "libavutil/attributes.h"
 #include "libavutil/internal.h"
+#include "libavcodec/fft.h"
 #include "libavcodec/synth_filter.h"

+#include "asm-offsets.h"
+
+#if HAVE_NEON || HAVE_VFP
+AV_CHECK_OFFSET(FFTContext, imdct_half, IMDCT_HALF);
+#endif
+
 void ff_synth_filter_float_neon(AVTXContext *imdct,
                                float *synth_buf_ptr, int *synth_buf_offset,
                                float synth_buf2[32], const float window[512],
--- a/libavcodec/aarch64/synth_filter_neon.S
+++ b/libavcodec/aarch64/synth_filter_neon.S
@@ -19,6 +19,8 @@
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

+#include "asm-offsets.h"
+
 #include "libavutil/aarch64/asm.S"

 .macro inner_loop
--- a/libavcodec/aarch64/vp8dsp_neon.S
+++ b/libavcodec/aarch64/vp8dsp_neon.S
@@ -330,32 +330,32 @@ endfunc
        //   v17: hev

        // convert to signed value:
-        eor             v3.16b, v3.16b, v21.16b           // PS0 = P0 ^ 0x80
-        eor             v4.16b, v4.16b, v21.16b           // QS0 = Q0 ^ 0x80
+        eor            v3.16b, v3.16b, v21.16b           // PS0 = P0 ^ 0x80
+        eor            v4.16b, v4.16b, v21.16b           // QS0 = Q0 ^ 0x80

-        movi            v20.8h, #3
-        ssubl           v18.8h, v4.8b,  v3.8b             // QS0 - PS0
-        ssubl2          v19.8h, v4.16b, v3.16b            //   (widened to 16bit)
-        eor             v2.16b, v2.16b, v21.16b           // PS1 = P1 ^ 0x80
-        eor             v5.16b, v5.16b, v21.16b           // QS1 = Q1 ^ 0x80
-        mul             v18.8h, v18.8h, v20.8h            // w = 3 * (QS0 - PS0)
-        mul             v19.8h, v19.8h, v20.8h
+        movi           v20.8h, #3
+        ssubl          v18.8h, v4.8b,  v3.8b             // QS0 - PS0
+        ssubl2         v19.8h, v4.16b, v3.16b            //   (widened to 16bit)
+        eor            v2.16b, v2.16b, v21.16b           // PS1 = P1 ^ 0x80
+        eor            v5.16b, v5.16b, v21.16b           // QS1 = Q1 ^ 0x80
+        mul            v18.8h, v18.8h, v20.8h            // w = 3 * (QS0 - PS0)
+        mul            v19.8h, v19.8h, v20.8h

-        sqsub           v20.16b, v2.16b, v5.16b           // clamp(PS1-QS1)
-        movi            v22.16b, #4
-        movi            v23.16b, #3
+        sqsub          v20.16b, v2.16b, v5.16b           // clamp(PS1-QS1)
+        movi           v22.16b, #4
+        movi           v23.16b, #3
    .if \inner
-        and             v20.16b, v20.16b, v17.16b         // if(hev) w += clamp(PS1-QS1)
+        and            v20.16b, v20.16b, v17.16b         // if(hev) w += clamp(PS1-QS1)
    .endif
-        saddw           v18.8h,  v18.8h, v20.8b           // w += clamp(PS1-QS1)
-        saddw2          v19.8h,  v19.8h, v20.16b
-        sqxtn           v18.8b,  v18.8h                   // narrow result back into v18
-        sqxtn2          v18.16b, v19.8h
+        saddw          v18.8h,  v18.8h, v20.8b           // w += clamp(PS1-QS1)
+        saddw2         v19.8h,  v19.8h, v20.16b
+        sqxtn          v18.8b,  v18.8h                   // narrow result back into v18
+        sqxtn2         v18.16b, v19.8h
    .if !\inner && !\simple
-        eor             v1.16b,  v1.16b,  v21.16b         // PS2 = P2 ^ 0x80
-        eor             v6.16b,  v6.16b,  v21.16b         // QS2 = Q2 ^ 0x80
+        eor            v1.16b,  v1.16b,  v21.16b         // PS2 = P2 ^ 0x80
+        eor            v6.16b,  v6.16b,  v21.16b         // QS2 = Q2 ^ 0x80
    .endif
-        and             v18.16b, v18.16b, v16.16b         // w &= normal_limit
+        and            v18.16b, v18.16b, v16.16b         // w &= normal_limit

        // registers used at this point..
        //   v0 -> P3  (don't corrupt)
@@ -375,44 +375,44 @@ endfunc
        //   P0 = s2u(PS0 + c2);

    .if \simple
-        sqadd           v19.16b, v18.16b, v22.16b           // c1 = clamp((w&hev)+4)
-        sqadd           v20.16b, v18.16b, v23.16b           // c2 = clamp((w&hev)+3)
-        sshr            v19.16b, v19.16b, #3                // c1 >>= 3
-        sshr            v20.16b, v20.16b, #3                // c2 >>= 3
-        sqsub           v4.16b,  v4.16b,  v19.16b           // QS0 = clamp(QS0-c1)
-        sqadd           v3.16b,  v3.16b,  v20.16b           // PS0 = clamp(PS0+c2)
-        eor             v4.16b,  v4.16b,  v21.16b           // Q0 = QS0 ^ 0x80
-        eor             v3.16b,  v3.16b,  v21.16b           // P0 = PS0 ^ 0x80
-        eor             v5.16b,  v5.16b,  v21.16b           // Q1 = QS1 ^ 0x80
-        eor             v2.16b,  v2.16b,  v21.16b           // P1 = PS1 ^ 0x80
+        sqadd          v19.16b, v18.16b, v22.16b           // c1 = clamp((w&hev)+4)
+        sqadd          v20.16b, v18.16b, v23.16b           // c2 = clamp((w&hev)+3)
+        sshr           v19.16b, v19.16b, #3                // c1 >>= 3
+        sshr           v20.16b, v20.16b, #3                // c2 >>= 3
+        sqsub          v4.16b,  v4.16b,  v19.16b           // QS0 = clamp(QS0-c1)
+        sqadd          v3.16b,  v3.16b,  v20.16b           // PS0 = clamp(PS0+c2)
+        eor            v4.16b,  v4.16b,  v21.16b           // Q0 = QS0 ^ 0x80
+        eor            v3.16b,  v3.16b,  v21.16b           // P0 = PS0 ^ 0x80
+        eor            v5.16b,  v5.16b,  v21.16b           // Q1 = QS1 ^ 0x80
+        eor            v2.16b,  v2.16b,  v21.16b           // P1 = PS1 ^ 0x80
    .elseif \inner
        // the !is4tap case of filter_common, only used for inner blocks
        //   c3 = ((c1&~hev) + 1) >> 1;
        //   Q1 = s2u(QS1 - c3);
        //   P1 = s2u(PS1 + c3);
-        sqadd           v19.16b, v18.16b, v22.16b           // c1 = clamp((w&hev)+4)
-        sqadd           v20.16b, v18.16b, v23.16b           // c2 = clamp((w&hev)+3)
-        sshr            v19.16b, v19.16b, #3                // c1 >>= 3
-        sshr            v20.16b, v20.16b, #3                // c2 >>= 3
-        sqsub           v4.16b,  v4.16b,  v19.16b           // QS0 = clamp(QS0-c1)
-        sqadd           v3.16b,  v3.16b,  v20.16b           // PS0 = clamp(PS0+c2)
-        bic             v19.16b, v19.16b, v17.16b           // c1 & ~hev
-        eor             v4.16b,  v4.16b,  v21.16b           // Q0 = QS0 ^ 0x80
-        srshr           v19.16b, v19.16b, #1                // c3 >>= 1
-        eor             v3.16b,  v3.16b,  v21.16b           // P0 = PS0 ^ 0x80
-        sqsub           v5.16b,  v5.16b,  v19.16b           // QS1 = clamp(QS1-c3)
-        sqadd           v2.16b,  v2.16b,  v19.16b           // PS1 = clamp(PS1+c3)
-        eor             v5.16b,  v5.16b,  v21.16b           // Q1 = QS1 ^ 0x80
-        eor             v2.16b,  v2.16b,  v21.16b           // P1 = PS1 ^ 0x80
+        sqadd          v19.16b, v18.16b, v22.16b           // c1 = clamp((w&hev)+4)
+        sqadd          v20.16b, v18.16b, v23.16b           // c2 = clamp((w&hev)+3)
+        sshr           v19.16b, v19.16b, #3                // c1 >>= 3
+        sshr           v20.16b, v20.16b, #3                // c2 >>= 3
+        sqsub          v4.16b,  v4.16b,  v19.16b           // QS0 = clamp(QS0-c1)
+        sqadd          v3.16b,  v3.16b,  v20.16b           // PS0 = clamp(PS0+c2)
+        bic            v19.16b, v19.16b, v17.16b           // c1 & ~hev
+        eor            v4.16b,  v4.16b,  v21.16b           // Q0 = QS0 ^ 0x80
+        srshr          v19.16b, v19.16b, #1                // c3 >>= 1
+        eor            v3.16b,  v3.16b,  v21.16b           // P0 = PS0 ^ 0x80
+        sqsub          v5.16b,  v5.16b,  v19.16b           // QS1 = clamp(QS1-c3)
+        sqadd          v2.16b,  v2.16b,  v19.16b           // PS1 = clamp(PS1+c3)
+        eor            v5.16b,  v5.16b,  v21.16b           // Q1 = QS1 ^ 0x80
+        eor            v2.16b,  v2.16b,  v21.16b           // P1 = PS1 ^ 0x80
    .else
-        and             v20.16b, v18.16b, v17.16b           // w & hev
-        sqadd           v19.16b, v20.16b, v22.16b           // c1 = clamp((w&hev)+4)
-        sqadd           v20.16b, v20.16b, v23.16b           // c2 = clamp((w&hev)+3)
-        sshr            v19.16b, v19.16b, #3                // c1 >>= 3
-        sshr            v20.16b, v20.16b, #3                // c2 >>= 3
-        bic             v18.16b, v18.16b, v17.16b           // w &= ~hev
-        sqsub           v4.16b,  v4.16b,  v19.16b           // QS0 = clamp(QS0-c1)
-        sqadd           v3.16b,  v3.16b,  v20.16b           // PS0 = clamp(PS0+c2)
+        and            v20.16b, v18.16b, v17.16b           // w & hev
+        sqadd          v19.16b, v20.16b, v22.16b           // c1 = clamp((w&hev)+4)
+        sqadd          v20.16b, v20.16b, v23.16b           // c2 = clamp((w&hev)+3)
+        sshr           v19.16b, v19.16b, #3                // c1 >>= 3
+        sshr           v20.16b, v20.16b, #3                // c2 >>= 3
+        bic            v18.16b, v18.16b, v17.16b           // w &= ~hev
+        sqsub          v4.16b,  v4.16b,  v19.16b           // QS0 = clamp(QS0-c1)
+        sqadd          v3.16b,  v3.16b,  v20.16b           // PS0 = clamp(PS0+c2)

        // filter_mbedge:
        //   a = clamp((27*w + 63) >> 7);
@@ -424,35 +424,35 @@ endfunc
        //   a = clamp((9*w + 63) >> 7);
        //   Q2 = s2u(QS2 - a);
        //   P2 = s2u(PS2 + a);
-        movi            v17.8h,  #63
-        sshll           v22.8h,  v18.8b, #3
-        sshll2          v23.8h,  v18.16b, #3
-        saddw           v22.8h,  v22.8h, v18.8b
-        saddw2          v23.8h,  v23.8h, v18.16b
-        add             v16.8h,  v17.8h, v22.8h
-        add             v17.8h,  v17.8h, v23.8h           //  9*w + 63
-        add             v19.8h,  v16.8h, v22.8h
-        add             v20.8h,  v17.8h, v23.8h           // 18*w + 63
-        add             v22.8h,  v19.8h, v22.8h
-        add             v23.8h,  v20.8h, v23.8h           // 27*w + 63
-        sqshrn          v16.8b,  v16.8h,  #7
-        sqshrn2         v16.16b, v17.8h, #7              // clamp(( 9*w + 63)>>7)
-        sqshrn          v19.8b,  v19.8h, #7
-        sqshrn2         v19.16b, v20.8h, #7              // clamp((18*w + 63)>>7)
-        sqshrn          v22.8b,  v22.8h, #7
-        sqshrn2         v22.16b, v23.8h, #7              // clamp((27*w + 63)>>7)
-        sqadd           v1.16b,  v1.16b,  v16.16b        // PS2 = clamp(PS2+a)
-        sqsub           v6.16b,  v6.16b,  v16.16b        // QS2 = clamp(QS2-a)
-        sqadd           v2.16b,  v2.16b,  v19.16b        // PS1 = clamp(PS1+a)
-        sqsub           v5.16b,  v5.16b,  v19.16b        // QS1 = clamp(QS1-a)
-        sqadd           v3.16b,  v3.16b,  v22.16b        // PS0 = clamp(PS0+a)
-        sqsub           v4.16b,  v4.16b,  v22.16b        // QS0 = clamp(QS0-a)
-        eor             v3.16b,  v3.16b,  v21.16b        // P0 = PS0 ^ 0x80
-        eor             v4.16b,  v4.16b,  v21.16b        // Q0 = QS0 ^ 0x80
-        eor             v2.16b,  v2.16b,  v21.16b        // P1 = PS1 ^ 0x80
-        eor             v5.16b,  v5.16b,  v21.16b        // Q1 = QS1 ^ 0x80
-        eor             v1.16b,  v1.16b,  v21.16b        // P2 = PS2 ^ 0x80
-        eor             v6.16b,  v6.16b,  v21.16b        // Q2 = QS2 ^ 0x80
+        movi           v17.8h,  #63
+        sshll          v22.8h,  v18.8b, #3
+        sshll2         v23.8h,  v18.16b, #3
+        saddw          v22.8h,  v22.8h, v18.8b
+        saddw2         v23.8h,  v23.8h, v18.16b
+        add            v16.8h,  v17.8h, v22.8h
+        add            v17.8h,  v17.8h, v23.8h           //  9*w + 63
+        add            v19.8h,  v16.8h, v22.8h
+        add            v20.8h,  v17.8h, v23.8h           // 18*w + 63
+        add            v22.8h,  v19.8h, v22.8h
+        add            v23.8h,  v20.8h, v23.8h           // 27*w + 63
+        sqshrn         v16.8b,  v16.8h,  #7
+        sqshrn2        v16.16b, v17.8h, #7              // clamp(( 9*w + 63)>>7)
+        sqshrn         v19.8b,  v19.8h, #7
+        sqshrn2        v19.16b, v20.8h, #7              // clamp((18*w + 63)>>7)
+        sqshrn         v22.8b,  v22.8h, #7
+        sqshrn2        v22.16b, v23.8h, #7              // clamp((27*w + 63)>>7)
+        sqadd          v1.16b,  v1.16b,  v16.16b        // PS2 = clamp(PS2+a)
+        sqsub          v6.16b,  v6.16b,  v16.16b        // QS2 = clamp(QS2-a)
+        sqadd          v2.16b,  v2.16b,  v19.16b        // PS1 = clamp(PS1+a)
+        sqsub          v5.16b,  v5.16b,  v19.16b        // QS1 = clamp(QS1-a)
+        sqadd          v3.16b,  v3.16b,  v22.16b        // PS0 = clamp(PS0+a)
+        sqsub          v4.16b,  v4.16b,  v22.16b        // QS0 = clamp(QS0-a)
+        eor            v3.16b,  v3.16b,  v21.16b        // P0 = PS0 ^ 0x80
+        eor            v4.16b,  v4.16b,  v21.16b        // Q0 = QS0 ^ 0x80
+        eor            v2.16b,  v2.16b,  v21.16b        // P1 = PS1 ^ 0x80
+        eor            v5.16b,  v5.16b,  v21.16b        // Q1 = QS1 ^ 0x80
+        eor            v1.16b,  v1.16b,  v21.16b        // P2 = PS2 ^ 0x80
+        eor            v6.16b,  v6.16b,  v21.16b        // Q2 = QS2 ^ 0x80
    .endif
 .endm

@@ -507,48 +507,48 @@ function ff_vp8_v_loop_filter8uv\name\()_neon, export=1
        sub             x0,  x0,  x2,  lsl #2
        sub             x1,  x1,  x2,  lsl #2
        // Load pixels:
-        ld1             {v0.d}[0],     [x0], x2  // P3
-        ld1             {v0.d}[1],     [x1], x2  // P3
-        ld1             {v1.d}[0],     [x0], x2  // P2
-        ld1             {v1.d}[1],     [x1], x2  // P2
-        ld1             {v2.d}[0],     [x0], x2  // P1
-        ld1             {v2.d}[1],     [x1], x2  // P1
-        ld1             {v3.d}[0],     [x0], x2  // P0
-        ld1             {v3.d}[1],     [x1], x2  // P0
-        ld1             {v4.d}[0],     [x0], x2  // Q0
-        ld1             {v4.d}[1],     [x1], x2  // Q0
-        ld1             {v5.d}[0],     [x0], x2  // Q1
-        ld1             {v5.d}[1],     [x1], x2  // Q1
-        ld1             {v6.d}[0],     [x0], x2  // Q2
-        ld1             {v6.d}[1],     [x1], x2  // Q2
-        ld1             {v7.d}[0],     [x0]      // Q3
-        ld1             {v7.d}[1],     [x1]      // Q3
+        ld1          {v0.d}[0],     [x0], x2  // P3
+        ld1          {v0.d}[1],     [x1], x2  // P3
+        ld1          {v1.d}[0],     [x0], x2  // P2
+        ld1          {v1.d}[1],     [x1], x2  // P2
+        ld1          {v2.d}[0],     [x0], x2  // P1
+        ld1          {v2.d}[1],     [x1], x2  // P1
+        ld1          {v3.d}[0],     [x0], x2  // P0
+        ld1          {v3.d}[1],     [x1], x2  // P0
+        ld1          {v4.d}[0],     [x0], x2  // Q0
+        ld1          {v4.d}[1],     [x1], x2  // Q0
+        ld1          {v5.d}[0],     [x0], x2  // Q1
+        ld1          {v5.d}[1],     [x1], x2  // Q1
+        ld1          {v6.d}[0],     [x0], x2  // Q2
+        ld1          {v6.d}[1],     [x1], x2  // Q2
+        ld1          {v7.d}[0],     [x0]      // Q3
+        ld1          {v7.d}[1],     [x1]      // Q3

-        dup             v22.16b, w3                 // flim_E
-        dup             v23.16b, w4                 // flim_I
+        dup          v22.16b, w3                 // flim_E
+        dup          v23.16b, w4                 // flim_I

        vp8_loop_filter inner=\inner, hev_thresh=w5

        // back up to P2:  u,v -= stride * 6
-        sub             x0,  x0,  x2,  lsl #2
-        sub             x1,  x1,  x2,  lsl #2
-        sub             x0,  x0,  x2,  lsl #1
-        sub             x1,  x1,  x2,  lsl #1
+        sub          x0,  x0,  x2,  lsl #2
+        sub          x1,  x1,  x2,  lsl #2
+        sub          x0,  x0,  x2,  lsl #1
+        sub          x1,  x1,  x2,  lsl #1

        // Store pixels:

-        st1             {v1.d}[0],     [x0], x2  // P2
-        st1             {v1.d}[1],     [x1], x2  // P2
-        st1             {v2.d}[0],     [x0], x2  // P1
-        st1             {v2.d}[1],     [x1], x2  // P1
-        st1             {v3.d}[0],     [x0], x2  // P0
-        st1             {v3.d}[1],     [x1], x2  // P0
-        st1             {v4.d}[0],     [x0], x2  // Q0
-        st1             {v4.d}[1],     [x1], x2  // Q0
-        st1             {v5.d}[0],     [x0], x2  // Q1
-        st1             {v5.d}[1],     [x1], x2  // Q1
-        st1             {v6.d}[0],     [x0]      // Q2
-        st1             {v6.d}[1],     [x1]      // Q2
+        st1          {v1.d}[0],     [x0], x2  // P2
+        st1          {v1.d}[1],     [x1], x2  // P2
+        st1          {v2.d}[0],     [x0], x2  // P1
+        st1          {v2.d}[1],     [x1], x2  // P1
+        st1          {v3.d}[0],     [x0], x2  // P0
+        st1          {v3.d}[1],     [x1], x2  // P0
+        st1          {v4.d}[0],     [x0], x2  // Q0
+        st1          {v4.d}[1],     [x1], x2  // Q0
+        st1          {v5.d}[0],     [x0], x2  // Q1
+        st1          {v5.d}[1],     [x1], x2  // Q1
+        st1          {v6.d}[0],     [x0]      // Q2
+        st1          {v6.d}[1],     [x1]      // Q2

        ret
 endfunc
@@ -579,7 +579,7 @@ function ff_vp8_h_loop_filter16\name\()_neon, export=1
        ld1             {v6.d}[1], [x0], x1
        ld1             {v7.d}[1], [x0], x1

-        transpose_8x16B v0,  v1,  v2,  v3,  v4,  v5,  v6,  v7, v30, v31
+        transpose_8x16B   v0,  v1,  v2,  v3,  v4,  v5,  v6,  v7, v30, v31

        dup             v22.16b, w2                 // flim_E
    .if !\simple
@@ -590,7 +590,7 @@ function ff_vp8_h_loop_filter16\name\()_neon, export=1

        sub             x0,  x0,  x1, lsl #4    // backup 16 rows

-        transpose_8x16B v0,  v1,  v2,  v3,  v4,  v5,  v6,  v7, v30, v31
+        transpose_8x16B   v0,  v1,  v2,  v3,  v4,  v5,  v6,  v7, v30, v31

        // Store pixels:
        st1             {v0.d}[0], [x0], x1
@@ -624,24 +624,24 @@ function ff_vp8_h_loop_filter8uv\name\()_neon, export=1
        sub             x1,  x1,  #4

        // Load pixels:
-        ld1             {v0.d}[0],     [x0], x2 // load u
-        ld1             {v0.d}[1],     [x1], x2 // load v
-        ld1             {v1.d}[0],     [x0], x2
-        ld1             {v1.d}[1],     [x1], x2
-        ld1             {v2.d}[0],     [x0], x2
-        ld1             {v2.d}[1],     [x1], x2
-        ld1             {v3.d}[0],     [x0], x2
-        ld1             {v3.d}[1],     [x1], x2
-        ld1             {v4.d}[0],     [x0], x2
-        ld1             {v4.d}[1],     [x1], x2
-        ld1             {v5.d}[0],     [x0], x2
-        ld1             {v5.d}[1],     [x1], x2
-        ld1             {v6.d}[0],     [x0], x2
-        ld1             {v6.d}[1],     [x1], x2
-        ld1             {v7.d}[0],     [x0], x2
-        ld1             {v7.d}[1],     [x1], x2
+        ld1          {v0.d}[0],     [x0], x2 // load u
+        ld1          {v0.d}[1],     [x1], x2 // load v
+        ld1          {v1.d}[0],     [x0], x2
+        ld1          {v1.d}[1],     [x1], x2
+        ld1          {v2.d}[0],     [x0], x2
+        ld1          {v2.d}[1],     [x1], x2
+        ld1          {v3.d}[0],     [x0], x2
+        ld1          {v3.d}[1],     [x1], x2
+        ld1          {v4.d}[0],     [x0], x2
+        ld1          {v4.d}[1],     [x1], x2
+        ld1          {v5.d}[0],     [x0], x2
+        ld1          {v5.d}[1],     [x1], x2
+        ld1          {v6.d}[0],     [x0], x2
+        ld1          {v6.d}[1],     [x1], x2
+        ld1          {v7.d}[0],     [x0], x2
+        ld1          {v7.d}[1],     [x1], x2

-        transpose_8x16B v0,  v1,  v2,  v3,  v4,  v5,  v6,  v7, v30, v31
+        transpose_8x16B   v0,  v1,  v2,  v3,  v4,  v5,  v6,  v7, v30, v31

        dup             v22.16b, w3                 // flim_E
        dup             v23.16b, w4                 // flim_I
@@ -651,25 +651,25 @@ function ff_vp8_h_loop_filter8uv\name\()_neon, export=1
        sub             x0,  x0,  x2, lsl #3    // backup u 8 rows
        sub             x1,  x1,  x2, lsl #3    // backup v 8 rows

-        transpose_8x16B v0,  v1,  v2,  v3,  v4,  v5,  v6,  v7, v30, v31
+        transpose_8x16B   v0,  v1,  v2,  v3,  v4,  v5,  v6,  v7, v30, v31

        // Store pixels:
-        st1             {v0.d}[0],     [x0], x2 // load u
-        st1             {v0.d}[1],     [x1], x2 // load v
-        st1             {v1.d}[0],     [x0], x2
-        st1             {v1.d}[1],     [x1], x2
-        st1             {v2.d}[0],     [x0], x2
-        st1             {v2.d}[1],     [x1], x2
-        st1             {v3.d}[0],     [x0], x2
-        st1             {v3.d}[1],     [x1], x2
-        st1             {v4.d}[0],     [x0], x2
-        st1             {v4.d}[1],     [x1], x2
-        st1             {v5.d}[0],     [x0], x2
-        st1             {v5.d}[1],     [x1], x2
-        st1             {v6.d}[0],     [x0], x2
-        st1             {v6.d}[1],     [x1], x2
-        st1             {v7.d}[0],     [x0]
-        st1             {v7.d}[1],     [x1]
+        st1          {v0.d}[0],     [x0], x2 // load u
+        st1          {v0.d}[1],     [x1], x2 // load v
+        st1          {v1.d}[0],     [x0], x2
+        st1          {v1.d}[1],     [x1], x2
+        st1          {v2.d}[0],     [x0], x2
+        st1          {v2.d}[1],     [x1], x2
+        st1          {v3.d}[0],     [x0], x2
+        st1          {v3.d}[1],     [x1], x2
+        st1          {v4.d}[0],     [x0], x2
+        st1          {v4.d}[1],     [x1], x2
+        st1          {v5.d}[0],     [x0], x2
+        st1          {v5.d}[1],     [x1], x2
+        st1          {v6.d}[0],     [x0], x2
+        st1          {v6.d}[1],     [x1], x2
+        st1          {v7.d}[0],     [x0]
+        st1          {v7.d}[1],     [x1]

        ret

--- a/Show More
+++ b/Show More
@@ -1 +1 @@
 .1.git
 .0.1