doc/t2h: Support texinfo 7.1 and 7.2 pretest

Here is a proposed patch for portability of doc/t2h.pm for GNU Texinfo 7.1 and 7.1.90 (7.2 pretest). I tested against 7.1 and 7.1.90 (7.2 pretest). There is a difference in the headings compared to the website version, maybe related to FA_ICONS not being set the same, but the result seems correct. I also renamed $element to $output_unit in ffmpeg_heading_command as in new equivalent makeinfo/texi2any code the $element variable is the $command variable in ffmpeg_heading_command, which is very confusing. I left as is the $command variable to have a patch easier to read, but it could make sense to rename $command as $element later on. The patch could also have effects with Texinfo 7.0, since some of the changes are for that version, but that probably never show up because it is for situations that may not exist in ffmpeg manuals (for example @node without sectioning command), or because the code is robust to some missing information (case of $heading_level in ffmpeg_heading_command that was not set, as far as I can tell). Signed-off-by: James Almer <jamrial@gmail.com> (cherry picked from commit 4d9cdf82ee)
avformat/oggparsecelt: bound extra_headers to avoid an effectively infinite loop
2026-06-21 21:21:34 +02:00 · 2026-05-21 09:36:57 -05:00 · 2026-05-16 18:17:56 +02:00 · 2026-05-16 18:17:41 +02:00 · 2026-05-16 18:17:41 +02:00 · 2026-05-16 18:17:40 +02:00
302 changed files with 6059 additions and 4441 deletions
@@ -0,0 +1,23 @@
+exclude: ^tests/ref/
+
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v5.0.0
+  hooks:
+    - id: check-case-conflict
+    - id: check-executables-have-shebangs
+    - id: check-illegal-windows-names
+    - id: check-shebang-scripts-are-executable
+    - id: check-yaml
+    - id: end-of-file-fixer
+    - id: fix-byte-order-marker
+    - id: mixed-line-ending
+    - id: trailing-whitespace
+- repo: local
+  hooks:
+    - id: aarch64-asm-indent
+      name: fix aarch64 assembly indentation
+      files: ^.*/aarch64/.*\.S$
+      language: script
+      entry: ./tools/check_arm_indent.sh --apply
+      pass_filenames: false
@@ -0,0 +1,29 @@
+name: Lint
+
+on:
+  push:
+    branches:
+      - release/6.0
+  pull_request:
+
+jobs:
+  lint:
+    name: Pre-Commit
+    runs-on: utilities
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install pre-commit CI
+        id: install
+        run: |
+            python3 -m venv ~/pre-commit
+            ~/pre-commit/bin/pip install --upgrade pip setuptools
+            ~/pre-commit/bin/pip install pre-commit
+            echo "envhash=$({ python3 --version && cat .forgejo/pre-commit/config.yaml; } | sha256sum | cut -d' ' -f1)" >> $FORGEJO_OUTPUT
+      - name: Cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pre-commit
+          key: pre-commit-${{ steps.install.outputs.envhash }}
+      - name: Run pre-commit CI
+        run: ~/pre-commit/bin/pre-commit run -c .forgejo/pre-commit/config.yaml --show-diff-on-failure --color=always --all-files
@@ -0,0 +1,80 @@
+name: Test
+
+on:
+  push:
+    branches:
+      - release/6.0
+  pull_request:
+
+jobs:
+  run_fate:
+    name: Fate (${{ matrix.runner }}, ${{ matrix.shared }}, ${{ matrix.bits }} bit)
+    strategy:
+      fail-fast: false
+      matrix:
+        runner: [linux-aarch64]
+        shared: ['static']
+        bits: ['64']
+        include:
+          - runner: linux-amd64
+            shared: 'static'
+            bits: '32'
+          - runner: linux-amd64
+            shared: 'shared'
+            bits: '64'
+    runs-on: ${{ matrix.runner }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Configure
+        run: |
+          ./configure --enable-gpl --enable-nonfree --enable-memory-poisoning --assert-level=2 \
+              $([ "${{ matrix.bits }}" != "32" ] || echo --arch=x86_32 --extra-cflags=-m32 --extra-cxxflags=-m32 --extra-ldflags=-m32) \
+              $([ "${{ matrix.shared }}" != "shared" ] || echo --enable-shared --disable-static) \
+              || CFGRES=$? && CFGRES=$?
+          cat ffbuild/config.log
+          exit $CFGRES
+      - name: Build
+        run: make -j$(nproc)
+      - name: Restore Cached Fate-Suite
+        id: cache
+        uses: actions/cache/restore@v4
+        with:
+          path: fate-suite
+          key: fate-suite
+          restore-keys: |
+            fate-suite-
+      - name: Sync Fate-Suite
+        id: fate
+        run: |
+          make fate-rsync SAMPLES=$PWD/fate-suite
+          echo "hash=$(find fate-suite -type f -printf "%P %s %T@\n" | sort | sha256sum | cut -d' ' -f1)" >> $FORGEJO_OUTPUT
+      - name: Cache Fate-Suite
+        uses: actions/cache/save@v4
+        if: ${{ format('fate-suite-{0}', steps.fate.outputs.hash) != steps.cache.outputs.cache-matched-key }}
+        with:
+          path: fate-suite
+          key: fate-suite-${{ steps.fate.outputs.hash }}
+      - name: Run Fate
+        run: LD_LIBRARY_PATH="$(printf "%s:" "$PWD"/lib*)$PWD" make fate fate-build SAMPLES=$PWD/fate-suite -j$(nproc)
+  compile_only:
+    name: Fate (Win64, Build-Only)
+    strategy:
+      fail-fast: false
+      matrix:
+        image: ["ghcr.io/btbn/ffmpeg-builds/win64-gpl-6.0:latest"]
+    runs-on: linux-amd64
+    container: ${{ matrix.image }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Configure
+        run: |
+          ./configure --pkg-config-flags="--static" $FFBUILD_TARGET_FLAGS $FF_CONFIGURE \
+              --cc="$CC" --cxx="$CXX" --ar="$AR" --ranlib="$RANLIB" --nm="$NM" \
+              --extra-cflags="$FF_CFLAGS" --extra-cxxflags="$FF_CXXFLAGS" \
+              --extra-libs="$FF_LIBS" --extra-ldflags="$FF_LDFLAGS" --extra-ldexeflags="$FF_LDEXEFLAGS"
+      - name: Build
+        run: make -j$(nproc)
+      - name: Run Fate
+        run: make -j$(nproc) fate-build
@@ -55,7 +55,7 @@ modified by someone else and passed on, the recipients should know
 that what they have is not the original version, so that the original
 author's reputation will not be affected by problems that might be
 introduced by others.
-
+
  Finally, software patents pose a constant threat to the existence of
 any free program.  We wish to make sure that a company cannot
 effectively restrict the users of a free program by obtaining a
@@ -111,7 +111,7 @@ modification follow.  Pay close attention to the difference between a
 "work based on the library" and a "work that uses the library".  The
 former contains code derived from the library, whereas the latter must
 be combined with the library in order to run.
-
+
                  GNU LESSER GENERAL PUBLIC LICENSE
   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION

@@ -158,7 +158,7 @@ Library.
  You may charge a fee for the physical act of transferring a copy,
 and you may at your option offer warranty protection in exchange for a
 fee.
-
+
  2. You may modify your copy or copies of the Library or any portion
 of it, thus forming a work based on the Library, and copy and
 distribute such modifications or work under the terms of Section 1
@@ -216,7 +216,7 @@ instead of to this License.  (If a newer version than version 2 of the
 ordinary GNU General Public License has appeared, then you can specify
 that version instead if you wish.)  Do not make any other change in
 these notices.
-
+
  Once this change is made in a given copy, it is irreversible for
 that copy, so the ordinary GNU General Public License applies to all
 subsequent copies and derivative works made from that copy.
@@ -267,7 +267,7 @@ Library will still fall under Section 6.)
 distribute the object code for the work under the terms of Section 6.
 Any executables containing that work also fall under Section 6,
 whether or not they are linked directly with the Library itself.
-
+
  6. As an exception to the Sections above, you may also combine or
 link a "work that uses the Library" with the Library to produce a
 work containing portions of the Library, and distribute that work
@@ -329,7 +329,7 @@ restrictions of other proprietary libraries that do not normally
 accompany the operating system.  Such a contradiction means you cannot
 use both them and the Library together in an executable that you
 distribute.
-
+
  7. You may place library facilities that are a work based on the
 Library side-by-side in a single library together with other library
 facilities not covered by this License, and distribute such a combined
@@ -370,7 +370,7 @@ subject to these terms and conditions.  You may not impose any further
 restrictions on the recipients' exercise of the rights granted herein.
 You are not responsible for enforcing compliance by third parties with
 this License.
-
+
  11. If, as a consequence of a court judgment or allegation of patent
 infringement or for any other reason (not limited to patent issues),
 conditions are imposed on you (whether by court order, agreement or
@@ -422,7 +422,7 @@ conditions either of that version or of any later version published by
 the Free Software Foundation.  If the Library does not specify a
 license version number, you may choose any version ever published by
 the Free Software Foundation.
-
+
  14. If you wish to incorporate parts of the Library into other free
 programs whose distribution conditions are incompatible with these,
 write to the author to ask for permission.  For software which is
@@ -456,7 +456,7 @@ SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
 DAMAGES.

                     END OF TERMS AND CONDITIONS
-
+
           How to Apply These Terms to Your New Libraries

  If you develop a new library, and you want it to be of the greatest
@@ -1,6 +1,6 @@
-See the Git history of the project (git://source.ffmpeg.org/ffmpeg) to
+See the Git history of the project (https://git.ffmpeg.org/ffmpeg) to
 get the names of people who have contributed to FFmpeg.

 To check the log, you can type the command "git log" in the FFmpeg
 source directory, or browse the online repository at
-http://source.ffmpeg.org.
+https://git.ffmpeg.org/ffmpeg
@@ -1,6 +1,275 @@
 Entries are sorted chronologically from oldest to youngest within each release,
 releases are sorted from youngest to oldest.

+version 6.0.2:
+ fate/subtitles: Ignore line endings for sub-scc test
+ avformat/mxfdec: Check index_edit_rate
+ swscale/utils: Fix xInc overflow
+ avformat/isom: Uninit layout in ff_mp4_read_dec_config_descr()
+ avcodec/exr: Dont use 64bits to hold 6bits
+ avcodec/exr: Check for remaining bits in huf_unpack_enc_table()
+ avformat/mpegts: Reset local nb_prg on add_program() failure
+ avformat/aiffdec: Check for previously set channels
+ avformat/mxfdec: Make edit_unit_byte_count unsigned
+ avformat/movenc: Check that cts fits in 32bit
+ avformat/mxfdec: Check first case of offset_temp computation for overflow
+ avfilter/vf_signature: Dont crash on no frames
+ avformat/westwood_vqa: Fix 2g packets
+ avformat/matroskadec: Check timescale
+ avformat/wavdec: satuarte next_tag_ofs, data_end
+ avformat/sbgdec: Check for negative duration
+ avformat/rpl: Use 64bit for total_audio_size and check it
+ avformat/timecode: use 64bit for intermediate for rounding in fps_from_frame_rate()
+ avformat/mov: use 64bit for intermediate for rounding
+ avformat/jacosubdec: Use 64bit for abs
+ avformat/concatdec: Check user_duration sum
+ avcodec/wavarc: Avoid signed integer overflow in sample
+ avcodec/truemotion1: Height not being a multiple of 4 is unsupported
+ avcodec/hcadec: do not set hfr_group_count to invalid values
+ avformat/concatdec: clip outpoint - inpoint overflow in get_best_effort_duration()
+ avformat/jacosubdec: clarify code
+ avformat/cafdec: Check that data chunk end fits within 64bit
+ avformat/iff: Saturate avio_tell() + 12
+ avformat/dxa: Adjust order of operations around block align
+ avformat/cafdec: dont seek beyond 64bit
+ avformat/id3v2: read_uslt() check for the amount read
+ avformat/wady: Check >0 samplerate and channels 1 || 2.
+ avcodec/proresenc_kostya: Remove bug similarity text
+ avcodec/vorbisdec: Check remaining data in vorbis_residue_decode_internal()
+ avformat/concatdec: Check in and outpoints to be to produce a positive representable duration
+ avcodec/8bps: Consider width in the minimal size check
+ libswscale/utils: Fix bayer to yuvj
+ swscale/swscale: Check srcSliceH for bayer
+ swscale/utils: Allocate more dithererror
+ avcodec/indeo3: Round dimensions up in allocate_frame_buffers()
+ avutil/rational: Document what is to be expected from av_d2q() of doubles representing rational numbers
+ avfilter/signature_lookup: Do not dereference NULL pointers after malloc failure
+ avfilter/signature_lookup: dont leave uncleared pointers in sll_free()
+ avcodec/mpegvideo_enc: Use ptrdiff_t for stride
+ libavformat/hlsenc.c: Populate OTI using AAC profile in write_codec_attr.
+ avcodec/mpegvideo_enc: Dont copy beyond the image
+ avfilter/vf_minterpolate: Check pts before division
+ avformat/flacdec: Avoid double AVERRORS
+ avfilter/vf_vidstabdetect: Avoid double AVERRORS
+ avfilter/vf_swaprect: round coordinates down
+ avfilter/vf_swaprect: Use height for vertical variables
+ avfilter/vf_swaprect: assert that rectangles are within memory
+ avfilter/af_alimiter: Check nextpos before use
+ avfilter/f_reverse: Apply PTS compensation only when pts is available
+ avfilter/af_stereowiden: Check length
+ avformat/mov: Fix MSAN issue with stsd_id
+ avfilter/vf_weave: Fix odd height handling
+ avfilter/edge_template: Fix small inputs with gaussian_blur()
+ avfilter/vf_gradfun: Do not overread last line
+ avfilter/avf_showspectrum: fix off by 1 error
+ avformat/mov: do not set sign bit for chunk_offsets
+ avcodec/jpeglsdec: Check Jpeg-LS LSE
+ configure: Enable section_data_rel_ro for FreeBSD and NetBSD aarch64 / arm
+ avcodec/av1dec: Fix resolving zero divisor
+ avformat/mov: Ignore duplicate ftyp
+ avformat/mov: Fix integer overflow in mov_read_packet().
+ avformat/mov: Check if a key is longer than the atom containing it
+ avfilter/buffersrc: fix overriding unknown channel layouts with negotiated one
+ avfilter/af_channelmap: disallow channel index 64
+ avfilter/af_channelmap: fix mapping if in_channel was a string but out_channel was not specified
+ avfilter/af_channelmap: fix error message if FL source channel was missing
+ avcodec/nvdec: reset bitstream_len/nb_slices when resetting bitstream pointer
+ avformat/mov: don't abort on duplicate Mastering Display Metadata boxes
+ fftools/ffplay: use correct buffersink channel layout parameters
+ swresample/resample: fix rounding errors with filter_size=1 and phase_shift=0
+ avformat/mxfdec: remove resolve_strong_ref usage with AnyType
+ avformat/libsrt: use SRT_EPOLL_IN for waiting for an incoming connection
+ avformat/mxfdec: do not use AnyType when resolving Descriptors and MultipleDescriptors
+ avformat/mxfdec: move resolving Descriptors to the multi descriptor resolve function
+ avutil/hwcontext_d3d11va: prefer DXGI 1.1 factory when available
+ avcodec/av1dec: fix matrix coefficients exposed by codec context
+ avformat/mov_chan: never override number of channels based on chan atom
+ avformat/mov_chan: do not assume channels are in native order
+ avcodec/nvdec: don't free NVDECContext->bitstream
+ lavc/dvdsubenc: only check canvas size when it is actually set
+
+
+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:
 - Radiance HDR image support
 - ddagrab (Desktop Duplication) video capture filter
@@ -91,10 +91,10 @@ ffbuild/.config: $(CONFIGURABLE_COMPONENTS)
 SUBDIR_VARS := CLEANFILES FFLIBS HOSTPROGS TESTPROGS TOOLS               \
               HEADERS ARCH_HEADERS BUILT_HEADERS SKIPHEADERS            \
               ARMV5TE-OBJS ARMV6-OBJS ARMV8-OBJS VFP-OBJS NEON-OBJS     \
-               ALTIVEC-OBJS VSX-OBJS RVV-OBJS MMX-OBJS X86ASM-OBJS       \
+               ALTIVEC-OBJS VSX-OBJS MMX-OBJS X86ASM-OBJS                \
               MIPSFPU-OBJS MIPSDSPR2-OBJS MIPSDSP-OBJS MSA-OBJS         \
-               MMI-OBJS LSX-OBJS LASX-OBJS OBJS SLIBOBJS SHLIBOBJS       \
-               STLIBOBJS HOSTOBJS TESTOBJS
+               MMI-OBJS LSX-OBJS LASX-OBJS RV-OBJS RVV-OBJS              \
+               OBJS SLIBOBJS SHLIBOBJS STLIBOBJS HOSTOBJS TESTOBJS

 define RESET
 $(1) :=
@@ -1 +1 @@
-5.1.git
+6.0.2
@@ -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.
@@ -2110,10 +2110,12 @@ ARCH_EXT_LIST_PPC="
    ldbrx
    power8
    ppc4xx
+    vec_xl
    vsx
 "

 ARCH_EXT_LIST_RISCV="
+    rv
    rvv
 "

@@ -2191,6 +2193,7 @@ HEADERS_LIST="
    opencv2_core_core_c_h
    OpenGL_gl3_h
    poll_h
+    pthread_np_h
    sys_param_h
    sys_resource_h
    sys_select_h
@@ -2293,6 +2296,8 @@ SYSTEM_FUNCS="
    posix_memalign
    prctl
    pthread_cancel
+    pthread_set_name_np
+    pthread_setname_np
    sched_getaffinity
    SecItemImport
    SetConsoleTextAttribute
@@ -2407,6 +2412,7 @@ HAVE_LIST="
    opencl_vaapi_intel_media
    perl
    pod2man
+    posix_ioctl
    texi2html
    xmllint
    zlib_gzip
@@ -2627,9 +2633,11 @@ altivec_deps="ppc"
 dcbzl_deps="ppc"
 ldbrx_deps="ppc"
 ppc4xx_deps="ppc"
+vec_xl_deps="altivec"
 vsx_deps="altivec"
 power8_deps="vsx"

+rv_deps="riscv"
 rvv_deps="riscv"

 loongson2_deps="mips"
@@ -3892,6 +3900,8 @@ if test "$target_os_default" = aix; then
    arch_default=$(uname -p)
    strip_default="strip -X32_64"
    nm_default="nm -g -X32_64"
+elif test "$MSYSTEM_CARCH" != ""; then
+    arch_default="$MSYSTEM_CARCH"
 else
    arch_default=$(uname -m)
 fi
@@ -5519,6 +5529,7 @@ case $target_os in
        ;;
    netbsd)
        disable symver
+        enable section_data_rel_ro
        oss_indev_extralibs="-lossaudio"
        oss_outdev_extralibs="-lossaudio"
        enabled gcc || check_ldflags -Wl,-zmuldefs
@@ -5537,6 +5548,7 @@ case $target_os in
        disable symver
        ;;
    freebsd)
+        enable section_data_rel_ro
        ;;
    bsd/os)
        add_extralibs -lpoll -lgnugetopt
@@ -6113,8 +6125,14 @@ elif enabled ppc; then
        check_cpp_condition power8 "altivec.h" "defined(_ARCH_PWR8)"
    fi

+    if enabled altivec; then
+        check_cc vec_xl altivec.h "const unsigned char *y1i = { 0 };
+                                   vector unsigned char y0 = vec_xl(0, y1i);"
+    fi
+
 elif enabled riscv; then

+    enabled rv && check_inline_asm rv '".option arch, +zbb\nrev8 t0, t1"'
    enabled rvv && check_inline_asm rvv '".option arch, +v\nvsetivli zero, 0, e8, m1, ta, ma"'

 elif enabled x86; then
@@ -6350,6 +6368,7 @@ check_headers malloc.h
 check_headers mftransform.h
 check_headers net/udplite.h
 check_headers poll.h
+check_headers pthread_np.h
 check_headers sys/param.h
 check_headers sys/resource.h
 check_headers sys/select.h
@@ -6513,6 +6532,12 @@ if ! disabled pthreads && ! enabled w32threads && ! enabled os2threads; then
    if enabled pthreads; then
        check_builtin sem_timedwait semaphore.h "sem_t *s; sem_init(s,0,0); sem_timedwait(s,0); sem_destroy(s)" $pthreads_extralibs
        check_func pthread_cancel $pthreads_extralibs
+        hdrs=pthread.h
+        if enabled pthread_np_h; then
+            hdrs="$hdrs pthread_np.h"
+        fi
+        check_lib pthread_set_name_np "$hdrs" pthread_set_name_np -lpthread
+        check_lib pthread_setname_np "$hdrs" pthread_setname_np -lpthread
    fi
 fi

@@ -6859,11 +6884,13 @@ pod2man --help     > /dev/null 2>&1 && enable pod2man   || disable pod2man
 rsync --help 2> /dev/null | grep -q 'contimeout' && enable rsync_contimeout || disable rsync_contimeout
 xmllint --version  > /dev/null 2>&1 && enable xmllint   || disable xmllint

+check_headers linux/fb.h
+check_headers linux/videodev2.h
+test_code cc linux/videodev2.h "struct v4l2_frmsizeenum vfse; vfse.discrete.width = 0;" && enable_sanitized struct_v4l2_frmivalenum_discrete
+test_code cc sys/ioctl.h "int ioctl(int, int, ...)" && enable posix_ioctl
+
 # check V4L2 codecs available in the API
 if enabled v4l2_m2m; then
-    check_headers linux/fb.h
-    check_headers linux/videodev2.h
-    test_code cc linux/videodev2.h "struct v4l2_frmsizeenum vfse; vfse.discrete.width = 0;" && enable_sanitized struct_v4l2_frmivalenum_discrete
    check_cc v4l2_m2m linux/videodev2.h "int i = V4L2_CAP_VIDEO_M2M_MPLANE | V4L2_CAP_VIDEO_M2M | V4L2_BUF_FLAG_LAST;"
    check_cc vc1_v4l2_m2m linux/videodev2.h "int i = V4L2_PIX_FMT_VC1_ANNEX_G;"
    check_cc mpeg1_v4l2_m2m linux/videodev2.h "int i = V4L2_PIX_FMT_MPEG1;"
@@ -6908,8 +6935,7 @@ 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 ||
-                   check_lib sndio sndio.h sio_open -lsndio; }
+enabled sndio && check_pkg_config sndio sndio sndio.h sio_open

 if enabled libcdio; then
    check_pkg_config libcdio libcdio_paranoia "cdio/cdda.h cdio/paranoia.h" cdio_cddap_open ||
@@ -7018,7 +7044,7 @@ fi

 if enabled x86; then
    case $target_os in
-        mingw32*|mingw64*|win32|win64|linux|cygwin*)
+        freebsd|mingw32*|mingw64*|win32|win64|linux|cygwin*)
            ;;
        *)
            disable ffnvcodec cuvid nvdec nvenc
@@ -7042,7 +7068,7 @@ enabled nvenc &&
    test_cc -I$source_path <<EOF || disable nvenc
 #include <ffnvcodec/nvEncodeAPI.h>
 NV_ENCODE_API_FUNCTION_LIST flist;
-void f(void) { struct { const GUID guid; } s[] = { { NV_ENC_PRESET_HQ_GUID } }; }
+void f(void) { struct { const GUID guid; } s[] = { { NV_ENC_CODEC_H264_GUID } }; }
 int main(void) { return 0; }
 EOF

@@ -7601,6 +7627,7 @@ if enabled ppc; then
    echo "POWER8 enabled            ${power8-no}"
    echo "PPC 4xx optimizations     ${ppc4xx-no}"
    echo "dcbzl available           ${dcbzl-no}"
+    echo "vec_xl available          ${vec_xl-no}"
 fi
 if enabled loongarch; then
    echo "LSX enabled               ${lsx-no}"
@@ -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         = 6.0.2

 # 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
@@ -3,9 +3,9 @@
 The FFmpeg developers.

 For details about the authorship, see the Git history of the project
-(git://source.ffmpeg.org/ffmpeg), e.g. by typing the command
+(https://git.ffmpeg.org/ffmpeg), e.g. by typing the command
@command{git log} in the FFmpeg source directory, or browsing the
-online repository at @url{http://source.ffmpeg.org}.
+online repository at @url{https://git.ffmpeg.org/ffmpeg}.

 Maintainers for the specific components are listed in the file
@file{MAINTAINERS} in the source code tree.
@@ -63,4 +63,3 @@ make -j<num>
 make -k
    Continue build in case of errors, this is useful for the regression tests
    sometimes but note that it will still not run all reg tests.
-
@@ -88,4 +88,3 @@ lead to this decision.

 The decisions from the TC are final, until the matters are reopened after
 no less than one year.
-
@@ -1949,22 +1949,6 @@ Set the number of slices, used in parallelized encoding. Default value
 is 0. This is only used when @option{slice_mode} is set to
@samp{fixed}.

-@item slice_mode
-Set slice mode. Can assume one of the following possible values:
-
-@table @samp
-@item fixed
-a fixed number of slices
-@item rowmb
-one slice per row of macroblocks
-@item auto
-automatic number of slices according to number of threads
-@item dyn
-dynamic slicing
-@end table
-
-Default value is @samp{auto}.
-
@item loopfilter
 Enable loop filter, if set to 1 (automatically enabled). To disable
 set a value of 0.
@@ -43,8 +43,8 @@ OBJS=$(addsuffix .o,$(EXAMPLES))
 # the following examples make explicit use of the math library
 avcodec:           LDLIBS += -lm
 encode_audio:      LDLIBS += -lm
-muxing:            LDLIBS += -lm
-resampling_audio:  LDLIBS += -lm
+mux:               LDLIBS += -lm
+resample_audio:    LDLIBS += -lm

 .phony: all clean-test clean

@@ -62,10 +62,10 @@ static int str_to_dict(char* optstr, AVDictionary **opt)
        return 0;
    key = strtok(optstr, " ");
    if (key == NULL)
-        return AVERROR(ENAVAIL);
+        return AVERROR(EINVAL);
    value = strtok(NULL, " ");
    if (value == NULL)
-        return AVERROR(ENAVAIL);
+        return AVERROR(EINVAL);
    av_dict_set(opt, key, value, 0);
    do {
        key = strtok(NULL, " ");
@@ -73,7 +73,7 @@ static int str_to_dict(char* optstr, AVDictionary **opt)
            return 0;
        value = strtok(NULL, " ");
        if (value == NULL)
-            return AVERROR(ENAVAIL);
+            return AVERROR(EINVAL);
        av_dict_set(opt, key, value, 0);
    } while(key != NULL);
    return 0;
@@ -181,7 +181,7 @@ static int open_input_file(char *filename)
        break;
    default:
        fprintf(stderr, "Codec is not supportted by qsv\n");
-        return AVERROR(ENAVAIL);
+        return AVERROR(EINVAL);
    }

    if (!(decoder_ctx = avcodec_alloc_context3(decoder)))
@@ -26943,11 +26943,6 @@ Specify the frame rate expected for the video stream.
@item pixel_aspect, sar
 The sample (pixel) aspect ratio of the input video.

-@item sws_param
-This option is deprecated and ignored. Prepend @code{sws_flags=@var{flags};}
-to the filtergraph description to specify swscale flags for automatically
-inserted scalers. See @ref{Filtergraph syntax}.
-
@item hw_frames_ctx
 When using a hardware pixel format, this should be a reference to an
 AVHWFramesContext describing input frames.
@@ -53,7 +53,7 @@ Most distribution and operating system provide a package for it.
@section Cloning the source tree

@example
-git clone git://source.ffmpeg.org/ffmpeg <target>
+git clone https://git.ffmpeg.org/ffmpeg.git <target>
@end example

 This will put the FFmpeg sources into the directory @var{<target>}.
@@ -795,12 +795,6 @@ deletes them. Increase this to allow continue clients to download segments which
 were recently referenced in the playlist. Default value is 1, meaning segments older than
@code{hls_list_size+1} will be deleted.

-@item hls_ts_options @var{options_list}
-Set output format options using a :-separated list of key=value
-parameters. Values containing @code{:} special characters must be
-escaped.
-@code{hls_ts_options} is deprecated, use hls_segment_options instead of it..
-
@item hls_start_number_source
 Start the playlist sequence number (@code{#EXT-X-MEDIA-SEQUENCE}) according to the specified source.
 Unless @code{hls_flags single_file} is set, it also specifies source of starting sequence numbers of
@@ -157,4 +157,3 @@ PFD[32]   would for example be signed 32 bit little-endian IEEE float
@item XVID @tab non-compliant MPEG-4 generated by old Xvid
@item XVIX @tab non-compliant MPEG-4 generated by old Xvid with interlacing bug
@end multitable
-
@@ -11,18 +11,8 @@ programmatic use.

@table @option

-@item ich, in_channel_count
-Set the number of input channels. Default value is 0. Setting this
-value is not mandatory if the corresponding channel layout
-@option{in_channel_layout} is set.
-
-@item och, out_channel_count
-Set the number of output channels. Default value is 0. Setting this
-value is not mandatory if the corresponding channel layout
-@option{out_channel_layout} is set.
-
-@item uch, used_channel_count
-Set the number of used input channels. Default value is 0. This option is
+@item uchl, used_chlayout
+Set used input channel layout. Default is unset. This option is
 only used for special remapping.

@item isr, in_sample_rate
@@ -41,8 +31,8 @@ Specify the output sample format. It is set by default to @code{none}.
 Set the internal sample format. Default value is @code{none}.
 This will automatically be chosen when it is not explicitly set.

-@item icl, in_channel_layout
-@item ocl, out_channel_layout
+@item ichl, in_chlayout
+@item ochl, out_chlayout
 Set the input/output channel layout.

 See @ref{channel layout syntax,,the Channel Layout section in the ffmpeg-utils(1) manual,ffmpeg-utils}
@@ -20,8 +20,57 @@
 # 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 $package_version = ff_get_conf('PACKAGE_VERSION');
+$package_version =~ s/\+dev$//;
+my $program_version_num = version->declare($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);
+
+my %sectioning_commands = %Texinfo::Common::sectioning_commands;
+if (scalar(keys(%sectioning_commands)) == 0) {
+  %sectioning_commands = %Texinfo::Commands::sectioning_heading_commands;
+}
+
+my %root_commands = %Texinfo::Common::root_commands;
+if (scalar(keys(%root_commands)) == 0) {
+  %root_commands = %Texinfo::Commands::root_commands;
+}

 sub ffmpeg_heading_command($$$$$)
 {
@@ -40,6 +89,9 @@ sub ffmpeg_heading_command($$$$$)
        return $result;
    }

+    # no need to set it as the $element_id is output unconditionally
+    my $heading_id;
+
    my $element_id = $self->command_id($command);
    $result .= "<a name=\"$element_id\"></a>\n"
        if (defined($element_id) and $element_id ne '');
@@ -47,24 +99,40 @@ sub ffmpeg_heading_command($$$$$)
    print STDERR "Process $command "
        .Texinfo::Structuring::_print_root_command_texi($command)."\n"
            if ($self->get_conf('DEBUG'));
-    my $element;
-    if ($Texinfo::Common::root_commands{$command->{'cmdname'}}
-        and $command->{'parent'}
-        and $command->{'parent'}->{'type'}
-        and $command->{'parent'}->{'type'} eq 'element') {
-        $element = $command->{'parent'};
+    my $output_unit;
+    if ($root_commands{$command->{'cmdname'}}) {
+        if ($command->{'associated_unit'}) {
+          $output_unit = $command->{'associated_unit'};
+        } elsif ($command->{'structure'}
+                 and $command->{'structure'}->{'associated_unit'}) {
+          $output_unit = $command->{'structure'}->{'associated_unit'};
+        } elsif ($command->{'parent'}
+                 and $command->{'parent'}->{'type'}
+                 and $command->{'parent'}->{'type'} eq 'element') {
+          $output_unit = $command->{'parent'};
+        }
    }
-    if ($element) {
-        $result .= &{$self->{'format_element_header'}}($self, $cmdname,
-                                                       $command, $element);
+
+    if ($output_unit) {
+        $result .= &{get_formatting_function($self, 'format_element_header')}($self, $cmdname,
+                                                       $command, $output_unit);
    }

    my $heading_level;
    # node is used as heading if there is nothing else.
    if ($cmdname eq 'node') {
-        if (!$element or (!$element->{'extra'}->{'section'}
-            and $element->{'extra'}->{'node'}
-            and $element->{'extra'}->{'node'} eq $command
+        if (!$output_unit or
+            (((!$output_unit->{'extra'}->{'section'}
+              and $output_unit->{'extra'}->{'node'}
+              and $output_unit->{'extra'}->{'node'} eq $command)
+             or
+             ((($output_unit->{'extra'}->{'unit_command'}
+                and $output_unit->{'extra'}->{'unit_command'} eq $command)
+               or
+               ($output_unit->{'unit_command'}
+                and $output_unit->{'unit_command'} eq $command))
+              and $command->{'extra'}
+              and not $command->{'extra'}->{'associated_section'}))
             # bogus node may not have been normalized
            and defined($command->{'extra'}->{'normalized'}))) {
            if ($command->{'extra'}->{'normalized'} eq 'Top') {
@@ -74,7 +142,15 @@ sub ffmpeg_heading_command($$$$$)
            }
        }
    } else {
-        $heading_level = $command->{'level'};
+        if (defined($command->{'extra'})
+            and defined($command->{'extra'}->{'section_level'})) {
+          $heading_level = $command->{'extra'}->{'section_level'};
+        } elsif ($command->{'structure'}
+                 and defined($command->{'structure'}->{'section_level'})) {
+          $heading_level = $command->{'structure'}->{'section_level'};
+        } else {
+          $heading_level = $command->{'level'};
+        }
    }

    my $heading = $self->command_text($command);
@@ -82,8 +158,8 @@ sub ffmpeg_heading_command($$$$$)
    # if there is an error in the node.
    if (defined($heading) and $heading ne '' and defined($heading_level)) {

-        if ($Texinfo::Common::root_commands{$cmdname}
-            and $Texinfo::Common::sectioning_commands{$cmdname}) {
+        if ($root_commands{$cmdname}
+            and $sectioning_commands{$cmdname}) {
            my $content_href = $self->command_contents_href($command, 'contents',
                                                            $self->{'current_filename'});
            if ($content_href) {
@@ -103,7 +179,13 @@ sub ffmpeg_heading_command($$$$$)
            }
        }

-        if ($self->in_preformatted()) {
+        my $in_preformatted;
+        if ($program_version_num >= 7.001090) {
+          $in_preformatted = $self->in_preformatted_context();
+        } else {
+          $in_preformatted = $self->in_preformatted();
+        }
+        if ($in_preformatted) {
            $result .= $heading."\n";
        } else {
            # if the level was changed, set the command name right
@@ -112,37 +194,41 @@ sub ffmpeg_heading_command($$$$$)
                $cmdname
                    = $Texinfo::Common::level_to_structuring_command{$cmdname}->[$heading_level];
            }
-            $result .= &{$self->{'format_heading_text'}}(
+            if ($program_version_num >= 7.000000) {
+                $result .= &{get_formatting_function($self,'format_heading_text')}($self,
+                     $cmdname, [$cmdname], $heading,
+                     $heading_level +$self->get_conf('CHAPTER_HEADER_LEVEL') -1,
+                     $heading_id, $command);
+
+            } else {
+              $result .= &{get_formatting_function($self,'format_heading_text')}(
                        $self, $cmdname, $heading,
                        $heading_level +
                        $self->get_conf('CHAPTER_HEADER_LEVEL') - 1, $command);
+            }
        }
    }
    $result .= $content if (defined($content));
    return $result;
 }

-foreach my $command (keys(%Texinfo::Common::sectioning_commands), 'node') {
+foreach my $command (keys(%sectioning_commands), 'node') {
    texinfo_register_command_formatting($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($$$)
@@ -151,17 +237,56 @@ sub ffmpeg_begin_file($$$)
    my $filename = shift;
    my $element = shift;

-    my $command;
-    if ($element and $self->get_conf('SPLIT')) {
-        $command = $self->element_command($element);
+    my ($element_command, $node_command, $command_for_title);
+    if ($element) {
+        if ($element->{'unit_command'}) {
+          $element_command = $element->{'unit_command'};
+        } elsif ($self->can('tree_unit_element_command')) {
+          $element_command = $self->tree_unit_element_command($element);
+        } elsif ($self->can('tree_unit_element_command')) {
+          $element_command = $self->element_command($element);
+        }
+
+       $node_command = $element_command;
+       if ($element_command and $element_command->{'cmdname'}
+           and $element_command->{'cmdname'} ne 'node'
+           and $element_command->{'extra'}
+           and $element_command->{'extra'}->{'associated_node'}) {
+         $node_command = $element_command->{'extra'}->{'associated_node'};
+       }
+
+       $command_for_title = $element_command if ($self->get_conf('SPLIT'));
    }

-    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);
+    my ($title, $description, $keywords, $encoding, $date, $css_lines, $doctype,
+        $root_html_element_attributes, $body_attributes, $copying_comment,
+        $after_body_open, $extra_head, $program_and_version, $program_homepage,
+        $program, $generator);
+    if ($program_version_num >= 7.001090) {
+        ($title, $description, $keywords, $encoding, $date, $css_lines, $doctype,
+         $root_html_element_attributes, $body_attributes, $copying_comment,
+         $after_body_open, $extra_head, $program_and_version, $program_homepage,
+         $program, $generator) = $self->_file_header_information($command_for_title,
+                                                                 $filename);
+    } elsif ($program_version_num >= 7.000000) {
+        ($title, $description, $encoding, $date, $css_lines, $doctype,
+         $root_html_element_attributes, $copying_comment, $after_body_open,
+         $extra_head, $program_and_version, $program_homepage,
+         $program, $generator) = $self->_file_header_information($command_for_title,
+                                                                 $filename);
+    } else {
+        ($title, $description, $encoding, $date, $css_lines,
+         $doctype, $root_html_element_attributes, $copying_comment,
+         $after_body_open, $extra_head, $program_and_version, $program_homepage,
+         $program, $generator) = $self->_file_header_informations($command_for_title);
+    }

-    my $links = $self->_get_links ($filename, $element);
+    my $links;
+    if ($program_version_num >= 7.000000) {
+      $links = $self->_get_links($filename, $element, $node_command);
+    } else {
+      $links = $self->_get_links ($filename, $element);
+    }

    my $head1 = $ENV{"FFMPEG_HEADER1"} || <<EOT;
 <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
@@ -204,13 +329,25 @@ sub ffmpeg_program_string($)
  if (defined($self->get_conf('PROGRAM'))
      and $self->get_conf('PROGRAM') ne ''
      and defined($self->get_conf('PACKAGE_URL'))) {
-    return $self->convert_tree(
+    if ($program_version_num >= 7.001090) {
+     return $self->convert_tree(
+      $self->cdt('This document was generated using @uref{{program_homepage}, @emph{{program}}}.',
+         { 'program_homepage' => {'text' => $self->get_conf('PACKAGE_URL')},
+           'program' => {'text' => $self->get_conf('PROGRAM') }}));
+    } else {
+     return $self->convert_tree(
      $self->gdt('This document was generated using @uref{{program_homepage}, @emph{{program}}}.',
-         { 'program_homepage' => $self->get_conf('PACKAGE_URL'),
-           'program' => $self->get_conf('PROGRAM') }));
+         { 'program_homepage' => {'text' => $self->get_conf('PACKAGE_URL')},
+           'program' => {'text' => $self->get_conf('PROGRAM') }}));
+    }
  } else {
-    return $self->convert_tree(
-      $self->gdt('This document was generated automatically.'));
+    if ($program_version_num >= 7.001090) {
+      return $self->convert_tree(
+        $self->cdt('This document was generated automatically.'));
+    } else {
+      return $self->convert_tree(
+        $self->gdt('This document was generated automatically.'));
+    }
  }
 }
 if ($program_version_6_8) {
@@ -223,7 +360,7 @@ 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;">
        $program_string
@@ -244,7 +381,7 @@ if ($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($$$$)
 {
    return '';
@@ -262,8 +399,14 @@ sub ffmpeg_float($$$$$)
    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 +478,13 @@ sub ffmpeg_float($$$$$)
            $caption->{'args'}->[0], 'float caption');
    }
    if ($prepended_text.$caption_text ne '') {
-        $prepended_text = $self->_attribute_class('div','float-caption'). '>'
-                . $prepended_text;
+        if ($program_version_num >= 7.000000) {
+            $prepended_text = $self->html_attribute_class('div',['float-caption']). '>'
+                    . $prepended_text;
+        } else {
+            $prepended_text = $self->_attribute_class('div','float-caption'). '>'
+                    . $prepended_text;
+        }
        $caption_text .= '</div>';
    }
    my $html_class = '';
@@ -349,8 +497,13 @@ sub ffmpeg_float($$$$$)
        $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',
@@ -44,4 +44,3 @@ a+b*c;
 here the reader knows that a,b,c are meant to be signed integers but for C
 standard compliance / to avoid undefined behavior they are stored in unsigned
 ints.
-
@@ -15,6 +15,7 @@ OBJS-$(HAVE_LASX)      += $(LASX-OBJS)       $(LASX-OBJS-yes)
 OBJS-$(HAVE_ALTIVEC) += $(ALTIVEC-OBJS) $(ALTIVEC-OBJS-yes)
 OBJS-$(HAVE_VSX)     += $(VSX-OBJS) $(VSX-OBJS-yes)

+OBJS-$(HAVE_RV)      += $(RV-OBJS)      $(RV-OBJS-yes)
 OBJS-$(HAVE_RVV)     += $(RVV-OBJS)     $(RVV-OBJS-yes)

 OBJS-$(HAVE_MMX)     += $(MMX-OBJS)     $(MMX-OBJS-yes)
@@ -1,3 +1,5 @@
+#!/bin/sh
+
 toupper(){
    echo "$@" | tr abcdefghijklmnopqrstuvwxyz ABCDEFGHIJKLMNOPQRSTUVWXYZ
 }
@@ -1337,6 +1337,9 @@ static void do_video_out(OutputFile *of,
        in_picture->quality = enc->global_quality;
        in_picture->pict_type = forced_kf_apply(ost, &ost->kf, enc->time_base, in_picture, i);

+        if (ost->top_field_first >= 0)
+            in_picture->top_field_first = !!ost->top_field_first;
+
        ret = submit_encode_frame(of, ost, in_picture);
        if (ret == AVERROR_EOF)
            break;
@@ -628,8 +628,12 @@ static void add_input_streams(const OptionsContext *o, Demuxer *d)
        MATCH_PER_STREAM_OPT(codec_tags, str, codec_tag, ic, st);
        if (codec_tag) {
            uint32_t tag = strtol(codec_tag, &next, 0);
-            if (*next)
-                tag = AV_RL32(codec_tag);
+            if (*next) {
+                uint8_t buf[4] = { 0 };
+                memcpy(buf, codec_tag, FFMIN(sizeof(buf), strlen(codec_tag)));
+                tag = AV_RL32(buf);
+            }
+
            st->codecpar->codec_tag = tag;
        }

@@ -352,11 +352,13 @@ static int read_binary(const char *path, uint8_t **data, int *len)

    *len = fsize;

-    return 0;
+    ret = 0;
 fail:
    avio_close(io);
-    av_freep(data);
-    *len = 0;
+    if (ret < 0) {
+        av_freep(data);
+        *len = 0;
+    }
    return ret;
 }

@@ -606,8 +606,11 @@ static OutputStream *new_output_stream(Muxer *mux, const OptionsContext *o,
    MATCH_PER_STREAM_OPT(codec_tags, str, codec_tag, oc, st);
    if (codec_tag) {
        uint32_t tag = strtol(codec_tag, &next, 0);
-        if (*next)
-            tag = AV_RL32(codec_tag);
+        if (*next) {
+            uint8_t buf[4] = { 0 };
+            memcpy(buf, codec_tag, FFMIN(sizeof(buf), strlen(codec_tag)));
+            tag = AV_RL32(buf);
+        }
        ost->st->codecpar->codec_tag = tag;
        if (ost->enc_ctx)
            ost->enc_ctx->codec_tag = tag;
@@ -1819,11 +1822,11 @@ static int copy_metadata(Muxer *mux, AVFormatContext *ic,
    parse_meta_type(mux, inspec,  &type_in,  &idx_in,  &istream_spec);
    parse_meta_type(mux, outspec, &type_out, &idx_out, &ostream_spec);

-    if (type_in == 'g' || type_out == 'g')
+    if (type_in == 'g' || type_out == 'g' || (!*outspec && !ic))
        *metadata_global_manual = 1;
-    if (type_in == 's' || type_out == 's')
+    if (type_in == 's' || type_out == 's' || (!*outspec && !ic))
        *metadata_streams_manual = 1;
-    if (type_in == 'c' || type_out == 'c')
+    if (type_in == 'c' || type_out == 'c' || (!*outspec && !ic))
        *metadata_chapters_manual = 1;

    /* ic is NULL when just disabling automatic mappings */
@@ -2063,7 +2066,7 @@ static void parse_forced_key_frames(KeyframeForceCtx *kf, const Muxer *mux,
        if (next)
            *next++ = 0;

-        if (!memcmp(p, "chapters", 8)) {
+        if (strstr(p, "chapters") == p) {
            AVChapter * const *ch = mux->fc->chapters;
            unsigned int    nb_ch = mux->fc->nb_chapters;
            int j;
@@ -1998,6 +1998,8 @@ static int configure_audio_filters(VideoState *is, const char *afilters, int for
        goto end;

    if (force_output_format) {
+        av_bprint_clear(&bp);
+        av_channel_layout_describe_bprint(&is->audio_tgt.ch_layout, &bp);
        sample_rates   [0] = is->audio_tgt.freq;
        if ((ret = av_opt_set_int(filt_asink, "all_channel_counts", 0, AV_OPT_SEARCH_CHILDREN)) < 0)
            goto end;
@@ -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;
        }
@@ -68,7 +68,7 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
    unsigned char *planemap = c->planemap;
    int ret;

-    if (buf_size < planes * height * 2)
+    if (buf_size < planes * height * (2 + 2*((avctx->width+128)/129)))
        return AVERROR_INVALIDDATA;

    if ((ret = ff_get_buffer(avctx, frame, 0)) < 0)
@@ -95,6 +95,7 @@ get_next:
           duration in seconds is still correct (as is the number of bits in
           the frame). */
        if (avctx->codec_id != AV_CODEC_ID_AAC) {
+#if CONFIG_AC3_PARSER
            AC3HeaderInfo hdr, *phrd = &hdr;
            int offset = ff_ac3_find_syncword(buf, buf_size);

@@ -146,7 +147,9 @@ FF_ENABLE_DEPRECATION_WARNINGS
            if (hdr.bitstream_mode == 0x7 && hdr.channels > 1)
                avctx->audio_service_type = AV_AUDIO_SERVICE_TYPE_KARAOKE;
            bit_rate = hdr.bit_rate;
+#endif
        } else {
+#if CONFIG_AAC_PARSER
            AACADTSHeaderInfo hdr, *phrd = &hdr;
            int ret = avpriv_adts_header_parse(&phrd, buf, buf_size);

@@ -154,6 +157,7 @@ FF_ENABLE_DEPRECATION_WARNINGS
                return i;

            bit_rate = hdr.bit_rate;
+#endif
        }

        /* Calculate the average bit rate */
@@ -2856,8 +2856,8 @@ static void imdct_and_windowing_eld(AACContext *ac, SingleChannelElement *sce)
        ac->mdct512_fn(ac->mdct512, buf, in, sizeof(INTFLOAT));

    for (i = 0; i < n; i+=2) {
-        buf[i + 0] = -(USE_FIXED + 1)*buf[i + 0];
-        buf[i + 1] =  (USE_FIXED + 1)*buf[i + 1];
+        buf[i + 0] = -(UINTFLOAT)(USE_FIXED + 1)*buf[i + 0];
+        buf[i + 1] =  (UINTFLOAT)(USE_FIXED + 1)*buf[i + 1];
    }
    // Like with the regular IMDCT at this point we still have the middle half
    // of a transform but with even symmetry on the left and odd symmetry on
@@ -34,7 +34,7 @@
 #include "libavutil/common.h"
 #include "libavutil/libm.h"
 #include "libavutil/mathematics.h"
-#include "libavutil/mem.h"
+#include "libavutil/mem_internal.h"
 #define NR_ALLPASS_BANDS20 30
 #define NR_ALLPASS_BANDS34 50
 #define PS_AP_LINKS 3
@@ -267,7 +267,7 @@ static av_cold void lame_window_init(AacPsyContext *ctx, AVCodecContext *avctx)
        AacPsyChannel *pch = &ctx->ch[i];

        if (avctx->flags & AV_CODEC_FLAG_QSCALE)
-            pch->attack_threshold = psy_vbr_map[avctx->global_quality / FF_QP2LAMBDA].st_lrm;
+            pch->attack_threshold = psy_vbr_map[av_clip(avctx->global_quality / FF_QP2LAMBDA, 0, 10)].st_lrm;
        else
            pch->attack_threshold = lame_calc_attack_threshold(avctx->bit_rate / avctx->ch_layout.nb_channels / 1000);

@@ -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
@@ -358,18 +358,18 @@ function fft\n\()_neon, align=6
 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
+        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]
@@ -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
@@ -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

@@ -489,10 +489,10 @@ function ff_pred16x16_plane_neon_10, export=1
        mul             v2.8h,  v2.8h,  v0.8h
        mul             v3.8h,  v3.8h,  v0.8h
        addp            v2.8h,  v2.8h,  v3.8h
-        addp            v2.8h,  v2.8h,  v2.8h
-        addp            v2.4h,  v2.4h,  v2.4h
-        sshll           v3.4s,  v2.4h,  #2
-        saddw           v2.4s,  v3.4s,  v2.4h
+        saddlp          v2.4s,  v2.8h
+        addp            v2.4s,  v2.4s,  v2.4s
+        shl             v3.4s,  v2.4s,  #2
+        add             v2.4s,  v3.4s,  v2.4s
        rshrn           v4.4h,  v2.4s,  #6
        trn2            v5.4h,  v4.4h,  v4.4h
        add             v2.4h,  v4.4h,  v5.4h
@@ -502,28 +502,26 @@ function ff_pred16x16_plane_neon_10, export=1
        add             v7.4h,  v7.4h,  v0.4h
        shl             v2.4h,  v7.4h,  #4
        ssubl           v2.4s,  v2.4h,  v3.4h
-        shl             v3.4h,  v4.4h,  #4
        ext             v0.16b, v0.16b, v0.16b, #14
-        ssubl           v6.4s,  v5.4h,  v3.4h
+        sxtl            v6.4s,  v5.4h          // c

        mov             v0.h[0],  wzr
-        mul             v0.8h,  v0.8h,  v4.h[0]
        dup             v16.4s, v2.s[0]
        dup             v17.4s, v2.s[0]
-        dup             v2.8h,  v4.h[0]
-        dup             v3.4s,  v6.s[0]
-        shl             v2.8h,  v2.8h,  #3
-        saddw           v16.4s, v16.4s, v0.4h
-        saddw2          v17.4s, v17.4s, v0.8h
-        saddw           v3.4s,  v3.4s,  v2.4h
+        dup             v2.8h,  v4.h[0]        // b
+        dup             v3.4s,  v6.s[0]        // c
+        sshll           v2.4s,  v2.4h,  #3     // b * 8
+        smlal           v16.4s, v0.4h, v4.h[0]
+        smlal2          v17.4s, v0.8h, v4.h[0]
+        sub             v3.4s,  v3.4s,  v2.4s

        mov             w3,      #16
        mvni            v4.8h,   #0xFC, lsl #8 // 1023 for clipping
 1:
        sqshrun         v0.4h,  v16.4s, #5
        sqshrun2        v0.8h,  v17.4s, #5
-        saddw           v16.4s, v16.4s, v2.4h
-        saddw           v17.4s, v17.4s, v2.4h
+        add             v16.4s, v16.4s, v2.4s
+        add             v17.4s, v17.4s, v2.4s
        sqshrun         v1.4h,  v16.4s, #5
        sqshrun2        v1.8h,  v17.4s, #5
        add             v16.4s, v16.4s, v3.4s
@@ -595,12 +593,11 @@ function ff_pred8x8_plane_neon_10, export=1
        ssubl           v2.4s,  v2.4h,  v3.4h
        ext             v0.16b, v0.16b, v0.16b, #14
        mov             v0.h[0],  wzr
-        mul             v0.8h,  v0.8h,  v5.h[0]
        dup             v1.4s,  v2.s[0]
        dup             v2.4s,  v2.s[0]
        dup             v3.8h,  v5.h[1]
-        saddw           v1.4s,  v1.4s,  v0.4h
-        saddw2          v2.4s,  v2.4s,  v0.8h
+        smlal           v1.4s,  v0.4h,  v5.h[0]
+        smlal2          v2.4s,  v0.8h,  v5.h[0]
        mov             w3,  #8
        mvni            v4.8h,  #0xFC,  lsl #8 // 1023 for clipping
 1:
@@ -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
@@ -264,19 +264,19 @@ 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
@@ -343,11 +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
@@ -360,7 +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]

@@ -369,8 +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
@@ -399,7 +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
@@ -416,14 +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
@@ -491,20 +491,20 @@ endfunc

 .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]
@@ -523,16 +523,16 @@ 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
        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
-        mov              x1,  x6
-        add              x3,  x6, #(24 +3*32)
-        mov              x2, #32
-        mov              x4, #-32
+        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

        add             x4, sp, #(\offset + 64)
@@ -541,10 +541,10 @@ function func_tr_16x4_\name
        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

-        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

        ret
@@ -557,21 +557,21 @@ 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

        mov             x30, x15
        ret
@@ -591,35 +591,35 @@ idct_16x16 10
 // 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
@@ -42,41 +42,41 @@ endconst
        // void put_hevc_qpel_h(int16_t *dst,
        //                      uint8_t *_src, ptrdiff_t _srcstride,
        //                      int height, intptr_t mx, intptr_t my, int width)
-        dst        .req x0
-        dststride  .req x7
-        src        .req x1
-        srcstride  .req x2
-        height     .req x3
-        heightw    .req w3
-        mx         .req x4
-        width      .req w6
+        dst             .req x0
+        dststride       .req x7
+        src             .req x1
+        srcstride       .req x2
+        height          .req x3
+        heightw         .req w3
+        mx              .req x4
+        width           .req w6
 .endif
 .ifc \type, qpel_uni
        // void put_hevc_qpel_uni_h(uint8_t *_dst,  ptrdiff_t _dststride,
        //                          uint8_t *_src, ptrdiff_t _srcstride,
        //                          int height, intptr_t mx, intptr_t my, int width)
-        dst        .req x0
-        dststride  .req x1
-        src        .req x2
-        srcstride  .req x3
-        height     .req x4
-        heightw    .req w4
-        mx         .req x5
-        width      .req w7
+        dst             .req x0
+        dststride       .req x1
+        src             .req x2
+        srcstride       .req x3
+        height          .req x4
+        heightw         .req w4
+        mx              .req x5
+        width           .req w7
 .endif
 .ifc \type, qpel_bi
        // void put_hevc_qpel_bi_h(uint8_t *_dst, ptrdiff_t _dststride,
        //                         uint8_t *_src, ptrdiff_t _srcstride,
        //                         int16_t *src2, int height, intptr_t mx,
        //                         intptr_t my, int width)
-        dst        .req x0
-        dststride  .req x1
-        src        .req x2
-        srcstride  .req x3
-        height     .req x5
-        heightw    .req w5
-        mx         .req x6
-        width      .req w8
+        dst             .req x0
+        dststride       .req x1
+        src             .req x2
+        srcstride       .req x3
+        height          .req x5
+        heightw         .req w5
+        mx              .req x6
+        width           .req w8
 .endif

 .ifc \type, qpel
@@ -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
@@ -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

@@ -17,146 +17,146 @@
 */

 .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
@@ -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
@@ -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
@@ -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
@@ -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

@@ -1579,11 +1579,11 @@ static int adpcm_decode_frame(AVCodecContext *avctx, AVFrame *frame,
                    nibble[0] = sign_extend(byte & 15, 4);
                    nibble[1] = sign_extend(byte >> 4, 4);

-                    out[2+n*2] = (nibble[0]*(scale<<14) + (history[0]*29336) - (history[1]*13136)) >> 14;
+                    out[2+n*2] = nibble[0]*scale + ((history[0]*3667 - history[1]*1642) >> 11);
                    history[1] = history[0];
                    history[0] = out[2+n*2];

-                    out[2+n*2+1] = (nibble[1]*(scale<<14) + (history[0]*29336) - (history[1]*13136)) >> 14;
+                    out[2+n*2+1] = nibble[1]*scale + ((history[0]*3667 - history[1]*1642) >> 11);
                    history[1] = history[0];
                    history[0] = out[2+n*2+1];
                }
@@ -145,8 +145,6 @@ typedef struct APEPredictor64 {
    uint64_t coeffsA[2][4];  ///< adaption coefficients
    uint64_t coeffsB[2][5];  ///< adaption coefficients
    int64_t historybuffer[HISTORY_SIZE + PREDICTOR_SIZE];
-
-    unsigned int sample_pos;
 } APEPredictor64;

 /** Decoder context */
@@ -860,8 +858,6 @@ static void init_predictor_decoder(APEContext *ctx)
    p64->lastA[0]   = p64->lastA[1]   = 0;

    p->sample_pos = 0;
-
-    p64->sample_pos = 0;
 }

 /** Get inverse sign of integer (-1 for positive, 1 for negative and 0 for zero) */
@@ -1170,7 +1166,8 @@ static void predictor_decode_mono_3930(APEContext *ctx, int count)
 static av_always_inline int predictor_update_filter(APEPredictor64 *p,
                                                    const int decoded, const int filter,
                                                    const int delayA,  const int delayB,
-                                                    const int adaptA,  const int adaptB)
+                                                    const int adaptA,  const int adaptB,
+                                                    int compression_level)
 {
    int64_t predictionA, predictionB;
    int32_t sign;
@@ -1198,7 +1195,13 @@ static av_always_inline int predictor_update_filter(APEPredictor64 *p,
                  p->buf[delayB - 3] * p->coeffsB[filter][3] +
                  p->buf[delayB - 4] * p->coeffsB[filter][4];

-    p->lastA[filter] = decoded + ((int64_t)((uint64_t)predictionA + (predictionB >> 1)) >> 10);
+    if (compression_level < COMPRESSION_LEVEL_INSANE) {
+        predictionA = (int32_t)predictionA;
+        predictionB = (int32_t)predictionB;
+        p->lastA[filter] = (int32_t)(decoded + (unsigned)((int32_t)(predictionA + (predictionB >> 1)) >> 10));
+    } else {
+        p->lastA[filter] = decoded + ((int64_t)((uint64_t)predictionA + (predictionB >> 1)) >> 10);
+    }
    p->filterA[filter] = p->lastA[filter] + ((int64_t)(p->filterA[filter] * 31ULL) >> 5);

    sign = APESIGN(decoded);
@@ -1226,10 +1229,12 @@ static void predictor_decode_stereo_3950(APEContext *ctx, int count)
    while (count--) {
        /* Predictor Y */
        *decoded0 = predictor_update_filter(p, *decoded0, 0, YDELAYA, YDELAYB,
-                                            YADAPTCOEFFSA, YADAPTCOEFFSB);
+                                            YADAPTCOEFFSA, YADAPTCOEFFSB,
+                                            ctx->compression_level);
        decoded0++;
        *decoded1 = predictor_update_filter(p, *decoded1, 1, XDELAYA, XDELAYB,
-                                            XADAPTCOEFFSA, XADAPTCOEFFSB);
+                                            XADAPTCOEFFSA, XADAPTCOEFFSB,
+                                            ctx->compression_level);
        decoded1++;

        /* Combined */
@@ -1611,13 +1616,24 @@ static int ape_decode_frame(AVCodecContext *avctx, AVFrame *frame,
    s->samples -= blockstodecode;

    if (avctx->err_recognition & AV_EF_CRCCHECK &&
-        s->fileversion >= 3900 && s->bps < 24) {
+        s->fileversion >= 3900) {
        uint32_t crc = s->CRC_state;
        const AVCRC *crc_tab = av_crc_get_table(AV_CRC_32_IEEE_LE);
+        int stride = s->bps == 24 ? 4 : (s->bps>>3);
+        int offset = s->bps == 24;
+        int bytes  = s->bps >> 3;
+
        for (i = 0; i < blockstodecode; i++) {
            for (ch = 0; ch < s->channels; ch++) {
-                uint8_t *smp = frame->data[ch] + (i*(s->bps >> 3));
-                crc = av_crc(crc_tab, crc, smp, s->bps >> 3);
+#if HAVE_BIGENDIAN
+                uint8_t *smp_native = frame->data[ch] + i*stride;
+                uint8_t smp[4];
+                for(int j = 0; j<stride; j++)
+                    smp[j] = smp_native[stride-j-1];
+#else
+                uint8_t *smp = frame->data[ch] + i*stride;
+#endif
+                crc = av_crc(crc_tab, crc, smp+offset, bytes);
            }
        }

@@ -48,4 +48,3 @@ function ff_scalarproduct_int16_neon, export=1
        vmov.32         r0,  d3[0]
        bx              lr
 endfunc
-
@@ -229,7 +229,7 @@ A .endif
  .endif

        // Begin loop
-01:
+1:
  .if TOTAL_TAPS == 0
        // Things simplify a lot in this case
        // In fact this could be pipelined further if it's worth it...
@@ -241,7 +241,7 @@ A .endif
        str     ST0, [PST, #-4]!
        str     ST0, [PST, #4 * (MAX_BLOCKSIZE + MAX_FIR_ORDER)]
        str     ST0, [PSAMP], #4 * MAX_CHANNELS
-        bne     01b
+        bne     1b
  .else
    .if \fir_taps & 1
      .set LOAD_REG, 1
@@ -333,7 +333,7 @@ T       orr     AC0, AC0, AC1
        str     ST3, [PST, #-4]!
        str     ST2, [PST, #4 * (MAX_BLOCKSIZE + MAX_FIR_ORDER)]
        str     ST3, [PSAMP], #4 * MAX_CHANNELS
-        bne     01b
+        bne     1b
  .endif
        b       99f

@@ -170,7 +170,7 @@ static uint8_t get_shear_params_valid(AV1DecContext *s, int idx)
    int16_t alpha, beta, gamma, delta, divf, divs;
    int64_t v, w;
    int32_t *param = &s->cur_frame.gm_params[idx][0];
-    if (param[2] < 0)
+    if (param[2] <= 0)
        return 0;

    alpha = av_clip_int16(param[2] - (1 << AV1_WARPEDMODEL_PREC_BITS));
@@ -675,7 +675,7 @@ static int set_context_with_sequence(AVCodecContext *avctx,
    avctx->color_range =
        seq->color_config.color_range ? AVCOL_RANGE_JPEG : AVCOL_RANGE_MPEG;
    avctx->color_primaries = seq->color_config.color_primaries;
-    avctx->colorspace = seq->color_config.color_primaries;
+    avctx->colorspace = seq->color_config.matrix_coefficients;
    avctx->color_trc = seq->color_config.transfer_characteristics;

    switch (seq->color_config.chroma_sample_position) {
@@ -870,7 +870,7 @@ static int binkb_decode_plane(BinkContext *c, AVFrame *frame, GetBitContext *gb,

    binkb_init_bundles(c);
    ref_start = frame->data[plane_idx];
-    ref_end   = frame->data[plane_idx] + (bh * frame->linesize[plane_idx] + bw) * 8;
+    ref_end   = frame->data[plane_idx] + ((bh - 1) * frame->linesize[plane_idx] + bw - 1) * 8;

    for (i = 0; i < 64; i++)
        coordmap[i] = (i & 7) + (i >> 3) * stride;
@@ -926,7 +926,7 @@ static int binkb_decode_plane(BinkContext *c, AVFrame *frame, GetBitContext *gb,
                xoff = binkb_get_value(c, BINKB_SRC_X_OFF);
                yoff = binkb_get_value(c, BINKB_SRC_Y_OFF) + ybias;
                ref = dst + xoff + yoff * stride;
-                if (ref < ref_start || ref + 8*stride > ref_end) {
+                if (ref < ref_start || ref > ref_end) {
                    av_log(c->avctx, AV_LOG_WARNING, "Reference block is out of bounds\n");
                } else if (ref + 8*stride < dst || ref >= dst + 8*stride) {
                    c->put_pixels_tab(dst, ref, stride, 8);
@@ -942,7 +942,7 @@ static int binkb_decode_plane(BinkContext *c, AVFrame *frame, GetBitContext *gb,
                xoff = binkb_get_value(c, BINKB_SRC_X_OFF);
                yoff = binkb_get_value(c, BINKB_SRC_Y_OFF) + ybias;
                ref = dst + xoff + yoff * stride;
-                if (ref < ref_start || ref + 8 * stride > ref_end) {
+                if (ref < ref_start || ref > ref_end) {
                    av_log(c->avctx, AV_LOG_WARNING, "Reference block is out of bounds\n");
                } else if (ref + 8*stride < dst || ref >= dst + 8*stride) {
                    c->put_pixels_tab(dst, ref, stride, 8);
@@ -974,7 +974,7 @@ static int binkb_decode_plane(BinkContext *c, AVFrame *frame, GetBitContext *gb,
                xoff = binkb_get_value(c, BINKB_SRC_X_OFF);
                yoff = binkb_get_value(c, BINKB_SRC_Y_OFF) + ybias;
                ref = dst + xoff + yoff * stride;
-                if (ref < ref_start || ref + 8 * stride > ref_end) {
+                if (ref < ref_start || ref > ref_end) {
                    av_log(c->avctx, AV_LOG_WARNING, "Reference block is out of bounds\n");
                } else if (ref + 8*stride < dst || ref >= dst + 8*stride) {
                    c->put_pixels_tab(dst, ref, stride, 8);
@@ -155,6 +155,7 @@ static int intlist_read(BonkContext *s, int *buf, int entries, int base_2_part)
    int n_zeros = 0, step = 256, dominant = 0;
    int pos = 0, level = 0;
    BitCount *bits = s->bits;
+    int passes = 1;

    memset(buf, 0, entries * sizeof(*buf));
    if (base_2_part) {
@@ -216,24 +217,28 @@ static int intlist_read(BonkContext *s, int *buf, int entries, int base_2_part)
    x = 0;
    n_zeros = 0;
    for (i = 0; n_zeros < entries; i++) {
+        if (x >= max_x)
+            return AVERROR_INVALIDDATA;
+
        if (pos >= entries) {
            pos = 0;
-            level += 1 << low_bits;
+            level += passes << low_bits;
+            passes = 1;
+            if (bits[x].bit && bits[x].count > entries - n_zeros)
+                passes =  bits[x].count / (entries - n_zeros);
        }

        if (level > 1 << 16)
            return AVERROR_INVALIDDATA;

-        if (x >= max_x)
-            return AVERROR_INVALIDDATA;
-
        if (buf[pos] >= level) {
            if (bits[x].bit)
-                buf[pos] += 1 << low_bits;
+                buf[pos] += passes << low_bits;
            else
                n_zeros++;

-            bits[x].count--;
+            av_assert1(bits[x].count >= passes);
+            bits[x].count -= passes;
            x += bits[x].count == 0;
        }

@@ -265,14 +270,14 @@ static inline int shift(int a, int b)

 static int predictor_calc_error(int *k, int *state, int order, int error)
 {
-    int i, x = error - shift_down(k[order-1] * state[order-1], LATTICE_SHIFT);
+    int i, x = error - (unsigned)shift_down(k[order-1] * (unsigned)state[order-1], LATTICE_SHIFT);
    int *k_ptr = &(k[order-2]),
        *state_ptr = &(state[order-2]);

    for (i = order-2; i >= 0; i--, k_ptr--, state_ptr--) {
        unsigned k_value = *k_ptr, state_value = *state_ptr;

-        x -= shift_down(k_value * state_value, LATTICE_SHIFT);
+        x -= (unsigned) shift_down(k_value * (unsigned)state_value, LATTICE_SHIFT);
        state_ptr[1] = state_value + shift_down(k_value * x, LATTICE_SHIFT);
    }

@@ -78,7 +78,7 @@ int64_t ff_dot_product(const int16_t *a, const int16_t *b, int length);
 *
 * @return value << offset, if offset>=0; value >> -offset - otherwise
 */
-static inline int bidir_sal(int value, int offset)
+static inline unsigned bidir_sal(unsigned value, int offset)
 {
    if(offset < 0) return value >> -offset;
    else           return value <<  offset;
@@ -90,4 +90,3 @@ const FFCodec ff_cljr_decoder = {
    FF_CODEC_DECODE_CB(decode_frame),
    .p.capabilities = AV_CODEC_CAP_DR1,
 };
-
@@ -70,6 +70,9 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *rframe,
    int buf_size = avpkt->size;
    CamStudioContext *c = avctx->priv_data;
    int ret;
+    int bpp = avctx->bits_per_coded_sample / 8;
+    int bugdelta = FFALIGN(avctx->width * bpp, 4)       * avctx->height
+                 -        (avctx->width     & ~3) * bpp * avctx->height;

    if (buf_size < 2) {
        av_log(avctx, AV_LOG_ERROR, "coded frame too small\n");
@@ -83,7 +86,7 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *rframe,
    switch ((buf[0] >> 1) & 7) {
    case 0: { // lzo compression
        int outlen = c->decomp_size, inlen = buf_size - 2;
-        if (av_lzo1x_decode(c->decomp_buf, &outlen, &buf[2], &inlen) || outlen) {
+        if (av_lzo1x_decode(c->decomp_buf, &outlen, &buf[2], &inlen) || (outlen && outlen != bugdelta)) {
            av_log(avctx, AV_LOG_ERROR, "error during lzo decompression\n");
            return AVERROR_INVALIDDATA;
        }
@@ -92,7 +95,7 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *rframe,
    case 1: { // zlib compression
 #if CONFIG_ZLIB
        unsigned long dlen = c->decomp_size;
-        if (uncompress(c->decomp_buf, &dlen, &buf[2], buf_size - 2) != Z_OK || dlen != c->decomp_size) {
+        if (uncompress(c->decomp_buf, &dlen, &buf[2], buf_size - 2) != Z_OK || (dlen != c->decomp_size && dlen != c->decomp_size - bugdelta)) {
            av_log(avctx, AV_LOG_ERROR, "error during zlib decompression\n");
            return AVERROR_INVALIDDATA;
        }
@@ -140,7 +140,7 @@ static int extract_packet_props(AVCodecInternal *avci, const AVPacket *pkt)
    if (pkt) {
        ret = av_packet_copy_props(avci->last_pkt_props, pkt);
        if (!ret)
-            avci->last_pkt_props->opaque = (void *)(intptr_t)pkt->size; // Needed for ff_decode_frame_props().
+            avci->last_pkt_props->stream_index = pkt->size; // Needed for ff_decode_frame_props().
    }
    return ret;
 }
@@ -461,7 +461,7 @@ FF_ENABLE_DEPRECATION_WARNINGS
        pkt->dts                  = AV_NOPTS_VALUE;
        if (!(codec->caps_internal & FF_CODEC_CAP_SETS_FRAME_PROPS)) {
            // See extract_packet_props() comment.
-            avci->last_pkt_props->opaque = (void *)((intptr_t)avci->last_pkt_props->opaque - consumed);
+            avci->last_pkt_props->stream_index = avci->last_pkt_props->stream_index - consumed;
            avci->last_pkt_props->pts = AV_NOPTS_VALUE;
            avci->last_pkt_props->dts = AV_NOPTS_VALUE;
        }
@@ -1355,7 +1355,7 @@ int ff_decode_frame_props(AVCodecContext *avctx, AVFrame *frame)
        int ret = ff_decode_frame_props_from_pkt(avctx, frame, pkt);
        if (ret < 0)
            return ret;
-        frame->pkt_size     = (int)(intptr_t)pkt->opaque;
+        frame->pkt_size = pkt->stream_index;
    }
 #if FF_API_REORDERED_OPAQUE
 FF_DISABLE_DEPRECATION_WARNINGS
@@ -157,7 +157,7 @@ static inline uint64_t get_ue_coef(GetBitContext *gb, const AVDOVIRpuDataHeader

    case RPU_COEFF_FLOAT:
        fpart.u32 = get_bits_long(gb, 32);
-        return fpart.f32 * (1 << hdr->coef_log2_denom);
+        return fpart.f32 * (1LL << hdr->coef_log2_denom);
    }

    return 0; /* unreachable */
@@ -176,7 +176,7 @@ static inline int64_t get_se_coef(GetBitContext *gb, const AVDOVIRpuDataHeader *

    case RPU_COEFF_FLOAT:
        fpart.u32 = get_bits_long(gb, 32);
-        return fpart.f32 * (1 << hdr->coef_log2_denom);
+        return fpart.f32 * (1LL << hdr->coef_log2_denom);
    }

    return 0; /* unreachable */
@@ -444,7 +444,7 @@ static int dpcm_decode_frame(AVCodecContext *avctx, AVFrame *frame,
            if (n & 0x80)
                s->sample[idx] = sign_extend((n & 0x7f) << 9, 16);
            else
-                s->sample[idx] += s->scale * wady_table[n & 0x7f];
+                s->sample[idx] += s->scale * (unsigned)wady_table[n & 0x7f];
            *output_samples++ = av_clip_int16(s->sample[idx]);
            idx ^= stereo;
        }
@@ -337,4 +337,3 @@ const AVDVProfile *av_dv_codec_profile2(int width, int height,

    return p;
 }
-
@@ -376,7 +376,8 @@ static int encode_dvd_subtitles(AVCodecContext *avctx,
    x2 = vrect.x + vrect.w - 1;
    y2 = vrect.y + vrect.h - 1;

-    if (x2 > avctx->width || y2 > avctx->height) {
+    if ((avctx->width  > 0 && x2 > avctx->width) ||
+        (avctx->height > 0 && y2 > avctx->height)) {
        av_log(avctx, AV_LOG_ERROR, "canvas_size(%d:%d) is too small(%d:%d) for render\n",
               avctx->width, avctx->height, x2, y2);
        ret = AVERROR(EINVAL);
@@ -104,7 +104,9 @@ static av_cold int dvvideo_encode_init(AVCodecContext *avctx)
    ff_fdctdsp_init(&fdsp, avctx);
    ff_me_cmp_init(&mecc, avctx);
    ff_pixblockdsp_init(&pdsp, avctx);
-    ff_set_cmp(&mecc, mecc.ildct_cmp, avctx->ildct_cmp);
+    ret = ff_set_cmp(&mecc, mecc.ildct_cmp, avctx->ildct_cmp);
+    if (ret < 0)
+        return AVERROR(EINVAL);

    s->get_pixels = pdsp.get_pixels;
    s->ildct_cmp  = mecc.ildct_cmp[5];
@@ -89,11 +89,6 @@ static CodeBook unpack_codebook(GetBitContext* gb, unsigned depth,
    unsigned i, j;
    CodeBook cb = { 0 };

-    if (size >= INT_MAX / 34 || get_bits_left(gb) < size * 34)
-        return cb;
-
-    if (size >= INT_MAX / sizeof(MacroBlock))
-        return cb;
    cb.blocks = av_malloc(size ? size * sizeof(MacroBlock) : 1);
    if (!cb.blocks)
        return cb;
@@ -163,7 +158,7 @@ static MacroBlock decode_macroblock(Escape124Context* s, GetBitContext* gb,

    // This condition can occur with invalid bitstreams and
    // *codebook_index == 2
-    if (block_index >= s->codebooks[*codebook_index].size)
+    if (block_index >= s->codebooks[*codebook_index].size || !s->codebooks[*codebook_index].blocks)
        return (MacroBlock) { { 0 } };

    return s->codebooks[*codebook_index].blocks[block_index];
@@ -225,7 +220,7 @@ static int escape124_decode_frame(AVCodecContext *avctx, AVFrame *frame,
    // represent a lower bound of the space needed for skipped superblocks. Non
    // skipped SBs need more space.
    if (get_bits_left(&gb) < 64 + s->num_superblocks * 23LL / 4320)
-        return -1;
+        return AVERROR_INVALIDDATA;

    frame_flags = get_bits_long(&gb, 32);
    frame_size  = get_bits_long(&gb, 32);
@@ -242,7 +237,7 @@ static int escape124_decode_frame(AVCodecContext *avctx, AVFrame *frame,
        if ((ret = av_frame_ref(frame, s->frame)) < 0)
            return ret;

-        return frame_size;
+        return 0;
    }

    for (i = 0; i < 3; i++) {
@@ -276,9 +271,14 @@ static int escape124_decode_frame(AVCodecContext *avctx, AVFrame *frame,
            }

            av_freep(&s->codebooks[i].blocks);
+            if (cb_size >= INT_MAX / 34 || get_bits_left(&gb) < (int)cb_size * 34)
+                return AVERROR_INVALIDDATA;
+
+            if (cb_size >= INT_MAX / sizeof(MacroBlock))
+                return AVERROR_INVALIDDATA;
            s->codebooks[i] = unpack_codebook(&gb, cb_depth, cb_size);
            if (!s->codebooks[i].blocks)
-                return -1;
+                return AVERROR(ENOMEM);
        }
    }

@@ -371,7 +371,7 @@ static int escape124_decode_frame(AVCodecContext *avctx, AVFrame *frame,

    *got_frame = 1;

-    return frame_size;
+    return 0;
 }


@@ -334,7 +334,10 @@ static int huf_unpack_enc_table(GetByteContext *gb,
        return ret;

    for (; im <= iM; im++) {
-        uint64_t l = freq[im] = get_bits(&gbit, 6);
+        int l;
+        if (get_bits_left(&gbit) < 6)
+            return AVERROR_INVALIDDATA;
+        l = freq[im] = get_bits(&gbit, 6);

        if (l == LONG_ZEROCODE_RUN) {
            int zerun = get_bits(&gbit, 8) + SHORTEST_LONG_RUN;
@@ -1930,8 +1933,10 @@ static int decode_header(EXRContext *s, AVFrame *frame)

            bytestream2_get_buffer(gb, key, FFMIN(sizeof(key) - 1, var_size));
            if (strncmp("scanlineimage", key, var_size) &&
-                strncmp("tiledimage", key, var_size))
-                return AVERROR_PATCHWELCOME;
+                strncmp("tiledimage", key, var_size)) {
+                ret = AVERROR_PATCHWELCOME;
+                goto fail;
+            }

            continue;
        } else if ((var_size = check_header_variable(s, "preview",
@@ -1939,12 +1944,16 @@ static int decode_header(EXRContext *s, AVFrame *frame)
            uint32_t pw = bytestream2_get_le32(gb);
            uint32_t ph = bytestream2_get_le32(gb);
            uint64_t psize = pw * ph;
-            if (psize > INT64_MAX / 4)
-                return AVERROR_INVALIDDATA;
+            if (psize > INT64_MAX / 4) {
+                ret = AVERROR_INVALIDDATA;
+                goto fail;
+            }
            psize *= 4;

-            if ((int64_t)psize >= bytestream2_get_bytes_left(gb))
-                return AVERROR_INVALIDDATA;
+            if ((int64_t)psize >= bytestream2_get_bytes_left(gb)) {
+                ret = AVERROR_INVALIDDATA;
+                goto fail;
+            }

            bytestream2_skip(gb, psize);

@@ -50,4 +50,3 @@ static inline int RENAME(get_context)(PlaneContext *p, TYPE *src,
               p->quant_table[1][(LT - T) & 0xFF] +
               p->quant_table[2][(T - RT) & 0xFF];
 }
-
@@ -475,6 +475,11 @@ static int read_extra_header(FFV1Context *f)
        return AVERROR_INVALIDDATA;
    }

+    if (f->num_h_slices > MAX_SLICES / f->num_v_slices) {
+        av_log(f->avctx, AV_LOG_ERROR, "slice count unsupported\n");
+        return AVERROR_PATCHWELCOME;
+    }
+
    f->quant_table_count = get_symbol(c, state, 0);
    if (f->quant_table_count > (unsigned)MAX_QUANT_TABLES || !f->quant_table_count) {
        av_log(f->avctx, AV_LOG_ERROR, "quant table count %d is invalid\n", f->quant_table_count);
@@ -201,4 +201,3 @@ static int RENAME(encode_rgb_frame)(FFV1Context *s, const uint8_t *src[4],
    }
    return 0;
 }
-
@@ -366,19 +366,19 @@ static int decode_subframe_fixed(FLACContext *s, int32_t *decoded,
        break;                                                        \
    case 1:                                                           \
        for (int i = pred_order; i < blocksize; i++)                  \
-            decoded[i] = (int64_t)residual[i] + (int64_t)decoded[i-1];\
+            decoded[i] = (uint64_t)residual[i] + (uint64_t)decoded[i-1];\
        break;                                                        \
    case 2:                                                           \
        for (int i = pred_order; i < blocksize; i++)                  \
-            decoded[i] = (int64_t)residual[i] + 2*(int64_t)decoded[i-1] - (int64_t)decoded[i-2];  \
+            decoded[i] = (uint64_t)residual[i] + 2*(uint64_t)decoded[i-1] - (uint64_t)decoded[i-2];  \
        break;                                                        \
    case 3:                                                           \
        for (int i = pred_order; i < blocksize; i++)                  \
-            decoded[i] = (int64_t)residual[i] + 3*(int64_t)decoded[i-1] - 3*(int64_t)decoded[i-2] + (int64_t)decoded[i-3];   \
+            decoded[i] = (uint64_t)residual[i] + 3*(uint64_t)decoded[i-1] - 3*(uint64_t)decoded[i-2] + (uint64_t)decoded[i-3];   \
        break;                                                        \
    case 4:                                                           \
        for (int i = pred_order; i < blocksize; i++)                  \
-            decoded[i] = (int64_t)residual[i] + 4*(int64_t)decoded[i-1] - 6*(int64_t)decoded[i-2] + 4*(int64_t)decoded[i-3] - (int64_t)decoded[i-4];   \
+            decoded[i] = (uint64_t)residual[i] + 4*(uint64_t)decoded[i-1] - 6*(uint64_t)decoded[i-2] + 4*(uint64_t)decoded[i-3] - (uint64_t)decoded[i-4];   \
        break;                                                        \
    default:                                                          \
        av_log(s->avctx, AV_LOG_ERROR, "illegal pred order %d\n", pred_order);   \
@@ -513,7 +513,7 @@ static int decode_subframe_lpc_33bps(FLACContext *s, int64_t *decoded,
    for (i = pred_order; i < s->blocksize; i++, decoded++) {
        int64_t sum = 0;
        for (j = 0; j < pred_order; j++)
-            sum += (int64_t)coeffs[j] * decoded[j];
+            sum += (int64_t)coeffs[j] * (uint64_t)decoded[j];
        decoded[j] = residual[i] + (sum >> qlevel);
    }

@@ -706,10 +706,10 @@ static void decorrelate_33bps(int ch_mode, int32_t **decoded, int64_t *decoded_3
    int i;
    if (ch_mode == FLAC_CHMODE_LEFT_SIDE ) {
        for (i = 0; i < len; i++)
-           decoded[1][i] = decoded[0][i] - decoded_33bps[i];
+           decoded[1][i] = decoded[0][i] - (uint64_t)decoded_33bps[i];
    } else if (ch_mode == FLAC_CHMODE_RIGHT_SIDE ) {
        for (i = 0; i < len; i++)
-           decoded[0][i] = decoded[1][i] + decoded_33bps[i];
+           decoded[0][i] = decoded[1][i] + (uint64_t)decoded_33bps[i];
    } else if (ch_mode == FLAC_CHMODE_MID_SIDE ) {
        for (i = 0; i < len; i++) {
            uint64_t a = decoded[0][i];
@@ -145,7 +145,8 @@ typedef struct G2MContext {
    int        got_header;

    uint8_t    *framebuf;
-    int        framebuf_stride, old_width, old_height;
+    int        framebuf_stride;
+    unsigned int framebuf_allocated;

    uint8_t    *synth_tile, *jpeg_tile, *epic_buf, *epic_buf_base;
    int        tile_stride, epic_buf_stride, old_tile_w, old_tile_h;
@@ -1160,14 +1161,13 @@ static int g2m_init_buffers(G2MContext *c)
 {
    int aligned_height;

-    if (!c->framebuf || c->old_width < c->width || c->old_height < c->height) {
-        c->framebuf_stride = FFALIGN(c->width + 15, 16) * 3;
-        aligned_height     = c->height + 15;
-        av_free(c->framebuf);
-        c->framebuf = av_calloc(c->framebuf_stride, aligned_height);
-        if (!c->framebuf)
-            return AVERROR(ENOMEM);
-    }
+    c->framebuf_stride = FFALIGN(c->width + 15, 16) * 3;
+    aligned_height = c->height + 15;
+
+    av_fast_mallocz(&c->framebuf, &c->framebuf_allocated, c->framebuf_stride * aligned_height);
+    if (!c->framebuf)
+        return AVERROR(ENOMEM);
+
    if (!c->synth_tile || !c->jpeg_tile ||
        (c->compression == 2 && !c->epic_buf_base) ||
        c->old_tile_w < c->tile_width ||
@@ -1617,6 +1617,7 @@ static av_cold int g2m_decode_end(AVCodecContext *avctx)
    av_freep(&c->jpeg_tile);
    av_freep(&c->cursor);
    av_freep(&c->framebuf);
+    c->framebuf_allocated = 0;

    return 0;
 }
@@ -353,7 +353,7 @@ static int16_t long_term_filter(AudioDSPContext *adsp, int pitch_delay_int,
        if (tmp > 0)
            L_temp0 >>= tmp;
        else
-            L_temp1 >>= -tmp;
+            L_temp1 >>= FFMIN(-tmp, 31);

        /* Check if longer filter increases the values of R'(k). */
        if (L_temp1 > L_temp0) {
@@ -581,7 +581,7 @@ void ff_g729_postfilter(AudioDSPContext *adsp, int16_t* ht_prev_data, int* voici
 int16_t ff_g729_adaptive_gain_control(int gain_before, int gain_after, int16_t *speech,
                                   int subframe_size, int16_t gain_prev)
 {
-    int gain; // (3.12)
+    unsigned gain; // (3.12)
    int n;
    int exp_before, exp_after;

@@ -603,7 +603,7 @@ int16_t ff_g729_adaptive_gain_control(int gain_before, int gain_after, int16_t *
            gain = ((gain_before - gain_after) << 14) / gain_after + 0x4000;
            gain = bidir_sal(gain, exp_after - exp_before);
        }
-        gain = av_clip_int16(gain);
+        gain = FFMIN(gain, 32767);
        gain = (gain * G729_AGC_FAC1 + 0x4000) >> 15; // gain * (1-0.9875)
    } else
        gain = 0;
@@ -281,7 +281,7 @@ static int decode_slice(MpegEncContext *s)
                ff_er_add_slice(&s->er, s->resync_mb_x, s->resync_mb_y,
                                s->mb_x, s->mb_y, ER_MB_ERROR & part_mask);

-                if (s->avctx->err_recognition & AV_EF_IGNORE_ERR)
+                if ((s->avctx->err_recognition & AV_EF_IGNORE_ERR) && get_bits_left(&s->gb) > 0)
                    continue;
                return AVERROR_INVALIDDATA;
            }
@@ -123,7 +123,7 @@ static inline int get_nalsize(int nal_length_size, const uint8_t *buf,

    if (*buf_index >= buf_size - nal_length_size) {
        // the end of the buffer is reached, refill it
-        return AVERROR(EAGAIN);
+        return AVERROR_INVALIDDATA;
    }

    for (i = 0; i < nal_length_size; i++)
@@ -162,4 +162,3 @@ static void MCFUNC(hl_motion)(const H264Context *h, H264SliceContext *sl,
    if (USES_LIST(mb_type, 1))
        prefetch_motion(h, sl, 1, PIXEL_SHIFT, CHROMA_IDC);
 }
-
@@ -646,10 +646,10 @@ static int h264_parse(AVCodecParserContext *s,
            int64_t num = time_base.num * (int64_t)avctx->pkt_timebase.den;
            if (s->dts != AV_NOPTS_VALUE) {
                // got DTS from the stream, update reference timestamp
-                p->reference_dts = s->dts - av_rescale(s->dts_ref_dts_delta, num, den);
+                p->reference_dts = av_sat_sub64(s->dts, av_rescale(s->dts_ref_dts_delta, num, den));
            } else if (p->reference_dts != AV_NOPTS_VALUE) {
                // compute DTS based on reference timestamp
-                s->dts = p->reference_dts + av_rescale(s->dts_ref_dts_delta, num, den);
+                s->dts = av_sat_add64(p->reference_dts, av_rescale(s->dts_ref_dts_delta, num, den));
            }

            if (p->reference_dts != AV_NOPTS_VALUE && s->pts == AV_NOPTS_VALUE)
@@ -109,6 +109,7 @@ static av_cold int decode_init(AVCodecContext *avctx)
    float scale = 1.f / 8.f;
    unsigned b, chunk;
    int version, ret;
+    unsigned hfr_group_count;

    avctx->sample_fmt = AV_SAMPLE_FMT_FLTP;
    c->crc_table = av_crc_get_table(AV_CRC_16_ANSI);
@@ -229,11 +230,12 @@ static av_cold int decode_init(AVCodecContext *avctx)
    if (c->total_band_count < c->base_band_count)
        return AVERROR_INVALIDDATA;

-    c->hfr_group_count = ceil2(c->total_band_count - (c->base_band_count + c->stereo_band_count),
+    hfr_group_count = ceil2(c->total_band_count - (c->base_band_count + c->stereo_band_count),
                               c->bands_per_hfr_group);

-    if (c->base_band_count + c->stereo_band_count + (unsigned long)c->hfr_group_count > 128ULL)
+    if (c->base_band_count + c->stereo_band_count + (uint64_t)hfr_group_count > 128ULL)
        return AVERROR_INVALIDDATA;
+    c->hfr_group_count = hfr_group_count;

    for (int i = 0; i < avctx->ch_layout.nb_channels; i++) {
        c->ch[i].chan_type = r[i];
@@ -1568,4 +1568,3 @@ void ff_hevc_hls_mvd_coding(HEVCLocalContext *lc, int x0, int y0, int log2_cb_si
    case 0: lc->pu.mvd.y = 0;                       break;
    }
 }
-
@@ -105,7 +105,7 @@ static int hevc_parse_slice_header(AVCodecParserContext *s, H2645NAL *nal,
        den = ps->sps->vui.vui_time_scale;
    }

-    if (num != 0 && den != 0)
+    if (num > 0 && den > 0)
        av_reduce(&avctx->framerate.den, &avctx->framerate.num,
                  num, den, 1 << 30);

@@ -374,7 +374,7 @@ static void export_stream_params(HEVCContext *s, const HEVCSPS *sps)
        den = sps->vui.vui_time_scale;
    }

-    if (num != 0 && den != 0)
+    if (num > 0 && den > 0)
        av_reduce(&avctx->framerate.den, &avctx->framerate.num,
                  num, den, 1 << 30);
 }
@@ -1523,7 +1523,8 @@ static void luma_mc_uni(HEVCLocalContext *lc, uint8_t *dst, ptrdiff_t dststride,

    if (x_off < QPEL_EXTRA_BEFORE || y_off < QPEL_EXTRA_AFTER ||
        x_off >= pic_width - block_w - QPEL_EXTRA_AFTER ||
-        y_off >= pic_height - block_h - QPEL_EXTRA_AFTER) {
+        y_off >= pic_height - block_h - QPEL_EXTRA_AFTER ||
+        ref == s->frame) {
        const ptrdiff_t edge_emu_stride = EDGE_EMU_BUFFER_STRIDE << s->ps.sps->pixel_shift;
        int offset     = QPEL_EXTRA_BEFORE * srcstride       + (QPEL_EXTRA_BEFORE << s->ps.sps->pixel_shift);
        int buf_offset = QPEL_EXTRA_BEFORE * edge_emu_stride + (QPEL_EXTRA_BEFORE << s->ps.sps->pixel_shift);
@@ -1673,6 +1674,7 @@ static void chroma_mc_uni(HEVCLocalContext *lc, uint8_t *dst0,
    intptr_t my          = av_mod_uintp2(mv->y, 2 + vshift);
    intptr_t _mx         = mx << (1 - hshift);
    intptr_t _my         = my << (1 - vshift);
+    int emu              = src0 == s->frame->data[1] || src0 == s->frame->data[2];

    x_off += mv->x >> (2 + hshift);
    y_off += mv->y >> (2 + vshift);
@@ -1680,7 +1682,8 @@ static void chroma_mc_uni(HEVCLocalContext *lc, uint8_t *dst0,

    if (x_off < EPEL_EXTRA_BEFORE || y_off < EPEL_EXTRA_AFTER ||
        x_off >= pic_width - block_w - EPEL_EXTRA_AFTER ||
-        y_off >= pic_height - block_h - EPEL_EXTRA_AFTER) {
+        y_off >= pic_height - block_h - EPEL_EXTRA_AFTER ||
+        emu) {
        const int edge_emu_stride = EDGE_EMU_BUFFER_STRIDE << s->ps.sps->pixel_shift;
        int offset0 = EPEL_EXTRA_BEFORE * (srcstride + (1 << s->ps.sps->pixel_shift));
        int buf_offset0 = EPEL_EXTRA_BEFORE *
@@ -1920,13 +1923,13 @@ static void hls_prediction_unit(HEVCLocalContext *lc, int x0, int y0,

    if (current_mv.pred_flag & PF_L0) {
        ref0 = refPicList[0].ref[current_mv.ref_idx[0]];
-        if (!ref0)
+        if (!ref0 || !ref0->frame->data[0])
            return;
        hevc_await_progress(s, ref0, &current_mv.mv[0], y0, nPbH);
    }
    if (current_mv.pred_flag & PF_L1) {
        ref1 = refPicList[1].ref[current_mv.ref_idx[1]];
-        if (!ref1)
+        if (!ref1 || !ref1->frame->data[0])
            return;
        hevc_await_progress(s, ref1, &current_mv.mv[1], y0, nPbH);
    }
@@ -2590,6 +2593,11 @@ static int hls_decode_entry_wpp(AVCodecContext *avctxt, void *hevc_lclist,
        if (ret < 0)
            goto error;
        hls_sao_param(lc, x_ctb >> s->ps.sps->log2_ctb_size, y_ctb >> s->ps.sps->log2_ctb_size);
+
+        s->deblock[ctb_addr_rs].beta_offset = s->sh.beta_offset;
+        s->deblock[ctb_addr_rs].tc_offset   = s->sh.tc_offset;
+        s->filter_slice_edges[ctb_addr_rs]  = s->sh.slice_loop_filter_across_slices_enabled_flag;
+
        more_data = hls_coding_quadtree(lc, x_ctb, y_ctb, s->ps.sps->log2_ctb_size, 0);

        if (more_data < 0) {
@@ -695,9 +695,9 @@ static void decode_422_bitstream(HYuvDecContext *s, int count)
 /* TODO instead of restarting the read when the code isn't in the first level
 * of the joint table, jump into the 2nd level of the individual table. */
 #define READ_2PIX_PLANE16(dst0, dst1, plane){\
-    dst0 = get_vlc2(&s->gb, s->vlc[plane].table, VLC_BITS, 3)<<2;\
+    dst0 = get_vlc2(&s->gb, s->vlc[plane].table, VLC_BITS, 3)*4;\
    dst0 += get_bits(&s->gb, 2);\
-    dst1 = get_vlc2(&s->gb, s->vlc[plane].table, VLC_BITS, 3)<<2;\
+    dst1 = get_vlc2(&s->gb, s->vlc[plane].table, VLC_BITS, 3)*4;\
    dst1 += get_bits(&s->gb, 2);\
 }
 static void decode_plane_bitstream(HYuvDecContext *s, int width, int plane)
@@ -755,7 +755,7 @@ static void decode_plane_bitstream(HYuvDecContext *s, int width, int plane)
            }
        }
        if( width&1 && get_bits_left(&s->gb)>0 ) {
-            int dst = get_vlc2(&s->gb, s->vlc[plane].table, VLC_BITS, 3)<<2;
+            int dst = (unsigned)get_vlc2(&s->gb, s->vlc[plane].table, VLC_BITS, 3)<<2;
            s->temp16[0][width-1] = dst + get_bits(&s->gb, 2);
        }
    }
@@ -45,4 +45,3 @@ enum AVPixelFormat avcodec_find_best_pix_fmt_of_list(const enum AVPixelFormat *p
        *loss_ptr = loss;
    return best;
 }
-
@@ -171,6 +171,9 @@ static av_cold int allocate_frame_buffers(Indeo3DecodeContext *ctx,
    int luma_size, chroma_size;
    ptrdiff_t luma_pitch, chroma_pitch;

+    luma_width  = FFALIGN(luma_width , 2);
+    luma_height = FFALIGN(luma_height, 2);
+
    if (luma_width  < 16 || luma_width  > 640 ||
        luma_height < 16 || luma_height > 480 ||
        luma_width  &  1 || luma_height &   1) {
@@ -721,11 +721,10 @@ static void encode_cblk(Jpeg2000EncoderContext *s, Jpeg2000T1Context *t1, Jpeg20

    if (max == 0){
        cblk->nonzerobits = 0;
-        bpno = 0;
    } else{
        cblk->nonzerobits = av_log2(max) + 1 - NMSEDEC_FRACBITS;
-        bpno = cblk->nonzerobits - 1;
    }
+    bpno = cblk->nonzerobits - 1;

    cblk->data[0] = 0;
    ff_mqc_initenc(&t1->mqc, cblk->data + 1);
@@ -1531,6 +1530,7 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt,
    int tileno, ret;
    Jpeg2000EncoderContext *s = avctx->priv_data;
    uint8_t *chunkstart, *jp2cstart, *jp2hstart;
+    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(avctx->pix_fmt);

    if ((ret = ff_alloc_packet(avctx, pkt, avctx->width*avctx->height*9 + AV_INPUT_BUFFER_MIN_SIZE)) < 0)
        return ret;
@@ -1543,7 +1543,7 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt,

    s->lambda = s->picture->quality * LAMBDA_SCALE;

-    if (avctx->pix_fmt == AV_PIX_FMT_BGR48 || avctx->pix_fmt == AV_PIX_FMT_GRAY16)
+    if (s->cbps[0] > 8)
        copy_frame_16(s);
    else
        copy_frame_8(s);
@@ -1587,7 +1587,7 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt,
        bytestream_put_byte(&s->buf, 1);
        bytestream_put_byte(&s->buf, 0);
        bytestream_put_byte(&s->buf, 0);
-        if (avctx->pix_fmt == AV_PIX_FMT_RGB24 || avctx->pix_fmt == AV_PIX_FMT_PAL8) {
+        if ((desc->flags & AV_PIX_FMT_FLAG_RGB) || avctx->pix_fmt == AV_PIX_FMT_PAL8) {
            bytestream_put_be32(&s->buf, 16);
        } else if (s->ncomponents == 1) {
            bytestream_put_be32(&s->buf, 17);
@@ -1717,6 +1717,7 @@ static av_cold int j2kenc_init(AVCodecContext *avctx)
    Jpeg2000EncoderContext *s = avctx->priv_data;
    Jpeg2000CodingStyle *codsty = &s->codsty;
    Jpeg2000QuantStyle  *qntsty = &s->qntsty;
+    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(avctx->pix_fmt);

    s->avctx = avctx;
    av_log(s->avctx, AV_LOG_DEBUG, "init\n");
@@ -1729,7 +1730,7 @@ static av_cold int j2kenc_init(AVCodecContext *avctx)

    if (avctx->pix_fmt == AV_PIX_FMT_PAL8 && (s->pred != FF_DWT97_INT || s->format != CODEC_JP2)) {
        av_log(s->avctx, AV_LOG_WARNING, "Forcing lossless jp2 for pal8\n");
-        s->pred = FF_DWT97_INT;
+        s->pred = 1;
        s->format = CODEC_JP2;
    }

@@ -1759,20 +1760,13 @@ static av_cold int j2kenc_init(AVCodecContext *avctx)
    s->width = avctx->width;
    s->height = avctx->height;

+    s->ncomponents = desc->nb_components;
    for (i = 0; i < 3; i++) {
-        if (avctx->pix_fmt == AV_PIX_FMT_GRAY16 || avctx->pix_fmt == AV_PIX_FMT_RGB48)
-            s->cbps[i] = 16;
-        else
-            s->cbps[i] = 8;
+        s->cbps[i] = desc->comp[i].depth;
    }

-    if (avctx->pix_fmt == AV_PIX_FMT_RGB24 || avctx->pix_fmt == AV_PIX_FMT_RGB48){
-        s->ncomponents = 3;
-    } else if (avctx->pix_fmt == AV_PIX_FMT_GRAY8 || avctx->pix_fmt == AV_PIX_FMT_PAL8 || avctx->pix_fmt == AV_PIX_FMT_GRAY16){
-        s->ncomponents = 1;
-    } else{ // planar YUV
+    if ((desc->flags & AV_PIX_FMT_FLAG_PLANAR) && s->ncomponents > 1) {
        s->planar = 1;
-        s->ncomponents = 3;
        ret = av_pix_fmt_get_chroma_sub_sample(avctx->pix_fmt,
                                               s->chroma_shift, s->chroma_shift + 1);
        if (ret)
@@ -1810,7 +1804,7 @@ static const AVOption options[] = {
    { "tile_height",   "Tile Height",       OFFSET(tile_height),   AV_OPT_TYPE_INT,   { .i64 = 256         }, 1,     1<<30,           VE, },
    { "pred",          "DWT Type",          OFFSET(pred),          AV_OPT_TYPE_INT,   { .i64 = 0           }, 0,         1,           VE, "pred"        },
    { "dwt97int",      NULL,                0,                     AV_OPT_TYPE_CONST, { .i64 = 0           }, INT_MIN, INT_MAX,       VE, "pred"        },
-    { "dwt53",         NULL,                0,                     AV_OPT_TYPE_CONST, { .i64 = 0           }, INT_MIN, INT_MAX,       VE, "pred"        },
+    { "dwt53",         NULL,                0,                     AV_OPT_TYPE_CONST, { .i64 = 1           }, INT_MIN, INT_MAX,       VE, "pred"        },
    { "sop",           "SOP marker",        OFFSET(sop),           AV_OPT_TYPE_INT,   { .i64 = 0           }, 0,         1,           VE, },
    { "eph",           "EPH marker",        OFFSET(eph),           AV_OPT_TYPE_INT,   { .i64 = 0           }, 0,         1,           VE, },
    { "prog",          "Progression Order", OFFSET(prog),          AV_OPT_TYPE_INT,   { .i64 = 0           }, JPEG2000_PGOD_LRCP,         JPEG2000_PGOD_CPRL,           VE, "prog" },
@@ -323,6 +323,16 @@ static int get_siz(Jpeg2000DecoderContext *s)
        return AVERROR_INVALIDDATA;
    }

+    if (s->image_offset_x >= s->width || s->image_offset_y >= s->height) {
+        av_log(s->avctx, AV_LOG_ERROR, "image offsets outside image");
+        return AVERROR_INVALIDDATA;
+    }
+
+    if (s->reduction_factor && (s->image_offset_x || s->image_offset_y) ){
+        av_log(s->avctx, AV_LOG_ERROR, "reduction factor with image offsets is not fully implemented");
+        return AVERROR_PATCHWELCOME;
+    }
+
    s->ncomponents = ncomponents;

    if (s->tile_width <= 0 || s->tile_height <= 0) {
@@ -388,7 +398,7 @@ static int get_siz(Jpeg2000DecoderContext *s)
        dimy = FFMAX(dimy, ff_jpeg2000_ceildiv(o_dimy, s->cdy[i]));
    }

-    ret = ff_set_dimensions(s->avctx, dimx, dimy);
+    ret = ff_set_dimensions(s->avctx, dimx << s->avctx->lowres, dimy << s->avctx->lowres);
    if (ret < 0)
        return ret;

@@ -2471,6 +2481,14 @@ static av_cold int jpeg2000_decode_init(AVCodecContext *avctx)
 {
    Jpeg2000DecoderContext *s = avctx->priv_data;

+    if (avctx->lowres)
+        av_log(avctx, AV_LOG_WARNING, "lowres is overriden by reduction_factor but set anyway\n");
+    if (!s->reduction_factor && avctx->lowres < JPEG2000_MAX_RESLEVELS) {
+        s->reduction_factor = avctx->lowres;
+    }
+    if (avctx->lowres != s->reduction_factor && avctx->lowres)
+        return AVERROR(EINVAL);
+
    ff_jpeg2000dsp_init(&s->dsp);
    ff_jpeg2000_init_tier1_luts();

@@ -382,6 +382,19 @@ int ff_jpegls_decode_picture(MJpegDecodeContext *s, int near,
    state->T3     = s->t3;
    state->reset  = s->reset;
    ff_jpegls_reset_coding_parameters(state, 0);
+
+    /* Testing parameters here, we cannot test in LSE or SOF because
+     * these interdepend and are allowed in either order
+     */
+    if (state->maxval >= (1<<state->bpp) ||
+        state->T1 > state->T2 ||
+        state->T2 > state->T3 ||
+        state->T3 > state->maxval ||
+        state->reset > FFMAX(255, state->maxval)) {
+        ret = AVERROR_INVALIDDATA;
+        goto end;
+    }
+
    ff_jpegls_init_state(state);

    if (s->bits <= 8)
@@ -152,6 +152,8 @@ static int zlib_decomp(AVCodecContext *avctx, const uint8_t *src, int src_len, i
    if (expected != (unsigned int)zstream->total_out) {
        av_log(avctx, AV_LOG_ERROR, "Decoded size differs (%d != %lu)\n",
               expected, zstream->total_out);
+        if (expected > (unsigned int)zstream->total_out)
+            return (unsigned int)zstream->total_out;
        return AVERROR_UNKNOWN;
    }
    return zstream->total_out;
@@ -169,8 +171,8 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
    int row, col;
    unsigned char *encoded = avpkt->data, *outptr;
    uint8_t *y_out, *u_out, *v_out;
-    unsigned int width = avctx->width; // Real image width
-    unsigned int height = avctx->height; // Real image height
+    int width = avctx->width; // Real image width
+    int height = avctx->height; // Real image height
    unsigned int mszh_dlen;
    unsigned char yq, y1q, uq, vq;
    int uqvq, ret;
@@ -227,16 +229,19 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
            break;
        case COMP_MSZH_NOCOMP: {
            int bppx2;
+            int aligned_width = width;
            switch (c->imgtype) {
            case IMGTYPE_YUV111:
            case IMGTYPE_RGB24:
                bppx2 = 6;
                break;
            case IMGTYPE_YUV422:
+                aligned_width &= ~3;
            case IMGTYPE_YUV211:
                bppx2 = 4;
                break;
            case IMGTYPE_YUV411:
+                aligned_width &= ~3;
            case IMGTYPE_YUV420:
                bppx2 = 3;
                break;
@@ -244,7 +249,7 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
                bppx2 = 0; // will error out below
                break;
            }
-            if (len < ((width * height * bppx2) >> 1))
+            if (len < ((aligned_width * height * bppx2) >> 1))
                return AVERROR_INVALIDDATA;
            break;
        }
@@ -276,12 +281,13 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
            ret = zlib_decomp(avctx, buf + 8 + mthread_inlen, len - 8 - mthread_inlen,
                              mthread_outlen, mthread_outlen);
            if (ret < 0) return ret;
+            len = c->decomp_size;
        } else {
            int ret = zlib_decomp(avctx, buf, len, 0, c->decomp_size);
            if (ret < 0) return ret;
+            len = ret;
        }
        encoded = c->decomp_buf;
-        len = c->decomp_size;
        break;
 #endif
    default:
@@ -309,8 +315,8 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
            }
            break;
        case IMGTYPE_YUV422:
+            pixel_ptr = 0;
            for (row = 0; row < height; row++) {
-                pixel_ptr = row * width * 2;
                yq = uq = vq =0;
                for (col = 0; col < width/4; col++) {
                    encoded[pixel_ptr] = yq -= encoded[pixel_ptr];
@@ -326,8 +332,8 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
            }
            break;
        case IMGTYPE_YUV411:
+            pixel_ptr = 0;
            for (row = 0; row < height; row++) {
-                pixel_ptr = row * width / 2 * 3;
                yq = uq = vq =0;
                for (col = 0; col < width/4; col++) {
                    encoded[pixel_ptr] = yq -= encoded[pixel_ptr];
@@ -403,6 +409,11 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
                v_out[ col >> 1     ] = *encoded++ + 128;
                v_out[(col >> 1) + 1] = *encoded++ + 128;
            }
+            if (col && col < width) {
+                u_out[ col >> 1     ] = u_out[(col>>1) - 1];
+                v_out[ col >> 1     ] = v_out[(col>>1) - 1];
+            }
+
            y_out -= frame->linesize[0];
            u_out -= frame->linesize[1];
            v_out -= frame->linesize[2];
@@ -424,6 +435,10 @@ static int decode_frame(AVCodecContext *avctx, AVFrame *frame,
                u_out[col >> 2] = *encoded++ + 128;
                v_out[col >> 2] = *encoded++ + 128;
            }
+            if (col && col < width) {
+                u_out[col >> 2] = u_out[(col>>2) - 1];
+                v_out[col >> 2] = v_out[(col>>2) - 1];
+            }
            y_out -= frame->linesize[0];
            u_out -= frame->linesize[1];
            v_out -= frame->linesize[2];
@@ -481,6 +496,7 @@ static av_cold int decode_init(AVCodecContext *avctx)
                                FFALIGN(avctx->height, 4);
    unsigned int max_decomp_size;
    int subsample_h, subsample_v;
+    int partial_h_supported = 0;

    if (avctx->extradata_size < 8) {
        av_log(avctx, AV_LOG_ERROR, "Extradata size too small.\n");
@@ -502,26 +518,24 @@ static av_cold int decode_init(AVCodecContext *avctx)
        av_log(avctx, AV_LOG_DEBUG, "Image type is YUV 1:1:1.\n");
        break;
    case IMGTYPE_YUV422:
-        c->decomp_size = basesize * 2;
+        c->decomp_size = (avctx->width & ~3) * avctx->height * 2;
        max_decomp_size = max_basesize * 2;
        avctx->pix_fmt = AV_PIX_FMT_YUV422P;
        av_log(avctx, AV_LOG_DEBUG, "Image type is YUV 4:2:2.\n");
-        if (avctx->width % 4) {
-            avpriv_request_sample(avctx, "Unsupported dimensions");
-            return AVERROR_INVALIDDATA;
-        }
+        partial_h_supported = 1;
        break;
    case IMGTYPE_RGB24:
-        c->decomp_size = basesize * 3;
+        c->decomp_size = FFALIGN(avctx->width*3, 4) * avctx->height;
        max_decomp_size = max_basesize * 3;
        avctx->pix_fmt = AV_PIX_FMT_BGR24;
        av_log(avctx, AV_LOG_DEBUG, "Image type is RGB 24.\n");
        break;
    case IMGTYPE_YUV411:
-        c->decomp_size = basesize / 2 * 3;
+        c->decomp_size = (avctx->width & ~3) * avctx->height / 2 * 3;
        max_decomp_size = max_basesize / 2 * 3;
        avctx->pix_fmt = AV_PIX_FMT_YUV411P;
        av_log(avctx, AV_LOG_DEBUG, "Image type is YUV 4:1:1.\n");
+        partial_h_supported = 1;
        break;
    case IMGTYPE_YUV211:
        c->decomp_size = basesize * 2;
@@ -541,7 +555,7 @@ static av_cold int decode_init(AVCodecContext *avctx)
    }

    av_pix_fmt_get_chroma_sub_sample(avctx->pix_fmt, &subsample_h, &subsample_v);
-    if (avctx->width % (1<<subsample_h) || avctx->height % (1<<subsample_v)) {
+    if ((avctx->width % (1<<subsample_h) && !partial_h_supported) || avctx->height % (1<<subsample_v)) {
        avpriv_request_sample(avctx, "Unsupported dimensions");
        return AVERROR_INVALIDDATA;
    }
@@ -575,7 +575,13 @@ static int libx265_encode_frame(AVCodecContext *avctx, AVPacket *pkt,
 {
    libx265Context *ctx = avctx->priv_data;
    x265_picture x265pic;
-    x265_picture x265pic_out = { 0 };
+#if (X265_BUILD >= 210) && (X265_BUILD < 213)
+    x265_picture x265pic_layers_out[MAX_SCALABLE_LAYERS];
+    x265_picture* x265pic_lyrptr_out[MAX_SCALABLE_LAYERS];
+#else
+    x265_picture x265pic_solo_out = { 0 };
+#endif
+    x265_picture* x265pic_out;
    x265_nal *nal;
    x265_sei *sei;
    uint8_t *dst;
@@ -698,8 +704,16 @@ FF_ENABLE_DEPRECATION_WARNINGS
        }
    }

+#if (X265_BUILD >= 210) && (X265_BUILD < 213)
+    for (i = 0; i < MAX_SCALABLE_LAYERS; i++)
+        x265pic_lyrptr_out[i] = &x265pic_layers_out[i];
+
    ret = ctx->api->encoder_encode(ctx->encoder, &nal, &nnal,
-                                   pic ? &x265pic : NULL, &x265pic_out);
+                                   pic ? &x265pic : NULL, x265pic_lyrptr_out);
+#else
+    ret = ctx->api->encoder_encode(ctx->encoder, &nal, &nnal,
+                                   pic ? &x265pic : NULL, &x265pic_solo_out);
+#endif

    for (i = 0; i < sei->numPayloads; i++)
        av_free(sei->payloads[i].payload);
@@ -729,10 +743,16 @@ FF_ENABLE_DEPRECATION_WARNINGS
            pkt->flags |= AV_PKT_FLAG_KEY;
    }

-    pkt->pts = x265pic_out.pts;
-    pkt->dts = x265pic_out.dts;
+#if (X265_BUILD >= 210) && (X265_BUILD < 213)
+    x265pic_out = x265pic_lyrptr_out[0];
+#else
+    x265pic_out = &x265pic_solo_out;
+#endif

-    switch (x265pic_out.sliceType) {
+    pkt->pts = x265pic_out->pts;
+    pkt->dts = x265pic_out->dts;
+
+    switch (x265pic_out->sliceType) {
    case X265_TYPE_IDR:
    case X265_TYPE_I:
        pict_type = AV_PICTURE_TYPE_I;
@@ -750,16 +770,16 @@ FF_ENABLE_DEPRECATION_WARNINGS
    }

 #if X265_BUILD >= 130
-    if (x265pic_out.sliceType == X265_TYPE_B)
+    if (x265pic_out->sliceType == X265_TYPE_B)
 #else
-    if (x265pic_out.frameData.sliceType == 'b')
+    if (x265pic_out->frameData.sliceType == 'b')
 #endif
        pkt->flags |= AV_PKT_FLAG_DISPOSABLE;

-    ff_side_data_set_encoder_stats(pkt, x265pic_out.frameData.qp * FF_QP2LAMBDA, NULL, 0, pict_type);
+    ff_side_data_set_encoder_stats(pkt, x265pic_out->frameData.qp * FF_QP2LAMBDA, NULL, 0, pict_type);

-    if (x265pic_out.userData) {
-        int idx = (int)(intptr_t)x265pic_out.userData - 1;
+    if (x265pic_out->userData) {
+        int idx = (int)(intptr_t)x265pic_out->userData - 1;
        ReorderedData *rd = &ctx->rd[idx];

 #if FF_API_REORDERED_OPAQUE
@@ -473,8 +473,9 @@ static int zero_cmp(MpegEncContext *s, const uint8_t *a, const uint8_t *b,
    return 0;
 }

-void ff_set_cmp(MECmpContext *c, me_cmp_func *cmp, int type)
+int ff_set_cmp(MECmpContext *c, me_cmp_func *cmp, int type)
 {
+    int ret = 0;
    int i;

    memset(cmp, 0, sizeof(void *) * 6);
@@ -533,9 +534,13 @@ void ff_set_cmp(MECmpContext *c, me_cmp_func *cmp, int type)
 #endif
        default:
            av_log(NULL, AV_LOG_ERROR,
-                   "internal error in cmp function selection\n");
+                   "invalid cmp function selection\n");
+            ret = -1;
+            break;
        }
    }
+
+    return ret;
 }

 #define BUTTERFLY2(o1, o2, i1, i2)              \
@@ -89,7 +89,7 @@ void ff_me_cmp_init_ppc(MECmpContext *c, AVCodecContext *avctx);
 void ff_me_cmp_init_x86(MECmpContext *c, AVCodecContext *avctx);
 void ff_me_cmp_init_mips(MECmpContext *c, AVCodecContext *avctx);

-void ff_set_cmp(MECmpContext *c, me_cmp_func *cmp, int type);
+int ff_set_cmp(MECmpContext *c, me_cmp_func *cmp, int type);

 void ff_dsputil_init_dwt(MECmpContext *c);

@@ -309,6 +309,7 @@ int ff_init_me(MpegEncContext *s){
    MotionEstContext * const c= &s->me;
    int cache_size= FFMIN(ME_MAP_SIZE>>ME_MAP_SHIFT, 1<<ME_MAP_SHIFT);
    int dia_size= FFMAX(FFABS(s->avctx->dia_size)&255, FFABS(s->avctx->pre_dia_size)&255);
+    int ret;

    if(FFMIN(s->avctx->dia_size, s->avctx->pre_dia_size) < -FFMIN(ME_MAP_SIZE, MAX_SAB_SIZE)){
        av_log(s->avctx, AV_LOG_ERROR, "ME_MAP size is too small for SAB diamond\n");
@@ -324,10 +325,12 @@ int ff_init_me(MpegEncContext *s){
        av_log(s->avctx, AV_LOG_INFO, "ME_MAP size may be a little small for the selected diamond size\n");
    }

-    ff_set_cmp(&s->mecc, s->mecc.me_pre_cmp, c->avctx->me_pre_cmp);
-    ff_set_cmp(&s->mecc, s->mecc.me_cmp,     c->avctx->me_cmp);
-    ff_set_cmp(&s->mecc, s->mecc.me_sub_cmp, c->avctx->me_sub_cmp);
-    ff_set_cmp(&s->mecc, s->mecc.mb_cmp,     c->avctx->mb_cmp);
+    ret  = ff_set_cmp(&s->mecc, s->mecc.me_pre_cmp, c->avctx->me_pre_cmp);
+    ret |= ff_set_cmp(&s->mecc, s->mecc.me_cmp,     c->avctx->me_cmp);
+    ret |= ff_set_cmp(&s->mecc, s->mecc.me_sub_cmp, c->avctx->me_sub_cmp);
+    ret |= ff_set_cmp(&s->mecc, s->mecc.mb_cmp,     c->avctx->mb_cmp);
+    if (ret < 0)
+        return ret;

    c->flags    = get_flags(c, 0, c->avctx->me_cmp    &FF_CMP_CHROMA);
    c->sub_flags= get_flags(c, 0, c->avctx->me_sub_cmp&FF_CMP_CHROMA);
@@ -185,7 +185,7 @@ static YuvPixel mp_get_yuv_from_rgb(MotionPixelsContext *mp, int x, int y)
    int color;

    color = *(uint16_t *)&mp->frame->data[0][y * mp->frame->linesize[0] + x * 2];
-    return mp_rgb_yuv_table[color];
+    return mp_rgb_yuv_table[color & 0x7FFF];
 }

 static void mp_set_rgb_from_yuv(MotionPixelsContext *mp, int x, int y, const YuvPixel *p)
@@ -2956,6 +2956,10 @@ static int ipu_decode_frame(AVCodecContext *avctx, AVFrame *frame,
    GetBitContext *gb = &m->gb;
    int ret;

+    // Check for minimal intra MB size (considering mb header, luma & chroma dc VLC, ac EOB VLC)
+    if (avpkt->size*8LL < (avctx->width+15)/16 * ((avctx->height+15)/16) * (2 + 3*4 + 2*2 + 2*6))
+        return AVERROR_INVALIDDATA;
+
    ret = ff_get_buffer(avctx, frame, 0);
    if (ret < 0)
        return ret;
--- a/Show More
+++ b/Show More
@@ -1 +1 @@
 .1.git
 .0.2