The VC1 decoder was missing lots of important fast paths for Arm, especially for 64-bit Arm. This submission fills in implementations for all functions where a fast path already existed and the fallback C implementation was taking 1% or more of the runtime, and adds a new fast path to permit vc1_unescape_buffer() to be overridden.
I've measured the playback speed on a 1.5 GHz Cortex-A72 (Raspberry Pi 4) using `ffmpeg -i <bitstream> -f null -` for a couple of example streams: Architecture: AArch32 AArch32 AArch64 AArch64 Stream: 1 2 1 2 Before speed: 1.22x 0.82x 1.00x 0.67x After speed: 1.31x 0.98x 1.39x 1.06x Improvement: 7.4% 20% 39% 58% `make fate` passes on both AArch32 and AArch64. Changes in v2: * Refactor checkasm tests to convert some macros into functions. * Remove cast-to-void of checked_call. * Limit 16-bit values in idctdsp checkasm test to +/-0x100. * Reinstate ff_add_pixels_clamped_arm. * Adapt vc1 deblocking filters to specify stride as ptrdiff_t. * Add align specifiers to a few VLD/VST instructions for AArch32 deblocking filter, and adapt checkasm test not to test with tighter alignment than is encountered in normal use. * Correct unescape buffer memcmp length. * Update benchmarks for AArch64 idctdsp. Ben Avison (10): checkasm: Add vc1dsp in-loop deblocking filter tests checkasm: Add vc1dsp inverse transform tests checkasm: Add idctdsp add/put-pixels-clamped tests avcodec/vc1: Introduce fast path for unescaping bitstream buffer avcodec/vc1: Arm 64-bit NEON deblocking filter fast paths avcodec/vc1: Arm 32-bit NEON deblocking filter fast paths avcodec/vc1: Arm 64-bit NEON inverse transform fast paths avcodec/idctdsp: Arm 64-bit NEON block add and clamp fast paths avcodec/vc1: Arm 64-bit NEON unescape fast path avcodec/vc1: Arm 32-bit NEON unescape fast path libavcodec/aarch64/Makefile | 4 +- libavcodec/aarch64/idctdsp_init_aarch64.c | 26 +- libavcodec/aarch64/idctdsp_neon.S | 130 ++ libavcodec/aarch64/vc1dsp_init_aarch64.c | 94 ++ libavcodec/aarch64/vc1dsp_neon.S | 1546 +++++++++++++++++++++ libavcodec/arm/vc1dsp_init_neon.c | 75 + libavcodec/arm/vc1dsp_neon.S | 761 ++++++++++ libavcodec/vc1dec.c | 20 +- libavcodec/vc1dsp.c | 2 + libavcodec/vc1dsp.h | 3 + tests/checkasm/Makefile | 2 + tests/checkasm/checkasm.c | 6 + tests/checkasm/checkasm.h | 2 + tests/checkasm/idctdsp.c | 98 ++ tests/checkasm/vc1dsp.c | 452 ++++++ tests/fate/checkasm.mak | 2 + 16 files changed, 3204 insertions(+), 19 deletions(-) create mode 100644 libavcodec/aarch64/idctdsp_neon.S create mode 100644 libavcodec/aarch64/vc1dsp_neon.S create mode 100644 tests/checkasm/idctdsp.c create mode 100644 tests/checkasm/vc1dsp.c -- 2.25.1 _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
