Chiebot-Mirror/FFmpeg - FFmpeg - Gitea: Git with a cup of tea

Author	SHA1	Message	Date
Sebastian Pop	c3a17ffff6	swscale/aarch64: use multiply accumulate and shift-right narrow This patch rewrites the innermost loop of ff_yuv2planeX_8_neon to avoid zips and horizontal adds by using fused multiply adds. The patch also uses ld1r to load one element and replicate it across all lanes of the vector. The patch also improves the clipping code by removing the shift right instructions and performing the shift with the shift-right narrow instructions. I see 8% difference on an m6g instance with neoverse-n1 CPUs: $ ffmpeg -nostats -f lavfi -i testsrc2=4k:d=2 -vf bench=start,scale=1024x1024,bench=stop -f null - before: t:0.014015 avg:0.014096 max:0.015018 min:0.013971 after: t:0.012985 avg:0.013013 max:0.013996 min:0.012818 Tested with `make check` on aarch64-linux. Signed-off-by: Sebastian Pop <spop@amazon.com> Reviewed-by: Clément Bœsch <u@pkh.me> Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>	5 years ago
Sebastian Pop	bd83191271	swscale/aarch64: use multiply accumulate and increase vector factor to 4 This patch implements ff_hscale_8_to_15_neon with NEON fused multiply accumulate and bumps the vectorization factor from 2 to 4. The speedup is of 25% on Graviton1 A1 instances based on A-72 cpus: $ ffmpeg -nostats -f lavfi -i testsrc2=4k:d=2 -vf bench=start,scale=1024x1024,bench=stop -f null - before: t:0.040303 avg:0.040287 max:0.040371 min:0.039214 after: t:0.032168 avg:0.032215 max:0.033081 min:0.032146 The speedup is of 39% on Graviton2 m6g instances based on Neoverse-N1 cpus: $ ffmpeg -nostats -f lavfi -i testsrc2=4k:d=2 -vf bench=start,scale=1024x1024,bench=stop -f null - before: t:0.019446 avg:0.019423 max:0.019493 min:0.019181 after: t:0.014015 avg:0.014096 max:0.015018 min:0.013971 Tested with `make check` on aarch64-linux. Signed-off-by: Sebastian Pop <spop@amazon.com> Reviewed-by: Jean-Baptiste Kempf <jb@videolan.org> Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>	5 years ago
Clément Bœsch	c921f4f687	sws/aarch64: add ff_yuv2planeX_8_neon	9 years ago
Clément Bœsch	cab9661dba	sws/aarch64/yuv2rgb: honor iOS calling convention y_offset and y_coeff being successive 32-bit integers, they are packed into 8 bytes instead of 2x8 bytes. See https://developer.apple.com/library/ios/documentation/Xcode/Conceptual/iPhoneOSABIReference/Articles/ARM64FunctionCallingConventions.html > iOS diverges from Procedure Call Standard for the ARM 64-bit > Architecture in several ways [...] > In the generic procedure call standard, all function arguments passed > on the stack consume slots in multiples of 8 bytes. In iOS, this > requirement is dropped, and values consume only the space required. [...] > Padding is still inserted on the stack to satisfy arguments’ alignment > requirements.	9 years ago
Clément Bœsch	040598218f	sws/aarch64: restore ff_hscale_8_to_15_neon() Fix final scaling and required filter alignment. Pass FATE.	9 years ago
Clément Bœsch	eadaef2a63	sws/aarch64: disable ff_hscale_8_to_15_neon temporarly Looks broken.	9 years ago
Clément Bœsch	263eb76bdf	sws/aarch64: add ff_hscale_8_to_15_neon ./ffmpeg -nostats -f lavfi -i testsrc2=4k:d=2 -vf bench=start,scale=1024x1024,bench=stop -f null - before: t:0.489726 avg:0.489883 max:0.491852 min:0.489482 after: t:0.256515 avg:0.256458 max:0.256999 min:0.253755	9 years ago
Clément Bœsch	277408b7f1	sws/aarch64/yuv2rgb: save a few mul and add 27ms to 26ms with UHD 2160 input.	9 years ago
Clément Bœsch	f1148390d7	sws/aarch64: add {nv12,nv21,yuv420p,yuv422p}_to_{argb,rgba,abgr,rgba}_neon	9 years ago