RepoMirrors
/
ffmpeg
mirror of https://git.ffmpeg.org/ffmpeg.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
ffmpeg/libswscale/aarch64/Makefile

12 lines
501 B
Makefile
Raw Normal View History

swscale: aarch64: Add a NEON implementation of interleaveBytes This allows speeding up format conversions from yuv420 to nv12. Cortex A53 A72 A73 interleave_bytes_c: 86077.5 51433.0 66972.0 interleave_bytes_neon: 19701.7 23019.2 15859.2 interleave_bytes_aligned_c: 86603.0 52017.2 67484.2 interleave_bytes_aligned_neon: 9061.0 7623.0 6309.0 Signed-off-by: Martin Storsjö <martin@martin.st>
2020-05-15 07:54:10 +00:00
OBJS += aarch64/rgb2rgb.o \
aarch64/swscale.o \
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
2016-03-18 15:39:34 +00:00
aarch64/swscale_unscaled.o \
sws/aarch64: add {nv12,nv21,yuv420p,yuv422p}_to_{argb,rgba,abgr,rgba}_neon
2016-02-08 14:14:17 +00:00
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
2016-03-18 15:39:34 +00:00
NEON-OBJS += aarch64/hscale.o \
swscale/aarch64: Add rgb24 to yuv implementation Test on Apple M1: rgb24_to_uv_8_c: 0.0 rgb24_to_uv_8_neon: 0.2 rgb24_to_uv_128_c: 1.0 rgb24_to_uv_128_neon: 0.5 rgb24_to_uv_1080_c: 7.0 rgb24_to_uv_1080_neon: 5.7 rgb24_to_uv_1920_c: 12.5 rgb24_to_uv_1920_neon: 9.5 rgb24_to_uv_half_8_c: 0.2 rgb24_to_uv_half_8_neon: 0.2 rgb24_to_uv_half_128_c: 1.0 rgb24_to_uv_half_128_neon: 0.5 rgb24_to_uv_half_1080_c: 6.2 rgb24_to_uv_half_1080_neon: 3.0 rgb24_to_uv_half_1920_c: 11.2 rgb24_to_uv_half_1920_neon: 5.2 rgb24_to_y_8_c: 0.2 rgb24_to_y_8_neon: 0.0 rgb24_to_y_128_c: 0.5 rgb24_to_y_128_neon: 0.5 rgb24_to_y_1080_c: 4.7 rgb24_to_y_1080_neon: 3.2 rgb24_to_y_1920_c: 8.0 rgb24_to_y_1920_neon: 5.7 On Pixel 6: rgb24_to_uv_8_c: 30.7 rgb24_to_uv_8_neon: 56.9 rgb24_to_uv_128_c: 213.9 rgb24_to_uv_128_neon: 173.2 rgb24_to_uv_1080_c: 1649.9 rgb24_to_uv_1080_neon: 1424.4 rgb24_to_uv_1920_c: 2907.9 rgb24_to_uv_1920_neon: 2480.7 rgb24_to_uv_half_8_c: 36.2 rgb24_to_uv_half_8_neon: 33.4 rgb24_to_uv_half_128_c: 167.9 rgb24_to_uv_half_128_neon: 99.4 rgb24_to_uv_half_1080_c: 1293.9 rgb24_to_uv_half_1080_neon: 778.7 rgb24_to_uv_half_1920_c: 2292.7 rgb24_to_uv_half_1920_neon: 1328.7 rgb24_to_y_8_c: 19.7 rgb24_to_y_8_neon: 27.7 rgb24_to_y_128_c: 129.9 rgb24_to_y_128_neon: 96.7 rgb24_to_y_1080_c: 995.4 rgb24_to_y_1080_neon: 767.7 rgb24_to_y_1920_c: 1747.4 rgb24_to_y_1920_neon: 1337.2 Note both tests use clang as compiler, which has vectorization enabled by default with -O3. Reviewed-by: Rémi Denis-Courmont <remi@remlab.net> Reviewed-by: Martin Storsjö <martin@martin.st> Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
2024-06-07 13:44:52 +00:00
aarch64/input.o \
sws/aarch64: add ff_yuv2planeX_8_neon
2016-04-01 15:27:29 +00:00
aarch64/output.o \
swscale/aarch64: add neon {lum,chr}ConvertRange chrRangeFromJpeg_8_c: 29.2 chrRangeFromJpeg_8_neon: 19.5 chrRangeFromJpeg_24_c: 80.5 chrRangeFromJpeg_24_neon: 34.0 chrRangeFromJpeg_128_c: 413.7 chrRangeFromJpeg_128_neon: 156.0 chrRangeFromJpeg_144_c: 471.0 chrRangeFromJpeg_144_neon: 174.2 chrRangeFromJpeg_256_c: 842.0 chrRangeFromJpeg_256_neon: 305.5 chrRangeFromJpeg_512_c: 1699.0 chrRangeFromJpeg_512_neon: 608.0 chrRangeToJpeg_8_c: 51.7 chrRangeToJpeg_8_neon: 22.7 chrRangeToJpeg_24_c: 149.7 chrRangeToJpeg_24_neon: 38.0 chrRangeToJpeg_128_c: 761.7 chrRangeToJpeg_128_neon: 176.7 chrRangeToJpeg_144_c: 866.2 chrRangeToJpeg_144_neon: 198.7 chrRangeToJpeg_256_c: 1516.5 chrRangeToJpeg_256_neon: 348.7 chrRangeToJpeg_512_c: 3067.2 chrRangeToJpeg_512_neon: 692.7 lumRangeFromJpeg_8_c: 24.0 lumRangeFromJpeg_8_neon: 17.0 lumRangeFromJpeg_24_c: 56.7 lumRangeFromJpeg_24_neon: 21.0 lumRangeFromJpeg_128_c: 294.5 lumRangeFromJpeg_128_neon: 76.7 lumRangeFromJpeg_144_c: 332.5 lumRangeFromJpeg_144_neon: 86.7 lumRangeFromJpeg_256_c: 586.0 lumRangeFromJpeg_256_neon: 152.2 lumRangeFromJpeg_512_c: 1190.0 lumRangeFromJpeg_512_neon: 298.0 lumRangeToJpeg_8_c: 31.7 lumRangeToJpeg_8_neon: 19.5 lumRangeToJpeg_24_c: 83.5 lumRangeToJpeg_24_neon: 24.2 lumRangeToJpeg_128_c: 440.5 lumRangeToJpeg_128_neon: 91.0 lumRangeToJpeg_144_c: 504.2 lumRangeToJpeg_144_neon: 101.0 lumRangeToJpeg_256_c: 879.7 lumRangeToJpeg_256_neon: 177.2 lumRangeToJpeg_512_c: 1794.2 lumRangeToJpeg_512_neon: 354.0
2024-06-11 12:28:58 +00:00
aarch64/range_convert_neon.o \
swscale: aarch64: Add a NEON implementation of interleaveBytes This allows speeding up format conversions from yuv420 to nv12. Cortex A53 A72 A73 interleave_bytes_c: 86077.5 51433.0 66972.0 interleave_bytes_neon: 19701.7 23019.2 15859.2 interleave_bytes_aligned_c: 86603.0 52017.2 67484.2 interleave_bytes_aligned_neon: 9061.0 7623.0 6309.0 Signed-off-by: Martin Storsjö <martin@martin.st>
2020-05-15 07:54:10 +00:00
aarch64/rgb2rgb_neon.o \
swscale/aarch64: add nv24/nv42 to yuv420p unscaled converter A55 A76 nv24_yuv420p_128_c: 4956.1 1267.0 nv24_yuv420p_128_neon: 3109.1 ( 1.59x) 640.0 ( 1.98x) nv24_yuv420p_1920_c: 35728.4 11736.2 nv24_yuv420p_1920_neon: 8011.1 ( 4.46x) 2436.0 ( 4.82x) nv42_yuv420p_128_c: 4956.4 1270.5 nv42_yuv420p_128_neon: 3074.6 ( 1.61x) 639.5 ( 1.99x) nv42_yuv420p_1920_c: 35685.9 11732.5 nv42_yuv420p_1920_neon: 7995.1 ( 4.46x) 2437.2 ( 4.81x)
2024-08-07 16:53:12 +00:00
aarch64/swscale_unscaled_neon.o \
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
2016-03-18 15:39:34 +00:00
aarch64/yuv2rgb_neon.o \