diff options
| author | Timothy Gu <timothygu99@gmail.com> | 2016-02-14 02:15:18 +0000 |
|---|---|---|
| committer | Timothy Gu <timothygu99@gmail.com> | 2016-02-14 09:12:37 -0800 |
| commit | a678d667816a86b7e5f8c4b558f8ed333bb98841 (patch) | |
| tree | aca9df8d14fb93c57296886b990e2c1975605902 | |
| parent | 4b750104ea2b8dec4e055216a047092650a3ba25 (diff) | |
| download | ffmpeg-a678d667816a86b7e5f8c4b558f8ed333bb98841.tar.gz | |
vf_blend: Use integers for divide mode
2.5x faster for 8-bit mode without autovectorization in GCC, 2x
slower with it on x86. However, since the platforms we enable GCC
autovectorization on most probably has support for SSE2
optimization (added in the subsequent commit), this commit should
in general do good.
| -rw-r--r-- | libavfilter/vf_blend.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/libavfilter/vf_blend.c b/libavfilter/vf_blend.c index 4b4d4350c4..61aa17ebeb 100644 --- a/libavfilter/vf_blend.c +++ b/libavfilter/vf_blend.c @@ -247,7 +247,7 @@ DEFINE_BLEND8(hardlight, (B < 128) ? MULTIPLY(2, B, A) : SCREEN(2, B, A)) DEFINE_BLEND8(hardmix, (A < (255 - B)) ? 0: 255) DEFINE_BLEND8(darken, FFMIN(A, B)) DEFINE_BLEND8(lighten, FFMAX(A, B)) -DEFINE_BLEND8(divide, av_clip_uint8(((float)A / ((float)B) * 255))) +DEFINE_BLEND8(divide, av_clip_uint8(B == 0 ? 255 : 255 * A / B)) DEFINE_BLEND8(dodge, DODGE(A, B)) DEFINE_BLEND8(burn, BURN(A, B)) DEFINE_BLEND8(softlight, (A > 127) ? B + (255 - B) * (A - 127.5) / 127.5 * (0.5 - fabs(B - 127.5) / 255): B - B * ((127.5 - A) / 127.5) * (0.5 - fabs(B - 127.5)/255)) @@ -287,7 +287,7 @@ DEFINE_BLEND16(hardlight, (B < 32768) ? MULTIPLY(2, B, A) : SCREEN(2, B, A)) DEFINE_BLEND16(hardmix, (A < (65535 - B)) ? 0: 65535) DEFINE_BLEND16(darken, FFMIN(A, B)) DEFINE_BLEND16(lighten, FFMAX(A, B)) -DEFINE_BLEND16(divide, av_clip_uint16(((float)A / ((float)B) * 65535))) +DEFINE_BLEND16(divide, av_clip_uint16(B == 0 ? 65535 : 65535 * A / B)) DEFINE_BLEND16(dodge, DODGE(A, B)) DEFINE_BLEND16(burn, BURN(A, B)) DEFINE_BLEND16(softlight, (A > 32767) ? B + (65535 - B) * (A - 32767.5) / 32767.5 * (0.5 - fabs(B - 32767.5) / 65535): B - B * ((32767.5 - A) / 32767.5) * (0.5 - fabs(B - 32767.5)/65535)) |