From 5e586e1befaab7b77883d73c0ebcb19f1d786ed8 Mon Sep 17 00:00:00 2001 From: Timothy Gu Date: Mon, 19 Oct 2015 02:25:11 +0100 Subject: huffyuvencdsp: Add ff_diff_bytes_{sse2,avx2} SSE2 version 4%-35% faster than MMX depending on the width. AVX2 version 1%-13% faster than SSE2 depending on the width. --- libavcodec/huffyuvenc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'libavcodec/huffyuvenc.c') diff --git a/libavcodec/huffyuvenc.c b/libavcodec/huffyuvenc.c index 49d711a948..e080cd90bb 100644 --- a/libavcodec/huffyuvenc.c +++ b/libavcodec/huffyuvenc.c @@ -60,12 +60,12 @@ static inline int sub_left_prediction(HYuvContext *s, uint8_t *dst, } return left; } else { - for (i = 0; i < 16; i++) { + for (i = 0; i < 32; i++) { const int temp = src[i]; dst[i] = temp - left; left = temp; } - s->hencdsp.diff_bytes(dst + 16, src + 16, src + 15, w - 16); + s->hencdsp.diff_bytes(dst + 32, src + 32, src + 31, w - 32); return src[w-1]; } } else { -- cgit v1.2.1