From c3d2426cca940b519ac654eb36ba04d0acc86ca9 Mon Sep 17 00:00:00 2001 From: James Almer Date: Sun, 31 Aug 2014 23:43:02 -0300 Subject: x86/hevc_res_add: add ff_hevc_transform_add32_8_avx2 ~20% faster than AVX. Reviewed-by: Michael Niedermayer Signed-off-by: James Almer --- libavcodec/x86/hevcdsp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'libavcodec/x86/hevcdsp.h') diff --git a/libavcodec/x86/hevcdsp.h b/libavcodec/x86/hevcdsp.h index 839e05269a..8dea1428f0 100644 --- a/libavcodec/x86/hevcdsp.h +++ b/libavcodec/x86/hevcdsp.h @@ -143,6 +143,8 @@ void ff_hevc_transform_add8_8_avx(uint8_t *dst, int16_t *coeffs, ptrdiff_t strid void ff_hevc_transform_add16_8_avx(uint8_t *dst, int16_t *coeffs, ptrdiff_t stride); void ff_hevc_transform_add32_8_avx(uint8_t *dst, int16_t *coeffs, ptrdiff_t stride); +void ff_hevc_transform_add32_8_avx2(uint8_t *dst, int16_t *coeffs, ptrdiff_t stride); + void ff_hevc_transform_add4_10_mmxext(uint8_t *dst, int16_t *coeffs, ptrdiff_t stride); void ff_hevc_transform_add8_10_sse2(uint8_t *dst, int16_t *coeffs, ptrdiff_t stride); void ff_hevc_transform_add16_10_sse2(uint8_t *dst, int16_t *coeffs, ptrdiff_t stride); -- cgit v1.2.3