diff options
| author | Justin Ruggles <justin.ruggles@gmail.com> | 2011-01-13 23:28:06 +0300 |
|---|---|---|
| committer | Michael Niedermayer <michaelni@gmx.at> | 2011-01-23 21:32:08 +0300 |
| commit | 015f9f1ad379745fe02ba219a83c406fdeaf37be (patch) | |
| tree | 77e942562738c7278d3f40ebccaadc2740f8e317 /libavcodec/x86 | |
| parent | fb397b1a193f15b5c104fc14caf49ded50ccf354 (diff) | |
Change DSPContext.vector_fmul() from dst=dst*src to dest=src0*src1.
Signed-off-by: Mans Rullgard <mans@mansr.com>
(cherry picked from commit 6eabb0d3ad42b91c1b4c298718c29961f7c1653a)
Diffstat (limited to 'libavcodec/x86')
| -rw-r--r-- | libavcodec/x86/dsputil_mmx.c | 24 |
1 files changed, 12 insertions, 12 deletions
diff --git a/libavcodec/x86/dsputil_mmx.c b/libavcodec/x86/dsputil_mmx.c index 825149e4a5..5ddfecae24 100644 --- a/libavcodec/x86/dsputil_mmx.c +++ b/libavcodec/x86/dsputil_mmx.c @@ -2074,38 +2074,38 @@ static void ac3_downmix_sse(float (*samples)[256], float (*matrix)[2], int out_c } } -static void vector_fmul_3dnow(float *dst, const float *src, int len){ +static void vector_fmul_3dnow(float *dst, const float *src0, const float *src1, int len){ x86_reg i = (len-4)*4; __asm__ volatile( "1: \n\t" - "movq (%1,%0), %%mm0 \n\t" - "movq 8(%1,%0), %%mm1 \n\t" - "pfmul (%2,%0), %%mm0 \n\t" - "pfmul 8(%2,%0), %%mm1 \n\t" + "movq (%2,%0), %%mm0 \n\t" + "movq 8(%2,%0), %%mm1 \n\t" + "pfmul (%3,%0), %%mm0 \n\t" + "pfmul 8(%3,%0), %%mm1 \n\t" "movq %%mm0, (%1,%0) \n\t" "movq %%mm1, 8(%1,%0) \n\t" "sub $16, %0 \n\t" "jge 1b \n\t" "femms \n\t" :"+r"(i) - :"r"(dst), "r"(src) + :"r"(dst), "r"(src0), "r"(src1) :"memory" ); } -static void vector_fmul_sse(float *dst, const float *src, int len){ +static void vector_fmul_sse(float *dst, const float *src0, const float *src1, int len){ x86_reg i = (len-8)*4; __asm__ volatile( "1: \n\t" - "movaps (%1,%0), %%xmm0 \n\t" - "movaps 16(%1,%0), %%xmm1 \n\t" - "mulps (%2,%0), %%xmm0 \n\t" - "mulps 16(%2,%0), %%xmm1 \n\t" + "movaps (%2,%0), %%xmm0 \n\t" + "movaps 16(%2,%0), %%xmm1 \n\t" + "mulps (%3,%0), %%xmm0 \n\t" + "mulps 16(%3,%0), %%xmm1 \n\t" "movaps %%xmm0, (%1,%0) \n\t" "movaps %%xmm1, 16(%1,%0) \n\t" "sub $32, %0 \n\t" "jge 1b \n\t" :"+r"(i) - :"r"(dst), "r"(src) + :"r"(dst), "r"(src0), "r"(src1) :"memory" ); } |