X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libavutil%2Fx86%2Ffloat_dsp.asm;h=517fd63638ddeee3fabeddfec459ffb25968b6f5;hb=648b422e171d5eab18f6c6fd346e4050d717b936;hp=06d2d2cfd1b891c8b127b3b9c498605827d8d948;hpb=73d193d1d0ff62a029a905d1404c0fd357f4c880;p=ffmpeg

diff --git a/libavutil/x86/float_dsp.asm b/libavutil/x86/float_dsp.asm
index 06d2d2cfd1b..517fd63638d 100644
--- a/libavutil/x86/float_dsp.asm
+++ b/libavutil/x86/float_dsp.asm
@@ -58,6 +58,39 @@ INIT_YMM avx
 VECTOR_FMUL
 %endif
 
+;-----------------------------------------------------------------------------
+; void vector_dmul(double *dst, const double *src0, const double *src1, int len)
+;-----------------------------------------------------------------------------
+%macro VECTOR_DMUL 0
+cglobal vector_dmul, 4,4,4, dst, src0, src1, len
+    lea       lend, [lenq*8 - mmsize*4]
+ALIGN 16
+.loop:
+    movaps    m0,     [src0q + lenq + 0*mmsize]
+    movaps    m1,     [src0q + lenq + 1*mmsize]
+    movaps    m2,     [src0q + lenq + 2*mmsize]
+    movaps    m3,     [src0q + lenq + 3*mmsize]
+    mulpd     m0, m0, [src1q + lenq + 0*mmsize]
+    mulpd     m1, m1, [src1q + lenq + 1*mmsize]
+    mulpd     m2, m2, [src1q + lenq + 2*mmsize]
+    mulpd     m3, m3, [src1q + lenq + 3*mmsize]
+    movaps    [dstq + lenq + 0*mmsize], m0
+    movaps    [dstq + lenq + 1*mmsize], m1
+    movaps    [dstq + lenq + 2*mmsize], m2
+    movaps    [dstq + lenq + 3*mmsize], m3
+
+    sub       lenq, mmsize*4
+    jge       .loop
+    RET
+%endmacro
+
+INIT_XMM sse2
+VECTOR_DMUL
+%if HAVE_AVX_EXTERNAL
+INIT_YMM avx
+VECTOR_DMUL
+%endif
+
 ;------------------------------------------------------------------------------
 ; void ff_vector_fmac_scalar(float *dst, const float *src, float mul, int len)
 ;------------------------------------------------------------------------------