RepoMirrors
/
ffmpeg
mirror of https://git.ffmpeg.org/ffmpeg.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

sse2 version of fullpel sad. 

16% faster on core2, 5% faster on p4. 10% slower (and thus disabled) on k8.

Originally committed as revision 8992 to svn://svn.ffmpeg.org/ffmpeg/trunk
This commit is contained in:
Loren Merritt 2007-05-11 01:11:45 +00:00
parent 164d75ebf3
commit 72946825fa
1 changed files with 32 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
libavcodec/i386/motion_est_mmx.c
View File

@ -88,6 +88,35 @@ static inline void sad8_1_mmx2(uint8_t *blk1, uint8_t *blk2, int stride, int h)
);
}
static int sad16_sse2(void *v, uint8_t *blk2, uint8_t *blk1, int stride, int h)
{
int ret;
asm volatile(
"pxor %%xmm6, %%xmm6 \n\t"
ASMALIGN(4)
"1: \n\t"
"movdqu (%1), %%xmm0 \n\t"
"movdqu (%1, %3), %%xmm1 \n\t"
"psadbw (%2), %%xmm0 \n\t"
"psadbw (%2, %3), %%xmm1 \n\t"
"paddw %%xmm0, %%xmm6 \n\t"
"paddw %%xmm1, %%xmm6 \n\t"
"lea (%1,%3,2), %1 \n\t"
"lea (%2,%3,2), %2 \n\t"
"sub $2, %0 \n\t"
" jg 1b \n\t"
: "+r" (h), "+r" (blk1), "+r" (blk2)
: "r" ((long)stride)
);
asm volatile(
"movhlps %%xmm6, %%xmm0 \n\t"
"paddw %%xmm0, %%xmm6 \n\t"
"movd %%xmm6, %0 \n\t"
: "=r"(ret)
);
return ret;
}
static inline void sad8_x2a_mmx2(uint8_t *blk1, uint8_t *blk2, int stride, int h)
{
asm volatile(
@ -424,4 +453,7 @@ void dsputil_init_pix_mmx(DSPContext* c, AVCodecContext *avctx)
c->pix_abs[1][3] = sad8_xy2_mmx2;
}
}
if ((mm_flags & MM_SSE2) && !(mm_flags & MM_3DNOW)) {
c->sad[0]= sad16_sse2;
}
}