search for: punpckhbw

...t;lea (%1,%1,2),%%esi\n" /* esi = _ystride*3 */ +"movq (%0,%%esi),%%mm4\n" /* mm4 = _pix[0..8]+_ystride*3] */ +"movq %%mm7,%%mm6\n" /* mm6 = _pix[0..8] */ +"punpcklbw %%mm0,%%mm6\n" /* expand unsigned _pix[0..3] to 16 bits */ +"movq %%mm4,%%mm5\n" +"punpckhbw %%mm0,%%mm7\n" /* expand unsigned _pix[4..8] to 16 bits */ +"punpcklbw %%mm0,%%mm4\n" /* expand other arrays too */ +"punpckhbw %%mm0,%%mm5\n" +"psubw %%mm4,%%mm6\n" /* mm6 = mm6 - mm4 */ +"psubw %%mm5,%%mm7\n" /* mm7 = mm7 - mm5 */ + /* mm7:mm6 = _p[0...

quite some speed improvement indeed. attached the updated patch to apply to svn/trunk. j -------------- next part -------------- A non-text attachment was scrubbed... Name: theora-mmx.patch.gz Type: application/x-gzip Size: 8648 bytes Desc: not available Url : http://lists.xiph.org/pipermail/theora-dev/attachments/20040824/5a5f2731/theora-mmx.patch-0001.bin

...( +" movl $0x7, %%eax \n\t" /* 8x loop */ +" pxor %%mm0, %%mm0 \n\t" /* zero mm0 */ +" .balign 16 \n\t" +"1: movq (%4), %%mm2 \n\t" /* load mm2 with _src */ +" movq %%mm2, %%mm3 \n\t" /* copy mm2 to mm3 */ +" punpckhbw %%mm0, %%mm2 \n\t" /* expand high part of _src to 16 bits */ +" punpcklbw %%mm0, %%mm3 \n\t" /* expand low part of _src to 16 bits */ +" paddsw (%1), %%mm3 \n\t" /* add low part with low part of residue */ +" paddsw 8(%1), %%mm2 \n\t" /* high with high */...

...( +" movl $0x7, %%eax \n\t" /* 8x loop */ +" pxor %%mm0, %%mm0 \n\t" /* zero mm0 */ +" .balign 16 \n\t" +"1: movq (%4), %%mm2 \n\t" /* load mm2 with _src */ +" movq %%mm2, %%mm3 \n\t" /* copy mm2 to mm3 */ +" punpckhbw %%mm0, %%mm2 \n\t" /* expand high part of _src to 16 bits */ +" punpcklbw %%mm0, %%mm3 \n\t" /* expand low part of _src to 16 bits */ +" paddsw (%1), %%mm3 \n\t" /* add low part with low part of residue */ +" paddsw 8(%1), %%mm2 \n\t" /* high with high */...