Lines Matching defs:movq
335 movq mm0,mask0
347 movq mm4,[esi]
349 movq mm6,mm0
352 movq [ebx],mm4
439 movq mm0,mask0
440 movq mm1,mask1
455 movq mm4,[esi]
457 movq mm6,mm0
458 movq mm7,[ebx]
461 movq [ebx],mm4
463 movq mm5,[esi+8]
465 movq mm7,mm1
466 movq mm6,[ebx+8]
469 movq [ebx+8],mm5
558 movq mm0,mask0
559 movq mm1,mask1
560 movq mm2,mask2
577 movq mm4,[esi]
579 movq mm6,mm0
580 movq mm7,[ebx]
583 movq [ebx],mm4
586 movq mm5,[esi+8]
588 movq mm7,mm1
589 movq mm6,[ebx+8]
592 movq [ebx+8],mm5
594 movq mm6,[esi+16]
596 movq mm4,mm2
597 movq mm7,[ebx+16]
600 movq [ebx+16],mm6
694 movq mm0,mask0
695 movq mm1,mask1
696 movq mm2,mask2
697 movq mm3,mask3
717 movq mm4,[esi]
719 movq mm6,mm0
720 movq mm7,[ebx]
723 movq [ebx],mm4
725 movq mm5,[esi+8]
727 movq mm7,mm1
728 movq mm6,[ebx+8]
731 movq [ebx+8],mm5
733 movq mm6,[esi+16]
735 movq mm4,mm2
736 movq mm7,[ebx+16]
739 movq [ebx+16],mm6
741 movq mm7,[esi+24]
743 movq mm5,mm3
744 movq mm4,[ebx+24]
747 movq [ebx+24],mm7
839 movq mm0,mask0
840 movq mm1,mask1
841 movq mm2,mask2
842 movq mm3,mask3
843 movq mm4,mask4
844 movq mm5,mask5
868 movq mm7,[esi]
870 movq mm6,mm0
873 movq [ebx],mm7
875 movq mm6,[esi+8]
877 movq mm7,mm1
880 movq [ebx+8],mm6
882 movq mm6,[esi+16]
884 movq mm7,mm2
887 movq [ebx+16],mm6
889 movq mm7,[esi+24]
891 movq mm6,mm3
894 movq [ebx+24],mm7
896 movq mm6,[esi+32]
898 movq mm7,mm4
901 movq [ebx+32],mm6
903 movq mm7,[esi+40]
905 movq mm6,mm5
908 movq [ebx+40],mm7
1237 movq mm1, mm0 ; 0 0 0 0 0 v2 v1 v0
1239 movq mm2, mm0 ; 0 0 0 v2 v1 v0 0 0
1244 movq mm3, mm0 ; v2 v1 v0 v2 v1 v0 v2 v1
1246 movq mm4, mm3 ; v2 v1 v0 v2 v1 v0 v2 v1
1248 movq [edi+16] , mm4
1250 movq [edi+8] , mm3
1253 movq [edi], mm0
1272 movq mm1, mm0 ; 0 0 0 0 0 v2 v1 v0
1274 movq mm2, mm0 ; 0 0 0 v2 v1 v0 0 0
1279 movq [edi+4], mm0 ; move to memory
1305 movq mm0, [esi] ; X X v2 v1 v0 v5 v4 v3
1306 movq mm7, mm0 ; X X v2 v1 v0 v5 v4 v3
1307 movq mm6, mm0 ; X X v2 v1 v0 v5 v4 v3
1312 movq mm5, mm6 ; 0 0 0 X X v2 v1 v0
1314 movq [edi], mm0 ; move quad to memory
1362 movq mm1, mm0 ; X X X X v0 v1 v2 v3
1364 movq mm2, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
1366 movq mm3, mm0 ; v2 v2 v2 v2 v3 v3 v3 v3
1369 movq [edi], mm0 ; move to memory v3
1371 movq [edi+8], mm3 ; move to memory v2
1372 movq mm4, mm2 ; v0 v0 v0 v0 v1 v1 v1 v1
1375 movq [edi+16], mm2 ; move to memory v1
1376 movq [edi+24], mm4 ; move to memory v0
1430 movq mm1, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
1433 movq [edi], mm0 ; move to memory v2 and v3
1435 movq [edi+8], mm1 ; move to memory v1 and v0
1470 movq mm0, [esi] ; v0 v1 v2 v3 v4 v5 v6 v7
1471 movq mm1, mm0 ; v0 v1 v2 v3 v4 v5 v6 v7
1473 //movq mm1, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
1475 movq [edi+8], mm1 ; move to memory v0 v1 v2 and v3
1477 movq [edi], mm0 ; move to memory v4 v5 v6 and v7
1519 movq mm1, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
1522 movq [edi], mm0
1523 movq [edi + 8], mm0
1524 movq [edi + 16], mm1
1525 movq [edi + 24], mm1
1565 movq mm1, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
1568 movq [edi], mm0
1570 movq [edi + 8], mm1
1611 movq [edi], mm0
1652 movq mm0, [esi] ; v3 v2 v1 v0 v7 v6 v5 v4
1653 movq mm1, mm0 ; v3 v2 v1 v0 v7 v6 v5 v4
1656 movq [edi], mm0
1657 movq [edi + 8], mm0
1658 movq [edi + 16], mm0
1659 movq [edi + 24], mm0
1660 movq [edi+32], mm1
1661 movq [edi + 40], mm1
1662 movq [edi+ 48], mm1
1664 movq [edi + 56], mm1
1701 movq mm0, [esi] ; v3 v2 v1 v0 v7 v6 v5 v4
1702 movq mm1, mm0 ; v3 v2 v1 v0 v7 v6 v5 v4
1705 movq [edi], mm0
1706 movq [edi + 8], mm0
1707 movq [edi+16], mm1
1708 movq [edi + 24], mm1
1746 movq mm0, [esi] ; v3 v2 v1 v0 v7 v6 v5 v4
1747 movq mm1, mm0 ; v3 v2 v1 v0 v7 v6 v5 v4
1750 movq [edi], mm0
1752 movq [edi + 8], mm1
2000 movq mm7, ActiveMask
2002 movq mm5, LBCarryMask
2004 movq mm4, HBClearMask
2007 movq mm2, [edi + ebx - 8] // Load previous aligned 8 bytes
2010 movq mm0, [edi + ebx] // Load mm0 with Avg(x)
2012 movq mm3, mm5
2014 movq mm1, [esi + ebx] // Load mm1 with Prior(x)
2015 movq mm6, mm7
2021 movq mm1, mm3 // now use mm1 for getting LBCarrys
2032 movq mm2, mm0 // mov updated Raws to mm2
2034 movq mm1, mm3 // now use mm1 for getting LBCarrys
2047 movq mm2, mm0 // mov updated Raws to mm2
2051 movq mm1, mm3 // now use mm1 for getting LBCarrys
2063 movq [edi + ebx - 8], mm0
2066 movq mm2, mm0 // mov updated Raw(x) to mm2
2082 movq mm4, HBClearMask
2086 movq mm7, ActiveMask
2090 movq mm6, mm7
2091 movq mm5, LBCarryMask
2094 movq mm2, [edi + ebx - 8] // Load previous aligned 8 bytes
2097 movq mm0, [edi + ebx]
2099 movq mm1, [esi + ebx]
2101 movq mm3, mm5
2107 movq mm1, mm3 // now use mm1 for getting LBCarrys
2117 movq mm2, mm0 // mov updated Raws to mm2
2120 movq mm1, mm3 // now use mm1 for getting LBCarrys
2131 movq [edi + ebx - 8], mm0
2133 movq mm2, mm0 // mov updated Raws to mm2
2145 movq mm7, ActiveMask
2148 movq mm5, LBCarryMask
2150 movq mm4, HBClearMask
2153 movq mm2, [edi + ebx - 8] // Load previous aligned 8 bytes
2156 movq mm0, [edi + ebx]
2158 movq mm1, [esi + ebx]
2160 movq mm3, mm5
2164 movq mm6, mm7
2167 movq mm1, mm3 // now use mm1 for getting LBCarrys
2177 movq mm2, mm0 // mov updated Raws to mm2
2179 movq mm1, mm3 // now use mm1 for getting LBCarrys
2190 movq mm2, mm0 // mov updated Raws to mm2
2194 movq mm1, mm3 // now use mm1 for getting LBCarrys
2205 movq mm2, mm0 // mov updated Raws to mm2
2210 movq mm1, mm3 // now use mm1 for getting LBCarrys
2221 movq [edi + ebx - 8], mm0
2223 movq mm2, mm0 // mov updated Raws to mm2
2265 movq mm5, LBCarryMask
2267 movq mm4, HBClearMask
2270 movq mm2, [edi + ebx - 8] // Load previous aligned 8 bytes
2273 movq mm0, [edi + ebx]
2274 movq mm3, mm5
2275 movq mm1, [esi + ebx]
2288 movq [edi + ebx - 8], mm0
2289 movq mm2, mm0 // reuse as Raw(x-bpp)
2297 movq mm5, LBCarryMask
2301 movq mm4, HBClearMask
2306 movq mm0, [edi + ebx]
2307 movq mm3, mm5
2308 movq mm1, [esi + ebx]
2310 movq mm2, [edx + ebx]
2322 movq [edi + ebx - 8], mm0
2488 movq mm1, [edi+ebx-8]
2491 movq mm2, [esi + ebx] // load b=Prior(x)
2493 movq mm3, [esi+ebx-8] // Prep c=Prior(x-bpp) bytes
2497 movq mm4, mm2
2500 movq mm5, mm1
2504 movq mm6, mm4
2524 movq mm7, mm4
2527 movq mm0, mm7
2544 movq mm3, [esi + ebx] // load c=Prior(x-bpp)
2546 movq mm2, mm3 // load b=Prior(x) step 1
2549 movq [edi + ebx], mm7 // write back updated value
2550 movq mm1, mm7 // Now mm1 will be used as Raw(x-bpp)
2557 movq mm5, mm1
2559 movq mm4, mm2
2564 movq mm6, mm5
2583 movq mm7, mm4
2586 movq mm0, mm7
2597 movq mm2, [esi + ebx] // load b=Prior(x)
2604 movq mm3, mm2 // load c=Prior(x-bpp) step 1
2609 movq mm4, mm2
2612 movq [edi + ebx], mm7 // write back updated value
2613 movq mm1, mm7
2622 movq mm5, mm1
2624 movq mm6, mm4
2645 movq mm7, mm4
2648 movq mm0, mm7
2671 movq [edi + ebx - 8], mm1 // write back updated value
2693 movq mm1, [edi+ebx-8]
2699 movq mm3, [esi+ebx-8] // read c=Prior(x-bpp) bytes
2701 movq mm2, [esi + ebx] // load b=Prior(x)
2706 movq mm4, mm2
2709 movq mm5, mm1
2713 movq mm6, mm4
2732 movq mm7, mm4
2735 movq mm0, mm7
2752 movq mm3, [esi + ebx - 8] // load c=Prior(x-bpp)
2755 movq mm2, [esi + ebx] // load b=Prior(x) step 1
2757 movq mm6, mm2
2758 movq [edi + ebx], mm7 // write back updated value
2759 movq mm1, [edi+ebx-8]
2761 movq mm5, mm7
2771 movq mm4, mm2
2773 movq mm5, mm1
2777 movq mm6, mm4
2796 movq mm7, mm4
2799 movq mm0, mm7
2821 movq [edi + ebx - 8], mm1 // write back updated value
2837 movq mm1, [edi+ebx-8] // Only time should need to read
2841 movq mm3, [esi+ebx-8] // read c=Prior(x-bpp) bytes
2843 movq mm2, [esi + ebx] // load b=Prior(x)
2846 movq mm4, mm2
2849 movq mm5, mm1
2853 movq mm6, mm4
2872 movq mm7, mm4
2875 movq mm0, mm7
2892 movq mm3, [esi + ebx] // load c=Prior(x-bpp)
2894 movq mm2, mm3 // load b=Prior(x) step 1
2897 movq [edi + ebx], mm7 // write back updated value
2898 movq mm1, mm7 // Now mm1 will be used as Raw(x-bpp)
2903 movq mm4, mm2
2905 movq mm5, mm1
2909 movq mm6, mm4
2928 movq mm7, mm4
2931 movq mm0, mm7
2953 movq [edi + ebx - 8], mm1 // write back updated value
2968 movq mm1, [edi+ebx-8] // Only time should need to read
2972 movq mm3, [esi+ebx-8] // read c=Prior(x-bpp) bytes
2974 movq mm2, [esi + ebx] // load b=Prior(x)
2977 movq mm4, mm2
2980 movq mm5, mm1
2984 movq mm6, mm4
3003 movq mm7, mm4
3006 movq mm0, mm7
3023 movq mm3, [esi+ebx-8] // read c=Prior(x-bpp) bytes
3025 movq mm2, [esi + ebx] // load b=Prior(x)
3028 movq [edi + ebx], mm7 // write back updated value
3029 movq mm1, [edi+ebx-8] // read a=Raw(x-bpp) bytes
3035 movq mm4, mm2
3037 movq mm5, mm1
3041 movq mm6, mm4
3060 movq mm7, mm4
3063 movq mm0, mm7
3085 movq [edi + ebx - 8], mm1 // write back updated value
3307 movq mm7, ActiveMask // Load ActiveMask for 2nd active byte group
3310 movq mm6, mm7
3315 movq mm1, [edi+ebx-8]
3320 movq mm0, [edi+ebx]
3323 movq mm1, mm0 // mov updated Raws to mm1
3328 movq mm1, mm0 // mov updated Raws to mm1
3334 movq [edi+ebx-8], mm0 // Write updated Raws back to array
3336 movq mm1, mm0
3388 movq mm1, [edi+ebx-8]
3392 movq mm0, [edi+ebx]
3395 movq mm1, mm0 // mov updated Raws to mm1
3402 movq [edi+ebx-8], mm0
3403 movq mm1, mm0 // Prep for doing 1st add at top of loop
3415 movq mm7, ActiveMask // Load ActiveMask for 2nd active byte group
3417 movq mm6, mm7
3422 movq mm5, mm6
3427 movq mm1, [edi+ebx-8]
3433 movq mm0, [edi+ebx]
3436 movq mm1, mm0 // mov updated Raws to mm1
3441 movq mm1, mm0 // mov updated Raws to mm1
3446 movq mm1, mm0 // mov updated Raws to mm1
3452 movq [edi+ebx-8], mm0 // Write updated Raws back to array
3453 movq mm1, mm0 // Prep for doing 1st add at top of loop
3466 movq mm7, [edi+ebx-8] // PRIME the pump (load the first
3470 movq mm0, [edi+ebx] // Load Sub(x) for 1st 8 bytes
3472 movq mm1, [edi+ebx+8] // Load Sub(x) for 2nd 8 bytes
3473 movq [edi+ebx], mm0 // Write Raw(x) for 1st 8 bytes
3480 movq mm2, [edi+ebx+16] // Load Sub(x) for 3rd 8 bytes
3481 movq [edi+ebx+8], mm1 // Write Raw(x) for 2nd 8 bytes
3483 movq mm3, [edi+ebx+24] // Load Sub(x) for 4th 8 bytes
3484 movq [edi+ebx+16], mm2 // Write Raw(x) for 3rd 8 bytes
3486 movq mm4, [edi+ebx+32] // Load Sub(x) for 5th 8 bytes
3487 movq [edi+ebx+24], mm3 // Write Raw(x) for 4th 8 bytes
3489 movq mm5, [edi+ebx+40] // Load Sub(x) for 6th 8 bytes
3490 movq [edi+ebx+32], mm4 // Write Raw(x) for 5th 8 bytes
3492 movq mm6, [edi+ebx+48] // Load Sub(x) for 7th 8 bytes
3493 movq [edi+ebx+40], mm5 // Write Raw(x) for 6th 8 bytes
3495 movq mm7, [edi+ebx+56] // Load Sub(x) for 8th 8 bytes
3496 movq [edi+ebx+48], mm6 // Write Raw(x) for 7th 8 bytes
3500 movq [edi+ebx-8], mm7 // Write Raw(x) for 8th 8 bytes
3505 movq mm0, [edi+ebx]
3509 movq [edi+ebx-8], mm0 // use -8 to offset early add to ebx
3510 movq mm7, mm0 // Move calculated Raw(x) data to mm1 to
3526 movq mm0, [edi+ebx]
3527 movq mm1, [esi+ebx]
3531 movq [edi+ebx-8], mm0 // mov does not affect flags; -8 to offset
3594 movq mm1, [esi+ebx]
3595 movq mm0, [edi+ebx]
3596 movq mm3, [esi+ebx+8]
3598 movq mm2, [edi+ebx+8]
3599 movq [edi+ebx], mm0
3601 movq mm5, [esi+ebx+16]
3602 movq [edi+ebx+8], mm2
3603 movq mm4, [edi+ebx+16]
3604 movq mm7, [esi+ebx+24]
3606 movq mm6, [edi+ebx+24]
3607 movq [edi+ebx+16], mm4
3609 movq mm1, [esi+ebx+32]
3610 movq [edi+ebx+24], mm6
3611 movq mm0, [edi+ebx+32]
3612 movq mm3, [esi+ebx+40]
3614 movq mm2, [edi+ebx+40]
3615 movq [edi+ebx+32], mm0
3617 movq mm5, [esi+ebx+48]
3618 movq [edi+ebx+40], mm2
3619 movq mm4, [edi+ebx+48]
3620 movq mm7, [esi+ebx+56]
3622 movq mm6, [edi+ebx+56]
3623 movq [edi+ebx+48], mm4
3627 movq [edi+ebx-8], mm6 // (+56)movq does not affect flags;
3647 movq mm1, [esi+ebx]
3648 movq mm0, [edi+ebx]
3652 movq [edi+ebx-8], mm0 // movq does not affect flags; -8 to offset add ebx