Lines Matching refs:D4
420 my ($H0,$H1,$H2,$H3,$H4, $T0,$T1,$T2,$T3,$T4, $D0,$D1,$D2,$D3,$D4, $MASK) =
881 vmovdqu `16*3`($ctx),$D4 # preload r0^2
912 vpshufd \$0xEE,$D4,$D3 # 34xx -> 3434
913 vpshufd \$0x44,$D4,$D0 # xx12 -> 1212
916 vpshufd \$0xEE,$D1,$D4
919 vmovdqa $D4,-0x80(%r11)
926 vpshufd \$0xEE,$D0,$D4
929 vmovdqa $D4,-0x60(%r11)
936 vpshufd \$0xEE,$D2,$D4
939 vmovdqa $D4,-0x40(%r11)
946 vpshufd \$0xEE,$D1,$D4
948 vmovdqa $D4,-0x20(%r11)
951 vmovdqa 0x00(%rsp),$D4 # preload r0^2
978 # and $D4 is preloaded with r0^2...
980 vpmuludq $T0,$D4,$D0 # d0 = h0*r0
981 vpmuludq $T1,$D4,$D1 # d1 = h1*r0
983 vpmuludq $T2,$D4,$D2 # d3 = h2*r0
985 vpmuludq $T3,$D4,$D3 # d3 = h3*r0
986 vpmuludq $T4,$D4,$D4 # d4 = h4*r0
993 vpaddq $H1,$D4,$D4 # d4 += h3*r1
1006 vpaddq $H0,$D4,$D4 # d4 += h2*r2
1021 vpaddq $H1,$D4,$D4 # d4 += h1*r3
1043 vpaddq $T4,$D4,$D4 # d4 += h0*r4
1093 vpaddq $T4,$D4,$D4
1100 vpaddq $T0,$D4,$D4 # d4 += h3*r1
1109 vpaddq $T0,$D4,$D4 # d4 += h2*r2
1122 vpaddq $T1,$D4,$D4 # d4 += h1*r3
1145 vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4
1154 vmovdqa 0x00(%rsp),$D4 # preload r0^2
1205 vpshufd \$0x10,$D4,$D4 # r0^n, xx12 -> x1x2
1228 vpmuludq $T2,$D4,$D2 # d2 = h2*r0
1229 vpmuludq $T0,$D4,$D0 # d0 = h0*r0
1231 vpmuludq $T1,$D4,$D1 # d1 = h1*r0
1232 vpmuludq $T3,$D4,$D3 # d3 = h3*r0
1233 vpmuludq $T4,$D4,$D4 # d4 = h4*r0
1236 vpaddq $H0,$D4,$D4 # d4 += h3*r1
1250 vpaddq $H1,$D4,$D4 # d4 += h2*r2
1263 vpaddq $H0,$D4,$D4 # d4 += h1*r3
1276 vpaddq $H2,$D4,$D4 # h4 = d4 + h0*r4
1327 vpaddq $T4,$D4,$D4 # d4 += h4*r0
1330 vpaddq $T0,$D4,$D4 # d4 += h3*r1
1344 vpaddq $T1,$D4,$D4 # d4 += h2*r2
1357 vpaddq $T0,$D4,$D4 # d4 += h1*r3
1370 vpaddq $T2,$D4,$D4 # d4 += h0*r4
1384 vpsrldq \$8,$D4,$T4
1390 vpaddq $T4,$D4,$D4
1400 vpaddq $H3,$D4,$D4 # h3 -> h4
1406 vpsrlq \$26,$D4,$H4
1407 vpand $MASK,$D4,$D4
1427 vpaddq $H3,$D4,$D4 # h3 -> h4
1433 vmovd $D4,`4*4-48-64`($ctx)
1517 my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) =
1845 vmovdqu `16*7-64`($ctx),%x#$D4
1858 vpermd $D4,$T0,$D4
1862 vmovdqa $D4,0xe0-0x90(%rax)
1932 vpmuludq $H2,$T2,$D4 # d4 = h2*r2
1942 vpaddq $T4,$D4,$D4 # d4 += h3*r1
1954 vpaddq $H2,$D4,$D4 # d4 += h4*r0
1973 vpaddq $T4,$D4,$D4 # d4 += h1*r3
1991 vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4
2005 vpsrlq \$26,$H4,$D4
2014 vpaddq $D4,$H0,$H0
2015 vpsllq \$2,$D4,$D4
2016 vpaddq $D4,$H0,$H0 # h4 -> h0
2067 vpmuludq $H2,$T2,$D4 # d4 = h2*r2
2077 vpaddq $T4,$D4,$D4 # d4 += h3*r1
2088 vpaddq $H2,$D4,$D4 # d4 += h4*r0
2102 vpaddq $T4,$D4,$D4 # d4 += h1*r3
2116 vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4
2155 vpsrlq \$26,$H4,$D4
2162 vpaddq $D4,$H0,$H0
2163 vpsllq \$2,$D4,$D4
2164 vpaddq $D4,$H0,$H0 # h4 -> h0
2213 map(s/%y/%z/,($D0,$D1,$D2,$D3,$D4));
2258 vmovdqu `16*7-64`($ctx),%x#$D4 # ... ${R4}
2273 vpermd $D4,$T2,$R4
2295 vpmuludq $T0,$R4,$D4 # d4 = r0'*r4
2308 vpaddq $M4,$D4,$D4 # d4 += r1'*r3
2319 vpaddq $M4,$D4,$D4 # d4 += r2'*r2
2329 vpaddq $M4,$D4,$D4 # d4 += r3'*r1
2339 vpaddq $M4,$D4,$D4 # d4 += r2'*r0
2355 vpaddq $M3,$D4,$D4 # d3 -> d4
2361 vpsrlq \$26,$D4,$M4
2362 vpandq $MASK,$D4,$D4
2382 vpaddq $M3,$D4,$D4 # d3 -> d4
2386 # $D0-$D4, ...
2410 vpermd $D4,$M0,${R4}{%k1}
2472 vpmuludq $H2,$R2,$D4 # d4 = h2*r2
2491 vpaddq $M4,$D4,$D4 # d4 += h0*r4
2500 vpaddq $M4,$D4,$D4 # d4 += h1*r3
2512 vpaddq $M4,$D4,$D4 # d4 += h3*r1
2522 vpaddq $M4,$D4,$D4 # d4 += h4*r0
2542 vpaddq $H3,$D4,$H4 # h3 -> h4
2552 vpsrlq \$26,$H4,$D4
2559 vpaddq $D4,$H0,$H0
2560 vpsllq \$2,$D4,$D4
2561 vpaddq $D4,$H0,$H0 # h4 -> h0
2614 vpmuludq $H2,$R2,$D4 # d4 = h2*r2
2631 vpaddq $M4,$D4,$D4 # d4 += h0*r4
2641 vpaddq $M4,$D4,$D4 # d4 += h1*r3
2651 vpaddq $M4,$D4,$D4 # d4 += h3*r1
2662 vpaddq $M4,$D4,$D4 # d4 += h4*r0
2679 vpermq \$0xb1,$D4,$H4
2684 vpaddq $D4,$H4,$H4
2691 vpermq \$0x2,$H4,$D4
2696 vpaddq $D4,$H4,$H4
2702 vextracti64x4 \$0x1,$H4,%y#$D4
2707 vpaddq $D4,$H4,${H4}{%k3}{z} # it's passed to .Ltail_avx2
2713 map(s/%z/%y/,($H0,$H1,$H2,$H3,$H4, $D0,$D1,$D2,$D3,$D4, $MASK));
2731 vpsrlq \$26,$H4,$D4
2740 vpaddq $D4,$H0,$H0
2741 vpsllq \$2,$D4,$D4
2744 vpaddq $D4,$H0,$H0 # h4 -> h0