Lines Matching full:h4
419 my ($H0,$H1,$H2,$H3,$H4, $T0,$T1,$T2,$T3,$T4, $D0,$D1,$D2,$D3,$D4, $MASK) =
716 vmovd $h2#d,$H4
818 vmovd $h2#d,$H4
848 vmovd 4*4($ctx),$H4
970 # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
971 # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
972 # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
973 # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
974 # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
985 vpmuludq $T4,$D4,$D4 # d4 = h4*r0
988 vpmuludq 0x20(%rsp),$T4,$H0 # h4*s1
991 vpaddq $H0,$D0,$D0 # d0 += h4*s1
999 vmovdqa $H4,0x40(%r11) #
1004 vmovdqa 0x40(%rsp),$H4 # s2^2
1011 vpmuludq $T4,$H4,$H0 # h4*s2
1012 vpmuludq $T3,$H4,$H4 # h3*s2
1013 vpaddq $H0,$D1,$D1 # d1 += h4*s2
1015 vpaddq $H4,$D0,$D0 # d0 += h3*s2
1017 vmovdqa 0x80(%rsp),$H4 # s4^2
1022 vpmuludq $T4,$H3,$H0 # h4*s3
1024 vpaddq $H0,$D2,$D2 # d2 += h4*s3
1028 vpmuludq $T2,$H4,$T2 # h2*s4
1033 vpmuludq $T3,$H4,$T3 # h3*s4
1034 vpmuludq $T4,$H4,$T4 # h4*s4
1037 vpaddq $T4,$D3,$D3 # d3 += h4*s4
1040 vpmuludq $T1,$H4,$T0 # h1*s4
1041 vpunpckhqdq $H1,$H0,$H4 # 4
1049 #vpsrlq \$40,$H4,$H4 # 4
1050 vpsrldq \$`40/8`,$H4,$H4 # 4
1055 vpand 0(%rcx),$H4,$H4 # .Lmask24
1059 vpor 32(%rcx),$H4,$H4 # padbit, yes, always
1065 vpaddq 0x40(%r11),$H4,$H4
1075 # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
1076 # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
1077 # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
1078 # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
1079 # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
1090 vpmuludq $H4,$T4,$T4 # h4*r0
1091 vpmuludq -0x70(%r11),$H4,$T0 # h4*s1
1094 vpaddq $T0,$D0,$D0 # d0 += h4*s1
1112 vpmuludq $H4,$T4,$T0 # h4*s2
1114 vpaddq $T0,$D1,$D1 # d1 += h4*s2
1123 vpmuludq $H4,$T3,$T0 # h4*s3
1125 vpaddq $T0,$D2,$D2 # d2 += h4*s3
1137 vpmuludq $H4,$T4,$H4 # h4*s4
1140 vpaddq $H4,$D3,$H3 # h3 = d3 + h4*s4
1141 vpmuludq -0x20(%r11),$H0,$H4 # h0*r4
1144 vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4
1169 vpaddq $D3,$H4,$H4 # h3 -> h4
1175 vpsrlq \$26,$H4,$D0
1176 vpand $MASK,$H4,$H4
1184 vpaddq $D0,$H0,$H0 # h4 -> h0
1196 vpaddq $D3,$H4,$H4 # h3 -> h4
1212 vpaddq $H4,$T4,$T4
1219 vmovdqa $H4,0x40(%r11)
1221 # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
1222 # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
1223 # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
1224 # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
1225 # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
1232 vpmuludq $T4,$D4,$D4 # d4 = h4*r0
1239 vpshufd \$0x10,`16*3-64`($ctx),$H4 # r2^n
1244 vpmuludq $T4,$H3,$H3 # h4*s1
1245 vpaddq $H3,$D0,$D0 # d0 += h4*s1
1248 vpmuludq $T2,$H4,$H1 # h2*r2
1250 vpmuludq $T1,$H4,$H0 # h1*r2
1253 vpmuludq $T0,$H4,$H4 # h0*r2
1254 vpaddq $H4,$D2,$D2 # d2 += h0*r2
1255 vpmuludq $T4,$H2,$H1 # h4*s2
1256 vpaddq $H1,$D1,$D1 # d1 += h4*s2
1257 vpshufd \$0x10,`16*6-64`($ctx),$H4 # s3^n
1266 vpmuludq $T4,$H4,$H1 # h4*s3
1267 vpaddq $H1,$D2,$D2 # d2 += h4*s3
1269 vpmuludq $T3,$H4,$H0 # h3*s3
1271 vpmuludq $T2,$H4,$H4 # h2*s3
1272 vpaddq $H4,$D0,$D0 # d0 += h2*s3
1275 vpaddq $H2,$D4,$D4 # h4 = d4 + h0*r4
1276 vpmuludq $T4,$H3,$H1 # h4*s4
1277 vpaddq $H1,$D3,$D3 # h3 = d3 + h4*s4
1292 vpunpckhqdq $H1,$H0,$H4 # 4
1296 vpsrlq \$40,$H4,$H4 # 4
1304 vpor 32(%rcx),$H4,$H4 # padbit, yes, always
1311 vpaddq 0x40(%r11),$H4,$H4
1325 vpmuludq $H4,$T4,$T4 # h4*r0
1326 vpaddq $T4,$D4,$D4 # d4 += h4*r0
1338 vpmuludq $H4,$T3,$T3 # h4*s1
1339 vpaddq $T3,$D0,$D0 # d0 += h4*s1
1349 vpmuludq $H4,$T2,$T1 # h4*s2
1350 vpaddq $T1,$D1,$D1 # d1 += h4*s2
1360 vpmuludq $H4,$T4,$T1 # h4*s3
1361 vpaddq $T1,$D2,$D2 # d2 += h4*s3
1370 vpmuludq $H4,$T3,$T1 # h4*s4
1371 vpaddq $T1,$D3,$D3 # d3 += h4*s4
1399 vpaddq $H3,$D4,$D4 # h3 -> h4
1405 vpsrlq \$26,$D4,$H4
1412 vpaddq $H4,$D0,$D0
1413 vpsllq \$2,$H4,$H4
1414 vpaddq $H4,$D0,$D0 # h4 -> h0
1426 vpaddq $H3,$D4,$D4 # h3 -> h4
1516 my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) =
1644 vmovd $h2#d,%x#$H4
1751 vmovd $h2#d,%x#$H4
1792 vmovd 4*4($ctx),%x#$H4
1910 vpaddq $H4,$T4,$H4
1914 # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
1915 # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
1916 # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
1917 # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
1918 # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
1923 # d4 = h2*r2 + h4*r0 + h3*r1 + h1*r3 + h0*r4
1924 # d3 = h2*r1 + h3*r0 + h1*r2 + h0*r3 + h4*5*r4
1925 # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
1926 # d1 = h2*5*r4 + h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3
1927 # d0 = h2*5*r3 + h0*r0 + h4*5*r1 + h3*5*r2 + h1*5*r4
1940 vpmuludq `32*2`(%rsp),$H4,$H2 # h4*s1
1942 vpaddq $H2,$D0,$D0 # d0 += h4*s1
1950 vpmuludq $H4,$T0,$H2 # h4*r0
1953 vpaddq $H2,$D4,$D4 # d4 += h4*r0
1957 vpmuludq $H4,$T1,$H2 # h4*s2
1960 vpaddq $H2,$D1,$D1 # d1 += h4*s2
1975 vpmuludq $H4,$T3,$H2 # h4*s3
1978 vpaddq $H2,$D2,$D2 # d2 += h4*s3
1982 vpmuludq $H4,$S4,$H4 # h4*s4
1985 vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4
1987 vpmuludq `32*7-0x90`(%rax),$H0,$H4 # h0*r4
1990 vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4
1998 vpaddq $D3,$H4,$H4 # h3 -> h4
2004 vpsrlq \$26,$H4,$D4
2005 vpand $MASK,$H4,$H4
2015 vpaddq $D4,$H0,$H0 # h4 -> h0
2035 vpaddq $D3,$H4,$H4 # h3 -> h4
2060 vpaddq $H4,$T4,$H4
2075 vpmuludq `32*2+4`(%rsp),$H4,$H2 # h4*s1
2077 vpaddq $H2,$D0,$D0 # d0 += h4*s1
2085 vpmuludq $H4,$T0,$H2 # h4*r0
2087 vpaddq $H2,$D4,$D4 # d4 += h4*r0
2090 vpmuludq $H4,$T1,$H2 # h4*s2
2092 vpaddq $H2,$D1,$D1 # d1 += h4*s2
2104 vpmuludq $H4,$T3,$H2 # h4*s3
2106 vpaddq $H2,$D2,$D2 # d2 += h4*s3
2109 vpmuludq $H4,$S4,$H4 # h4*s4
2111 vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4
2112 vpmuludq `32*7+4-0x90`(%rax),$H0,$H4 # h0*r4
2115 vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4
2124 vpsrldq \$8,$H4,$T4
2129 vpaddq $T4,$H4,$H4
2133 vpermq \$0x2,$H4,$T4
2138 vpaddq $T4,$H4,$H4
2148 vpaddq $D3,$H4,$H4 # h3 -> h4
2154 vpsrlq \$26,$H4,$D4
2155 vpand $MASK,$H4,$H4
2163 vpaddq $D4,$H0,$H0 # h4 -> h0
2175 vpaddq $D3,$H4,$H4 # h3 -> h4
2181 vmovd %x#$H4,`4*4-48-64`($ctx)
2213 map(s/%y/%z/,($H0,$H1,$H2,$H3,$H4));
2454 # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
2455 # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
2456 # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
2457 # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
2458 # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
2463 # d3 = h2*r1 + h0*r3 + h1*r2 + h3*r0 + h4*5*r4
2464 # d4 = h2*r2 + h0*r4 + h1*r3 + h3*r1 + h4*r0
2465 # d0 = h2*5*r3 + h0*r0 + h1*5*r4 + h3*5*r2 + h4*5*r1
2466 # d1 = h2*5*r4 + h0*r1 + h1*r0 + h3*5*r3 + h4*5*r2
2467 # d2 = h2*r0 + h0*r2 + h1*r1 + h3*5*r4 + h4*5*r3
2480 vpaddq $H4,$T4,$H4
2515 vpmuludq $H4,$S4,$M3
2516 vpmuludq $H4,$R0,$M4
2519 vpaddq $M3,$D3,$D3 # d3 += h4*s4
2521 vpaddq $M4,$D4,$D4 # d4 += h4*r0
2526 vpmuludq $H4,$S1,$M0
2527 vpmuludq $H4,$S2,$M1
2528 vpmuludq $H4,$S3,$M2
2529 vpaddq $M0,$D0,$H0 # h0 = d0 + h4*s1
2530 vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2
2531 vpaddq $M2,$D2,$H2 # h2 = d3 + h4*s3
2541 vpaddq $H3,$D4,$H4 # h3 -> h4
2551 vpsrlq \$26,$H4,$D4
2552 vpandq $MASK,$H4,$H4
2560 vpaddq $D4,$H0,$H0 # h4 -> h0
2579 vpaddq $D3,$H4,$H4 # h3 -> h4
2622 vpaddq $H4,$T4,$H4
2655 vpmuludq $H4,$S4,$M3
2656 vpmuludq $H4,$R0,$M4
2660 vpaddq $M3,$D3,$H3 # h3 = d3 + h4*s4
2661 vpaddq $M4,$D4,$D4 # d4 += h4*r0
2666 vpmuludq $H4,$S1,$M0
2667 vpmuludq $H4,$S2,$M1
2668 vpmuludq $H4,$S3,$M2
2669 vpaddq $M0,$D0,$H0 # h0 = d0 + h4*s1
2670 vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2
2671 vpaddq $M2,$D2,$H2 # h2 = d3 + h4*s3
2678 vpermq \$0xb1,$D4,$H4
2683 vpaddq $D4,$H4,$H4
2690 vpermq \$0x2,$H4,$D4
2695 vpaddq $D4,$H4,$H4
2701 vextracti64x4 \$0x1,$H4,%y#$D4
2706 vpaddq $D4,$H4,${H4}{%k3}{z} # it's passed to .Ltail_avx2
2712 map(s/%z/%y/,($H0,$H1,$H2,$H3,$H4, $D0,$D1,$D2,$D3,$D4, $MASK));
2722 vpaddq $D3,$H4,$H4 # h3 -> h4
2730 vpsrlq \$26,$H4,$D4
2731 vpand $MASK,$H4,$H4
2743 vpaddq $D4,$H0,$H0 # h4 -> h0
2761 vpaddq $D3,$H4,$H4 # h3 -> h4
2772 vmovd %x#$H4,`4*4-48-64`($ctx)