Lines Matching full:h3
419 my ($H0,$H1,$H2,$H3,$H4, $T0,$T1,$T2,$T3,$T4, $D0,$D1,$D2,$D3,$D4, $MASK) =
715 vmovd $h1#d,$H3
817 vmovd $h1#d,$H3
847 vmovd 4*3($ctx),$H3
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
984 vpmuludq $T3,$D4,$D3 # d3 = h3*r0
990 vpmuludq $T3,$H2,$H1 # h3*r1
992 vpaddq $H1,$D4,$D4 # d4 += h3*r1
993 vmovdqa $H3,0x30(%r11) #
997 vmovdqa 0x30(%rsp),$H3 # r2^2
1001 vpmuludq $T2,$H3,$H0 # h2*r2
1006 vpmuludq $T1,$H3,$H1 # h1*r2
1007 vpmuludq $T0,$H3,$H3 # h0*r2
1010 vpaddq $H3,$D2,$D2 # d2 += h0*r2
1012 vpmuludq $T3,$H4,$H4 # h3*s2
1014 vmovdqa 0x60(%rsp),$H3 # s3^2
1015 vpaddq $H4,$D0,$D0 # d0 += h3*s2
1022 vpmuludq $T4,$H3,$H0 # h4*s3
1023 vpmuludq $T3,$H3,$H1 # h3*s3
1026 vpaddq $H1,$D1,$D1 # d1 += h3*s3
1027 vpmuludq $T2,$H3,$H3 # h2*s3
1029 vpaddq $H3,$D0,$D0 # d0 += h2*s3
1033 vpmuludq $T3,$H4,$T3 # h3*s4
1036 vpaddq $T3,$D2,$D2 # d2 += h3*s4
1038 vpsrldq \$6,$H1,$H3 #
1047 vpunpcklqdq $H3,$H2,$H3 # 2:3
1053 vpsrlq \$4,$H3,$H2
1056 vpsrlq \$30,$H3,$H3
1058 vpand $MASK,$H3,$H3 # 3
1064 vpaddq 0x30(%r11),$H3,$H3
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
1087 vpmuludq $H3,$T4,$T1 # h3*r0
1096 vpmuludq $H3,$T2,$T0 # h3*r1
1099 vpaddq $T0,$D4,$D4 # d4 += h3*r1
1116 vpmuludq $H3,$T4,$T4 # h3*s2
1118 vpaddq $T4,$D0,$D0 # d0 += h3*s2
1127 vpmuludq $H3,$T3,$T2 # h3*s3
1129 vpaddq $T2,$D1,$D1 # d1 += h3*s3
1134 vpmuludq $H3,$T4,$H3 # h3*s4
1139 vpaddq $H3,$D2,$H2 # h2 = d2 + h3*s4
1140 vpaddq $H4,$D3,$H3 # h3 = d3 + h4*s4
1167 vpsrlq \$26,$H3,$D3
1168 vpand $MASK,$H3,$H3
1169 vpaddq $D3,$H4,$H4 # h3 -> h4
1188 vpaddq $D2,$H3,$H3 # h2 -> h3
1194 vpsrlq \$26,$H3,$D3
1195 vpand $MASK,$H3,$H3
1196 vpaddq $D3,$H4,$H4 # h3 -> h4
1211 vpaddq $H3,$T3,$T3
1218 vmovdqa $H3,0x30(%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
1231 vpmuludq $T3,$D4,$D3 # d3 = h3*r0
1234 vpmuludq $T3,$H2,$H0 # h3*r1
1235 vpaddq $H0,$D4,$D4 # d4 += h3*r1
1236 vpshufd \$0x10,`16*2-64`($ctx),$H3 # s1^n
1244 vpmuludq $T4,$H3,$H3 # h4*s1
1245 vpaddq $H3,$D0,$D0 # d0 += h4*s1
1252 vpshufd \$0x10,`16*5-64`($ctx),$H3 # r3^n
1258 vpmuludq $T3,$H2,$H2 # h3*s2
1259 vpaddq $H2,$D0,$D0 # d0 += h3*s2
1261 vpmuludq $T1,$H3,$H0 # h1*r3
1263 vpmuludq $T0,$H3,$H3 # h0*r3
1264 vpaddq $H3,$D3,$D3 # d3 += h0*r3
1268 vpshufd \$0x10,`16*8-64`($ctx),$H3 # s4^n
1269 vpmuludq $T3,$H4,$H0 # h3*s3
1270 vpaddq $H0,$D1,$D1 # d1 += h3*s3
1276 vpmuludq $T4,$H3,$H1 # h4*s4
1277 vpaddq $H1,$D3,$D3 # h3 = d3 + h4*s4
1278 vpmuludq $T3,$H3,$H0 # h3*s4
1279 vpaddq $H0,$D2,$D2 # h2 = d2 + h3*s4
1280 vpmuludq $T2,$H3,$H1 # h2*s4
1282 vpmuludq $T1,$H3,$H3 # h1*s4
1283 vpaddq $H3,$D0,$D0 # h0 = d0 + h1*s4
1291 vpsrldq \$6,$H1,$H3
1294 vpunpcklqdq $H3,$H2,$H3 # 2:3
1299 vpsrlq \$4,$H3,$H2
1301 vpsrlq \$30,$H3,$H3
1303 vpand $MASK,$H3,$H3 # 3
1310 vpaddq 0x30(%r11),$H3,$H3
1323 vpmuludq $H3,$T4,$T1 # h3*r0
1324 vpaddq $T1,$D3,$D3 # d3 += h3*r0
1328 vpmuludq $H3,$T2,$T0 # h3*r1
1329 vpaddq $T0,$D4,$D4 # d4 += h3*r1
1352 vpmuludq $H3,$T2,$T2 # h3*s2
1353 vpaddq $T2,$D0,$D0 # d0 += h3*s2
1363 vpmuludq $H3,$T4,$T0 # h3*s3
1364 vpaddq $T0,$D1,$D1 # d1 += h3*s3
1372 vpmuludq $H3,$T3,$T0 # h3*s4
1373 vpaddq $T0,$D2,$D2 # d2 += h3*s4
1397 vpsrlq \$26,$D3,$H3
1399 vpaddq $H3,$D4,$D4 # h3 -> h4
1418 vpaddq $H2,$D3,$D3 # h2 -> h3
1424 vpsrlq \$26,$D3,$H3
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) =
1643 vmovd $h1#d,%x#$H3
1750 vmovd $h1#d,%x#$H3
1791 vmovd 4*3($ctx),%x#$H3
1908 vpaddq $H3,$T3,$H3
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
1939 vpmuludq $H3,$T1,$T4 # h3*r1
1941 vpaddq $T4,$D4,$D4 # d4 += h3*r1
1949 vpmuludq $H3,$T0,$T4 # h3*r0
1952 vpaddq $T4,$D3,$D3 # d3 += h3*r0
1956 vpmuludq $H3,$T1,$T4 # h3*s2
1959 vpaddq $T4,$D0,$D0 # d0 += h3*s2
1974 vpmuludq $H3,$T3,$T4 # h3*s3
1977 vpaddq $T4,$D1,$D1 # d1 += h3*s3
1981 vpmuludq $H3,$S4,$H3 # h3*s4
1984 vpaddq $H3,$D2,$H2 # h2 = d2 + h3*r4
1985 vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4
1996 vpsrlq \$26,$H3,$D3
1997 vpand $MASK,$H3,$H3
1998 vpaddq $D3,$H4,$H4 # h3 -> h4
2022 vpaddq $D2,$H3,$H3 # h2 -> h3
2033 vpsrlq \$26,$H3,$D3
2034 vpand $MASK,$H3,$H3
2035 vpaddq $D3,$H4,$H4 # h3 -> h4
2058 vpaddq $H3,$T3,$H3
2074 vpmuludq $H3,$T1,$T4 # h3*r1
2076 vpaddq $T4,$D4,$D4 # d4 += h3*r1
2084 vpmuludq $H3,$T0,$T4 # h3*r0
2086 vpaddq $T4,$D3,$D3 # d3 += h3*r0
2089 vpmuludq $H3,$T1,$T4 # h3*s2
2091 vpaddq $T4,$D0,$D0 # d0 += h3*s2
2103 vpmuludq $H3,$T3,$T4 # h3*s3
2105 vpaddq $T4,$D1,$D1 # d1 += h3*s3
2108 vpmuludq $H3,$S4,$H3 # h3*s4
2110 vpaddq $H3,$D2,$H2 # h2 = d2 + h3*r4
2111 vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4
2123 vpsrldq \$8,$H3,$T3
2128 vpaddq $T3,$H3,$H3
2132 vpermq \$0x2,$H3,$T3
2137 vpaddq $T3,$H3,$H3
2146 vpsrlq \$26,$H3,$D3
2147 vpand $MASK,$H3,$H3
2148 vpaddq $D3,$H4,$H4 # h3 -> h4
2167 vpaddq $D2,$H3,$H3 # h2 -> h3
2173 vpsrlq \$26,$H3,$D3
2174 vpand $MASK,$H3,$H3
2175 vpaddq $D3,$H4,$H4 # h3 -> h4
2180 vmovd %x#$H3,`4*3-48-64`($ctx)
2213 map(s/%y/%z/,($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
2479 vpaddq $H3,$T3,$H3
2506 vpmuludq $H3,$R0,$M3
2507 vpmuludq $H3,$R1,$M4
2510 vpaddq $M3,$D3,$D3 # d3 += h3*r0
2511 vpaddq $M4,$D4,$D4 # d4 += h3*r1
2517 vpmuludq $H3,$S2,$M0
2518 vpmuludq $H3,$S3,$M1
2520 vpmuludq $H3,$S4,$M2
2522 vpaddq $M0,$D0,$D0 # d0 += h3*s2
2523 vpaddq $M1,$D1,$D1 # d1 += h3*s3
2524 vpaddq $M2,$D2,$D2 # d2 += h3*s4
2539 vpsrlq \$26,$D3,$H3
2541 vpaddq $H3,$D4,$H4 # h3 -> h4
2567 vpaddq $D2,$D3,$H3 # h2 -> h3
2577 vpsrlq \$26,$H3,$D3
2578 vpandq $MASK,$H3,$H3
2579 vpaddq $D3,$H4,$H4 # h3 -> h4
2621 vpaddq $H3,$T3,$H3
2645 vpmuludq $H3,$R0,$M3
2646 vpmuludq $H3,$R1,$M4
2649 vpaddq $M3,$D3,$D3 # d3 += h3*r0
2650 vpaddq $M4,$D4,$D4 # d4 += h3*r1
2657 vpmuludq $H3,$S2,$M0
2658 vpmuludq $H3,$S3,$M1
2659 vpmuludq $H3,$S4,$M2
2660 vpaddq $M3,$D3,$H3 # h3 = d3 + h4*s4
2662 vpaddq $M0,$D0,$D0 # d0 += h3*s2
2663 vpaddq $M1,$D1,$D1 # d1 += h3*s3
2664 vpaddq $M2,$D2,$D2 # d2 += h3*s4
2677 vpermq \$0xb1,$H3,$D3
2682 vpaddq $D3,$H3,$H3
2689 vpermq \$0x2,$H3,$D3
2694 vpaddq $D3,$H3,$H3
2700 vextracti64x4 \$0x1,$H3,%y#$D3
2705 vpaddq $D3,$H3,${H3}{%k3}{z} # keep single qword in case
2712 map(s/%z/%y/,($H0,$H1,$H2,$H3,$H4, $D0,$D1,$D2,$D3,$D4, $MASK));
2717 vpsrlq \$26,$H3,$D3
2718 vpand $MASK,$H3,$H3
2722 vpaddq $D3,$H4,$H4 # h3 -> h4
2749 vpaddq $D2,$H3,$H3 # h2 -> h3
2757 vpsrlq \$26,$H3,$D3
2758 vpand $MASK,$H3,$H3
2761 vpaddq $D3,$H4,$H4 # h3 -> h4
2771 vmovd %x#$H3,`4*3-48-64`($ctx)