Lines Matching refs:H1
420 my ($H0,$H1,$H2,$H3,$H4, $T0,$T1,$T2,$T3,$T4, $D0,$D1,$D2,$D3,$D4, $MASK) =
714 vmovd %rdx#d,$H1
816 vmovd %rdx#d,$H1
846 vmovd 4*1($ctx),$H1
990 vmovdqa $H1,0x10(%r11) #
991 vpmuludq $T3,$H2,$H1 # h3*r1
993 vpaddq $H1,$D4,$D4 # d4 += h3*r1
996 vpmuludq $T1,$H2,$H1 # h1*r1
999 vpaddq $H1,$D2,$D2 # d2 += h1*r1
1007 vpmuludq $T1,$H3,$H1 # h1*r2
1009 vpaddq $H1,$D3,$D3 # d3 += h1*r2
1019 vpmuludq $T1,$H2,$H1 # h1*r3
1021 vpaddq $H1,$D4,$D4 # d4 += h1*r3
1024 vpmuludq $T3,$H3,$H1 # h3*s3
1027 vpaddq $H1,$D1,$D1 # d1 += h3*s3
1032 vmovdqu 16*1($inp),$H1 #
1039 vpsrldq \$6,$H1,$H3 #
1042 vpunpckhqdq $H1,$H0,$H4 # 4
1047 vpunpcklqdq $H1,$H0,$H0 # 0:1
1052 vpsrlq \$26,$H0,$H1
1055 vpand $MASK,$H1,$H1 # 1
1063 vpaddq 0x10(%r11),$H1,$H1
1083 vpmuludq $H1,$T4,$T1 # h1*r0
1101 vpmuludq $H1,$T2,$T1 # h1*r1
1108 vpmuludq $H1,$T3,$T1 # h1*r2
1118 vpmuludq $H1,$T2,$T1 # h1*r3
1143 vpmuludq $H1,$T4,$H0
1174 vpaddq $D0,$D1,$H1 # h0 -> h1
1179 vpsrlq \$26,$H1,$D1
1180 vpand $MASK,$H1,$H1
1193 vpaddq $D0,$H1,$H1 # h0 -> h1
1211 vpaddq $H1,$T1,$T1
1218 vmovdqa $H1,0x10(%r11)
1238 vpmuludq $T2,$H2,$H1 # h2*r1
1239 vpaddq $H1,$D3,$D3 # d3 += h2*r1
1249 vpmuludq $T2,$H4,$H1 # h2*r2
1250 vpaddq $H1,$D4,$D4 # d4 += h2*r2
1256 vpmuludq $T4,$H2,$H1 # h4*s2
1257 vpaddq $H1,$D1,$D1 # d1 += h4*s2
1267 vpmuludq $T4,$H4,$H1 # h4*s3
1268 vpaddq $H1,$D2,$D2 # d2 += h4*s3
1277 vpmuludq $T4,$H3,$H1 # h4*s4
1278 vpaddq $H1,$D3,$D3 # h3 = d3 + h4*s4
1281 vpmuludq $T2,$H3,$H1 # h2*s4
1282 vpaddq $H1,$D1,$D1 # h1 = d1 + h2*s4
1289 vmovdqu 16*1($inp),$H1
1292 vpsrldq \$6,$H1,$H3
1293 vpunpckhqdq $H1,$H0,$H4 # 4
1294 vpunpcklqdq $H1,$H0,$H0 # 0:1
1298 vpsrlq \$26,$H0,$H1
1301 vpand $MASK,$H1,$H1 # 1
1309 vpaddq 0x10(%r11),$H1,$H1
1319 vpmuludq $H1,$T4,$T1 # h1*r0
1335 vpmuludq $H1,$T2,$T0 # h1*r1
1345 vpmuludq $H1,$T4,$T0 # h1*r2
1356 vpmuludq $H1,$T3,$T0 # h1*r3
1377 vpmuludq $H1,$T3,$T3 # h1*s4
1409 vpsrlq \$26,$D1,$H1
1411 vpaddq $H1,$D2,$D2 # h1 -> h2
1517 my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) =
1642 vmovd %rdx#d,%x#$H1
1749 vmovd %rdx#d,%x#$H1
1790 vmovd 4*1($ctx),%x#$H1
1907 vpaddq $H1,$T1,$H1
1937 vpmuludq $H1,$T1,$H2 # h1*r1, borrow $H2 as temp
1947 vpmuludq $H1,$T0,$H2 # h1*r0
1963 vpmuludq $H1,$T2,$T4 # h1*r2
1970 vpmuludq $H1,$H2,$T4 # h1*r3
1989 vpmuludq $H1,$S4,$H0 # h1*s4
2003 vpaddq $D0,$D1,$H1 # h0 -> h1
2010 vpsrlq \$26,$H1,$D1
2011 vpand $MASK,$H1,$H1
2030 vpaddq $D0,$H1,$H1 # h0 -> h1
2057 vpaddq $H1,$T1,$H1
2072 vpmuludq $H1,$T1,$H2 # h1*r1
2081 vpmuludq $H1,$T0,$H2 # h1*r0
2095 vpmuludq $H1,$T2,$T4 # h1*r2
2100 vpmuludq $H1,$H2,$T4 # h1*r3
2114 vpmuludq $H1,$S4,$H0 # h1*s4
2153 vpaddq $D0,$D1,$H1 # h0 -> h1
2158 vpsrlq \$26,$H1,$D1
2159 vpand $MASK,$H1,$H1
2172 vpaddq $D0,$H1,$H1 # h0 -> h1
2179 vmovd %x#$H1,`4*1-48-64`($ctx)
2214 map(s/%y/%z/,($H0,$H1,$H2,$H3,$H4));
2479 vpaddq $H1,$T1,$H1 # accumulate input
2495 vpmuludq $H1,$R2,$M3
2496 vpmuludq $H1,$R3,$M4
2497 vpmuludq $H1,$S4,$M0
2509 vpmuludq $H1,$R0,$M1
2510 vpmuludq $H1,$R1,$M2
2531 vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2
2548 vpaddq $D0,$H1,$H1 # h0 -> h1
2555 vpsrlq \$26,$H1,$D1
2556 vpandq $MASK,$H1,$H1
2574 vpaddq $D0,$H1,$H1 # h0 -> h1
2621 vpaddq $H1,$T1,$H1 # accumulate input
2636 vpmuludq $H1,$R2,$M3
2637 vpmuludq $H1,$R3,$M4
2638 vpmuludq $H1,$S4,$M0
2648 vpmuludq $H1,$R0,$M1
2649 vpmuludq $H1,$R1,$M2
2671 vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2
2681 vpermq \$0xb1,$H1,$D1
2686 vpaddq $D1,$H1,$H1
2693 vpermq \$0x2,$H1,$D1
2698 vpaddq $D1,$H1,$H1
2704 vextracti64x4 \$0x1,$H1,%y#$D1
2709 vpaddq $D1,$H1,${H1}{%k3}{z}
2713 map(s/%z/%y/,($H0,$H1,$H2,$H3,$H4, $D0,$D1,$D2,$D3,$D4, $MASK));
2729 vpaddq $D0,$H1,$H1 # h0 -> h1
2734 vpsrlq \$26,$H1,$D1
2735 vpand $MASK,$H1,$H1
2756 vpaddq $D0,$H1,$H1 # h0 -> h1
2770 vmovd %x#$H1,`4*1-48-64`($ctx)
2900 my ($H0,$H1,$H2,$r2r1r0,$r1r0s2,$r0s2s1,$Dlo,$Dhi) = map("%ymm$_",(0..5,16,17));
2965 vpermq \$0b01010101,$Dlo,${H1}{%k7}{z}
2974 vpmadd52luq $r1r0s2,$H1,$Dlo
2975 vpmadd52huq $r1r0s2,$H1,$Dhi
3023 my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17));
3049 vmovq 8($ctx),%x#$H1
3101 vmovdqa $R1,$H1
3127 vpmadd52luq $H1,$S2,$D0lo
3128 vpmadd52huq $H1,$S2,$D0hi
3129 vpmadd52luq $H1,$R0,$D1lo
3130 vpmadd52huq $H1,$R0,$D1hi
3131 vpmadd52luq $H1,$R1,$D2lo
3132 vpmadd52huq $H1,$R1,$D2hi
3145 vpandq $mask44,$D1lo,$H1
3163 vpaddq $tmp,$H1,$H1
3168 vpunpcklqdq $R1,$H1,$R1 # 1,2
3169 vpbroadcastq %x#$H1,%x#$H1 # 2,2
3187 vinserti128 \$1,%x#$R1,$H1,$R1 # 1,2,3,4
3200 vmovq 8($ctx),%x#$H1
3264 vpaddq $T1,$H1,$H1
3291 vpmadd52luq $H1,$S2,$D0lo
3292 vpmadd52huq $H1,$S2,$D0hi
3293 vpmadd52luq $H1,$R0,$D1lo
3294 vpmadd52huq $H1,$R0,$D1hi
3295 vpmadd52luq $H1,$R1,$D2lo
3296 vpmadd52huq $H1,$R1,$D2hi
3311 vpandq $mask44,$D1lo,$H1
3335 vpaddq $tmp,$H1,$H1
3353 vpaddq $T1,$H1,$H1
3375 vpmadd52luq $H1,$S2,$D0lo
3376 vpmadd52huq $H1,$S2,$D0hi
3377 vpmadd52luq $H1,$R0,$D1lo
3378 vpmadd52huq $H1,$R0,$D1hi
3379 vpmadd52luq $H1,$R1,$D2lo
3380 vpmadd52huq $H1,$R1,$D2hi
3390 vpsrldq \$8,$D1hi,$H1
3396 vpaddq $H1,$D1hi,$D1hi
3403 vpermq \$0x2,$D1hi,$H1
3409 vpaddq $H1,$D1hi,${D1hi}{%k1}{z}
3424 vpandq $mask44,$D1lo,$H1
3442 vpaddq $tmp,$H1,$H1
3449 vmovq %x#$H1,8($ctx)
3464 my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17));
3486 vmovq 8($ctx),%x#$H1
3576 map(s/%y/%z/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2);
3629 vpaddq $T1,$H1,$H1
3656 vpmadd52luq $H1,$S2,$D0lo
3657 vpmadd52huq $H1,$S2,$D0hi
3658 vpmadd52luq $H1,$R0,$D1lo
3659 vpmadd52huq $H1,$R0,$D1hi
3660 vpmadd52luq $H1,$R1,$D2lo
3661 vpmadd52huq $H1,$R1,$D2hi
3676 vpandq $mask44,$D1lo,$H1
3700 vpaddq $tmp,$H1,$H1
3708 vpaddq $T1,$H1,$H1
3730 vpmadd52luq $H1,$SS2,$D0lo
3731 vpmadd52huq $H1,$SS2,$D0hi
3732 vpmadd52luq $H1,$RR0,$D1lo
3733 vpmadd52huq $H1,$RR0,$D1hi
3734 vpmadd52luq $H1,$RR1,$D2lo
3735 vpmadd52huq $H1,$RR1,$D2hi
3745 vpsrldq \$8,$D1hi,$H1
3751 vpaddq $H1,$D1hi,$D1hi
3758 vpermq \$0x2,$D1hi,$H1
3764 vpaddq $H1,$D1hi,$D1hi
3771 vextracti64x4 \$1,$D1hi,%y#$H1
3776 map(s/%z/%y/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2);
3784 vpaddq $H1,$D1hi,${D1hi}{%k1}{z}
3799 vpandq $mask44,$D1lo,$H1
3817 vpaddq $tmp,$H1,$H1
3822 vmovq %x#$H1,8($ctx)