Lines Matching refs:H1
344 my ($H0,$H1,$H2,$H3,$H4, $T0,$T1,$T2,$T3,$T4, $D0,$D1,$D2,$D3,$D4, $MASK) =
636 vmovd %rdx#d,$H1
739 vmovd %rdx#d,$H1
773 vmovd 4*1($ctx),$H1
914 vmovdqa $H1,0x10(%r11) #
915 vpmuludq $T3,$H2,$H1 # h3*r1
917 vpaddq $H1,$D4,$D4 # d4 += h3*r1
920 vpmuludq $T1,$H2,$H1 # h1*r1
923 vpaddq $H1,$D2,$D2 # d2 += h1*r1
931 vpmuludq $T1,$H3,$H1 # h1*r2
933 vpaddq $H1,$D3,$D3 # d3 += h1*r2
943 vpmuludq $T1,$H2,$H1 # h1*r3
945 vpaddq $H1,$D4,$D4 # d4 += h1*r3
948 vpmuludq $T3,$H3,$H1 # h3*s3
951 vpaddq $H1,$D1,$D1 # d1 += h3*s3
956 vmovdqu 16*1($inp),$H1 #
963 vpsrldq \$6,$H1,$H3 #
966 vpunpckhqdq $H1,$H0,$H4 # 4
971 vpunpcklqdq $H1,$H0,$H0 # 0:1
976 vpsrlq \$26,$H0,$H1
979 vpand $MASK,$H1,$H1 # 1
987 vpaddq 0x10(%r11),$H1,$H1
1007 vpmuludq $H1,$T4,$T1 # h1*r0
1025 vpmuludq $H1,$T2,$T1 # h1*r1
1032 vpmuludq $H1,$T3,$T1 # h1*r2
1042 vpmuludq $H1,$T2,$T1 # h1*r3
1067 vpmuludq $H1,$T4,$H0
1098 vpaddq $D0,$D1,$H1 # h0 -> h1
1103 vpsrlq \$26,$H1,$D1
1104 vpand $MASK,$H1,$H1
1117 vpaddq $D0,$H1,$H1 # h0 -> h1
1135 vpaddq $H1,$T1,$T1
1142 vmovdqa $H1,0x10(%r11)
1162 vpmuludq $T2,$H2,$H1 # h2*r1
1163 vpaddq $H1,$D3,$D3 # d3 += h2*r1
1173 vpmuludq $T2,$H4,$H1 # h2*r2
1174 vpaddq $H1,$D4,$D4 # d4 += h2*r2
1180 vpmuludq $T4,$H2,$H1 # h4*s2
1181 vpaddq $H1,$D1,$D1 # d1 += h4*s2
1191 vpmuludq $T4,$H4,$H1 # h4*s3
1192 vpaddq $H1,$D2,$D2 # d2 += h4*s3
1201 vpmuludq $T4,$H3,$H1 # h4*s4
1202 vpaddq $H1,$D3,$D3 # h3 = d3 + h4*s4
1205 vpmuludq $T2,$H3,$H1 # h2*s4
1206 vpaddq $H1,$D1,$D1 # h1 = d1 + h2*s4
1213 vmovdqu 16*1($inp),$H1
1216 vpsrldq \$6,$H1,$H3
1217 vpunpckhqdq $H1,$H0,$H4 # 4
1218 vpunpcklqdq $H1,$H0,$H0 # 0:1
1222 vpsrlq \$26,$H0,$H1
1225 vpand $MASK,$H1,$H1 # 1
1233 vpaddq 0x10(%r11),$H1,$H1
1243 vpmuludq $H1,$T4,$T1 # h1*r0
1259 vpmuludq $H1,$T2,$T0 # h1*r1
1269 vpmuludq $H1,$T4,$T0 # h1*r2
1280 vpmuludq $H1,$T3,$T0 # h1*r3
1301 vpmuludq $H1,$T3,$T3 # h1*s4
1333 vpsrlq \$26,$D1,$H1
1335 vpaddq $H1,$D2,$D2 # h1 -> h2
1442 my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) =
1566 vmovd %rdx#d,%x#$H1
1674 vmovd %rdx#d,%x#$H1
1711 vmovd 4*1($ctx),%x#$H1
1824 vpaddq $H1,$T1,$H1
1854 vpmuludq $H1,$T1,$H2 # h1*r1, borrow $H2 as temp
1864 vpmuludq $H1,$T0,$H2 # h1*r0
1880 vpmuludq $H1,$T2,$T4 # h1*r2
1887 vpmuludq $H1,$H2,$T4 # h1*r3
1906 vpmuludq $H1,$S4,$H0 # h1*s4
1920 vpaddq $D0,$D1,$H1 # h0 -> h1
1927 vpsrlq \$26,$H1,$D1
1928 vpand $MASK,$H1,$H1
1947 vpaddq $D0,$H1,$H1 # h0 -> h1
1974 vpaddq $H1,$T1,$H1
1989 vpmuludq $H1,$T1,$H2 # h1*r1
1998 vpmuludq $H1,$T0,$H2 # h1*r0
2012 vpmuludq $H1,$T2,$T4 # h1*r2
2017 vpmuludq $H1,$H2,$T4 # h1*r3
2031 vpmuludq $H1,$S4,$H0 # h1*s4
2070 vpaddq $D0,$D1,$H1 # h0 -> h1
2075 vpsrlq \$26,$H1,$D1
2076 vpand $MASK,$H1,$H1
2089 vpaddq $D0,$H1,$H1 # h0 -> h1
2096 vmovd %x#$H1,`4*1-48-64`($ctx)
2139 map(s/%y/%z/,($H0,$H1,$H2,$H3,$H4));
2407 vpaddq $H1,$T1,$H1 # accumulate input
2423 vpmuludq $H1,$R2,$M3
2424 vpmuludq $H1,$R3,$M4
2425 vpmuludq $H1,$S4,$M0
2437 vpmuludq $H1,$R0,$M1
2438 vpmuludq $H1,$R1,$M2
2459 vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2
2476 vpaddq $D0,$H1,$H1 # h0 -> h1
2483 vpsrlq \$26,$H1,$D1
2484 vpandq $MASK,$H1,$H1
2502 vpaddq $D0,$H1,$H1 # h0 -> h1
2549 vpaddq $H1,$T1,$H1 # accumulate input
2564 vpmuludq $H1,$R2,$M3
2565 vpmuludq $H1,$R3,$M4
2566 vpmuludq $H1,$S4,$M0
2576 vpmuludq $H1,$R0,$M1
2577 vpmuludq $H1,$R1,$M2
2599 vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2
2609 vpermq \$0xb1,$H1,$D1
2614 vpaddq $D1,$H1,$H1
2621 vpermq \$0x2,$H1,$D1
2626 vpaddq $D1,$H1,$H1
2632 vextracti64x4 \$0x1,$H1,%y#$D1
2637 vpaddq $D1,$H1,${H1}{%k3}{z}
2641 map(s/%z/%y/,($H0,$H1,$H2,$H3,$H4, $D0,$D1,$D2,$D3,$D4, $MASK));
2657 vpaddq $D0,$H1,$H1 # h0 -> h1
2662 vpsrlq \$26,$H1,$D1
2663 vpand $MASK,$H1,$H1
2684 vpaddq $D0,$H1,$H1 # h0 -> h1
2698 vmovd %x#$H1,`4*1-48-64`($ctx)
2802 my ($H0,$H1,$H2,$r2r1r0,$r1r0s2,$r0s2s1,$Dlo,$Dhi) = map("%ymm$_",(0..5,16,17));
2869 vpermq \$0b01010101,$Dlo,${H1}{%k7}{z}
2878 vpmadd52luq $r1r0s2,$H1,$Dlo
2879 vpmadd52huq $r1r0s2,$H1,$Dhi
2928 my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17));
2955 vmovq 8($ctx),%x#$H1
3007 vmovdqa $R1,$H1
3033 vpmadd52luq $H1,$S2,$D0lo
3034 vpmadd52huq $H1,$S2,$D0hi
3035 vpmadd52luq $H1,$R0,$D1lo
3036 vpmadd52huq $H1,$R0,$D1hi
3037 vpmadd52luq $H1,$R1,$D2lo
3038 vpmadd52huq $H1,$R1,$D2hi
3051 vpandq $mask44,$D1lo,$H1
3069 vpaddq $tmp,$H1,$H1
3074 vpunpcklqdq $R1,$H1,$R1 # 1,2
3075 vpbroadcastq %x#$H1,%x#$H1 # 2,2
3093 vinserti128 \$1,%x#$R1,$H1,$R1 # 1,2,3,4
3106 vmovq 8($ctx),%x#$H1
3170 vpaddq $T1,$H1,$H1
3197 vpmadd52luq $H1,$S2,$D0lo
3198 vpmadd52huq $H1,$S2,$D0hi
3199 vpmadd52luq $H1,$R0,$D1lo
3200 vpmadd52huq $H1,$R0,$D1hi
3201 vpmadd52luq $H1,$R1,$D2lo
3202 vpmadd52huq $H1,$R1,$D2hi
3217 vpandq $mask44,$D1lo,$H1
3241 vpaddq $tmp,$H1,$H1
3259 vpaddq $T1,$H1,$H1
3281 vpmadd52luq $H1,$S2,$D0lo
3282 vpmadd52huq $H1,$S2,$D0hi
3283 vpmadd52luq $H1,$R0,$D1lo
3284 vpmadd52huq $H1,$R0,$D1hi
3285 vpmadd52luq $H1,$R1,$D2lo
3286 vpmadd52huq $H1,$R1,$D2hi
3296 vpsrldq \$8,$D1hi,$H1
3302 vpaddq $H1,$D1hi,$D1hi
3309 vpermq \$0x2,$D1hi,$H1
3315 vpaddq $H1,$D1hi,${D1hi}{%k1}{z}
3330 vpandq $mask44,$D1lo,$H1
3348 vpaddq $tmp,$H1,$H1
3355 vmovq %x#$H1,8($ctx)
3371 my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17));
3394 vmovq 8($ctx),%x#$H1
3484 map(s/%y/%z/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2);
3537 vpaddq $T1,$H1,$H1
3564 vpmadd52luq $H1,$S2,$D0lo
3565 vpmadd52huq $H1,$S2,$D0hi
3566 vpmadd52luq $H1,$R0,$D1lo
3567 vpmadd52huq $H1,$R0,$D1hi
3568 vpmadd52luq $H1,$R1,$D2lo
3569 vpmadd52huq $H1,$R1,$D2hi
3584 vpandq $mask44,$D1lo,$H1
3608 vpaddq $tmp,$H1,$H1
3616 vpaddq $T1,$H1,$H1
3638 vpmadd52luq $H1,$SS2,$D0lo
3639 vpmadd52huq $H1,$SS2,$D0hi
3640 vpmadd52luq $H1,$RR0,$D1lo
3641 vpmadd52huq $H1,$RR0,$D1hi
3642 vpmadd52luq $H1,$RR1,$D2lo
3643 vpmadd52huq $H1,$RR1,$D2hi
3653 vpsrldq \$8,$D1hi,$H1
3659 vpaddq $H1,$D1hi,$D1hi
3666 vpermq \$0x2,$D1hi,$H1
3672 vpaddq $H1,$D1hi,$D1hi
3679 vextracti64x4 \$1,$D1hi,%y#$H1
3684 map(s/%z/%y/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2);
3692 vpaddq $H1,$D1hi,${D1hi}{%k1}{z}
3707 vpandq $mask44,$D1lo,$H1
3725 vpaddq $tmp,$H1,$H1
3730 vmovq %x#$H1,8($ctx)