Lines Matching full:t2
571 .macro CALC_AAD_HASH GHASH_MUL AAD AADLEN T1 T2 T3 T4 T5 T6 T7 T8
587 \GHASH_MUL \T8, \T2, \T1, \T3, \T4, \T5, \T6
635 \GHASH_MUL \T7, \T2, \T1, \T3, \T4, \T5, \T6
863 .macro GHASH_MUL_AVX GH HK T1 T2 T3 T4 T5
865 vpshufd $0b01001110, \GH, \T2
867 vpxor \GH , \T2, \T2 # T2 = (a1+a0)
872 vpclmulqdq $0x00, \T3, \T2, \T2 # T2 = (a1+a0)*(b1+b0)
873 vpxor \GH, \T2,\T2
874 vpxor \T1, \T2,\T2 # T2 = a0*b1+a1*b0
876 vpslldq $8, \T2,\T3 # shift-L T3 2 DWs
877 vpsrldq $8, \T2,\T2 # shift-R T2 2 DWs
879 vpxor \T2, \T1, \T1 # <T1:GH> = GH x HK
882 vpslld $31, \GH, \T2 # packed right shifting << 31
886 vpxor \T3, \T2, \T2 # xor the shifted versions
887 vpxor \T4, \T2, \T2
889 vpsrldq $4, \T2, \T5 # shift-R T5 1 DW
891 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
892 vpxor \T2, \GH, \GH # first phase of the reduction complete
896 vpsrld $1,\GH, \T2 # packed left shifting >> 1
899 vpxor \T3, \T2, \T2 # xor the shifted versions
900 vpxor \T4, \T2, \T2
902 vpxor \T5, \T2, \T2
903 vpxor \T2, \GH, \GH
909 .macro PRECOMPUTE_AVX HK T1 T2 T3 T4 T5 T6
918 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
924 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
930 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
936 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
942 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
948 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
954 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
969 .macro INITIAL_BLOCKS_AVX REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 X…
1043 … GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
1204 .macro GHASH_8_ENCRYPT_8_PARALLEL_AVX REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 …
1206 vmovdqa \XMM1, \T2
1289 vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
1290 vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
1292 vpshufd $0b01001110, \T2, \T6
1293 vpxor \T2, \T6, \T6
1492 vpxor 16*i(arg4, %r11), \T5, \T2
1494 vaesenclast \T2, reg_j, reg_j
1496 vaesenclast \T2, reg_j, \T3
1508 vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
1517 vpslld $31, \T7, \T2 # packed right shifting << 31
1521 vpxor \T3, \T2, \T2 # xor the shifted versions
1522 vpxor \T4, \T2, \T2
1524 vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
1526 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
1527 vpxor \T2, \T7, \T7 # first phase of the reduction complete
1542 vpsrld $1, \T7, \T2 # packed left shifting >> 1
1545 vpxor \T3, \T2, \T2 # xor the shifted versions
1546 vpxor \T4, \T2, \T2
1548 vpxor \T1, \T2, \T2
1549 vpxor \T2, \T7, \T7
1571 .macro GHASH_LAST_8_AVX T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
1576 vpshufd $0b01001110, \XMM1, \T2
1577 vpxor \XMM1, \T2, \T2
1583 vpclmulqdq $0x00, \T3, \T2, \XMM1
1587 vpshufd $0b01001110, \XMM2, \T2
1588 vpxor \XMM2, \T2, \T2
1597 vpclmulqdq $0x00, \T3, \T2, \T2
1598 vpxor \T2, \XMM1, \XMM1
1602 vpshufd $0b01001110, \XMM3, \T2
1603 vpxor \XMM3, \T2, \T2
1612 vpclmulqdq $0x00, \T3, \T2, \T2
1613 vpxor \T2, \XMM1, \XMM1
1617 vpshufd $0b01001110, \XMM4, \T2
1618 vpxor \XMM4, \T2, \T2
1627 vpclmulqdq $0x00, \T3, \T2, \T2
1628 vpxor \T2, \XMM1, \XMM1
1632 vpshufd $0b01001110, \XMM5, \T2
1633 vpxor \XMM5, \T2, \T2
1642 vpclmulqdq $0x00, \T3, \T2, \T2
1643 vpxor \T2, \XMM1, \XMM1
1647 vpshufd $0b01001110, \XMM6, \T2
1648 vpxor \XMM6, \T2, \T2
1657 vpclmulqdq $0x00, \T3, \T2, \T2
1658 vpxor \T2, \XMM1, \XMM1
1662 vpshufd $0b01001110, \XMM7, \T2
1663 vpxor \XMM7, \T2, \T2
1672 vpclmulqdq $0x00, \T3, \T2, \T2
1673 vpxor \T2, \XMM1, \XMM1
1677 vpshufd $0b01001110, \XMM8, \T2
1678 vpxor \XMM8, \T2, \T2
1687 vpclmulqdq $0x00, \T3, \T2, \T2
1689 vpxor \T2, \XMM1, \XMM1
1691 vpxor \T7, \XMM1, \T2
1696 vpslldq $8, \T2, \T4
1697 vpsrldq $8, \T2, \T2
1700 vpxor \T2, \T6, \T6 # <T6:T7> holds the result of
1705 vpslld $31, \T7, \T2 # packed right shifting << 31
1709 vpxor \T3, \T2, \T2 # xor the shifted versions
1710 vpxor \T4, \T2, \T2
1712 vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
1714 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
1715 vpxor \T2, \T7, \T7 # first phase of the reduction complete
1720 vpsrld $1, \T7, \T2 # packed left shifting >> 1
1723 vpxor \T3, \T2, \T2 # xor the shifted versions
1724 vpxor \T4, \T2, \T2
1726 vpxor \T1, \T2, \T2
1727 vpxor \T2, \T7, \T7
1845 .macro GHASH_MUL_AVX2 GH HK T1 T2 T3 T4 T5
1848 vpclmulqdq $0x00,\HK,\GH,\T2 # T2 = a0*b0
1858 vpxor \T2, \GH, \GH
1864 vpclmulqdq $0x01, \GH, \T3, \T2
1865 vpslldq $8, \T2, \T2 # shift-L T2 2 DWs
1867 vpxor \T2, \GH, \GH # first phase of the reduction complete
1870 vpclmulqdq $0x00, \GH, \T3, \T2
1871 …vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-…
1876 vpxor \T2, \GH, \GH # second phase of the reduction complete
1883 .macro PRECOMPUTE_AVX2 HK T1 T2 T3 T4 T5 T6
1887 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
1890 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
1893 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
1896 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
1899 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
1902 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
1905 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
1917 .macro INITIAL_BLOCKS_AVX2 REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 …
1993 …GHASH_MUL_AVX2 reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks bloc…
2159 .macro GHASH_8_ENCRYPT_8_PARALLEL_AVX2 REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7…
2161 vmovdqa \XMM1, \T2
2244 vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
2245 vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
2246 vpclmulqdq $0x01, \T5, \T2, \T6 # T6 = a1*b0
2247 vpclmulqdq $0x10, \T5, \T2, \T5 # T5 = a0*b1
2449 vpxor 16*i(arg4, %r11), \T5, \T2
2451 vaesenclast \T2, reg_j, reg_j
2453 vaesenclast \T2, reg_j, \T3
2465 vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
2475 vpclmulqdq $0x01, \T7, \T3, \T2
2476 vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
2478 vpxor \T2, \T7, \T7 # first phase of the reduction complete
2493 vpclmulqdq $0x00, \T7, \T3, \T2
2494 vpsrldq $4, \T2, \T2 # shift-R xmm2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
2499 vpxor \T2, \T4, \T4 # second phase of the reduction complete
2521 .macro GHASH_LAST_8_AVX2 T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
2527 vpshufd $0b01001110, \XMM1, \T2
2529 vpxor \XMM1, \T2, \T2
2535 vpclmulqdq $0x00, \T3, \T2, \XMM1
2540 vpshufd $0b01001110, \XMM2, \T2
2542 vpxor \XMM2, \T2, \T2
2551 vpclmulqdq $0x00, \T3, \T2, \T2
2553 vpxor \T2, \XMM1, \XMM1
2558 vpshufd $0b01001110, \XMM3, \T2
2560 vpxor \XMM3, \T2, \T2
2569 vpclmulqdq $0x00, \T3, \T2, \T2
2571 vpxor \T2, \XMM1, \XMM1
2576 vpshufd $0b01001110, \XMM4, \T2
2578 vpxor \XMM4, \T2, \T2
2587 vpclmulqdq $0x00, \T3, \T2, \T2
2589 vpxor \T2, \XMM1, \XMM1
2594 vpshufd $0b01001110, \XMM5, \T2
2596 vpxor \XMM5, \T2, \T2
2605 vpclmulqdq $0x00, \T3, \T2, \T2
2607 vpxor \T2, \XMM1, \XMM1
2612 vpshufd $0b01001110, \XMM6, \T2
2614 vpxor \XMM6, \T2, \T2
2623 vpclmulqdq $0x00, \T3, \T2, \T2
2625 vpxor \T2, \XMM1, \XMM1
2630 vpshufd $0b01001110, \XMM7, \T2
2632 vpxor \XMM7, \T2, \T2
2641 vpclmulqdq $0x00, \T3, \T2, \T2
2643 vpxor \T2, \XMM1, \XMM1
2648 vpshufd $0b01001110, \XMM8, \T2
2650 vpxor \XMM8, \T2, \T2
2659 vpclmulqdq $0x00, \T3, \T2, \T2
2661 vpxor \T2, \XMM1, \XMM1
2663 vpxor \T7, \XMM1, \T2
2668 vpslldq $8, \T2, \T4
2669 vpsrldq $8, \T2, \T2
2672 vpxor \T2, \T6, \T6 # <T6:T7> holds the result of the
2679 vpclmulqdq $0x01, \T7, \T3, \T2
2680 vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
2682 vpxor \T2, \T7, \T7 # first phase of the reduction complete
2687 vpclmulqdq $0x00, \T7, \T3, \T2
2688 …vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs sh…
2693 vpxor \T2, \T4, \T4 # second phase of the reduction complete