Lines Matching full:t2
595 .macro CALC_AAD_HASH GHASH_MUL AAD AADLEN T1 T2 T3 T4 T5 T6 T7 T8
611 \GHASH_MUL \T8, \T2, \T1, \T3, \T4, \T5, \T6
657 \GHASH_MUL \T7, \T2, \T1, \T3, \T4, \T5, \T6
885 .macro GHASH_MUL_AVX GH HK T1 T2 T3 T4 T5
887 vpshufd $0b01001110, \GH, \T2
889 vpxor \GH , \T2, \T2 # T2 = (a1+a0)
894 vpclmulqdq $0x00, \T3, \T2, \T2 # T2 = (a1+a0)*(b1+b0)
895 vpxor \GH, \T2,\T2
896 vpxor \T1, \T2,\T2 # T2 = a0*b1+a1*b0
898 vpslldq $8, \T2,\T3 # shift-L T3 2 DWs
899 vpsrldq $8, \T2,\T2 # shift-R T2 2 DWs
901 vpxor \T2, \T1, \T1 # <T1:GH> = GH x HK
904 vpslld $31, \GH, \T2 # packed right shifting << 31
908 vpxor \T3, \T2, \T2 # xor the shifted versions
909 vpxor \T4, \T2, \T2
911 vpsrldq $4, \T2, \T5 # shift-R T5 1 DW
913 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
914 vpxor \T2, \GH, \GH # first phase of the reduction complete
918 vpsrld $1,\GH, \T2 # packed left shifting >> 1
921 vpxor \T3, \T2, \T2 # xor the shifted versions
922 vpxor \T4, \T2, \T2
924 vpxor \T5, \T2, \T2
925 vpxor \T2, \GH, \GH
931 .macro PRECOMPUTE_AVX HK T1 T2 T3 T4 T5 T6
940 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
946 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
952 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
958 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
964 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
970 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
976 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
991 .macro INITIAL_BLOCKS_AVX REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 X…
1065 … GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
1226 .macro GHASH_8_ENCRYPT_8_PARALLEL_AVX REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 …
1228 vmovdqa \XMM1, \T2
1311 vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
1312 vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
1314 vpshufd $0b01001110, \T2, \T6
1315 vpxor \T2, \T6, \T6
1514 vpxor 16*i(arg4, %r11), \T5, \T2
1516 vaesenclast \T2, reg_j, reg_j
1518 vaesenclast \T2, reg_j, \T3
1530 vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
1539 vpslld $31, \T7, \T2 # packed right shifting << 31
1543 vpxor \T3, \T2, \T2 # xor the shifted versions
1544 vpxor \T4, \T2, \T2
1546 vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
1548 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
1549 vpxor \T2, \T7, \T7 # first phase of the reduction complete
1564 vpsrld $1, \T7, \T2 # packed left shifting >> 1
1567 vpxor \T3, \T2, \T2 # xor the shifted versions
1568 vpxor \T4, \T2, \T2
1570 vpxor \T1, \T2, \T2
1571 vpxor \T2, \T7, \T7
1593 .macro GHASH_LAST_8_AVX T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
1598 vpshufd $0b01001110, \XMM1, \T2
1599 vpxor \XMM1, \T2, \T2
1605 vpclmulqdq $0x00, \T3, \T2, \XMM1
1609 vpshufd $0b01001110, \XMM2, \T2
1610 vpxor \XMM2, \T2, \T2
1619 vpclmulqdq $0x00, \T3, \T2, \T2
1620 vpxor \T2, \XMM1, \XMM1
1624 vpshufd $0b01001110, \XMM3, \T2
1625 vpxor \XMM3, \T2, \T2
1634 vpclmulqdq $0x00, \T3, \T2, \T2
1635 vpxor \T2, \XMM1, \XMM1
1639 vpshufd $0b01001110, \XMM4, \T2
1640 vpxor \XMM4, \T2, \T2
1649 vpclmulqdq $0x00, \T3, \T2, \T2
1650 vpxor \T2, \XMM1, \XMM1
1654 vpshufd $0b01001110, \XMM5, \T2
1655 vpxor \XMM5, \T2, \T2
1664 vpclmulqdq $0x00, \T3, \T2, \T2
1665 vpxor \T2, \XMM1, \XMM1
1669 vpshufd $0b01001110, \XMM6, \T2
1670 vpxor \XMM6, \T2, \T2
1679 vpclmulqdq $0x00, \T3, \T2, \T2
1680 vpxor \T2, \XMM1, \XMM1
1684 vpshufd $0b01001110, \XMM7, \T2
1685 vpxor \XMM7, \T2, \T2
1694 vpclmulqdq $0x00, \T3, \T2, \T2
1695 vpxor \T2, \XMM1, \XMM1
1699 vpshufd $0b01001110, \XMM8, \T2
1700 vpxor \XMM8, \T2, \T2
1709 vpclmulqdq $0x00, \T3, \T2, \T2
1711 vpxor \T2, \XMM1, \XMM1
1713 vpxor \T7, \XMM1, \T2
1718 vpslldq $8, \T2, \T4
1719 vpsrldq $8, \T2, \T2
1722 vpxor \T2, \T6, \T6 # <T6:T7> holds the result of
1727 vpslld $31, \T7, \T2 # packed right shifting << 31
1731 vpxor \T3, \T2, \T2 # xor the shifted versions
1732 vpxor \T4, \T2, \T2
1734 vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
1736 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
1737 vpxor \T2, \T7, \T7 # first phase of the reduction complete
1742 vpsrld $1, \T7, \T2 # packed left shifting >> 1
1745 vpxor \T3, \T2, \T2 # xor the shifted versions
1746 vpxor \T4, \T2, \T2
1748 vpxor \T1, \T2, \T2
1749 vpxor \T2, \T7, \T7
1867 .macro GHASH_MUL_AVX2 GH HK T1 T2 T3 T4 T5
1870 vpclmulqdq $0x00,\HK,\GH,\T2 # T2 = a0*b0
1880 vpxor \T2, \GH, \GH
1886 vpclmulqdq $0x01, \GH, \T3, \T2
1887 vpslldq $8, \T2, \T2 # shift-L T2 2 DWs
1889 vpxor \T2, \GH, \GH # first phase of the reduction complete
1892 vpclmulqdq $0x00, \GH, \T3, \T2
1893 …vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-…
1898 vpxor \T2, \GH, \GH # second phase of the reduction complete
1905 .macro PRECOMPUTE_AVX2 HK T1 T2 T3 T4 T5 T6
1909 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
1912 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
1915 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
1918 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
1921 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
1924 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
1927 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
1939 .macro INITIAL_BLOCKS_AVX2 REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 …
2015 …GHASH_MUL_AVX2 reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks bloc…
2181 .macro GHASH_8_ENCRYPT_8_PARALLEL_AVX2 REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7…
2183 vmovdqa \XMM1, \T2
2266 vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
2267 vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
2268 vpclmulqdq $0x01, \T5, \T2, \T6 # T6 = a1*b0
2269 vpclmulqdq $0x10, \T5, \T2, \T5 # T5 = a0*b1
2471 vpxor 16*i(arg4, %r11), \T5, \T2
2473 vaesenclast \T2, reg_j, reg_j
2475 vaesenclast \T2, reg_j, \T3
2487 vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
2497 vpclmulqdq $0x01, \T7, \T3, \T2
2498 vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
2500 vpxor \T2, \T7, \T7 # first phase of the reduction complete
2515 vpclmulqdq $0x00, \T7, \T3, \T2
2516 vpsrldq $4, \T2, \T2 # shift-R xmm2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
2521 vpxor \T2, \T4, \T4 # second phase of the reduction complete
2543 .macro GHASH_LAST_8_AVX2 T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
2549 vpshufd $0b01001110, \XMM1, \T2
2551 vpxor \XMM1, \T2, \T2
2557 vpclmulqdq $0x00, \T3, \T2, \XMM1
2562 vpshufd $0b01001110, \XMM2, \T2
2564 vpxor \XMM2, \T2, \T2
2573 vpclmulqdq $0x00, \T3, \T2, \T2
2575 vpxor \T2, \XMM1, \XMM1
2580 vpshufd $0b01001110, \XMM3, \T2
2582 vpxor \XMM3, \T2, \T2
2591 vpclmulqdq $0x00, \T3, \T2, \T2
2593 vpxor \T2, \XMM1, \XMM1
2598 vpshufd $0b01001110, \XMM4, \T2
2600 vpxor \XMM4, \T2, \T2
2609 vpclmulqdq $0x00, \T3, \T2, \T2
2611 vpxor \T2, \XMM1, \XMM1
2616 vpshufd $0b01001110, \XMM5, \T2
2618 vpxor \XMM5, \T2, \T2
2627 vpclmulqdq $0x00, \T3, \T2, \T2
2629 vpxor \T2, \XMM1, \XMM1
2634 vpshufd $0b01001110, \XMM6, \T2
2636 vpxor \XMM6, \T2, \T2
2645 vpclmulqdq $0x00, \T3, \T2, \T2
2647 vpxor \T2, \XMM1, \XMM1
2652 vpshufd $0b01001110, \XMM7, \T2
2654 vpxor \XMM7, \T2, \T2
2663 vpclmulqdq $0x00, \T3, \T2, \T2
2665 vpxor \T2, \XMM1, \XMM1
2670 vpshufd $0b01001110, \XMM8, \T2
2672 vpxor \XMM8, \T2, \T2
2681 vpclmulqdq $0x00, \T3, \T2, \T2
2683 vpxor \T2, \XMM1, \XMM1
2685 vpxor \T7, \XMM1, \T2
2690 vpslldq $8, \T2, \T4
2691 vpsrldq $8, \T2, \T2
2694 vpxor \T2, \T6, \T6 # <T6:T7> holds the result of the
2701 vpclmulqdq $0x01, \T7, \T3, \T2
2702 vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
2704 vpxor \T2, \T7, \T7 # first phase of the reduction complete
2709 vpclmulqdq $0x00, \T7, \T3, \T2
2710 …vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs sh…
2715 vpxor \T2, \T4, \T4 # second phase of the reduction complete