Lines Matching refs:T2
605 .macro CALC_AAD_HASH GHASH_MUL AAD AADLEN T1 T2 T3 T4 T5 T6 T7 T8
621 \GHASH_MUL \T8, \T2, \T1, \T3, \T4, \T5, \T6
667 \GHASH_MUL \T7, \T2, \T1, \T3, \T4, \T5, \T6
895 .macro GHASH_MUL_AVX GH HK T1 T2 T3 T4 T5
897 vpshufd $0b01001110, \GH, \T2
899 vpxor \GH , \T2, \T2 # T2 = (a1+a0)
904 vpclmulqdq $0x00, \T3, \T2, \T2 # T2 = (a1+a0)*(b1+b0)
905 vpxor \GH, \T2,\T2
906 vpxor \T1, \T2,\T2 # T2 = a0*b1+a1*b0
908 vpslldq $8, \T2,\T3 # shift-L T3 2 DWs
909 vpsrldq $8, \T2,\T2 # shift-R T2 2 DWs
911 vpxor \T2, \T1, \T1 # <T1:GH> = GH x HK
914 vpslld $31, \GH, \T2 # packed right shifting << 31
918 vpxor \T3, \T2, \T2 # xor the shifted versions
919 vpxor \T4, \T2, \T2
921 vpsrldq $4, \T2, \T5 # shift-R T5 1 DW
923 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
924 vpxor \T2, \GH, \GH # first phase of the reduction complete
928 vpsrld $1,\GH, \T2 # packed left shifting >> 1
931 vpxor \T3, \T2, \T2 # xor the shifted versions
932 vpxor \T4, \T2, \T2
934 vpxor \T5, \T2, \T2
935 vpxor \T2, \GH, \GH
941 .macro PRECOMPUTE_AVX HK T1 T2 T3 T4 T5 T6
950 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
956 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
962 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
968 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
974 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
980 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
986 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
1001 .macro INITIAL_BLOCKS_AVX REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC
1075 GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
1236 .macro GHASH_8_ENCRYPT_8_PARALLEL_AVX REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
1238 vmovdqa \XMM1, \T2
1321 vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
1322 vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
1324 vpshufd $0b01001110, \T2, \T6
1325 vpxor \T2, \T6, \T6
1524 vpxor 16*i(arg4, %r11), \T5, \T2
1526 vaesenclast \T2, reg_j, reg_j
1528 vaesenclast \T2, reg_j, \T3
1540 vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
1549 vpslld $31, \T7, \T2 # packed right shifting << 31
1553 vpxor \T3, \T2, \T2 # xor the shifted versions
1554 vpxor \T4, \T2, \T2
1556 vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
1558 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
1559 vpxor \T2, \T7, \T7 # first phase of the reduction complete
1574 vpsrld $1, \T7, \T2 # packed left shifting >> 1
1577 vpxor \T3, \T2, \T2 # xor the shifted versions
1578 vpxor \T4, \T2, \T2
1580 vpxor \T1, \T2, \T2
1581 vpxor \T2, \T7, \T7
1603 .macro GHASH_LAST_8_AVX T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
1608 vpshufd $0b01001110, \XMM1, \T2
1609 vpxor \XMM1, \T2, \T2
1615 vpclmulqdq $0x00, \T3, \T2, \XMM1
1619 vpshufd $0b01001110, \XMM2, \T2
1620 vpxor \XMM2, \T2, \T2
1629 vpclmulqdq $0x00, \T3, \T2, \T2
1630 vpxor \T2, \XMM1, \XMM1
1634 vpshufd $0b01001110, \XMM3, \T2
1635 vpxor \XMM3, \T2, \T2
1644 vpclmulqdq $0x00, \T3, \T2, \T2
1645 vpxor \T2, \XMM1, \XMM1
1649 vpshufd $0b01001110, \XMM4, \T2
1650 vpxor \XMM4, \T2, \T2
1659 vpclmulqdq $0x00, \T3, \T2, \T2
1660 vpxor \T2, \XMM1, \XMM1
1664 vpshufd $0b01001110, \XMM5, \T2
1665 vpxor \XMM5, \T2, \T2
1674 vpclmulqdq $0x00, \T3, \T2, \T2
1675 vpxor \T2, \XMM1, \XMM1
1679 vpshufd $0b01001110, \XMM6, \T2
1680 vpxor \XMM6, \T2, \T2
1689 vpclmulqdq $0x00, \T3, \T2, \T2
1690 vpxor \T2, \XMM1, \XMM1
1694 vpshufd $0b01001110, \XMM7, \T2
1695 vpxor \XMM7, \T2, \T2
1704 vpclmulqdq $0x00, \T3, \T2, \T2
1705 vpxor \T2, \XMM1, \XMM1
1709 vpshufd $0b01001110, \XMM8, \T2
1710 vpxor \XMM8, \T2, \T2
1719 vpclmulqdq $0x00, \T3, \T2, \T2
1721 vpxor \T2, \XMM1, \XMM1
1723 vpxor \T7, \XMM1, \T2
1728 vpslldq $8, \T2, \T4
1729 vpsrldq $8, \T2, \T2
1732 vpxor \T2, \T6, \T6 # <T6:T7> holds the result of
1737 vpslld $31, \T7, \T2 # packed right shifting << 31
1741 vpxor \T3, \T2, \T2 # xor the shifted versions
1742 vpxor \T4, \T2, \T2
1744 vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
1746 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
1747 vpxor \T2, \T7, \T7 # first phase of the reduction complete
1752 vpsrld $1, \T7, \T2 # packed left shifting >> 1
1755 vpxor \T3, \T2, \T2 # xor the shifted versions
1756 vpxor \T4, \T2, \T2
1758 vpxor \T1, \T2, \T2
1759 vpxor \T2, \T7, \T7
1877 .macro GHASH_MUL_AVX2 GH HK T1 T2 T3 T4 T5
1880 vpclmulqdq $0x00,\HK,\GH,\T2 # T2 = a0*b0
1890 vpxor \T2, \GH, \GH
1896 vpclmulqdq $0x01, \GH, \T3, \T2
1897 vpslldq $8, \T2, \T2 # shift-L T2 2 DWs
1899 vpxor \T2, \GH, \GH # first phase of the reduction complete
1902 vpclmulqdq $0x00, \GH, \T3, \T2
1903 vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
1908 vpxor \T2, \GH, \GH # second phase of the reduction complete
1915 .macro PRECOMPUTE_AVX2 HK T1 T2 T3 T4 T5 T6
1919 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
1922 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
1925 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
1928 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
1931 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
1934 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
1937 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
1949 .macro INITIAL_BLOCKS_AVX2 REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC VER
2025 GHASH_MUL_AVX2 reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
2191 .macro GHASH_8_ENCRYPT_8_PARALLEL_AVX2 REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
2193 vmovdqa \XMM1, \T2
2276 vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
2277 vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
2278 vpclmulqdq $0x01, \T5, \T2, \T6 # T6 = a1*b0
2279 vpclmulqdq $0x10, \T5, \T2, \T5 # T5 = a0*b1
2481 vpxor 16*i(arg4, %r11), \T5, \T2
2483 vaesenclast \T2, reg_j, reg_j
2485 vaesenclast \T2, reg_j, \T3
2497 vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
2507 vpclmulqdq $0x01, \T7, \T3, \T2
2508 vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
2510 vpxor \T2, \T7, \T7 # first phase of the reduction complete
2525 vpclmulqdq $0x00, \T7, \T3, \T2
2526 vpsrldq $4, \T2, \T2 # shift-R xmm2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
2531 vpxor \T2, \T4, \T4 # second phase of the reduction complete
2553 .macro GHASH_LAST_8_AVX2 T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
2559 vpshufd $0b01001110, \XMM1, \T2
2561 vpxor \XMM1, \T2, \T2
2567 vpclmulqdq $0x00, \T3, \T2, \XMM1
2572 vpshufd $0b01001110, \XMM2, \T2
2574 vpxor \XMM2, \T2, \T2
2583 vpclmulqdq $0x00, \T3, \T2, \T2
2585 vpxor \T2, \XMM1, \XMM1
2590 vpshufd $0b01001110, \XMM3, \T2
2592 vpxor \XMM3, \T2, \T2
2601 vpclmulqdq $0x00, \T3, \T2, \T2
2603 vpxor \T2, \XMM1, \XMM1
2608 vpshufd $0b01001110, \XMM4, \T2
2610 vpxor \XMM4, \T2, \T2
2619 vpclmulqdq $0x00, \T3, \T2, \T2
2621 vpxor \T2, \XMM1, \XMM1
2626 vpshufd $0b01001110, \XMM5, \T2
2628 vpxor \XMM5, \T2, \T2
2637 vpclmulqdq $0x00, \T3, \T2, \T2
2639 vpxor \T2, \XMM1, \XMM1
2644 vpshufd $0b01001110, \XMM6, \T2
2646 vpxor \XMM6, \T2, \T2
2655 vpclmulqdq $0x00, \T3, \T2, \T2
2657 vpxor \T2, \XMM1, \XMM1
2662 vpshufd $0b01001110, \XMM7, \T2
2664 vpxor \XMM7, \T2, \T2
2673 vpclmulqdq $0x00, \T3, \T2, \T2
2675 vpxor \T2, \XMM1, \XMM1
2680 vpshufd $0b01001110, \XMM8, \T2
2682 vpxor \XMM8, \T2, \T2
2691 vpclmulqdq $0x00, \T3, \T2, \T2
2693 vpxor \T2, \XMM1, \XMM1
2695 vpxor \T7, \XMM1, \T2
2700 vpslldq $8, \T2, \T4
2701 vpsrldq $8, \T2, \T2
2704 vpxor \T2, \T6, \T6 # <T6:T7> holds the result of the
2711 vpclmulqdq $0x01, \T7, \T3, \T2
2712 vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
2714 vpxor \T2, \T7, \T7 # first phase of the reduction complete
2719 vpclmulqdq $0x00, \T7, \T3, \T2
2720 vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
2725 vpxor \T2, \T4, \T4 # second phase of the reduction complete