Lines Matching refs:T2
251 .macro GHASH_MUL_AVX GH HK T1 T2 T3 T4 T5
253 vpshufd $0b01001110, \GH, \T2
255 vpxor \GH , \T2, \T2 # T2 = (a1+a0)
260 vpclmulqdq $0x00, \T3, \T2, \T2 # T2 = (a1+a0)*(b1+b0)
261 vpxor \GH, \T2,\T2
262 vpxor \T1, \T2,\T2 # T2 = a0*b1+a1*b0
264 vpslldq $8, \T2,\T3 # shift-L T3 2 DWs
265 vpsrldq $8, \T2,\T2 # shift-R T2 2 DWs
267 vpxor \T2, \T1, \T1 # <T1:GH> = GH x HK
270 vpslld $31, \GH, \T2 # packed right shifting << 31
274 vpxor \T3, \T2, \T2 # xor the shifted versions
275 vpxor \T4, \T2, \T2
277 vpsrldq $4, \T2, \T5 # shift-R T5 1 DW
279 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
280 vpxor \T2, \GH, \GH # first phase of the reduction complete
284 vpsrld $1,\GH, \T2 # packed left shifting >> 1
287 vpxor \T3, \T2, \T2 # xor the shifted versions
288 vpxor \T4, \T2, \T2
290 vpxor \T5, \T2, \T2
291 vpxor \T2, \GH, \GH
297 .macro PRECOMPUTE_AVX HK T1 T2 T3 T4 T5 T6
306 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
312 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
318 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
324 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
330 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
336 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
342 GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
357 .macro INITIAL_BLOCKS_AVX num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 …
467 GHASH_MUL_AVX reg_i, \T2, \T1, \T3, \T4, \T5, \T6
471 … GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
633 .macro GHASH_8_ENCRYPT_8_PARALLEL_AVX T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8…
635 vmovdqa \XMM1, \T2
718 vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
719 vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
721 vpshufd $0b01001110, \T2, \T6
722 vpxor \T2, \T6, \T6
903 vpxor 16*i(arg3, %r11), \T5, \T2
905 vaesenclast \T2, reg_j, reg_j
907 vaesenclast \T2, reg_j, \T3
919 vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
928 vpslld $31, \T7, \T2 # packed right shifting << 31
932 vpxor \T3, \T2, \T2 # xor the shifted versions
933 vpxor \T4, \T2, \T2
935 vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
937 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
938 vpxor \T2, \T7, \T7 # first phase of the reduction complete
953 vpsrld $1, \T7, \T2 # packed left shifting >> 1
956 vpxor \T3, \T2, \T2 # xor the shifted versions
957 vpxor \T4, \T2, \T2
959 vpxor \T1, \T2, \T2
960 vpxor \T2, \T7, \T7
982 .macro GHASH_LAST_8_AVX T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
987 vpshufd $0b01001110, \XMM1, \T2
988 vpxor \XMM1, \T2, \T2
994 vpclmulqdq $0x00, \T3, \T2, \XMM1
998 vpshufd $0b01001110, \XMM2, \T2
999 vpxor \XMM2, \T2, \T2
1008 vpclmulqdq $0x00, \T3, \T2, \T2
1009 vpxor \T2, \XMM1, \XMM1
1013 vpshufd $0b01001110, \XMM3, \T2
1014 vpxor \XMM3, \T2, \T2
1023 vpclmulqdq $0x00, \T3, \T2, \T2
1024 vpxor \T2, \XMM1, \XMM1
1028 vpshufd $0b01001110, \XMM4, \T2
1029 vpxor \XMM4, \T2, \T2
1038 vpclmulqdq $0x00, \T3, \T2, \T2
1039 vpxor \T2, \XMM1, \XMM1
1043 vpshufd $0b01001110, \XMM5, \T2
1044 vpxor \XMM5, \T2, \T2
1053 vpclmulqdq $0x00, \T3, \T2, \T2
1054 vpxor \T2, \XMM1, \XMM1
1058 vpshufd $0b01001110, \XMM6, \T2
1059 vpxor \XMM6, \T2, \T2
1068 vpclmulqdq $0x00, \T3, \T2, \T2
1069 vpxor \T2, \XMM1, \XMM1
1073 vpshufd $0b01001110, \XMM7, \T2
1074 vpxor \XMM7, \T2, \T2
1083 vpclmulqdq $0x00, \T3, \T2, \T2
1084 vpxor \T2, \XMM1, \XMM1
1088 vpshufd $0b01001110, \XMM8, \T2
1089 vpxor \XMM8, \T2, \T2
1098 vpclmulqdq $0x00, \T3, \T2, \T2
1100 vpxor \T2, \XMM1, \XMM1
1102 vpxor \T7, \XMM1, \T2
1107 vpslldq $8, \T2, \T4
1108 vpsrldq $8, \T2, \T2
1111 vpxor \T2, \T6, \T6 # <T6:T7> holds the result of
1116 vpslld $31, \T7, \T2 # packed right shifting << 31
1120 vpxor \T3, \T2, \T2 # xor the shifted versions
1121 vpxor \T4, \T2, \T2
1123 vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
1125 vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
1126 vpxor \T2, \T7, \T7 # first phase of the reduction complete
1131 vpsrld $1, \T7, \T2 # packed left shifting >> 1
1134 vpxor \T3, \T2, \T2 # xor the shifted versions
1135 vpxor \T4, \T2, \T2
1137 vpxor \T1, \T2, \T2
1138 vpxor \T2, \T7, \T7
1543 .macro GHASH_MUL_AVX2 GH HK T1 T2 T3 T4 T5
1546 vpclmulqdq $0x00,\HK,\GH,\T2 # T2 = a0*b0
1556 vpxor \T2, \GH, \GH
1562 vpclmulqdq $0x01, \GH, \T3, \T2
1563 vpslldq $8, \T2, \T2 # shift-L T2 2 DWs
1565 vpxor \T2, \GH, \GH # first phase of the reduction complete
1568 vpclmulqdq $0x00, \GH, \T3, \T2
1569 …vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-…
1574 vpxor \T2, \GH, \GH # second phase of the reduction complete
1581 .macro PRECOMPUTE_AVX2 HK T1 T2 T3 T4 T5 T6
1585 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
1588 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
1591 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
1594 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
1597 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
1600 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
1603 GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
1616 .macro INITIAL_BLOCKS_AVX2 num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7…
1727 GHASH_MUL_AVX2 reg_i, \T2, \T1, \T3, \T4, \T5, \T6
1731 …GHASH_MUL_AVX2 reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks bloc…
1897 .macro GHASH_8_ENCRYPT_8_PARALLEL_AVX2 T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM…
1899 vmovdqa \XMM1, \T2
1982 vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
1983 vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
1984 vpclmulqdq $0x01, \T5, \T2, \T6 # T6 = a1*b0
1985 vpclmulqdq $0x10, \T5, \T2, \T5 # T5 = a0*b1
2170 vpxor 16*i(arg3, %r11), \T5, \T2
2172 vaesenclast \T2, reg_j, reg_j
2174 vaesenclast \T2, reg_j, \T3
2186 vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
2196 vpclmulqdq $0x01, \T7, \T3, \T2
2197 vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
2199 vpxor \T2, \T7, \T7 # first phase of the reduction complete
2214 vpclmulqdq $0x00, \T7, \T3, \T2
2215 vpsrldq $4, \T2, \T2 # shift-R xmm2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
2220 vpxor \T2, \T4, \T4 # second phase of the reduction complete
2242 .macro GHASH_LAST_8_AVX2 T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
2248 vpshufd $0b01001110, \XMM1, \T2
2250 vpxor \XMM1, \T2, \T2
2256 vpclmulqdq $0x00, \T3, \T2, \XMM1
2261 vpshufd $0b01001110, \XMM2, \T2
2263 vpxor \XMM2, \T2, \T2
2272 vpclmulqdq $0x00, \T3, \T2, \T2
2274 vpxor \T2, \XMM1, \XMM1
2279 vpshufd $0b01001110, \XMM3, \T2
2281 vpxor \XMM3, \T2, \T2
2290 vpclmulqdq $0x00, \T3, \T2, \T2
2292 vpxor \T2, \XMM1, \XMM1
2297 vpshufd $0b01001110, \XMM4, \T2
2299 vpxor \XMM4, \T2, \T2
2308 vpclmulqdq $0x00, \T3, \T2, \T2
2310 vpxor \T2, \XMM1, \XMM1
2315 vpshufd $0b01001110, \XMM5, \T2
2317 vpxor \XMM5, \T2, \T2
2326 vpclmulqdq $0x00, \T3, \T2, \T2
2328 vpxor \T2, \XMM1, \XMM1
2333 vpshufd $0b01001110, \XMM6, \T2
2335 vpxor \XMM6, \T2, \T2
2344 vpclmulqdq $0x00, \T3, \T2, \T2
2346 vpxor \T2, \XMM1, \XMM1
2351 vpshufd $0b01001110, \XMM7, \T2
2353 vpxor \XMM7, \T2, \T2
2362 vpclmulqdq $0x00, \T3, \T2, \T2
2364 vpxor \T2, \XMM1, \XMM1
2369 vpshufd $0b01001110, \XMM8, \T2
2371 vpxor \XMM8, \T2, \T2
2380 vpclmulqdq $0x00, \T3, \T2, \T2
2382 vpxor \T2, \XMM1, \XMM1
2384 vpxor \T7, \XMM1, \T2
2389 vpslldq $8, \T2, \T4
2390 vpsrldq $8, \T2, \T2
2393 vpxor \T2, \T6, \T6 # <T6:T7> holds the result of the
2400 vpclmulqdq $0x01, \T7, \T3, \T2
2401 vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
2403 vpxor \T2, \T7, \T7 # first phase of the reduction complete
2408 vpclmulqdq $0x00, \T7, \T3, \T2
2409 …vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs sh…
2414 vpxor \T2, \T4, \T4 # second phase of the reduction complete