/linux/arch/x86/crypto/ |
H A D | sm4-aesni-avx-asm_64.S | 33 #define RA2 %xmm10 macro 159 vmovdqa RA0, RA2; 165 vmovdqu 2*16(%rdx), RA2; 175 vpshufb RTMP2, RA2, RA2; 186 transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); 217 ROUND(0, RA0, RA1, RA2, RA3); 218 ROUND(1, RA1, RA2, RA3, RA0); 219 ROUND(2, RA2, RA3, RA0, RA1); 220 ROUND(3, RA3, RA0, RA1, RA2); 229 transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); [all …]
|
H A D | sm4-aesni-avx2-asm_64.S | 34 #define RA2 %ymm10 macro 171 vpshufb RTMP2, RA2, RA2; 179 transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); 245 ROUND(0, RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3); 246 ROUND(1, RA1, RA2, RA3, RA0, RB1, RB2, RB3, RB0); 247 ROUND(2, RA2, RA3, RA0, RA1, RB2, RB3, RB0, RB1); 248 ROUND(3, RA3, RA0, RA1, RA2, RB3, RB0, RB1, RB2); 257 transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); 261 vpshufb RTMP2, RA2, RA2; 317 vpshufb RTMP3, RTMP0, RA2; [all …]
|
H A D | twofish-avx-x86_64-asm_64.S | 42 #define RA2 %xmm4 macro 248 inpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2); 267 outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2); 288 inpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2); 289 rotate_1l(RA2); 306 outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2); 321 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 325 store_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2); 341 load_8way(%rdx, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2); 345 store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); [all …]
|
H A D | cast6-avx-x86_64-asm_64.S | 42 #define RA2 %xmm4 macro 270 inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM); 294 outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM); 318 inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM); 341 outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM); 358 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 362 store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 381 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 385 store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 406 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); [all …]
|
H A D | serpent-avx-x86_64-asm_64.S | 37 #define RA2 %xmm6 macro 564 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2); 601 write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2); 617 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2); 667 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 671 store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 685 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 703 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
|
H A D | serpent-avx2-asm_64.S | 31 #define RA2 %ymm3 macro 564 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2); 601 write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2); 617 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2); 669 load_16way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 673 store_16way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 691 load_16way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); 713 load_16way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
|
H A D | serpent-sse2-x86_64-asm_64.S | 28 #define RA2 %xmm5 macro 634 read_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2); 676 write_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2); 682 xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2); 698 read_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
|