| /arch/x86/crypto/ |
| D | sm4-aesni-avx-asm_64.S | 32 #define RA2 %xmm10 macro
160 vmovdqa RA0, RA2;
166 vmovdqu 2*16(%rdx), RA2;
176 vpshufb RTMP2, RA2, RA2;
187 transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
218 ROUND(0, RA0, RA1, RA2, RA3);
219 ROUND(1, RA1, RA2, RA3, RA0);
220 ROUND(2, RA2, RA3, RA0, RA1);
221 ROUND(3, RA3, RA0, RA1, RA2);
230 transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
[all …]
|
| D | sm4-aesni-avx2-asm_64.S | 33 #define RA2 %ymm10 macro
173 vpshufb RTMP2, RA2, RA2;
181 transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
247 ROUND(0, RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3);
248 ROUND(1, RA1, RA2, RA3, RA0, RB1, RB2, RB3, RB0);
249 ROUND(2, RA2, RA3, RA0, RA1, RB2, RB3, RB0, RB1);
250 ROUND(3, RA3, RA0, RA1, RA2, RB3, RB0, RB1, RB2);
259 transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
263 vpshufb RTMP2, RA2, RA2;
320 vpshufb RTMP3, RTMP0, RA2;
[all …]
|
| D | twofish-avx-x86_64-asm_64.S | 42 #define RA2 %xmm4 macro
249 inpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
268 outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
290 inpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
291 rotate_1l(RA2);
308 outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
323 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
327 store_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
343 load_8way(%rdx, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
347 store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
[all …]
|
| D | cast6-avx-x86_64-asm_64.S | 42 #define RA2 %xmm4 macro
266 inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
290 outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
314 inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
337 outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
354 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
358 store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
377 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
381 store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
402 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
[all …]
|
| D | serpent-avx2-asm_64.S | 31 #define RA2 %ymm3 macro
565 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
602 write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
619 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
671 load_16way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
675 store_16way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
693 load_16way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
715 load_16way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
|
| D | serpent-avx-x86_64-asm_64.S | 37 #define RA2 %xmm6 macro
565 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
602 write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
619 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
669 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
673 store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
687 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
705 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
|
| 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);
|