| /linux/arch/x86/crypto/ |
| H A D | sm4-aesni-avx-asm_64.S | 37 #define RB1 %xmm13 macro
181 vmovdqa .Lpost_tf_lo_s rRIP, RB1;
197 transform_post(RX0, RB1, RB2, MASK_4BIT, RTMP0); \
268 vpshufb RTMP2, RB1, RB1;
274 transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
333 ROUND(0, RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3);
334 ROUND(1, RA1, RA2, RA3, RA0, RB1, RB2, RB3, RB0);
335 ROUND(2, RA2, RA3, RA0, RA1, RB2, RB3, RB0, RB1);
336 ROUND(3, RA3, RA0, RA1, RA2, RB3, RB0, RB1, RB2);
346 transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
[all …]
|
| H A D | sm4-aesni-avx2-asm_64.S | 38 #define RB1 %ymm13 macro
174 vpshufb RTMP2, RB1, RB1;
180 transpose_4x4(RB0, RB1, RB2, RB3, 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);
258 transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
264 vpshufb RTMP2, RB1, RB1;
323 vpshufb RTMP3, RTMP0, RB1;
[all …]
|
| H A D | cast6-avx-x86_64-asm_64.S | 38 #define RB1 %xmm1 macro
269 inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
293 outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
317 inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
340 outunpack_blocks(RA1, RB1, RC1, RD1, 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 | twofish-avx-x86_64-asm_64.S | 38 #define RB1 %xmm1 macro
245 inpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
266 outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
285 inpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
305 outunpack_blocks(RA1, RB1, RC1, RD1, 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);
364 load_8way(%rdx, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
[all …]
|
| H A D | serpent-avx-x86_64-asm_64.S | 30 #define RB1 %xmm1 macro
563 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
600 write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
616 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
653 write_blocks(RC1, RD1, RB1, RE1, 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);
689 store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
703 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
[all …]
|
| H A D | serpent-avx2-asm_64.S | 32 #define RB1 %ymm4 macro
563 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
600 write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
616 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
653 write_blocks(RC1, RD1, RB1, RE1, 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);
695 store_16way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
713 load_16way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
[all …]
|
| H A D | serpent-sse2-x86_64-asm_64.S | 23 #define RB1 %xmm1 macro
633 read_blocks(%rdx, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
675 write_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
681 xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
697 read_blocks(%rdx, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
735 write_blocks(%rsi, RC1, RD1, RB1, RE1, RK0, RK1, RK2);
|