| /Linux-v6.1/arch/x86/crypto/ |
| D | sm4-aesni-avx-asm_64.S | 36 #define RB1 %xmm13 macro
182 vmovdqa .Lpost_tf_lo_s rRIP, RB1;
198 transform_post(RX0, RB1, RB2, MASK_4BIT, RTMP0); \
270 vpshufb RTMP2, RB1, RB1;
276 transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
335 ROUND(0, RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3);
336 ROUND(1, RA1, RA2, RA3, RA0, RB1, RB2, RB3, RB0);
337 ROUND(2, RA2, RA3, RA0, RA1, RB2, RB3, RB0, RB1);
338 ROUND(3, RA3, RA0, RA1, RA2, RB3, RB0, RB1, RB2);
348 transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
[all …]
|
| D | sm4-aesni-avx2-asm_64.S | 37 #define RB1 %ymm13 macro
176 vpshufb RTMP2, RB1, RB1;
182 transpose_4x4(RB0, RB1, RB2, RB3, 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);
260 transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
266 vpshufb RTMP2, RB1, RB1;
326 vpshufb RTMP3, RTMP0, RB1;
[all …]
|
| D | twofish-avx-x86_64-asm_64.S | 38 #define RB1 %xmm1 macro
246 inpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
267 outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
287 inpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
307 outunpack_blocks(RA1, RB1, RC1, RD1, 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);
366 load_8way(%rdx, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
[all …]
|
| D | cast6-avx-x86_64-asm_64.S | 38 #define RB1 %xmm1 macro
265 inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
289 outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
313 inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
336 outunpack_blocks(RA1, RB1, RC1, RD1, 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-avx-x86_64-asm_64.S | 30 #define RB1 %xmm1 macro
564 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
601 write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
618 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
655 write_blocks(RC1, RD1, RB1, RE1, 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);
691 store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
705 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
[all …]
|
| D | serpent-avx2-asm_64.S | 32 #define RB1 %ymm4 macro
564 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
601 write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
618 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
655 write_blocks(RC1, RD1, RB1, RE1, 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);
697 store_16way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
715 load_16way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
[all …]
|
| 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);
|
