Lines Matching +full:cortex +full:- +full:r5
1 /* Do not modify. This file is auto-generated from sha256-armv4.pl. */
2 @ Copyright 2007-2020 The OpenSSL Project Authors. All Rights Reserved.
21 @ Performance is ~2x better than gcc 3.4 generated code and in "abso-
22 @ lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per
23 @ byte [on single-issue Xscale PXA250 core].
27 @ Rescheduling for dual-issue pipeline resulted in 22% improvement on
28 @ Cortex A8 core and ~20 cycles per processed byte.
32 @ Profiler-assisted and platform-specific optimization resulted in 16%
33 @ improvement on Cortex A8 core and ~15.4 cycles per processed byte.
37 @ Add NEON implementation. On Cortex A8 it was measured to process one
38 @ byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon
39 @ S4 does it in 12.5 cycles too, but it's 50% faster than integer-only
40 @ code (meaning that latter performs sub-optimally, nothing was done
84 .size K256,.-K256
91 .word OPENSSL_armcap_P-.Lsha256_block_data_order
119 stmdb sp!,{r0,r1,r2,r4-r11,lr}
120 ldmia r0,{r4,r5,r6,r7,r8,r9,r10,r11}
129 eor r3,r5,r6 @ magic
177 eor r12,r4,r5 @ a^b, b^c in next round
180 eor r12,r4,r5 @ a^b, b^c in next round
186 eor r3,r3,r5 @ Maj(a,b,c)
301 add r5,r5,r9 @ d+=h
310 eor r0,r5,r5,ror#5
312 eor r0,r0,r5,ror#19 @ Sigma1(e)
327 eor r0,r5,r5,ror#5
329 eor r0,r0,r5,ror#19 @ Sigma1(e)
336 and r2,r2,r5
392 eor r2,r5,r6
450 eor r2,r4,r5
454 eor r2,r2,r5 @ Ch(e,f,g)
506 add r5,r5,r2 @ h+=X[i]
509 add r5,r5,r0,ror#6 @ h+=Sigma1(e)
511 add r5,r5,r12 @ h+=K256[i]
514 add r5,r5,r2 @ h+=Ch(e,f,g)
533 add r9,r9,r5 @ d+=h
535 add r5,r5,r0,ror#2 @ h+=Sigma0(a)
536 @ add r5,r5,r3 @ h+=Maj(a,b,c)
543 add r5,r5,r3 @ h+=Maj(a,b,c) from the past
550 add r5,r5,r3 @ h+=Maj(a,b,c) from the past
571 eor r0,r5,r5,ror#11
583 eor r3,r5,r6 @ a^b, b^c in next round
586 eor r3,r5,r6 @ a^b, b^c in next round
589 eor r0,r0,r5,ror#20 @ Sigma0(a)
641 eor r12,r4,r5 @ a^b, b^c in next round
644 eor r12,r4,r5 @ a^b, b^c in next round
650 eor r3,r3,r5 @ Maj(a,b,c)
765 add r5,r5,r9 @ d+=h
774 eor r0,r5,r5,ror#5
776 eor r0,r0,r5,ror#19 @ Sigma1(e)
791 eor r0,r5,r5,ror#5
793 eor r0,r0,r5,ror#19 @ Sigma1(e)
800 and r2,r2,r5
856 eor r2,r5,r6
914 eor r2,r4,r5
918 eor r2,r2,r5 @ Ch(e,f,g)
970 add r5,r5,r2 @ h+=X[i]
973 add r5,r5,r0,ror#6 @ h+=Sigma1(e)
975 add r5,r5,r12 @ h+=K256[i]
978 add r5,r5,r2 @ h+=Ch(e,f,g)
997 add r9,r9,r5 @ d+=h
999 add r5,r5,r0,ror#2 @ h+=Sigma0(a)
1000 @ add r5,r5,r3 @ h+=Maj(a,b,c)
1007 add r5,r5,r3 @ h+=Maj(a,b,c) from the past
1014 add r5,r5,r3 @ h+=Maj(a,b,c) from the past
1035 eor r0,r5,r5,ror#11
1047 eor r3,r5,r6 @ a^b, b^c in next round
1050 eor r3,r5,r6 @ a^b, b^c in next round
1053 eor r0,r0,r5,ror#20 @ Sigma0(a)
1097 eor r12,r4,r5 @ a^b, b^c in next round
1100 eor r12,r4,r5 @ a^b, b^c in next round
1106 eor r3,r3,r5 @ Maj(a,b,c)
1203 add r5,r5,r9 @ d+=h
1220 eor r0,r5,r5,ror#5 @ from BODY_00_15
1222 eor r0,r0,r5,ror#19 @ Sigma1(e)
1229 and r2,r2,r5
1276 eor r2,r5,r6
1325 eor r2,r4,r5
1329 eor r2,r2,r5 @ Ch(e,f,g)
1372 add r5,r5,r2 @ h+=X[i]
1375 add r5,r5,r0,ror#6 @ h+=Sigma1(e)
1377 add r5,r5,r12 @ h+=K256[i]
1380 add r5,r5,r2 @ h+=Ch(e,f,g)
1399 add r9,r9,r5 @ d+=h
1401 add r5,r5,r0,ror#2 @ h+=Sigma0(a)
1402 @ add r5,r5,r3 @ h+=Maj(a,b,c)
1406 add r5,r5,r3 @ h+=Maj(a,b,c) from the past
1428 eor r0,r5,r5,ror#11
1440 eor r3,r5,r6 @ a^b, b^c in next round
1443 eor r3,r5,r6 @ a^b, b^c in next round
1446 eor r0,r0,r5,ror#20 @ Sigma0(a)
1489 eor r12,r4,r5 @ a^b, b^c in next round
1492 eor r12,r4,r5 @ a^b, b^c in next round
1498 eor r3,r3,r5 @ Maj(a,b,c)
1595 add r5,r5,r9 @ d+=h
1612 eor r0,r5,r5,ror#5 @ from BODY_00_15
1614 eor r0,r0,r5,ror#19 @ Sigma1(e)
1621 and r2,r2,r5
1668 eor r2,r5,r6
1717 eor r2,r4,r5
1721 eor r2,r2,r5 @ Ch(e,f,g)
1764 add r5,r5,r2 @ h+=X[i]
1767 add r5,r5,r0,ror#6 @ h+=Sigma1(e)
1769 add r5,r5,r12 @ h+=K256[i]
1772 add r5,r5,r2 @ h+=Ch(e,f,g)
1791 add r9,r9,r5 @ d+=h
1793 add r5,r5,r0,ror#2 @ h+=Sigma0(a)
1794 @ add r5,r5,r3 @ h+=Maj(a,b,c)
1798 add r5,r5,r3 @ h+=Maj(a,b,c) from the past
1820 eor r0,r5,r5,ror#11
1832 eor r3,r5,r6 @ a^b, b^c in next round
1835 eor r3,r5,r6 @ a^b, b^c in next round
1838 eor r0,r0,r5,ror#20 @ Sigma0(a)
1856 add r5,r5,r2
1869 stmia r3,{r4,r5,r6,r7,r8,r9,r10,r11}
1876 ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,r11,pc}
1878 ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,r11,lr}
1881 .word 0xe12fff1e @ interoperable with Thumb ISA:-)
1883 .size sha256_block_data_order,.-sha256_block_data_order
1885 .arch armv7-a
1894 stmdb sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
1898 bic r11,r11,#15 @ align for 128-bit stores
1913 vrev32.8 q1,q1 @ big-endian
1929 ldmia r0,{r4,r5,r6,r7,r8,r9,r10,r11}
1933 eor r3,r5,r6
1951 eor r12,r4,r5
1961 eor r3,r3,r5
2010 add r5,r5,r9
2017 eor r0,r5,r5,ror#5
2020 and r2,r2,r5
2022 eor r3,r0,r5,ror#19
2038 eor r2,r5,r6
2063 eor r2,r4,r5
2072 eor r2,r2,r5
2087 add r5,r5,r2
2099 add r5,r5,r12,ror#6
2103 add r5,r5,r2
2108 add r9,r9,r5
2109 add r5,r5,r0,ror#2
2117 add r5,r5,r3
2121 eor r0,r5,r5,ror#11
2125 eor r3,r5,r6
2126 eor r0,r0,r5,ror#20
2147 eor r12,r4,r5
2157 eor r3,r3,r5
2206 add r5,r5,r9
2213 eor r0,r5,r5,ror#5
2216 and r2,r2,r5
2218 eor r3,r0,r5,ror#19
2234 eor r2,r5,r6
2259 eor r2,r4,r5
2268 eor r2,r2,r5
2283 add r5,r5,r2
2295 add r5,r5,r12,ror#6
2299 add r5,r5,r2
2304 add r9,r9,r5
2305 add r5,r5,r0,ror#2
2313 add r5,r5,r3
2317 eor r0,r5,r5,ror#11
2321 eor r3,r5,r6
2322 eor r0,r0,r5,ror#20
2359 eor r12,r4,r5
2367 eor r3,r3,r5
2399 add r5,r5,r9
2404 eor r0,r5,r5,ror#5
2406 and r2,r2,r5
2407 eor r3,r0,r5,ror#19
2421 eor r2,r5,r6
2441 eor r2,r4,r5
2447 eor r2,r2,r5
2457 add r5,r5,r2
2465 add r5,r5,r12,ror#6
2468 add r5,r5,r2
2471 add r9,r9,r5
2472 add r5,r5,r0,ror#2
2477 add r5,r5,r3
2480 eor r0,r5,r5,ror#11
2483 eor r3,r5,r6
2484 eor r0,r0,r5,ror#20
2503 eor r12,r4,r5
2511 eor r3,r3,r5
2543 add r5,r5,r9
2548 eor r0,r5,r5,ror#5
2550 and r2,r2,r5
2551 eor r3,r0,r5,ror#19
2565 eor r2,r5,r6
2585 eor r2,r4,r5
2591 eor r2,r2,r5
2601 add r5,r5,r2
2609 add r5,r5,r12,ror#6
2612 add r5,r5,r2
2615 add r9,r9,r5
2616 add r5,r5,r0,ror#2
2621 add r5,r5,r3
2624 eor r0,r5,r5,ror#11
2627 eor r3,r5,r6
2628 eor r0,r0,r5,ror#20
2643 add r5,r5,r12
2652 str r5,[r2],#4
2665 eorne r3,r5,r6
2668 ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,pc}
2669 .size sha256_block_data_order_neon,.-sha256_block_data_order_neon
2798 sub r3,r3,#256-16 @ rewind
2816 .size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8