Implementation notes: amd64, margaux, crypto_hash/blake256

Computer: margaux
Microarchitecture: amd64; Core 2 65nm (6fb)
Architecture: amd64
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20230530
Operation: crypto_hash
Primitive: blake256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
19311	7670 0 0	20163 844 896	`sse2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
19788	8132 0 0	20627 844 896	`sse2-2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
19824	8077 0 0	20787 844 896	`sse2-2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
19840	7582 0 0	17501 836 896	`sse2-2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
19847	7669 0 0	19267 844 896	`sse2-2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
20267	8122 0 0	18835 844 896	`sse2-2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
20809	10056 0 0	22547 844 896	`bswap`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
20815	9976 0 0	22691 844 896	`bswap`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
20875	10040 0 0	22755 844 896	`regs`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
20932	10104 0 0	20392 780 928	`regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
20933	9632 0 0	20339 844 896	`regs`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
20941	9632 0 0	21235 844 896	`regs`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
20969	10072 0 0	22563 844 896	`regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
20971	9576 0 0	20283 844 896	`bswap`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
21072	10104 0 0	20392 780 928	`bswap`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
21086	9544 0 0	21147 844 896	`bswap`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
21468	10150 0 0	21492 796 960	`bswap`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
21556	10647 0 0	22517 804 960	`bswap`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
21593	11117 0 0	24157 804 960	`bswap`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
21619	10647 0 0	22517 804 960	`regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
21655	11722 0 0	24765 804 960	`regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
21990	7186 0 0	17117 836 896	`sse2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
21991	9602 0 0	22645 804 960	`sse2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22100	7689 0 0	18403 844 896	`sse2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
22107	25812 0 0	38643 844 896	`sphlib`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
22176	7681 0 0	20403 844 896	`sse2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
22186	25780 0 0	37499 844 896	`sphlib`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
22203	25074 0 0	37683 844 896	`sphlib`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
22215	10034 0 0	23077 804 960	`sse2-2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22222	25812 0 0	36635 844 896	`sphlib`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
22250	24995 0 0	38109 804 960	`sphlib`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22279	24805 0 0	36741 804 960	`sphlib`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22312	9960 0 0	19885 836 896	`bswap`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
22361	10026 0 0	19949 836 896	`regs`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
22380	7273 0 0	18883 844 896	`sse2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
22498	8567 0 0	20437 804 960	`sse2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22579	10793 0 0	22148 796 960	`regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22638	7801 0 0	18088 780 928	`sse2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22681	9037 0 0	20388 796 960	`sse2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22733	9095 0 0	20965 804 960	`sse2-2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22783	8362 0 0	18648 780 928	`sse2-2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
22956	7266 0 0	17560 780 928	`ssse3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
23056	8145 0 0	19492 796 960	`ssse3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
23077	8914 0 0	21957 804 960	`ssse3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
23290	25456 0 0	35509 836 896	`sphlib`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
23315	8103 0 0	19973 804 960	`ssse3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
23437	9701 0 0	21044 796 960	`sse2-2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
23625	23519 0 0	35013 804 960	`sphlib`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
24847	22923 0 0	33304 780 928	`sphlib`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
26041	10328 0 0	22819 844 896	`sandy`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
26076	10248 0 0	22963 844 896	`sandy`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
26172	9816 0 0	21419 844 896	`sandy`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
26290	9848 0 0	20555 844 896	`sandy`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
27154	10891 0 0	21176 780 928	`sandy`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
27212	10236 0 0	20157 836 896	`sandy`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
27803	11367 0 0	23237 804 960	`sandy`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
28208	11837 0 0	24877 804 960	`sandy`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
30037	10964 0 0	22308 796 960	`sandy`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
32000	2633 0 0	12920 780 928	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
32020	8115 0 0	19645 804 960	`sphlib-small`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
32526	7577 0 0	17960 780 928	`sphlib-small`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
33916	3006 0 0	14356 796 960	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
39171	3291 0 0	16003 844 896	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
39246	3323 0 0	15811 844 896	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
39797	2754 0 0	14355 844 896	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
40402	9396 0 0	21131 844 896	`sphlib-small`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
40602	9428 0 0	20267 844 896	`sphlib-small`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
40844	9460 0 0	22307 844 896	`sphlib-small`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
41060	2844 0 0	13555 844 896	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
41098	8497 0 0	18565 836 896	`sphlib-small`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
41156	8722 0 0	21347 844 896	`sphlib-small`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
42924	11157 0 0	23125 804 960	`sphlib-small`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
42965	11363 0 0	24477 804 960	`sphlib-small`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
43261	2713 0 0	12637 836 896	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230531	20230530
44014	5162 0 0	18189 804 960	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530
47337	3735 0 0	15605 804 960	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230531	20230530

Test failure

Implementation: avxs
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

error 111

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avxs
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avxs
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avxs
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avxs
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avxs
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avxs
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	avxs
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	avxs

Compiler output

Implementation: avxs
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

hash.c: hash.c:155:61: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_final' that is compiled without support for 'ssse3'
hash.c: __m128i w0 = _mm_load_si128((__m128i*)(&S->h[0])); w0 = _mm_shuffle_epi8(w0, u32to8);
hash.c: ^
hash.c: hash.c:156:61: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_final' that is compiled without support for 'ssse3'
hash.c: __m128i w1 = _mm_load_si128((__m128i*)(&S->h[4])); w1 = _mm_shuffle_epi8(w1, u32to8);
hash.c: ^
hash.c: 2 errors generated.

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avxs

Compiler output

Implementation: sse41
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

hash.c: In file included from hash.c:121:
hash.c: ./rounds.sse41.h:17:55: warning: implicit conversion from 'long' to 'int' changes value from 2242054355 to -2052912941 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(3964562569, 698298832, 57701188, 2242054355);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.sse41.h:17:22: warning: implicit conversion from 'long' to 'int' changes value from 3964562569 to -330404727 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(3964562569, 698298832, 57701188, 2242054355);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.sse41.h:20:33: warning: implicit conversion from 'long' to 'int' changes value from 2752067618 to -1542899678 [-Wconstant-conversion]
hash.c: buf1 = _mm_set_epi32(137296536, 2752067618, 320440878, 608135816);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.sse41.h:47:34: warning: implicit conversion from 'long' to 'int' changes value from 3380367581 to -914599715 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(3041331479, 3380367581, 887688300, 953160567);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.sse41.h:47:22: warning: implicit conversion from 'long' to 'int' changes value from 3041331479 to -1253635817 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(3041331479, 3380367581, 887688300, 953160567);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.sse41.h:50:46: warning: implicit conversion from 'long' to 'int' changes value from 3193202383 to -1101764913 [-Wconstant-conversion]
hash.c: buf1 = _mm_set_epi32(1065670069, 3232508343, 3193202383, 1160258022);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.sse41.h:50:34: warning: implicit conversion from 'long' to 'int' changes value from 3232508343 to -1062458953 [-Wconstant-conversion]
hash.c: buf1 = _mm_set_epi32(1065670069, 3232508343, 3193202383, 1160258022);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.sse41.h:81:57: warning: implicit conversion from 'long' to 'int' changes value from 3193202383 to -1101764913 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(137296536, 3041331479, 1160258022, 3193202383);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41

Compiler output

Implementation: sse41
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from hash.c:5:
hash.c: rounds.sse41.h: In function 'blake256_compress':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:166:1: error: inlining failed in call to 'always_inline' '_mm_blend_epi16': target specific option mismatch
hash.c: 166 | _mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
hash.c: | ^~~~~~~~~~~~~~~
hash.c: In file included from hash.c:121:
hash.c: rounds.sse41.h:881:8: note: called from here
hash.c: 881 | tmp1 = _mm_blend_epi16(tmp0, m3, 0xC0);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:5:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:166:1: error: inlining failed in call to 'always_inline' '_mm_blend_epi16': target specific option mismatch
hash.c: 166 | _mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
hash.c: | ^~~~~~~~~~~~~~~
hash.c: In file included from hash.c:121:
hash.c: rounds.sse41.h:880:8: note: called from here
hash.c: 880 | tmp0 = _mm_blend_epi16(m0,m1,0x0F);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:5:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:166:1: error: inlining failed in call to 'always_inline' '_mm_blend_epi16': target specific option mismatch
hash.c: 166 | _mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
hash.c: | ^~~~~~~~~~~~~~~
hash.c: In file included from hash.c:121:
hash.c: rounds.sse41.h:852:8: note: called from here
hash.c: 852 | tmp6 = _mm_blend_epi16(tmp5, tmp4, 0xC0);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse41
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse41
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse41
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse41

Compiler output

Implementation: sse41-2
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41-2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41-2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41-2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41-2

Compiler output

Implementation: sse41-2
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

hash.c: In file included from hash.c:2:
hash.c: ./blake256.h:105:15: warning: '_mm_roti_epi32' macro redefined [-Wmacro-redefined]
hash.c: #define _mm_roti_epi32(r, c) ((8==-c) ? _mm_shuffle_epi8(r,r8) : ( (16==-c) ? _mm_shuffle_epi8(r,r16) : _mm_xor_si128(_mm_srli_epi32( (r), -(c) ),_mm_slli_epi32( (r), 32-(-c) )) ) )
hash.c: ^
hash.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/xopintrin.h:233:9: note: previous definition is here
hash.c: #define _mm_roti_epi32(A, N) \
hash.c: ^
hash.c: hash.c:93:22: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: const __m128i m0 = _mm_shuffle_epi8(LOADU(datablock + 00), u8to32);
hash.c: ^
hash.c: hash.c:94:22: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: const __m128i m1 = _mm_shuffle_epi8(LOADU(datablock + 16), u8to32);
hash.c: ^
hash.c: hash.c:95:22: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: const __m128i m2 = _mm_shuffle_epi8(LOADU(datablock + 32), u8to32);
hash.c: ^
hash.c: hash.c:96:22: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: const __m128i m3 = _mm_shuffle_epi8(LOADU(datablock + 48), u8to32);
hash.c: ^
hash.c: hash.c:115:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: ROUND( 0);
hash.c: ^
hash.c: ./rounds.h:52:3: note: expanded from macro 'ROUND'
hash.c: G1(row1,row2,row3,row4,buf1); \
hash.c: ^
hash.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41-2

Compiler output

Implementation: sse41-2
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:39,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:32,
hash.c: from blake256.h:7,
hash.c: from hash.c:2:
hash.c: hash.c: In function 'blake256_compress':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:166:1: error: inlining failed in call to 'always_inline' '_mm_blend_epi16': target specific option mismatch
hash.c: 166 | _mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
hash.c: | ^~~~~~~~~~~~~~~
hash.c: In file included from rounds.h:45,
hash.c: from blake256.h:127,
hash.c: from hash.c:2:
hash.c: load.sse41.h:313:6: note: called from here
hash.c: 313 | t2 = _mm_blend_epi16(t0,t1,0x0F); \
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: rounds.h:58:3: note: in expansion of macro 'LOAD_MSG_9_4'
hash.c: 58 | LOAD_MSG_ ##r ##_4(buf4); \
hash.c: | ^~~~~~~~~
hash.c: hash.c:124:3: note: in expansion of macro 'ROUND'
hash.c: 124 | ROUND( 9);
hash.c: | ^~~~~
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:39,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:32,
hash.c: from blake256.h:7,
hash.c: from hash.c:2:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:166:1: error: inlining failed in call to 'always_inline' '_mm_blend_epi16': target specific option mismatch
hash.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse41-2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse41-2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse41-2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse41-2

Compiler output

Implementation: ssse3
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

hash.c: In file included from hash.c:122:
hash.c: ./rounds.ssse3.h:3:55: warning: implicit conversion from 'long' to 'int' changes value from 2242054355 to -2052912941 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(3964562569, 698298832, 57701188, 2242054355);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.ssse3.h:3:22: warning: implicit conversion from 'long' to 'int' changes value from 3964562569 to -330404727 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(3964562569, 698298832, 57701188, 2242054355);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.ssse3.h:6:33: warning: implicit conversion from 'long' to 'int' changes value from 2752067618 to -1542899678 [-Wconstant-conversion]
hash.c: buf1 = _mm_set_epi32(137296536, 2752067618, 320440878, 608135816);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.ssse3.h:27:34: warning: implicit conversion from 'long' to 'int' changes value from 3380367581 to -914599715 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(3041331479, 3380367581, 887688300, 953160567);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.ssse3.h:27:22: warning: implicit conversion from 'long' to 'int' changes value from 3041331479 to -1253635817 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(3041331479, 3380367581, 887688300, 953160567);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.ssse3.h:30:46: warning: implicit conversion from 'long' to 'int' changes value from 3193202383 to -1101764913 [-Wconstant-conversion]
hash.c: buf1 = _mm_set_epi32(1065670069, 3232508343, 3193202383, 1160258022);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.ssse3.h:30:34: warning: implicit conversion from 'long' to 'int' changes value from 3232508343 to -1062458953 [-Wconstant-conversion]
hash.c: buf1 = _mm_set_epi32(1065670069, 3232508343, 3193202383, 1160258022);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ./rounds.ssse3.h:51:57: warning: implicit conversion from 'long' to 'int' changes value from 3193202383 to -1101764913 [-Wconstant-conversion]
hash.c: buf2 = _mm_set_epi32(137296536, 3041331479, 1160258022, 3193202383);
hash.c: ~~~~~~~~~~~~~ ^~~~~~~~~~
hash.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	ssse3
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	ssse3
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	ssse3
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	ssse3
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	ssse3

Compiler output

Implementation: xop
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

hash.c: hash.c:115:3: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake256_compress' that is compiled without support for 'xop'
hash.c: ROUND( 0);
hash.c: ^
hash.c: ./rounds.h:51:3: note: expanded from macro 'ROUND'
hash.c: LOAD_MSG_ ##r ##_1(buf1); \
hash.c: ^
hash.c: <scratch space>:178:1: note: expanded from here
hash.c: LOAD_MSG_0_1
hash.c: ^
hash.c: ./load.xop.h:19:6: note: expanded from macro 'LOAD_MSG_0_1'
hash.c: s0 = _mm_perm_epi8(m0, m1, _mm_set_epi32(TOB(6),TOB(4),TOB(2),TOB(0)) ); \
hash.c: ^
hash.c: hash.c:115:3: error: '__builtin_ia32_vprotdi' needs target feature xop
hash.c: ./rounds.h:52:3: note: expanded from macro 'ROUND'
hash.c: G1(row1,row2,row3,row4,buf1); \
hash.c: ^
hash.c: ./rounds.h:8:10: note: expanded from macro 'G1'
hash.c: row4 = _mm_roti_epi32(row4, -16); \
hash.c: ^
hash.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/xopintrin.h:234:13: note: expanded from macro '_mm_roti_epi32'
hash.c: ((__m128i)__builtin_ia32_vprotdi((__v4si)(__m128i)(A), (N)))
hash.c: ^
hash.c: hash.c:115:3: error: '__builtin_ia32_vprotdi' needs target feature xop
hash.c: ./rounds.h:52:3: note: expanded from macro 'ROUND'
hash.c: G1(row1,row2,row3,row4,buf1); \
hash.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	xop
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	xop
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	xop
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	xop

Compiler output

Implementation: xop
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

hash.c: hash.c:93:22: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: const __m128i m0 = _mm_shuffle_epi8(LOADU(datablock + 00), u8to32);
hash.c: ^
hash.c: hash.c:94:22: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: const __m128i m1 = _mm_shuffle_epi8(LOADU(datablock + 16), u8to32);
hash.c: ^
hash.c: hash.c:95:22: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: const __m128i m2 = _mm_shuffle_epi8(LOADU(datablock + 32), u8to32);
hash.c: ^
hash.c: hash.c:96:22: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: const __m128i m3 = _mm_shuffle_epi8(LOADU(datablock + 48), u8to32);
hash.c: ^
hash.c: hash.c:115:3: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake256_compress' that is compiled without support for 'xop'
hash.c: ROUND( 0);
hash.c: ^
hash.c: ./rounds.h:51:3: note: expanded from macro 'ROUND'
hash.c: LOAD_MSG_ ##r ##_1(buf1); \
hash.c: ^
hash.c: <scratch space>:178:1: note: expanded from here
hash.c: LOAD_MSG_0_1
hash.c: ^
hash.c: ./load.xop.h:19:6: note: expanded from macro 'LOAD_MSG_0_1'
hash.c: s0 = _mm_perm_epi8(m0, m1, _mm_set_epi32(TOB(6),TOB(4),TOB(2),TOB(0)) ); \
hash.c: ^
hash.c: hash.c:115:3: error: '__builtin_ia32_vprotdi' needs target feature xop
hash.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	xop

Compiler output

Implementation: xop
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:38,
hash.c: from blake256.h:7,
hash.c: from hash.c:2:
hash.c: hash.c: In function 'blake256_compress':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/xopintrin.h:266:1: error: inlining failed in call to 'always_inline' '_mm_roti_epi32': target specific option mismatch
hash.c: 266 | _mm_roti_epi32(__m128i __A, const int __B)
hash.c: | ^~~~~~~~~~~~~~
hash.c: In file included from blake256.h:127,
hash.c: from hash.c:2:
hash.c: rounds.h:19:10: note: called from here
hash.c: 19 | row2 = _mm_roti_epi32(row2, -7); \
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
hash.c: rounds.h:59:3: note: in expansion of macro 'G2'
hash.c: 59 | G2(row1,row2,row3,row4,buf4); \
hash.c: | ^~
hash.c: hash.c:128:3: note: in expansion of macro 'ROUND'
hash.c: 128 | ROUND(13);
hash.c: | ^~~~~
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:38,
hash.c: from blake256.h:7,
hash.c: from hash.c:2:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/xopintrin.h:266:1: error: inlining failed in call to 'always_inline' '_mm_roti_epi32': target specific option mismatch
hash.c: 266 | _mm_roti_epi32(__m128i __A, const int __B)
hash.c: | ^~~~~~~~~~~~~~
hash.c: In file included from blake256.h:127,
hash.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop