Implementation notes: amd64, h3neo, crypto_hash/blake256

Computer: h3neo
Microarchitecture: amd64; K10 45nm (100f63)
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20240107
Operation: crypto_hash
Primitive: blake256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
21887	10104 0 0	20368 780 928	`bswap`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
21957	10104 0 0	20368 780 928	`regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
22568	11180 0 0	24725 804 960	`bswap`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
22582	11161 0 0	24693 804 960	`regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
22627	10679 0 0	22877 804 960	`regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
22666	10679 0 0	22877 804 960	`bswap`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
22703	10072 0 0	22947 844 896	`regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
22707	10056 0 0	22947 844 896	`bswap`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
22966	25003 0 0	38613 804 960	`sphlib`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
23040	24693 0 0	36957 804 960	`sphlib`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
23131	9451 0 0	20011 844 896	`bswap`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23152	9483 0 0	20995 844 896	`bswap`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23154	9931 0 0	22363 844 896	`bswap`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23169	9947 0 0	22363 844 896	`regs`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23188	9539 0 0	21035 844 896	`regs`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23190	9507 0 0	20083 844 896	`regs`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23658	9858 0 0	19805 836 896	`bswap`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23692	9882 0 0	19837 836 896	`regs`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23860	24434 0 0	36067 844 896	`sphlib`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23881	24466 0 0	37019 844 896	`sphlib`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23884	24466 0 0	35147 844 896	`sphlib`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
23933	10173 0 0	21484 796 960	`bswap`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
23991	25074 0 0	38083 844 896	`sphlib`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
25076	10837 0 0	22156 796 960	`regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
25104	24723 0 0	34781 836 896	`sphlib`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
25223	22923 0 0	33296 780 928	`sphlib`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
25830	23851 0 0	35325 804 960	`sphlib`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
30635	8132 0 0	21011 844 896	`sse2-2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
33206	8228 0 0	20651 844 896	`sse2-2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
33243	7820 0 0	19323 844 896	`sse2-2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
33449	7733 0 0	17677 836 896	`sse2-2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
34773	8293 0 0	18851 844 896	`sse2-2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
35359	7670 0 0	20563 844 896	`sse2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
35534	7577 0 0	17936 780 928	`sphlib-small`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
35559	8179 0 0	19685 804 960	`sphlib-small`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
36433	9652 0 0	23189 804 960	`sse2-2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
36765	9375 0 0	21573 804 960	`sse2-2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
37874	9535 0 0	20852 796 960	`sse2-2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
38544	7299 0 0	17261 836 896	`sse2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
38564	7386 0 0	18907 844 896	`sse2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
38582	7794 0 0	20235 844 896	`sse2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
38665	2633 0 0	12912 780 928	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
39575	9108 0 0	22645 804 960	`sse2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
39808	8799 0 0	20997 804 960	`sse2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
40251	7948 0 0	18531 844 896	`sse2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
41294	8683 0 0	19988 796 960	`sse2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
42493	3048 0 0	14348 796 960	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
42661	3323 0 0	16195 844 896	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
43921	11659 0 0	25269 804 960	`sphlib-small`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
44050	3128 0 0	15539 844 896	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
44229	8626 0 0	20275 844 896	`sphlib-small`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
44373	8706 0 0	21259 844 896	`sphlib-small`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
44403	8433 0 0	18509 836 896	`sphlib-small`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
44487	8658 0 0	19355 844 896	`sphlib-small`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
44531	2716 0 0	13283 844 896	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
44578	2608 0 0	14115 844 896	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
45029	10891 0 0	21168 780 928	`sandy`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
45251	8199 0 0	18480 780 928	`sse2-2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
46622	11447 0 0	23645 804 960	`sandy`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
46674	11948 0 0	25493 804 960	`sandy`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
46750	10328 0 0	23203 844 896	`sandy`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
47059	11221 0 0	23517 804 960	`sphlib-small`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
47869	10770 0 0	23195 844 896	`sandy`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
47886	10290 0 0	20875 844 896	`sandy`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
47899	10322 0 0	21827 844 896	`sandy`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
48169	10514 0 0	20477 836 896	`sandy`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
48258	2624 0 0	12573 836 896	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
50188	7545 0 0	17808 780 928	`sse2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
50247	8722 0 0	21747 844 896	`sphlib-small`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
51415	4553 0 0	18069 804 960	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
53180	3767 0 0	15965 804 960	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
53923	10637 0 0	21932 796 960	`sandy`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212

Compiler output

Implementation: avxs
Security model: constbranchindex
Compiler: clang -march=native -O2 -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: 5, 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
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avxs

Compiler output

Implementation: avxs
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:37,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:32,
hash.c: from hash.c:7:
hash.c: hash.c: In function 'blake256_final':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:156:61: note: called from here
hash.c: 156 | __m128i w1 = _mm_load_si128((__m128i*)(&S->h[4])); w1 = _mm_shuffle_epi8(w1, u32to8);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:37,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:32,
hash.c: from hash.c:7:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:155:61: note: called from here
hash.c: 155 | __m128i w0 = _mm_load_si128((__m128i*)(&S->h[0])); w0 = _mm_shuffle_epi8(w0, u32to8);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:37,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:32,
hash.c: from hash.c:7:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
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	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: 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:4:
hash.c: hash.c: In function 'blake256_compress':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:107:8: note: called from here
hash.c: 107 | m3 = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 48)), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:4:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:106:8: note: called from here
hash.c: 106 | m2 = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 32)), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:4:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:105:8: note: called from here
hash.c: 105 | m1 = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 16)), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:4:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
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

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: 5, 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
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:37,
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/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:96:22: note: called from here
hash.c: 96 | const __m128i m3 = _mm_shuffle_epi8(LOADU(datablock + 48), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:37,
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/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:95:22: note: called from here
hash.c: 95 | const __m128i m2 = _mm_shuffle_epi8(LOADU(datablock + 32), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:37,
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: ...

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

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: ssse3
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from hash.c:4:
hash.c: hash.c: In function 'blake256_compress':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:108:15: note: called from here
hash.c: 108 | m.u128[3] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 48)), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:4:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:107:15: note: called from here
hash.c: 107 | m.u128[2] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 32)), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:4:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:106:15: note: called from here
hash.c: 106 | m.u128[1] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 16)), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:4:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	ssse3
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	ssse3
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	ssse3
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -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: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: 5, 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
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	xop