Implementation notes: amd64, icelake, crypto_hash/blake512

Computer: icelake
Architecture: amd64
CPU ID: GenuineIntel-000706e5-bfebfbff
SUPERCOP version: 20200826
Operation: crypto_hash
Primitive: blake512

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
7391	9755 0 0	24576 4096 0	`sse41`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
7397	9755 0 0	24576 4096 0	`sse41`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
7411	9649 0 0	20480 4096 0	`sse41`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
8294	9821 0 0	20480 4096 0	`sse2s`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
8313	9543 0 0	20480 4096 0	`ssse3`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
8315	9874 0 0	24576 4096 0	`sse2s`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
8319	9596 0 0	24576 4096 0	`ssse3`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
8321	9874 0 0	24576 4096 0	`sse2s`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
8327	9596 0 0	24576 4096 0	`ssse3`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
9485	10281 0 0	24576 4096 0	`sse2`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
9495	10281 0 0	24576 4096 0	`sse2`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
9506	10228 0 0	20480 4096 0	`sse2`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
9842	13794 0 0	24576 4096 0	`regs`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
9871	26790 0 0	40960 4096 0	`sphlib`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
9900	14813 0 0	28672 4096 0	`bswap`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
9903	12097 0 0	24576 4096 0	`sse41`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
9908	12097 0 0	28672 4096 0	`sse41`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
9936	14795 0 0	28672 4096 0	`regs`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
9956	13794 0 0	24576 4096 0	`bswap`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
9971	25290 0 0	36864 4096 0	`sphlib`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
10011	11315 0 0	24576 4096 0	`sse41`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
10041	28976 0 0	45056 4096 0	`sphlib`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
10112	13879 0 0	24576 4096 0	`sandy`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
10204	13693 0 0	24576 4096 0	`sandy`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10287	14300 0 0	28672 4096 0	`bswap`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
10295	13693 0 0	28672 4096 0	`sandy`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10297	14300 0 0	28672 4096 0	`regs`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
10324	13693 0 0	28672 4096 0	`sandy`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10382	6670 0 0	16384 4096 0	`sphlib-small`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10400	14700 0 0	28672 4096 0	`sandy`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
10405	7216 0 0	20480 4096 0	`sphlib-small`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10415	3687 0 0	16384 4096 0	`ref`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10427	3687 0 0	16384 4096 0	`ref`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10442	7184 0 0	20480 4096 0	`sphlib-small`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10527	8219 0 0	20480 4096 0	`bswap`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10540	8219 0 0	20480 4096 0	`bswap`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10575	8166 0 0	20480 4096 0	`bswap`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10631	3539 0 0	16384 4096 0	`ref`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10653	7583 0 0	20480 4096 0	`sphlib-small`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
10725	26864 0 0	40960 4096 0	`sphlib`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10734	26432 0 0	36864 4096 0	`sphlib`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
10736	15213 0 0	28672 4096 0	`sandy`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
10813	26832 0 0	40960 4096 0	`sphlib`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
11049	9260 0 0	24576 4096 0	`regs`	`clang_-march=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
11051	9260 0 0	24576 4096 0	`regs`	`clang_-march=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
11068	9207 0 0	20480 4096 0	`regs`	`clang_-march=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200826	20200826
11497	12980 0 0	24576 4096 0	`ssse3`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
11511	13475 0 0	28672 4096 0	`ssse3`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
11592	12557 0 0	24576 4096 0	`ssse3`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
12156	13444 0 0	24576 4096 0	`sse2s`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
12374	13561 0 0	24576 4096 0	`sse2s`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
12395	13939 0 0	28672 4096 0	`sse2s`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
13303	14915 0 0	28672 4096 0	`sse2`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
13309	14420 0 0	28672 4096 0	`sse2`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
13386	13720 0 0	24576 4096 0	`sse2`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
13469	11222 0 0	24576 4096 0	`sphlib-small`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
13532	3273 0 0	16384 4096 0	`ref`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
13715	11760 0 0	24576 4096 0	`sphlib-small`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
15126	6331 0 0	20480 4096 0	`ref`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826
15444	4731 0 0	16384 4096 0	`ref`	`opt-local-bin-gcc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200826	20200826

Compiler output

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

hash.c: In file included from hash.c:8:
hash.c: ./rounds.h:8:10: warning: '_mm_roti_epi64' macro redefined [-Wmacro-redefined]
hash.c: #define _mm_roti_epi64(x, c) \
hash.c: ^
hash.c: /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/lib/clang/11.0.3/include/xopintrin.h:236:9: note: previous definition is here
hash.c: #define _mm_roti_epi64(A, N) \
hash.c: ^
hash.c: 1 warning generated.

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
clang -march=icelake-client -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41
clang -march=icelake-client -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41
clang -march=icelake-client -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse41

Compiler output

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

hash.c: hash.c:81:8: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: m0 = BSWAP64(m0);
hash.c: ^
hash.c: ./rounds.h:13:21: note: expanded from macro 'BSWAP64'
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^
hash.c: hash.c:82:8: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: m1 = BSWAP64(m1);
hash.c: ^
hash.c: ./rounds.h:13:21: note: expanded from macro 'BSWAP64'
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^
hash.c: hash.c:83:8: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: m2 = BSWAP64(m2);
hash.c: ^
hash.c: ./rounds.h:13:21: note: expanded from macro 'BSWAP64'
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^
hash.c: hash.c:84:8: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: m3 = BSWAP64(m3);
hash.c: ^
hash.c: ./rounds.h:13:21: note: expanded from macro 'BSWAP64'
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^
hash.c: hash.c:85:8: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: ...

Number of similar (compiler,implementation) pairs: 3, namely:

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

Compiler output

Implementation: xop
Security model: constbranchindex
Compiler: opt-local-bin-gcc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from /opt/local/lib/gcc10/gcc/x86_64-apple-darwin19/10.2.0/include/x86intrin.h:38,
hash.c: from hash.c:5:
hash.c: hash.c: In function 'blake512_compress':
hash.c: /opt/local/lib/gcc10/gcc/x86_64-apple-darwin19/10.2.0/include/xopintrin.h:266:1: error: inlining failed in call to 'always_inline' '_mm_roti_epi64': target specific option mismatch
hash.c: 266 | _mm_roti_epi64(__m128i __A, const int __B)
hash.c: | ^~~~~~~~~~~~~~
hash.c: In file included from hash.c:8:
hash.c: rounds.h:825:11: note: called from here
hash.c: 825 | row2h = _mm_roti_epi64(row2h, -11); \
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: rounds.h:867:3: note: in expansion of macro 'G2'
hash.c: 867 | G2(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h,b0,b1); \
hash.c: | ^~
hash.c: hash.c:132:3: note: in expansion of macro 'ROUND'
hash.c: 132 | ROUND(15);
hash.c: | ^~~~~
hash.c: In file included from /opt/local/lib/gcc10/gcc/x86_64-apple-darwin19/10.2.0/include/x86intrin.h:38,
hash.c: from hash.c:5:
hash.c: /opt/local/lib/gcc10/gcc/x86_64-apple-darwin19/10.2.0/include/xopintrin.h:266:1: error: inlining failed in call to 'always_inline' '_mm_roti_epi64': target specific option mismatch
hash.c: 266 | _mm_roti_epi64(__m128i __A, const int __B)
hash.c: | ^~~~~~~~~~~~~~
hash.c: In file included from hash.c:8:
hash.c: rounds.h:824:11: note: called from here
hash.c: 824 | row2l = _mm_roti_epi64(row2l, -11); \
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: ...

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
opt-local-bin-gcc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop
opt-local-bin-gcc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop
opt-local-bin-gcc -march=icelake-client -mtune=icelake-client -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop

Compiler output

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

hash.c: hash.c:92:15: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: m.u128[0] = BSWAP64(m.u128[0]);
hash.c: ^
hash.c: ./rounds.h:15:21: note: expanded from macro 'BSWAP64'
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^
hash.c: hash.c:93:15: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: m.u128[1] = BSWAP64(m.u128[1]);
hash.c: ^
hash.c: ./rounds.h:15:21: note: expanded from macro 'BSWAP64'
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^
hash.c: hash.c:94:15: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: m.u128[2] = BSWAP64(m.u128[2]);
hash.c: ^
hash.c: ./rounds.h:15:21: note: expanded from macro 'BSWAP64'
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^
hash.c: hash.c:95:15: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: m.u128[3] = BSWAP64(m.u128[3]);
hash.c: ^
hash.c: ./rounds.h:15:21: note: expanded from macro 'BSWAP64'
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^
hash.c: hash.c:96:15: error: always_inline function '_mm_perm_epi8' requires target feature 'xop', but would be inlined into function 'blake512_compress' that is compiled without support for 'xop'
hash.c: ...

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
clang -march=icelake-client -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	xop-2
clang -march=icelake-client -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	xop-2
clang -march=icelake-client -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	xop-2

Compiler output

Implementation: xop-2
Security model: constbranchindex
Compiler: opt-local-bin-gcc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from /opt/local/lib/gcc10/gcc/x86_64-apple-darwin19/10.2.0/include/x86intrin.h:38,
hash.c: from hash.c:5:
hash.c: hash.c: In function 'blake512_compress':
hash.c: /opt/local/lib/gcc10/gcc/x86_64-apple-darwin19/10.2.0/include/xopintrin.h:212:1: error: inlining failed in call to 'always_inline' '_mm_perm_epi8': target specific option mismatch
hash.c: 212 | _mm_perm_epi8(__m128i __A, __m128i __B, __m128i __C)
hash.c: | ^~~~~~~~~~~~~
hash.c: In file included from hash.c:8:
hash.c: rounds.h:15:21: note: called from here
hash.c: 15 | #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c:99:15: note: in expansion of macro 'BSWAP64'
hash.c: 99 | m.u128[7] = BSWAP64(m.u128[7]);
hash.c: | ^~~~~~~
hash.c: In file included from /opt/local/lib/gcc10/gcc/x86_64-apple-darwin19/10.2.0/include/x86intrin.h:38,
hash.c: from hash.c:5:
hash.c: /opt/local/lib/gcc10/gcc/x86_64-apple-darwin19/10.2.0/include/xopintrin.h:212:1: error: inlining failed in call to 'always_inline' '_mm_perm_epi8': target specific option mismatch
hash.c: 212 | _mm_perm_epi8(__m128i __A, __m128i __B, __m128i __C)
hash.c: | ^~~~~~~~~~~~~
hash.c: In file included from hash.c:8:
hash.c: rounds.h:15:21: note: called from here
hash.c: 15 | #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c:98:15: note: in expansion of macro 'BSWAP64'
hash.c: 98 | m.u128[6] = BSWAP64(m.u128[6]);
hash.c: | ^~~~~~~
hash.c: ...

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
opt-local-bin-gcc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop-2
opt-local-bin-gcc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop-2
opt-local-bin-gcc -march=icelake-client -mtune=icelake-client -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	xop-2