Implementation notes: amd64, h3neo, crypto_aead/romulust

Computer: h3neo
Microarchitecture: amd64; K10 45nm (100f63)
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20240425
Operation: crypto_aead
Primitive: romulust

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
3343731	30957 640 0	46811 1492 1024	`aadomn/opt32`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
3408610	30065 640 0	44371 1492 1024	`aadomn/opt32`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
3452019	31169 640 0	46419 1492 1024	`aadomn/opt32`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
3984323	24138 640 0	38187 1492 1024	`aadomn/opt32`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
4019533	20802 640 0	36525 1452 1088	`aadomn/opt32`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240503	20240425
4489245	19489 640 0	34340 1444 1088	`aadomn/opt32`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240503	20240425
4759361	20264 640 0	33848 1428 1056	`aadomn/opt32`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240503	20240425
4852043	20151 640 0	33373 1484 1024	`aadomn/opt32`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
5102027	34703 640 0	51781 1452 1088	`aadomn/opt32`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240503	20240425
6916883	10091 12 0	26595 856 1024	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
8717781	13630 12 0	30605 816 1088	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240503	20240425
10149113	10020 12 0	24971 856 1024	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
10165010	10235 12 0	26123 856 1024	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
26944497	5239 12 0	18549 848 1024	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
27620941	8232 12 0	22251 856 1024	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240503	20240425
30610494	7347 12 0	23013 816 1088	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240503	20240425
32412042	6171 12 0	20900 808 1088	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240503	20240425
34622250	5568 12 0	19048 792 1056	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240503	20240425

Compiler output

Implementation: aadomn/x86
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

skinny128.c: skinny128.c:95:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: tk_1 = _mm_shuffle_epi8(tk_1, _mm_set_epi32(0x03040602, 0x05000701, 0x0b0c0e0a, 0x0d080f09));
skinny128.c: ^
skinny128.c: skinny128.c:97:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: tk_1 = _mm_shuffle_epi8(tk_1, perm_tk);
skinny128.c: ^
skinny128.c: skinny128.c:99:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: tk_1 = _mm_shuffle_epi8(tk_1, perm_tk);
skinny128.c: ^
skinny128.c: skinny128.c:101:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: tk_1 = _mm_shuffle_epi8(tk_1, perm_tk);
skinny128.c: ^
skinny128.c: skinny128.c:103:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: tk_1 = _mm_shuffle_epi8(tk_1, perm_tk);
skinny128.c: ^
skinny128.c: skinny128.c:105:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: tk_1 = _mm_shuffle_epi8(tk_1, perm_tk);
skinny128.c: ^
skinny128.c: skinny128.c:107:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: tk_1 = _mm_shuffle_epi8(tk_1, perm_tk);
skinny128.c: ^
skinny128.c: skinny128.c:109:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: tk_1 = _mm_shuffle_epi8(tk_1, perm_tk);
skinny128.c: ^
skinny128.c: skinny128.c:113:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: ...

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	aadomn/x86
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	aadomn/x86
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	aadomn/x86
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	aadomn/x86
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	aadomn/x86

Compiler output

Implementation: aadomn/x86
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

skinny128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:37,
skinny128.c: from skinny128.c:10:
skinny128.c: skinny128.c: In function 'skinny128_384_plus':
skinny128.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
skinny128.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
skinny128.c: | ^~~~~~~~~~~~~~~~
skinny128.c: skinny128.c:46:13: note: called from here
skinny128.c: 46 | state = _mm_shuffle_epi8(state, m1); /* state <- (r2, - , r2, r0) */ \
skinny128.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~
skinny128.c: skinny128.c:57:5: note: in expansion of macro 'SR_MC'
skinny128.c: 57 | SR_MC(); \
skinny128.c: | ^~~~~
skinny128.c: skinny128.c:132:5: note: in expansion of macro 'DOUBLE_ROUND'
skinny128.c: 132 | DOUBLE_ROUND(rtk_1+48, rtk_23+304);
skinny128.c: | ^~~~~~~~~~~~
skinny128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:37,
skinny128.c: from skinny128.c:10:
skinny128.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
skinny128.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
skinny128.c: | ^~~~~~~~~~~~~~~~
skinny128.c: skinny128.c:44:14: note: called from here
skinny128.c: 44 | tmp0 = _mm_shuffle_epi8(state, m0); /* tmp0 <- (r3, r0, r1, r2) */ \
skinny128.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~
skinny128.c: skinny128.c:57:5: note: in expansion of macro 'SR_MC'
skinny128.c: 57 | SR_MC(); \
skinny128.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	aadomn/x86
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	aadomn/x86
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	aadomn/x86
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	aadomn/x86