Implementation notes: amd64, wolfdale, crypto_core/aes128decrypt

Computer: wolfdale
Microarchitecture: amd64; Core 2 45nm (1067a)
Architecture: amd64
CPU ID: GenuineIntel-0001067a-bfebfbff
SUPERCOP version: 20240107
Operation: crypto_core
Primitive: aes128decrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
613	12192 0 0	25240 780 984	`T:dolbeau/std-4rt-nodk`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
618	11524 0 0	23648 780 984	`T:dolbeau/std-4rt-nodk`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
647	5354 0 0	17488 780 984	`T:dolbeau/std-1rt-nodk`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
654	8070 0 0	21112 780 984	`T:dolbeau/std-2rt-nodk`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
654	11595 0 0	23287 772 984	`T:dolbeau/std-4rt-nodk`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
655	5396 0 0	16019 756 952	`T:dolbeau/std-1rt-nodk`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
661	6071 0 0	19112 780 984	`T:dolbeau/std-1rt-nodk`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
666	12112 0 0	26264 812 920	`T:dolbeau/std-4rt-nodk`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
683	12188 0 0	26072 812 920	`T:dolbeau/std-4rt-nodk`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
691	5360 0 0	17063 772 984	`T:dolbeau/std-1rt-nodk`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
696	11490 0 0	24824 812 920	`T:dolbeau/std-4rt-nodk`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
701	7466 0 0	18099 756 952	`T:dolbeau/std-2rt-nodk`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
702	7381 0 0	19504 780 984	`T:dolbeau/std-2rt-nodk`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
702	7408 0 0	19111 772 984	`T:dolbeau/std-2rt-nodk`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
733	11563 0 0	22195 756 952	`T:dolbeau/std-4rt-nodk`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
737	5367 0 0	18696 812 920	`T:dolbeau/std-1rt-nodk`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
742	6004 0 0	20152 812 920	`T:dolbeau/std-1rt-nodk`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
742	6073 0 0	19960 812 920	`T:dolbeau/std-1rt-nodk`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
746	5439 0 0	16558 804 920	`T:dolbeau/std-1rt-nodk`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
748	11862 0 0	23542 804 920	`T:dolbeau/std-4rt-nodk`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
750	11691 0 0	22814 804 920	`T:dolbeau/std-4rt-nodk`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
757	7601 0 0	18718 804 920	`T:dolbeau/std-2rt-nodk`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
760	8148 0 0	22296 812 920	`T:dolbeau/std-2rt-nodk`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
769	7494 0 0	20824 812 920	`T:dolbeau/std-2rt-nodk`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
775	8198 0 0	22072 812 920	`T:dolbeau/std-2rt-nodk`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
976	140 0 0	13650 828 920	`T:openssl`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
979	140 0 0	11432 820 920	`T:openssl`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
981	140 0 0	14466 828 920	`T:openssl`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
981	138 0 0	12451 812 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
983	138 0 0	13387 812 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
983	140 0 0	10934 788 952	`T:openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
984	140 0 0	11968 820 920	`T:openssl`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
986	140 0 0	14194 828 920	`T:openssl`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
993	139 0 0	12010 804 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
1017	5855 0 0	17542 804 920	`T:dolbeau/std-1rt-nodk`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
1021	7966 0 0	19654 804 920	`T:dolbeau/std-2rt-nodk`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
342390	5726 0 0	18792 780 984	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
522988	2768 0 0	16088 812 920	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
553288	6168 0 0	20016 812 920	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
557134	6008 0 0	20144 812 920	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
668868	2531 0 0	13622 804 920	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
826092	2362 0 0	14014 804 920	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
957459	2195 0 0	14296 780 984	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
1004302	2133 0 0	13799 772 984	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
1643611	1854 0 0	12435 756 952	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212

Compiler output

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

core.c: core.c:49:16: error: always_inline function '_mm_aesimc_si128' requires target feature 'aes', but would be inlined into function 'aes128ni_setkey_decrypt' that is compiled without support for 'aes'
core.c: rkeys[i] = _mm_aesimc_si128(tkeys[10-i]);
core.c: ^
core.c: core.c:29:3: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
core.c: BLOCK1(0x01);
core.c: ^
core.c: core.c:20:11: note: expanded from macro 'BLOCK1'
core.c: temp1 = _mm_aeskeygenassist_si128(temp0, IMM); \
core.c: ^
core.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/__wmmintrin_aes.h:136:12: note: expanded from macro '_mm_aeskeygenassist_si128'
core.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
core.c: ^
core.c: core.c:30:3: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
core.c: BLOCK1(0x02);
core.c: ^
core.c: core.c:20:11: note: expanded from macro 'BLOCK1'
core.c: temp1 = _mm_aeskeygenassist_si128(temp0, IMM); \
core.c: ^
core.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/__wmmintrin_aes.h:136:12: note: expanded from macro '_mm_aeskeygenassist_si128'
core.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
core.c: ^
core.c: core.c:31:3: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
core.c: BLOCK1(0x04);
core.c: ^
core.c: core.c:20:11: note: expanded from macro 'BLOCK1'
core.c: ...

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

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

Compiler output

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

core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:39,
core.c: from core.c:9:
core.c: core.c: In function 'aes128ni_setkey_encrypt':
core.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/wmmintrin.h:87:1: error: inlining failed in call to 'always_inline' '_mm_aeskeygenassist_si128': target specific option mismatch
core.c: 87 | _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:20:11: note: called from here
core.c: 20 | temp1 = _mm_aeskeygenassist_si128(temp0, IMM); \
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:38:3: note: in expansion of macro 'BLOCK1'
core.c: 38 | BLOCK1(0x36);
core.c: | ^~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:39,
core.c: from core.c:9:
core.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/wmmintrin.h:87:1: error: inlining failed in call to 'always_inline' '_mm_aeskeygenassist_si128': target specific option mismatch
core.c: 87 | _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:20:11: note: called from here
core.c: 20 | temp1 = _mm_aeskeygenassist_si128(temp0, IMM); \
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:37:3: note: in expansion of macro 'BLOCK1'
core.c: 37 | BLOCK1(0x1b);
core.c: | ^~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:39,
core.c: from core.c:9:
core.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int