Implementation notes: amd64, gcc14, crypto_core/aes256encrypt

Computer: gcc14
Architecture: amd64
CPU ID: GenuineIntel-00010676-bfebfbff
SUPERCOP version: 20220506
Operation: crypto_core
Primitive: aes256encrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
616	6230 0 0	18661 836 944	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
625	6127 0 0	19251 820 912	`T:dolbeau/std-4ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
625	6229 0 0	20622 844 944	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
626	6100 0 0	17309 812 912	`T:dolbeau/std-4ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
629	6260 0 0	18381 836 944	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
630	4091 0 0	16443 820 912	`T:dolbeau/std-2ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
630	6111 0 0	19395 820 912	`T:dolbeau/std-4ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
631	6111 0 0	18459 820 912	`T:dolbeau/std-4ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
632	4068 0 0	15277 812 912	`T:dolbeau/std-2ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
633	4091 0 0	16443 820 912	`T:dolbeau/std-2ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
634	3208 0 0	15637 836 944	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
635	4107 0 0	17235 820 912	`T:dolbeau/std-2ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
635	6111 0 0	18459 820 912	`T:dolbeau/std-4ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
645	3078 0 0	16211 820 912	`T:dolbeau/std-1ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
646	3194 0 0	17598 844 944	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
646	4091 0 0	17379 820 912	`T:dolbeau/std-2ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
649	3062 0 0	15419 820 912	`T:dolbeau/std-1ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
649	3062 0 0	16355 820 912	`T:dolbeau/std-1ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
649	3062 0 0	15419 820 912	`T:dolbeau/std-1ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
650	4207 0 0	16645 836 944	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
651	4191 0 0	18590 844 944	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
655	3051 0 0	14253 812 912	`T:dolbeau/std-1ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
659	4249 0 0	15329 820 944	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
666	3194 0 0	14273 820 944	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
670	4222 0 0	16349 836 944	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
684	3189 0 0	15325 836 944	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
748	6344 0 0	17425 820 944	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
976	137 0 0	12681 836 912	`T:openssl`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
976	137 0 0	12681 836 912	`T:openssl`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
977	137 0 0	11531 828 912	`T:openssl`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
977	137 0 0	13457 836 912	`T:openssl`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
977	143 0 0	11367 836 944	`T:openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
980	138 0 0	14740 860 944	`T:openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
982	137 0 0	13617 836 912	`T:openssl`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
986	141 0 0	12451 852 944	`T:openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
987	138 0 0	12763 852 944	`T:openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
455043	3996 0 0	18414 844 944	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
647120	2926 0 0	16203 820 912	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
650319	2926 0 0	16043 820 912	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
657895	2926 0 0	15267 820 912	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
662647	2926 0 0	15267 820 912	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
961201	1578 0 0	12781 812 912	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210114	20210114
1194194	1690 0 0	13813 836 944	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
1225863	1539 0 0	12569 820 944	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114
1234769	1796 0 0	14229 836 944	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210114	20210114

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:43:3: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
core.c: BLOCK1(0x01);
core.c: ^
core.c: core.c:24:11: note: expanded from macro 'BLOCK1'
core.c: temp1 = _mm_aeskeygenassist_si128(temp2, IMM); \
core.c: ^
core.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/__wmmintrin_aes.h:62:12: note: expanded from macro '_mm_aeskeygenassist_si128'
core.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
core.c: ^
core.c: core.c:44:3: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
core.c: BLOCK2(0x01);
core.c: ^
core.c: core.c:34:11: note: expanded from macro 'BLOCK2'
core.c: temp1 = _mm_aeskeygenassist_si128(temp0, IMM); \
core.c: ^
core.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/__wmmintrin_aes.h:62:12: note: expanded from macro '_mm_aeskeygenassist_si128'
core.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
core.c: ^
core.c: core.c:46:3: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
core.c: BLOCK1(0x02);
core.c: ^
core.c: core.c:24:11: note: expanded from macro 'BLOCK1'
core.c: temp1 = _mm_aeskeygenassist_si128(temp2, IMM); \
core.c: ^
core.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/__wmmintrin_aes.h:62:12: note: expanded from macro '_mm_aeskeygenassist_si128'
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/6/include/immintrin.h:39:0,
core.c: from core.c:9:
core.c: core.c: In function 'aes256ni_setkey_encrypt':
core.c: /usr/lib/gcc/x86_64-linux-gnu/6/include/wmmintrin.h:87:1: error: inlining failed in call to always_inline '_mm_aeskeygenassist_si128': target specific option mismatch
core.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
core.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:24:9: note: called from here
core.c: temp1 = _mm_aeskeygenassist_si128(temp2, IMM); \
core.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:61:3: note: in expansion of macro 'BLOCK1'
core.c: BLOCK1(0x40);
core.c: ^~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/6/include/immintrin.h:39:0,
core.c: from core.c:9:
core.c: /usr/lib/gcc/x86_64-linux-gnu/6/include/wmmintrin.h:87:1: error: inlining failed in call to always_inline '_mm_aeskeygenassist_si128': target specific option mismatch
core.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
core.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:34:9: note: called from here
core.c: temp1 = _mm_aeskeygenassist_si128(temp0, IMM); \
core.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:59:3: note: in expansion of macro 'BLOCK2'
core.c: BLOCK2(0x20);
core.c: ^~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/6/include/immintrin.h:39:0,
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