Implementation notes: amd64, dali, crypto_core/aes256encrypt

Computer: dali
Microarchitecture: amd64; Zen (820f01)
Architecture: amd64
CPU ID: AuthenticAMD-00820f01-178bfbff
SUPERCOP version: 20240625
Operation: crypto_core
Primitive: aes256encrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
75	606 0 0	13656 780 984	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
76	575 0 0	14160 812 952	`dolbeau/aesenc-int`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
76	575 0 0	11838 804 920	`dolbeau/aesenc-int`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
77	575 0 0	14288 812 952	`dolbeau/aesenc-int`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
92	838 0 0	12390 804 920	`dolbeau/aesenc-int`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
93	646 0 0	12688 780 984	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
94	633 0 0	11323 756 952	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
96	635 0 0	12351 772 984	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
450	6144 0 0	17430 804 920	`T:dolbeau/std-4ft`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
451	6237 0 0	19312 780 984	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
452	6098 0 0	19832 812 952	`T:dolbeau/std-4ft`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
453	6098 0 0	19704 812 952	`T:dolbeau/std-4ft`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
455	6239 0 0	18320 780 984	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
463	6259 0 0	18015 772 984	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
464	6132 0 0	20064 812 920	`T:dolbeau/std-4ft`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
479	6391 0 0	17966 804 920	`T:dolbeau/std-4ft`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
484	4228 0 0	17296 780 984	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
486	3239 0 0	16304 780 984	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
489	4230 0 0	16304 780 984	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
493	4128 0 0	18064 812 920	`T:dolbeau/std-2ft`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
494	3173 0 0	13899 756 952	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
500	4258 0 0	16015 772 984	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
525	3233 0 0	15312 780 984	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
536	3265 0 0	15007 772 984	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
548	4276 0 0	15003 756 952	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
548	145 0 0	14070 828 952	`T:openssl`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
549	145 0 0	11636 820 920	`T:openssl`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
554	145 0 0	11884 820 920	`T:openssl`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
555	145 0 0	13942 828 952	`T:openssl`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
556	145 0 0	14270 828 920	`T:openssl`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
560	143 0 0	13431 812 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
561	144 0 0	12086 804 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
564	143 0 0	12423 812 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
564	145 0 0	11042 788 952	`T:openssl`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
571	6275 0 0	17003 756 952	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
608	3153 0 0	16760 812 952	`T:dolbeau/std-1ft`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
608	4187 0 0	15462 804 920	`T:dolbeau/std-2ft`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
609	4148 0 0	17880 812 952	`T:dolbeau/std-2ft`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
612	4148 0 0	17752 812 952	`T:dolbeau/std-2ft`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
614	3208 0 0	14486 804 920	`T:dolbeau/std-1ft`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
618	3153 0 0	16888 812 952	`T:dolbeau/std-1ft`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
666	3197 0 0	17136 812 920	`T:dolbeau/std-1ft`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
788	4559 0 0	16134 804 920	`T:dolbeau/std-2ft`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
1000	3551 0 0	15126 804 920	`T:dolbeau/std-1ft`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
225820	3874 0 0	16952 780 984	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
381151	3002 0 0	16608 812 952	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
399155	3908 0 0	17624 812 952	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
403221	3880 0 0	17792 812 920	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
683387	1794 0 0	13342 804 920	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
850239	1767 0 0	13046 804 920	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
863908	1828 0 0	13559 772 984	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
875799	1936 0 0	13992 780 984	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
1180049	1607 0 0	12291 756 952	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625

Compiler output

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-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: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-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: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-11/lib/clang/11.0.1/include/__wmmintrin_aes.h:136:12: note: expanded from macro '_mm_aeskeygenassist_si128'
core.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`dolbeau/aesenc-int`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

core.c: core.c: In function 'aes256ni_encrypt':
core.c: core.c:69: warning: ignoring '#pragma unroll ' [-Wunknown-pragmas]
core.c:    69 | #pragma unroll(13)
core.c:       |

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

Implementation	Compiler
`dolbeau/aesenc-int`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`dolbeau/aesenc-int`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`dolbeau/aesenc-int`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`dolbeau/aesenc-int`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

Compiler output

core.c: In file included from core.c:9:
core.c: stdaes-common.h:548:21: warning: 'KT3' defined but not used [-Wunused-variable]
core.c:   548 | static unsigned int KT3[256] = KT0Data;
core.c:       |                     ^~~
core.c: stdaes-common.h:541:21: warning: 'KT2' defined but not used [-Wunused-variable]
core.c:   541 | static unsigned int KT2[256] = KT0Data;
core.c:       |                     ^~~
core.c: stdaes-common.h:534:21: warning: 'KT1' defined but not used [-Wunused-variable]
core.c:   534 | static unsigned int KT1[256] = KT0Data;
core.c:       |                     ^~~
core.c: stdaes-common.h:527:21: warning: 'KT0' defined but not used [-Wunused-variable]
core.c:   527 | static unsigned int KT0[256] = KT0Data;
core.c:       |                     ^~~
core.c: stdaes-common.h:450:21: warning: 'RT3' defined but not used [-Wunused-variable]
core.c:   450 | static unsigned int RT3[256] = { RT };
core.c:       |                     ^~~
core.c: stdaes-common.h:443:21: warning: 'RT2' defined but not used [-Wunused-variable]
core.c:   443 | static unsigned int RT2[256] = { RT };
core.c:       |                     ^~~
core.c: stdaes-common.h:436:21: warning: 'RT1' defined but not used [-Wunused-variable]
core.c:   436 | static unsigned int RT1[256] = { RT };
core.c:       |                     ^~~
core.c: stdaes-common.h:429:21: warning: 'RT0' defined but not used [-Wunused-variable]
core.c:   429 | static unsigned int RT0[256] = { RT };
core.c:       |                     ^~~
core.c: ...

Number of similar (implementation,compiler) pairs: 12, namely:

Implementation	Compiler
`T:dolbeau/std-1ft`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-1ft`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-1ft`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-1ft`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-2ft`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-2ft`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-2ft`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-2ft`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-4ft`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-4ft`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-4ft`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/std-4ft`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

Passed TIMECOP

TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 17, namely:

Implementation	Compiler
`dolbeau/aesenc-int`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`dolbeau/aesenc-int`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`dolbeau/aesenc-int`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`dolbeau/aesenc-int`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`dolbeau/aesenc-int`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`dolbeau/aesenc-int`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`dolbeau/aesenc-int`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`dolbeau/aesenc-int`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`