Implementation notes: amd64, cherry, crypto_core/aes128encrypt

Computer: cherry
Microarchitecture: amd64; Silvermont (406c4)
Architecture: amd64
CPU ID: GenuineIntel-000406c4-bfebfbff
SUPERCOP version: 20240716
Operation: crypto_core
Primitive: aes128encrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
230	527 0 0	13136 812 920	`dolbeau/aesenc-int`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
230	527 0 0	14784 812 920	`dolbeau/aesenc-int`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
230	527 0 0	11622 804 920	`dolbeau/aesenc-int`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
255	618 0 0	13880 780 984	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
261	529 0 0	11163 756 952	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
262	599 0 0	12688 780 984	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
279	770 0 0	12406 804 920	`dolbeau/aesenc-int`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
284	597 0 0	12287 772 984	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
585	6125 0 0	17246 804 920	`T:dolbeau/std-4ft`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
590	6836 0 0	20736 812 920	`T:dolbeau/std-4ft`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
592	6100 0 0	18744 812 920	`T:dolbeau/std-4ft`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
618	6186 0 0	18336 780 984	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
618	6922 0 0	20224 780 984	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
642	6830 0 0	21128 812 920	`T:dolbeau/std-4ft`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
642	6201 0 0	17935 772 984	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
669	6186 0 0	16859 756 952	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
673	4883 0 0	18176 780 984	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
680	4147 0 0	16288 780 984	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
700	4721 0 0	19016 812 920	`T:dolbeau/std-2ft`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
704	4100 0 0	16744 812 920	`T:dolbeau/std-2ft`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
704	4732 0 0	18640 812 920	`T:dolbeau/std-2ft`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
718	4169 0 0	15903 772 984	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
725	4085 0 0	15214 804 920	`T:dolbeau/std-2ft`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
737	6406 0 0	18078 804 920	`T:dolbeau/std-4ft`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
744	3676 0 0	17584 812 920	`T:dolbeau/std-1ft`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
747	3865 0 0	17168 780 984	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
748	3746 0 0	18040 812 920	`T:dolbeau/std-1ft`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
754	3160 0 0	15296 780 984	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
767	4165 0 0	14827 756 952	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
772	3092 0 0	13755 756 952	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
780	3172 0 0	14911 772 984	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
836	140 0 0	11432 820 920	`T:openssl`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
839	140 0 0	14610 828 920	`T:openssl`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
839	140 0 0	12467 812 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
839	141 0 0	12066 804 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
840	140 0 0	12962 828 920	`T:openssl`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
841	142 0 0	10958 788 952	`T:openssl`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
842	140 0 0	11960 820 920	`T:openssl`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
844	140 0 0	13635 812 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
857	140 0 0	14218 828 920	`T:openssl`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
1034	3190 0 0	14318 804 920	`T:dolbeau/std-1ft`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
1036	3170 0 0	15816 812 920	`T:dolbeau/std-1ft`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
1224	4559 0 0	16230 804 920	`T:dolbeau/std-2ft`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
1347	3583 0 0	15254 804 920	`T:dolbeau/std-1ft`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
360061	3283 0 0	16576 780 984	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
475129	2698 0 0	15312 812 920	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
509158	3689 0 0	17960 812 920	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
553777	3688 0 0	17552 812 920	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
726024	1521 0 0	12630 804 920	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
1071135	1730 0 0	13358 804 920	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
1288527	1783 0 0	13888 780 984	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
1385923	1715 0 0	13431 772 984	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
1406082	1469 0 0	12075 756 952	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716

Compiler output

core.c: core.c:13:25: warning: unused variable 'temp2' [-Wunused-variable]
core.c:   __m128i temp0, temp1, temp2, temp4;
core.c:                         ^
core.c: 1 warning generated.

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

Compiler output

core.c: core.c:13:25: warning: unused variable 'temp2' [-Wunused-variable]
core.c:   __m128i temp0, temp1, temp2, temp4;
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 (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 'aes128ni_setkey_encrypt':
core.c: core.c:13:25: warning: unused variable 'temp2' [-Wunused-variable]
core.c:    13 |   __m128i temp0, temp1, temp2, temp4;
core.c:       |                         ^~~~~
core.c: core.c: In function 'aes128ni_encrypt':
core.c: core.c:46: warning: ignoring '#pragma unroll ' [-Wunknown-pragmas]
core.c:    46 | #pragma unroll(9)
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)`