Implementation notes: amd64, rome0, crypto_core/aes128encrypt

Computer: rome0
Microarchitecture: amd64; Zen 2 (830f10)
Architecture: amd64
CPU ID: AuthenticAMD-00830f10-178bfbff
SUPERCOP version: 20240716
Operation: crypto_core
Primitive: aes128encrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
57	459 0 0	14184 780 984	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
58	449 0 0	14048 812 952	`dolbeau/aesenc-int`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
58	449 0 0	14176 812 952	`dolbeau/aesenc-int`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
59	449 0 0	11710 804 920	`dolbeau/aesenc-int`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
66	505 0 0	11195 756 952	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
67	518 0 0	12544 780 984	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
69	507 0 0	12207 772 984	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
70	658 0 0	12214 804 920	`dolbeau/aesenc-int`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
326	6752 0 0	20488 812 952	`T:dolbeau/std-4ft`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
333	6072 0 0	19672 812 952	`T:dolbeau/std-4ft`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
340	6836 0 0	20768 812 920	`T:dolbeau/std-4ft`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
340	6193 0 0	18256 780 984	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
342	6917 0 0	20640 780 984	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
349	6211 0 0	17967 772 984	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
353	4732 0 0	18672 812 920	`T:dolbeau/std-2ft`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
355	6391 0 0	17966 804 920	`T:dolbeau/std-4ft`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
357	3676 0 0	17616 812 920	`T:dolbeau/std-1ft`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
362	3117 0 0	13851 756 952	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
363	6187 0 0	16907 756 952	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
364	6175 0 0	17462 804 920	`T:dolbeau/std-4ft`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
365	4177 0 0	16240 780 984	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
365	4850 0 0	18576 780 984	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
367	4203 0 0	15951 772 984	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
377	3864 0 0	17584 780 984	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
387	3191 0 0	15248 780 984	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
393	3200 0 0	14943 772 984	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
398	4172 0 0	14907 756 952	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
401	140 0 0	13938 828 952	`T:openssl`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
403	140 0 0	14250 828 920	`T:openssl`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
404	140 0 0	11616 820 920	`T:openssl`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
404	139 0 0	12066 804 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
404	140 0 0	11022 788 952	`T:openssl`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
406	138 0 0	12403 812 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
408	138 0 0	14099 812 952	`T:openssl`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
410	140 0 0	14066 828 952	`T:openssl`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
413	140 0 0	11880 820 920	`T:openssl`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
417	4698 0 0	18440 812 952	`T:dolbeau/std-2ft`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
424	4122 0 0	17736 812 952	`T:dolbeau/std-2ft`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
427	4143 0 0	15430 804 920	`T:dolbeau/std-2ft`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
431	3759 0 0	17496 812 952	`T:dolbeau/std-1ft`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
437	3135 0 0	16744 812 952	`T:dolbeau/std-1ft`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
451	3151 0 0	14438 804 920	`T:dolbeau/std-1ft`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
577	4559 0 0	16134 804 920	`T:dolbeau/std-2ft`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
728	3551 0 0	15126 804 920	`T:dolbeau/std-1ft`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
151257	3683 0 0	17432 780 984	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
232406	3688 0 0	17584 812 920	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
240300	2762 0 0	16368 812 952	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
285262	3716 0 0	17432 812 952	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
412695	1730 0 0	13278 804 920	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
538613	1873 0 0	13928 780 984	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
576404	1772 0 0	13495 772 984	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
581278	1704 0 0	12982 804 920	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625
824430	1539 0 0	12211 756 952	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240625	20240625

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)`