Implementation notes: amd64, renoir, crypto_core/aes256encrypt

Computer: renoir
Microarchitecture: amd64; Zen 2 (860f01)
Architecture: amd64
CPU ID: AuthenticAMD-00860f01-178bfbff
SUPERCOP version: 20240625
Operation: crypto_core
Primitive: aes256encrypt
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
68575 0 014160 812 952dolbeau/aesenc-intclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
68575 0 014288 812 952dolbeau/aesenc-intclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
68575 0 011838 804 920dolbeau/aesenc-intclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
73606 0 014328 780 984dolbeau/aesenc-intgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
86838 0 012390 804 920dolbeau/aesenc-intclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
89646 0 012672 780 984dolbeau/aesenc-intgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
90633 0 011323 756 952dolbeau/aesenc-intgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
92635 0 012351 772 984dolbeau/aesenc-intgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4286098 0 019832 812 952T:dolbeau/std-4ftclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4306098 0 019704 812 952T:dolbeau/std-4ftclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4326144 0 017430 804 920T:dolbeau/std-4ftclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4386263 0 019984 780 984T:dolbeau/std-4ftgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4406239 0 018304 780 984T:dolbeau/std-4ftgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4476132 0 020064 812 920T:dolbeau/std-4ftclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4506259 0 018015 772 984T:dolbeau/std-4ftgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4526391 0 017966 804 920T:dolbeau/std-4ftclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4564128 0 018064 812 920T:dolbeau/std-2ftclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4644230 0 016288 780 984T:dolbeau/std-2ftgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4753233 0 015296 780 984T:dolbeau/std-1ftgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4783218 0 016944 780 984T:dolbeau/std-1ftgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4803173 0 013899 756 952T:dolbeau/std-1ftgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4854258 0 016015 772 984T:dolbeau/std-2ftgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
4934276 0 015003 756 952T:dolbeau/std-2ftgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5203265 0 015007 772 984T:dolbeau/std-1ftgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
521144 0 012086 804 952T:opensslgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
527143 0 012407 812 952T:opensslgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
530145 0 011042 788 952T:opensslgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
535145 0 014070 828 952T:opensslclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
535145 0 014270 828 920T:opensslclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
538145 0 011636 820 920T:opensslclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
538143 0 014103 812 952T:opensslgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
540145 0 013942 828 952T:opensslclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
542145 0 011884 820 920T:opensslclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5456275 0 017003 756 952T:dolbeau/std-4ftgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5484231 0 017952 780 984T:dolbeau/std-2ftgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5853153 0 016760 812 952T:dolbeau/std-1ftclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5854148 0 017880 812 952T:dolbeau/std-2ftclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5874187 0 015462 804 920T:dolbeau/std-2ftclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5903208 0 014486 804 920T:dolbeau/std-1ftclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5924148 0 017752 812 952T:dolbeau/std-2ftclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5973153 0 016888 812 952T:dolbeau/std-1ftclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
6103197 0 017136 812 920T:dolbeau/std-1ftclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
7684559 0 016134 804 920T:dolbeau/std-2ftclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
9933551 0 015126 804 920T:dolbeau/std-1ftclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
2089763874 0 017624 780 984refgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
3321513002 0 016608 812 952refclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
3572483880 0 017792 812 920refclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
3938593908 0 017624 812 952refclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
5694831794 0 013342 804 920refclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
7461751936 0 013976 780 984refgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
7952801828 0 013559 772 984refgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
8026751767 0 013046 804 920refclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625
11376511607 0 012291 756 952refgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062520240625

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:
ImplementationCompiler
dolbeau/aesenc-intclang -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:
ImplementationCompiler
dolbeau/aesenc-intgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
dolbeau/aesenc-intgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
dolbeau/aesenc-intgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
dolbeau/aesenc-intgcc -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:
ImplementationCompiler
T:dolbeau/std-1ftgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-1ftgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-1ftgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-1ftgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-2ftgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-2ftgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-2ftgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-2ftgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-4ftgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-4ftgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-4ftgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:dolbeau/std-4ftgcc -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:
ImplementationCompiler
dolbeau/aesenc-intclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
dolbeau/aesenc-intclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
dolbeau/aesenc-intclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
dolbeau/aesenc-intclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
dolbeau/aesenc-intgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
dolbeau/aesenc-intgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
dolbeau/aesenc-intgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
dolbeau/aesenc-intgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)