Test results for amd64, hunsnivy, crypto_core/rainbowcalsecret363232

[Page version: 20250427 16:10:44]

Measurements for amd64, hunsnivy, crypto_core Test results for amd64, hunsnivy, crypto_core Test results for crypto_core/rainbowcalsecret363232

Computer: hunsnivy
Microarchitecture: amd64; Ivy Bridge+AES (306a9)
Architecture: amd64
CPU ID: GenuineIntel-000306a9-bfebfbff
SUPERCOP version: 20250415
Operation: crypto_core
Primitive: rainbowcalsecret363232

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
2838007	33452 8 0	45224 788 984	`ssse3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
3145362	42719 8 0	54680 788 984	`ssse3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
3166171	55382 8 0	68144 820 920	`ssse3`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
3263403	45172 8 0	57736 788 984	`ssse3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
3286942	64173 8 0	78616 820 920	`ssse3`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
3500373	45607 8 0	56318 812 920	`ssse3`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
5926929	22929 8 0	33707 764 952	`ssse3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
7648397	25572 8 0	37270 812 920	`ssse3`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
9061437	30957 0 0	43616 812 920	`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
10565820	29114 0 0	42304 812 920	`amd64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
11501291	31587 0 0	44104 812 920	`amd64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
11615524	31940 0 0	46144 812 920	`amd64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
11825223	19185 0 0	30190 804 920	`amd64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
12055583	31850 0 0	43800 780 984	`amd64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
12119085	36604 0 0	49152 780 984	`amd64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
13057824	27978 0 0	39656 780 984	`amd64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
15426480	34463 0 0	45640 812 920	`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
15800223	34591 0 0	47456 812 920	`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
17878138	21194 0 0	33776 780 984	`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
17925113	16372 0 0	28368 780 984	`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
18398236	18336 0 0	29342 804 920	`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
21091256	16220 0 0	27928 780 984	`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
21464213	10582 0 0	21251 756 952	`amd64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
30977329	9616 0 0	20299 756 952	`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
48989754	12046 0 0	23646 804 920	`amd64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415
63544206	10744 0 0	22342 804 920	`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250417	20250415

Compiler output

parallel_matrix_op.c: In file included from parallel_matrix_op.c:8:
parallel_matrix_op.c: In file included from ./blas.h:25:
parallel_matrix_op.c: ./blas_avx2.h:121:15: error: '__builtin_ia32_permti256' needs target feature avx2
parallel_matrix_op.c:         __m256i ml = _mm256_permute2x128_si256( m_tab , m_tab , 0 );
parallel_matrix_op.c:                      ^
parallel_matrix_op.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:821:12: note: expanded from macro '_mm256_permute2x128_si256'
parallel_matrix_op.c:   (__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M))
parallel_matrix_op.c:            ^
parallel_matrix_op.c: In file included from parallel_matrix_op.c:8:
parallel_matrix_op.c: In file included from ./blas.h:25:
parallel_matrix_op.c: ./blas_avx2.h:122:15: error: '__builtin_ia32_permti256' needs target feature avx2
parallel_matrix_op.c:         __m256i mh = _mm256_permute2x128_si256( m_tab , m_tab , 0x11 );
parallel_matrix_op.c:                      ^
parallel_matrix_op.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:821:12: note: expanded from macro '_mm256_permute2x128_si256'
parallel_matrix_op.c:   (__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M))
parallel_matrix_op.c:            ^
parallel_matrix_op.c: In file included from parallel_matrix_op.c:8:
parallel_matrix_op.c: In file included from ./blas.h:25:
parallel_matrix_op.c: In file included from ./blas_avx2.h:15:
parallel_matrix_op.c: ./gf16_avx2.h:29:9: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'linear_transform_8x8_256b' that is compiled without support for 'avx2'
parallel_matrix_op.c:         return _mm256_shuffle_epi8(tab_l,v&mask_f)^_mm256_shuffle_epi8(tab_h,_mm256_srli_epi16(v,4)&mask_f);
parallel_matrix_op.c:                ^
parallel_matrix_op.c: ./gf16_avx2.h:29:71: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'linear_transform_8x8_256b' that is compiled without support for 'avx2'
parallel_matrix_op.c:         return _mm256_shuffle_epi8(tab_l,v&mask_f)^_mm256_shuffle_epi8(tab_h,_mm256_srli_epi16(v,4)&mask_f);
parallel_matrix_op.c:                                                                              ^
parallel_matrix_op.c: ...

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

Implementation	Compiler
`avx2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

blas_comm.c: In file included from blas_comm.c:6:
blas_comm.c: In file included from ./blas.h:25:
blas_comm.c: ./blas_avx2.h:88:17: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'gf256v_add_avx2' that is compiled without support for 'avx'
blas_comm.c:                 __m256i inp = _mm256_loadu_si256( (__m256i*) (a+i*32) );
blas_comm.c:                               ^
blas_comm.c: ./blas_avx2.h:88:17: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
blas_comm.c: ./blas_avx2.h:89:17: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'gf256v_add_avx2' that is compiled without support for 'avx'
blas_comm.c:                 __m256i out = _mm256_loadu_si256( (__m256i*) (accu_b+i*32) );
blas_comm.c:                               ^
blas_comm.c: ./blas_avx2.h:89:17: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
blas_comm.c: ./blas_avx2.h:91:3: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'gf256v_add_avx2' that is compiled without support for 'avx'
blas_comm.c:                 _mm256_storeu_si256( (__m256i*) (accu_b+i*32) , out );
blas_comm.c:                 ^
blas_comm.c: ./blas_avx2.h:91:3: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
blas_comm.c: 6 errors generated.

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

Implementation	Compiler
`avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

parallel_matrix_op.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
parallel_matrix_op.c:                  from blas_avx2.h:10,
parallel_matrix_op.c:                  from blas.h:25,
parallel_matrix_op.c:                  from parallel_matrix_op.c:8:
parallel_matrix_op.c: gf16_avx2.h: In function 'linear_transform_8x8_256b':
parallel_matrix_op.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avx2intrin.h:588:1: error: inlining failed in call to 'always_inline' '_mm256_shuffle_epi8': target specific option mismatch
parallel_matrix_op.c:   588 | _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
parallel_matrix_op.c:       | ^~~~~~~~~~~~~~~~~~~
parallel_matrix_op.c: In file included from blas_avx2.h:15,
parallel_matrix_op.c:                  from blas.h:25,
parallel_matrix_op.c:                  from parallel_matrix_op.c:8:
parallel_matrix_op.c: gf16_avx2.h:29:45: note: called from here
parallel_matrix_op.c:    29 |  return _mm256_shuffle_epi8(tab_l,v&mask_f)^_mm256_shuffle_epi8(tab_h,_mm256_srli_epi16(v,4)&mask_f);
parallel_matrix_op.c:       |                                             ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
parallel_matrix_op.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
parallel_matrix_op.c:                  from blas_avx2.h:10,
parallel_matrix_op.c:                  from blas.h:25,
parallel_matrix_op.c:                  from parallel_matrix_op.c:8:
parallel_matrix_op.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avx2intrin.h:759:1: error: inlining failed in call to 'always_inline' '_mm256_srli_epi16': target specific option mismatch
parallel_matrix_op.c:   759 | _mm256_srli_epi16 (__m256i __A, int __B)
parallel_matrix_op.c:       | ^~~~~~~~~~~~~~~~~
parallel_matrix_op.c: In file included from blas_avx2.h:15,
parallel_matrix_op.c:                  from blas.h:25,
parallel_matrix_op.c:                  from parallel_matrix_op.c:8:
parallel_matrix_op.c: gf16_avx2.h:29:71: note: called from here
parallel_matrix_op.c: ...

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

Implementation	Compiler
`avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

Compiler output

parallel_matrix_op.c: In file included from parallel_matrix_op.c:8:
parallel_matrix_op.c: In file included from ./blas.h:25:
parallel_matrix_op.c: In file included from ./blas_sse.h:17:
parallel_matrix_op.c: ./gf16_sse.h:34:9: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'linear_transform_8x8_128b' that is compiled without support for 'ssse3'
parallel_matrix_op.c:         return _mm_shuffle_epi8(tab_l,v&mask_f)^_mm_shuffle_epi8(tab_h,_mm_srli_epi16(v,4)&mask_f);
parallel_matrix_op.c:                ^
parallel_matrix_op.c: ./gf16_sse.h:34:42: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'linear_transform_8x8_128b' that is compiled without support for 'ssse3'
parallel_matrix_op.c:         return _mm_shuffle_epi8(tab_l,v&mask_f)^_mm_shuffle_epi8(tab_h,_mm_srli_epi16(v,4)&mask_f);
parallel_matrix_op.c:                                                 ^
parallel_matrix_op.c: 2 errors generated.

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

Implementation	Compiler
`ssse3`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Passed TIMECOP

TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 26, namely:

Implementation	Compiler
`amd64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`amd64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`amd64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`amd64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`amd64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`amd64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`amd64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`amd64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`amd64`	`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)`
`ssse3`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ssse3`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ssse3`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ssse3`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ssse3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ssse3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ssse3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ssse3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`