Test results for amd64, h4atom, crypto_core/rainbowcalsecret363232

[Page version: 20251115 13:22:58]

Measurements for amd64, h4atom, crypto_core Test results for amd64, h4atom, crypto_core Test results for crypto_core/rainbowcalsecret363232

Computer: h4atom
Microarchitecture: amd64; Bonnell (106ca)
Architecture: amd64
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20250922
Operation: crypto_core
Primitive: rainbowcalsecret363232

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
15342849	49243 8 0	62255 828 936	`ssse3`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
16734780	35684 8 0	47551 828 936	`ssse3`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
17353600	34401 8 0	45791 828 936	`ssse3`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
17609144	35543 8 0	47670 788 1000	`ssse3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
17743156	33920 8 0	43793 820 936	`ssse3`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
19321671	47900 8 0	60166 788 1000	`ssse3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
19348533	60234 8 0	73014 788 1000	`ssse3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
24964692	24249 8 0	34921 764 968	`ssse3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
26879280	42959 0 0	55750 780 1000	`amd64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
27201616	18887 0 0	32471 820 936	`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
28299098	33755 0 0	46022 780 1000	`amd64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
28949956	19229 0 0	36391 820 936	`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
30578768	12142 0 0	23137 812 936	`amd64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
31421951	13082 0 0	25943 820 936	`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
31563703	12835 0 0	24431 820 936	`amd64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
33227312	29214 0 0	42647 820 936	`amd64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
33827577	28962 0 0	40958 780 1000	`amd64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
34124484	15854 0 0	28479 820 936	`amd64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
34471948	29486 0 0	46487 820 936	`amd64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
39266299	26122 0 0	38958 780 1000	`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
40434742	18484 0 0	30790 780 1000	`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
42118962	10717 0 0	21729 812 936	`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
45813357	11418 0 0	22999 820 936	`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
48989168	10933 0 0	21489 756 968	`amd64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
52580456	17961 0 0	29974 780 1000	`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415
71289520	10000 0 0	20553 756 968	`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250829	20250415

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:    88 |                 __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:    89 |                 __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:    91 |                 _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: 5, namely:

Implementation	Compiler
`avx2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`

Compiler output

blas_comm.c: In file included from blas_avx2.h:15,
blas_comm.c:                  from blas.h:25,
blas_comm.c:                  from blas_comm.c:6:
blas_comm.c: gf16_avx2.h: In function 'linear_transform_8x8_256b':
blas_comm.c: gf16_avx2.h:28:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
blas_comm.c:    28 | {
blas_comm.c:       | ^
blas_comm.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/14/include/immintrin.h:43,
blas_comm.c:                  from blas_avx2.h:10:
blas_comm.c: /usr/lib/gcc/x86_64-linux-gnu/14/include/avxintrin.h: In function 'gf256v_add_avx2':
blas_comm.c: /usr/lib/gcc/x86_64-linux-gnu/14/include/avxintrin.h:933:1: error: inlining failed in call to 'always_inline' '_mm256_storeu_si256': target specific option mismatch
blas_comm.c:   933 | _mm256_storeu_si256 (__m256i_u *__P, __m256i __A)
blas_comm.c:       | ^~~~~~~~~~~~~~~~~~~
blas_comm.c: blas_avx2.h:91:17: note: called from here
blas_comm.c:    91 |                 _mm256_storeu_si256( (__m256i*) (accu_b+i*32) , out );
blas_comm.c:       |                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blas_comm.c: /usr/lib/gcc/x86_64-linux-gnu/14/include/avxintrin.h:927:1: error: inlining failed in call to 'always_inline' '_mm256_loadu_si256': target specific option mismatch
blas_comm.c:   927 | _mm256_loadu_si256 (__m256i_u const *__P)
blas_comm.c:       | ^~~~~~~~~~~~~~~~~~
blas_comm.c: blas_avx2.h:89:31: note: called from here
blas_comm.c:    89 |                 __m256i out = _mm256_loadu_si256( (__m256i*) (accu_b+i*32) );
blas_comm.c:       |                               ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blas_comm.c: /usr/lib/gcc/x86_64-linux-gnu/14/include/avxintrin.h:927:1: error: inlining failed in call to 'always_inline' '_mm256_loadu_si256': target specific option mismatch
blas_comm.c:   927 | _mm256_loadu_si256 (__m256i_u const *__P)
blas_comm.c:       | ^~~~~~~~~~~~~~~~~~
blas_comm.c: ...

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

Implementation	Compiler
`avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`

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:    34 |         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:    34 |         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_19.1.7_(3+b1))`

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_19.1.7_(3+b1))`
`amd64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`amd64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`amd64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`amd64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`amd64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`amd64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`amd64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`amd64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`ssse3`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`ssse3`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`ssse3`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`ssse3`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_19.1.7_(3+b1))`
`ssse3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`ssse3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`ssse3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`
`ssse3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (14.2.0)`