Test results for amd64, h6sandy, crypto_core/rainbowcalsecret363232

[Page version: 20241016 12:05:22]

Measurements for amd64, h6sandy, crypto_core Test results for amd64, h6sandy, crypto_core Test results for crypto_core/rainbowcalsecret363232

Computer: h6sandy
Microarchitecture: amd64; Sandy Bridge (206a7)
Architecture: amd64
CPU ID: GenuineIntel-000206a7-bfebfbff
SUPERCOP version: 20241011
Operation: crypto_core
Primitive: rainbowcalsecret363232

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
2933271	35380 8 0	47813 812 992	`ssse3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
3073557	55407 8 0	69667 852 928	`ssse3`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
3311995	44813 8 0	57405 812 992	`ssse3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
3372366	33131 8 0	44451 852 928	`ssse3`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
3497632	47975 8 0	61445 812 992	`ssse3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
3630897	31794 8 0	42637 844 928	`ssse3`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
3699762	38358 8 0	50723 852 928	`ssse3`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
7011271	24643 8 0	36008 788 960	`ssse3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
10732431	18698 0 0	32043 844 928	`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
12627896	28685 0 0	41899 844 928	`amd64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
13701443	31523 0 0	45307 844 928	`amd64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
13780455	38737 0 0	52277 804 992	`amd64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
14054594	25606 0 0	38261 804 992	`amd64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
14553602	17971 0 0	30275 844 928	`amd64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
14712000	11951 0 0	23141 836 928	`amd64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
14781532	25074 0 0	37517 804 992	`amd64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
15441141	12675 0 0	24187 844 928	`amd64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
18476665	20419 0 0	34507 844 928	`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
19225789	14619 0 0	27331 844 928	`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
20373884	14849 0 0	27573 804 992	`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
20408478	22958 0 0	36549 804 992	`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
21989537	11225 0 0	22763 844 928	`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
22339334	11010 0 0	22352 780 960	`amd64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
23318412	14805 0 0	27269 804 992	`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
23627924	10592 0 0	21797 836 928	`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011
31897488	10065 0 0	21424 780 960	`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241012	20241011

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-14/lib/clang/14.0.0/include/avx2intrin.h:821:13: 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-14/lib/clang/14.0.0/include/avx2intrin.h:821:13: 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 (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

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 (Ubuntu_Clang_14.0.0)`

Compiler output

parallel_matrix_op.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
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/11/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:29:52: 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/11/include/immintrin.h:47,
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/11/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:29:78: 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 (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

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:         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 (Ubuntu_Clang_14.0.0)`

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 (Ubuntu_Clang_14.0.0)`
`amd64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`amd64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`amd64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`amd64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`amd64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`amd64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`amd64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`amd64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ssse3`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ssse3`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ssse3`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ssse3`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ssse3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ssse3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ssse3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ssse3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`