Implementation notes: amd64, comet, crypto_core/rainbowcalsecret363232

Computer: comet
Microarchitecture: amd64; Comet Lake (806ec)
Architecture: amd64
CPU ID: GenuineIntel-000806ec-bfebfbff
SUPERCOP version: 20240808
Operation: crypto_core
Primitive: rainbowcalsecret363232

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
2211791	86403 8 0	101761 860 1024	`avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
2669586	34273 8 0	45908 788 992	`ssse3`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
2706929	33131 8 0	44441 860 928	`ssse3`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
2815212	38990 8 0	50601 860 928	`avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
2899378	32346 8 0	43983 852 1024	`ssse3`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
2922543	62033 8 0	76057 860 1024	`ssse3`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
3137878	48645 8 0	63697 860 960	`avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
3188089	44099 8 0	55948 788 992	`ssse3`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
3246736	42817 8 0	56537 860 960	`ssse3`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
3256717	38113 8 0	49724 788 992	`avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
3332988	49595 8 0	61444 788 992	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
3337633	36646 8 0	49127 852 1024	`avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
3374456	48023 8 0	61460 788 992	`ssse3`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
3459800	53940 8 0	67356 788 992	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
4466700	23496 8 0	34063 764 960	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
4803571	24004 8 0	34599 764 960	`ssse3`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
8036499	18698 0 0	32097 852 928	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
9705910	28685 0 0	41953 852 928	`amd64`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
10113461	31874 0 0	43732 780 992	`amd64`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
10170394	29927 0 0	44953 852 1024	`amd64`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
10460368	36933 0 0	50340 780 992	`amd64`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
10681888	17307 0 0	32233 852 960	`amd64`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
11162535	11951 0 0	24335 844 1024	`amd64`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
11329398	27717 0 0	39220 780 992	`amd64`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
11926313	12675 0 0	24177 852 928	`amd64`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
12829261	19417 0 0	34617 852 1024	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
14174736	14741 0 0	29713 852 960	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
15110144	17106 0 0	29004 780 992	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
15292577	22706 0 0	36156 780 992	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
16122812	11225 0 0	22753 852 928	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
16410779	16813 0 0	28340 780 992	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
17018469	10805 0 0	21271 756 960	`amd64`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
17957715	10592 0 0	22991 844 1024	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808
24971723	9898 0 0	20375 756 960	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240810	20240808

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_14.0.6)`

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_14.0.6)`

Passed TIMECOP

TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 34, namely:

Implementation	Compiler
`amd64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`amd64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`amd64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`amd64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`amd64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`amd64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`amd64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`amd64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`amd64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`avx2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ssse3`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ssse3`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ssse3`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ssse3`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ssse3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ssse3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ssse3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ssse3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`