Implementation notes: amd64, saber214, crypto_sign/rainbow1aclassic363232

Computer: saber214
Microarchitecture: amd64; Bulldozer (600f20)
Architecture: amd64
CPU ID: AuthenticAMD-00600f20-1789c3f5
SUPERCOP version: 20240625
Operation: crypto_sign
Primitive: rainbow1aclassic363232
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
322174188355 8 52217362 904 1664T:ssse3gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
32385482511 8 52135514 920 1632T:ssse3clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
325207105017 8 52156514 920 1632T:ssse3clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
33983993746 8 52143922 904 1664T:ssse3gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
36146876999 8 52130170 920 1632T:ssse3clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
36183868176 8 52121548 912 1632T:ssse3clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
37874176875 8 52128010 904 1664T:ssse3gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
44384453699 8 52110482 896 1664T:ssse3gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
490298141783 0 52205842 896 1664T:refgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
52644261986 0 52125730 912 1632T:refclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
54105982243 0 52145546 912 1632T:amd64clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
557768195344 0 52259466 896 1664T:amd64gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
63340285629 0 52148162 912 1632T:amd64clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
67345066180 0 52129058 896 1664T:amd64gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
68177158445 0 52119458 912 1632T:amd64clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
71941662523 0 52126114 912 1632T:refclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
73160242334 0 52104570 912 1632T:amd64clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
75479447841 0 52110098 912 1632T:refclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
77215440818 0 52102260 904 1632T:amd64clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
77555057176 0 52119778 896 1664T:amd64gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
97655545093 0 52107898 896 1664T:refgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
98673132217 0 5294090 888 1664T:amd64gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
100478238636 0 52100810 912 1632T:refclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
104566845906 0 52108450 896 1664T:refgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
108831734615 0 5296196 904 1632T:refclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625
142129129400 0 5291146 888 1664T:refgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070320240625

Compiler output


blas_matrix_avx2.c: blas_matrix_avx2.c:40:9: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'gf16mat_prod_16_multab_avx2' that is compiled without support for 'avx2'
blas_matrix_avx2.c:                 rl ^= _mm256_shuffle_epi8( mt , inp&mask_f );
blas_matrix_avx2.c:                       ^
blas_matrix_avx2.c: blas_matrix_avx2.c:41:53: error: always_inline function '_mm256_andnot_si256' requires target feature 'avx2', but would be inlined into function 'gf16mat_prod_16_multab_avx2' that is compiled without support for 'avx2'
blas_matrix_avx2.c:                 rh ^= _mm256_shuffle_epi8( mt , _mm256_srli_epi16(_mm256_andnot_si256(mask_f,inp),4) );
blas_matrix_avx2.c:                                                                   ^
blas_matrix_avx2.c: blas_matrix_avx2.c:41:35: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'gf16mat_prod_16_multab_avx2' that is compiled without support for 'avx2'
blas_matrix_avx2.c:                 rh ^= _mm256_shuffle_epi8( mt , _mm256_srli_epi16(_mm256_andnot_si256(mask_f,inp),4) );
blas_matrix_avx2.c:                                                 ^
blas_matrix_avx2.c: blas_matrix_avx2.c:41:9: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'gf16mat_prod_16_multab_avx2' that is compiled without support for 'avx2'
blas_matrix_avx2.c:                 rh ^= _mm256_shuffle_epi8( mt , _mm256_srli_epi16(_mm256_andnot_si256(mask_f,inp),4) );
blas_matrix_avx2.c:                       ^
blas_matrix_avx2.c: blas_matrix_avx2.c:44:19: error: always_inline function '_mm256_slli_epi16' requires target feature 'avx2', but would be inlined into function 'gf16mat_prod_16_multab_avx2' that is compiled without support for 'avx2'
blas_matrix_avx2.c:         __m256i r = rl ^ _mm256_slli_epi16( rh , 4 );
blas_matrix_avx2.c:                          ^
blas_matrix_avx2.c: blas_matrix_avx2.c:46:15: error: '__builtin_ia32_extract128i256' needs target feature avx2
blas_matrix_avx2.c:         __m128i r1 = _mm256_extracti128_si256( r , 1 );
blas_matrix_avx2.c:                      ^
blas_matrix_avx2.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx2intrin.h:824:13: note: expanded from macro '_mm256_extracti128_si256'
blas_matrix_avx2.c:   ((__m128i)__builtin_ia32_extract128i256((__v4di)(__m256i)(V), (int)(M)))
blas_matrix_avx2.c:             ^
blas_matrix_avx2.c: 6 errors generated.

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
T:avx2clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:avx2clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:avx2clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:avx2clang -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:
ImplementationCompiler
T:avx2clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


blas_matrix_avx2.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
blas_matrix_avx2.c:                  from gf16_avx2.h:22,
blas_matrix_avx2.c:                  from blas_matrix_avx2.c:9:
blas_matrix_avx2.c: gf16_avx2.h: In function 'tbl32_gf16_log':
blas_matrix_avx2.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
blas_matrix_avx2.c:   588 | _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
blas_matrix_avx2.c:       | ^~~~~~~~~~~~~~~~~~~
blas_matrix_avx2.c: In file included from blas_matrix_avx2.c:9:
blas_matrix_avx2.c: gf16_avx2.h:45:16: note: called from here
blas_matrix_avx2.c:    45 |         return _mm256_shuffle_epi8(tab_l,a);
blas_matrix_avx2.c:       |                ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
blas_matrix_avx2.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
blas_matrix_avx2.c:                  from gf16_avx2.h:22,
blas_matrix_avx2.c:                  from blas_matrix_avx2.c:9:
blas_matrix_avx2.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
blas_matrix_avx2.c:   588 | _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
blas_matrix_avx2.c:       | ^~~~~~~~~~~~~~~~~~~
blas_matrix_avx2.c: In file included from blas_matrix_avx2.c:9:
blas_matrix_avx2.c: gf16_avx2.h:45:16: note: called from here
blas_matrix_avx2.c:    45 |         return _mm256_shuffle_epi8(tab_l,a);
blas_matrix_avx2.c:       |                ^~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
T:avx2gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:avx2gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:avx2gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:avx2gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

Compiler output


blas_matrix_ref.c: In file included from blas_matrix_ref.c:6:
blas_matrix_ref.c: In file included from ./blas.h:25:
blas_matrix_ref.c: In file included from ./blas_sse.h:16:
blas_matrix_ref.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'
blas_matrix_ref.c:         return _mm_shuffle_epi8(tab_l,v&mask_f)^_mm_shuffle_epi8(tab_h,_mm_srli_epi16(v,4)&mask_f);
blas_matrix_ref.c:                ^
blas_matrix_ref.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'
blas_matrix_ref.c:         return _mm_shuffle_epi8(tab_l,v&mask_f)^_mm_shuffle_epi8(tab_h,_mm_srli_epi16(v,4)&mask_f);
blas_matrix_ref.c:                                                 ^
blas_matrix_ref.c: 2 errors generated.

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
T:ssse3clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)