Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
---|---|---|---|---|---|---|
472088 | 103688 6228 16 | 123824 7072 1640 | T:avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
501304 | 66222 6228 16 | 84528 7072 1640 | T:avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
512412 | 64646 6228 16 | 82480 7072 1640 | T:avx2 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
522048 | 97595 6228 16 | 118142 7096 1576 | T:avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
577308 | 62308 6228 16 | 80496 7088 1672 | T:avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
594944 | 141724 6228 16 | 163374 7096 1576 | T:opt | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
628544 | 84887 6228 16 | 102510 7096 1576 | T:avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
629160 | 155889 6228 16 | 175966 7096 1576 | T:sse2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
636296 | 61511 6228 16 | 78359 7064 1608 | T:avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
646556 | 92236 6228 16 | 112886 7096 1576 | T:sse2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
666892 | 92837 6228 16 | 114672 7072 1640 | T:opt | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
695484 | 54450 6228 16 | 74440 7072 1640 | T:opt | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
741399 | 160716 6228 16 | 180710 7096 1576 | T:avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
746488 | 53420 6228 16 | 73072 7088 1672 | T:opt | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
747100 | 80082 6228 16 | 97766 7096 1576 | T:sse2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
757832 | 150971 6228 16 | 170854 7096 1576 | T:sse2 | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
777796 | 145497 6228 16 | 166750 7096 1576 | T:opt | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
785436 | 52655 6228 16 | 72168 7072 1640 | T:opt | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
852024 | 91245 6228 16 | 113406 7096 1576 | T:opt | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
852216 | 50429 6228 16 | 68775 7064 1608 | T:opt | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
865884 | 75587 6228 16 | 94798 7096 1576 | T:opt | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
995605 | 57926 6228 16 | 76128 7088 1672 | T:sse2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
6239600 | 58332 76 16 | 80974 936 1576 | T:ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
6473896 | 54666 76 16 | 76648 896 1640 | T:ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
6477816 | 52722 76 16 | 75262 936 1576 | T:ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
6769772 | 38066 76 16 | 59758 936 1576 | T:ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
7109824 | 25395 76 16 | 45352 896 1640 | T:ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
7264483 | 22597 76 16 | 42440 928 1672 | T:ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
7316388 | 29161 76 16 | 48318 936 1576 | T:ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
8123584 | 23039 76 16 | 42528 896 1640 | T:ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
8471284 | 20305 76 16 | 38615 888 1608 | T:ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
bitslice_fft_256.c: bitslice_fft_256.c:87:25: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'bitslice_butterflies12_256' that is compiled without support for 'avx' bitslice_fft_256.c: out[i][b] = _mm256_set_epi64x(-((in[0][b] >> reversal[4*i+3]) & 1), bitslice_fft_256.c: ^ bitslice_fft_256.c: bitslice_fft_256.c:87:25: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI bitslice_fft_256.c: bitslice_fft_256.c:99:22: error: '__builtin_ia32_pshufd256' needs target feature avx2 bitslice_fft_256.c: vb = _mm256_shuffle_epi32(tmp[b], _MM_SHUFFLE(3, 2, 3, 2)); bitslice_fft_256.c: ^ bitslice_fft_256.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx2intrin.h:470:13: note: expanded from macro '_mm256_shuffle_epi32' bitslice_fft_256.c: ((__m256i)__builtin_ia32_pshufd256((__v8si)(__m256i)(a), (int)(imm))) bitslice_fft_256.c: ^ bitslice_fft_256.c: bitslice_fft_256.c:100:22: error: '__builtin_ia32_pslldqi256_byteshift' needs target feature avx2 bitslice_fft_256.c: va = _mm256_slli_si256(out[k][b], 8); bitslice_fft_256.c: ^ bitslice_fft_256.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx2intrin.h:497:13: note: expanded from macro '_mm256_slli_si256' bitslice_fft_256.c: ((__m256i)__builtin_ia32_pslldqi256_byteshift((__v4di)(__m256i)(a), (int)(imm))) bitslice_fft_256.c: ^ bitslice_fft_256.c: bitslice_fft_256.c:101:22: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'bitslice_butterflies12_256' that is compiled without support for 'avx2' bitslice_fft_256.c: vb = _mm256_xor_si256(va, vb); bitslice_fft_256.c: ^ bitslice_fft_256.c: bitslice_fft_256.c:101:22: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI bitslice_fft_256.c: bitslice_fft_256.c:102:29: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'bitslice_butterflies12_256' that is compiled without support for 'avx2' bitslice_fft_256.c: out[k][b] = _mm256_xor_si256(out[k][b], vb); bitslice_fft_256.c: ^ bitslice_fft_256.c: bitslice_fft_256.c:102:29: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI bitslice_fft_256.c: bitslice_fft_256.c:112:22: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'bitslice_butterflies12_256' that is compiled without support for 'avx' bitslice_fft_256.c: ...
Implementation | Compiler |
T:avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
m4r.c: m4r.c: In function 'zero_vector': m4r.c: m4r.c:85:20: error: incompatible types when assigning to type 'vector' {aka '__m128i'} from type '__m256i' m4r.c: 85 | *vec_ptr = _mm256_setzero_si256(); vec_ptr++; m4r.c: | ^~~~~~~~~~~~~~~~~~~~ m4r.c: m4r.c:86:20: error: incompatible types when assigning to type 'vector' {aka '__m128i'} from type '__m256i' m4r.c: 86 | *vec_ptr = _mm256_setzero_si256(); vec_ptr++; m4r.c: | ^~~~~~~~~~~~~~~~~~~~ m4r.c: m4r.c: In function '_m4ri_make_table_rev': m4r.c: m4r.c:147:12: error: incompatible types when assigning to type 'vector' {aka '__m128i'} from type '__m256i' m4r.c: 147 | mask = _mm256_set_epi64x(v[3], v[2], v[1], v[0]); m4r.c: | ^~~~~~~~~~~~~~~~~ m4r.c: m4r.c:196:46: error: incompatible type for argument 1 of '_mm256_and_si256' m4r.c: 196 | S_ptr[nblocks-1] = _mm256_and_si256(S_ptr[nblocks-1], mask); m4r.c: | ~~~~~^~~~~~~~~~~ m4r.c: | | m4r.c: | vector {aka __m128i} m4r.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47, m4r.c: from bits.h:28, m4r.c: from m4r.c:26: m4r.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:179:27: note: expected '__m256i' but argument is of type 'vector' {aka '__m128i'} m4r.c: 179 | _mm256_and_si256 (__m256i __A, __m256i __B) m4r.c: | ~~~~~~~~^~~ m4r.c: m4r.c:196:59: error: incompatible type for argument 2 of '_mm256_and_si256' m4r.c: 196 | S_ptr[nblocks-1] = _mm256_and_si256(S_ptr[nblocks-1], mask); m4r.c: | ^~~~ m4r.c: ...
Implementation | Compiler |
T:sse2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:sse2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:sse2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:sse2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |