Implementation notes: amd64, gemini, crypto_sign/rainbow1b
Computer: gemini
Microarchitecture: amd64; Goldmont Plus (706a8)
Architecture: amd64
CPU ID: GenuineIntel-000706a8-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_sign
Primitive: rainbow1b
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
4243433 | 88741 0 1049652 | 107388 916 1051384 | T:ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
4274100 | 95153 0 1049652 | 116108 916 1051384 | T:ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
4277493 | 95153 0 1049652 | 116124 916 1051384 | T:portable | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
4618417 | 88741 0 1049652 | 107404 916 1051384 | T:portable | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
10891827 | 148702 0 1049700 | 168972 892 1051480 | T:portable | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
11365564 | 19080 0 1049652 | 37034 908 1051384 | T:portable | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
11674878 | 46758 0 1049652 | 67428 916 1051384 | T:ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
11678372 | 46758 0 1049652 | 67444 916 1051384 | T:portable | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
11717304 | 29360 0 1049700 | 48020 892 1051480 | T:ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
11717449 | 29360 0 1049700 | 48020 892 1051480 | T:portable | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
12084983 | 22729 0 1049700 | 41836 892 1051480 | T:ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
12089691 | 22729 0 1049700 | 41836 892 1051480 | T:portable | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
13838703 | 13612 0 1049652 | 32362 908 1051384 | T:portable | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
13841916 | 13612 0 1049652 | 32346 908 1051384 | T:ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
14697230 | 9649 0 1049700 | 27381 892 1051480 | T:ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240713 | 20240625 |
Test failure
error 142
Alarm clock
Number of similar (implementation,compiler) pairs: 3, namely:
Implementation | Compiler |
T:portable | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
T:ref | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
T:ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
Compiler output
rainbow.c: In file included from rainbow.c:4:
rainbow.c: In file included from ./rainbow.h:7:
rainbow.c: In file included from ./blas.h:17:
rainbow.c: ./blas_avx2.h:265:39: error: always_inline function '_mm256_setzero_si256' requires target feature 'avx', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx'
rainbow.c: for(unsigned i=0;i<n_ymm;i++) r[i] = _mm256_setzero_si256();
rainbow.c: ^
rainbow.c: ./blas_avx2.h:265:39: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:270:16: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx'
rainbow.c: __m256i bi = _mm256_set1_epi16( b_u16[i] );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:270:16: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:273:18: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx'
rainbow.c: __m256i tmp = _mm256_loadu_si256( (__m256i*)(mat+j*32) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:273:18: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:274:36: error: always_inline function '_mm256_maddubs_epi16' requires target feature 'avx2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx2'
rainbow.c: r[j] = _mm256_add_epi16( r[j] , _mm256_maddubs_epi16( tmp , bi ) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:274:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:274:11: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx2'
rainbow.c: r[j] = _mm256_add_epi16( r[j] , _mm256_maddubs_epi16( tmp , bi ) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:274:11: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:282:10: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
rainbow.c: r[j] = _gf31v_reduce_u16_avx2( r[j] );
rainbow.c: ...
Number of similar (implementation,compiler) pairs: 5, namely:
Implementation | Compiler |
T:avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
T:avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
T:avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
T:avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
T:avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
Compiler output
blas.c: In file included from blas.h:17,
blas.c: from blas.c:1:
blas.c: blas_avx2.h: In function '_gf31v_u8_to_u16_avx2':
blas.c: blas_avx2.h:17:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
blas.c: 17 | __m256i _gf31v_u8_to_u16_avx2( __m128i a ) {
blas.c: | ^~~~~~~
rainbow.c: In file included from blas.h:17,
rainbow.c: from rainbow.h:7,
rainbow.c: from rainbow.c:4:
rainbow.c: blas_avx2.h: In function '_gf31v_u8_to_u16_avx2':
rainbow.c: blas_avx2.h:17:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
rainbow.c: 17 | __m256i _gf31v_u8_to_u16_avx2( __m128i a ) {
rainbow.c: | ^~~~~~~
rainbow.c: blas_avx2.h: In function '_gf31v_reduce_u16_avx2':
rainbow.c: blas_avx2.h:110:9: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
rainbow.c: 110 | __m256i _gf31v_reduce_u16_avx2( __m256i a ){
rainbow.c: | ^~~~~~~~~~~~~~~~~~~~~~
rainbow.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:51,
rainbow.c: from blas_avx2.h:8,
rainbow.c: from blas.h:17,
rainbow.c: from rainbow.h:7,
rainbow.c: from rainbow.c:4:
rainbow.c: blas_avx2.h: In function '_gf31v_u8_to_u16_avx2':
rainbow.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avxintrin.h:768:1: error: inlining failed in call to 'always_inline' '_mm256_insertf128_si256': target specific option mismatch
rainbow.c: 768 | _mm256_insertf128_si256 (__m256i __X, __m128i __Y, const int __O)
rainbow.c: | ^~~~~~~~~~~~~~~~~~~~~~~
rainbow.c: In file included from blas.h:17,
rainbow.c: from rainbow.h:7,
rainbow.c: from rainbow.c:4:
rainbow.c: blas_avx2.h:22:9: note: called from here
rainbow.c: 22 | return _mm256_insertf128_si256 ( _mm256_castsi128_si256(a0) , a1 , 1 );
rainbow.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
Implementation | Compiler |
T:avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
T:avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
T:avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
T:avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |