Implementation notes: amd64, hydra5, crypto_decode/256x2
Computer: hydra5
Microarchitecture: amd64; K10 32nm (300f10)
Architecture: amd64
CPU ID: AuthenticAMD-00300f10-178bfbff
SUPERCOP version: 20240808
Operation: crypto_decode
Primitive: 256x2
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
1061 | 125 0 0 | 13013 804 960 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1063 | 125 0 0 | 11677 804 960 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1065 | 126 0 0 | 10868 796 960 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1069 | 102 0 0 | 10280 860 896 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1089 | 99 0 0 | 11584 860 896 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1089 | 99 0 0 | 12920 860 896 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1089 | 83 0 0 | 9458 852 896 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1090 | 99 0 0 | 12920 860 896 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1094 | 121 0 0 | 9872 780 928 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
Compiler output
decode.c: decode.c:16:17: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_decode_256x2_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: __m256i x = _mm256_set1_epi32(*(int32_t *) s);
decode.c: ^
decode.c: decode.c:16:17: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:18:31: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'crypto_decode_256x2_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: x = _mm256_shuffle_epi8(x,COPY);
decode.c: ^
decode.c: decode.c:5:14: note: expanded from macro 'COPY'
decode.c: #define COPY _mm256_set_epi64x(0x0303030303030303,0x0202020202020202,0x0101010101010101,0x0000000000000000)
decode.c: ^
decode.c: decode.c:18:31: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:5:14: note: expanded from macro 'COPY'
decode.c: #define COPY _mm256_set_epi64x(0x0303030303030303,0x0202020202020202,0x0101010101010101,0x0000000000000000)
decode.c: ^
decode.c: decode.c:18:9: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: x = _mm256_shuffle_epi8(x,COPY);
decode.c: ^
decode.c: decode.c:18:9: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:20:31: error: always_inline function '_mm256_set1_epi64x' requires target feature 'avx', but would be inlined into function 'crypto_decode_256x2_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: x = _mm256_andnot_si256(x,MASK);
decode.c: ^
decode.c: decode.c:6:14: note: expanded from macro 'MASK'
decode.c: #define MASK _mm256_set1_epi64x(0x8040201008040201)
decode.c: ^
decode.c: decode.c:20:31: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: ...
Number of similar (implementation,compiler) pairs: 5, namely:
Implementation | Compiler |
avx | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
decode.c: decode.c: In function 'crypto_decode_256x2_avx_constbranchindex':
decode.c: decode.c:16:13: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
decode.c: 16 | __m256i x = _mm256_set1_epi32(*(int32_t *) s);
decode.c: | ^
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:43,
decode.c: from decode.c:1:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:933:1: error: inlining failed in call to 'always_inline' '_mm256_storeu_si256': target specific option mismatch
decode.c: 933 | _mm256_storeu_si256 (__m256i_u *__P, __m256i __A)
decode.c: | ^~~~~~~~~~~~~~~~~~~
decode.c: decode.c:23:5: note: called from here
decode.c: 23 | _mm256_storeu_si256(r,x);
decode.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:43,
decode.c: from decode.c:1:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:1349:1: error: inlining failed in call to 'always_inline' '_mm256_set1_epi64x': target specific option mismatch
decode.c: 1349 | _mm256_set1_epi64x (long long __A)
decode.c: | ^~~~~~~~~~~~~~~~~~
decode.c: decode.c:7:15: note: called from here
decode.c: 7 | #define MASK2 _mm256_set1_epi64x(0x0101010101010101)
decode.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: decode.c:22:10: note: in expansion of macro 'MASK2'
decode.c: 22 | x &= MASK2;
decode.c: | ^~~~~
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
decode.c: from decode.c:1:
decode.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
Implementation | Compiler |
avx | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Passed TIMECOP
TIMECOP iterations: 10
Number of similar (implementation,compiler) pairs: 9, namely:
Implementation | Compiler |
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) |