[Page version: 20250523 09:19:40]
Measurements for amd64, h3neo, crypto_decode Test results for amd64, h3neo, crypto_decode Test results for crypto_decode/1013x7177Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
---|---|---|---|---|---|---|
22299 | 2584 0 0 | 13587 844 896 | int16 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
22299 | 2584 0 0 | 14507 844 896 | int16 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
23600 | 2665 0 0 | 15059 844 896 | int16 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
23949 | 2488 0 0 | 12547 844 896 | int16 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
23964 | 2300 0 0 | 11717 836 896 | int16 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
25573 | 2490 0 0 | 12304 780 928 | int16 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
26072 | 2625 0 0 | 14173 804 960 | int16 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
26120 | 3930 0 0 | 16805 804 960 | int16 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
26652 | 2578 0 0 | 13332 796 960 | int16 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
34807 | 3384 0 0 | 14379 844 896 | portable | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
34818 | 3384 0 0 | 15299 844 896 | portable | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
35883 | 3178 0 0 | 13259 844 896 | portable | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
36024 | 3013 0 0 | 12437 836 896 | portable | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
37833 | 3520 0 0 | 15883 844 896 | portable | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
38403 | 4670 0 0 | 17549 804 960 | portable | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
38953 | 3213 0 0 | 14773 804 960 | portable | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
138375 | 2346 0 0 | 14747 844 896 | ref | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
141496 | 1824 0 0 | 14653 804 960 | ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
143227 | 2274 0 0 | 14195 844 896 | ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
143369 | 1330 0 0 | 12347 844 896 | ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
146161 | 1616 0 0 | 13125 804 960 | ref | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
148010 | 1893 0 0 | 11712 780 928 | portable | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
148360 | 1183 0 0 | 11251 844 896 | ref | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
152129 | 1952 0 0 | 12748 796 960 | portable | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
153335 | 1614 0 0 | 11021 836 896 | ref | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
164166 | 1655 0 0 | 12356 796 960 | ref | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
165439 | 1524 0 0 | 11200 780 928 | ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20250428 | 20250415 |
decode.c: decode.c:273:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_1013x7177_avx_constbranchindex' that is compiled without support for 'avx' decode.c: A2 = A0 = _mm256_loadu_si256((__m256i *) &R5[i]); decode.c: ^ decode.c: decode.c:273:15: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI decode.c: decode.c:274:10: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_1013x7177_avx_constbranchindex' that is compiled without support for 'avx' decode.c: S0 = _mm256_loadu_si256((__m256i *) (s+2*i)); decode.c: ^ decode.c: decode.c:274:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI decode.c: decode.c:275:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x7177_avx_constbranchindex' that is compiled without support for 'avx2' decode.c: S1 = _mm256_srli_epi16(S0,8); decode.c: ^ decode.c: decode.c:275:10: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI decode.c: decode.c:276:11: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_decode_1013x7177_avx_constbranchindex' that is compiled without support for 'avx' decode.c: S0 &= _mm256_set1_epi16(255); decode.c: ^ decode.c: decode.c:276:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI decode.c: decode.c:277:14: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi] decode.c: A0 = sub(mulhiconst(A0,538),mulhiconst(mulloconst(A0,-2118),7921)); /* -3961...4095 */ decode.c: ^ decode.c: decode.c:277:44: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi] decode.c: A0 = sub(mulhiconst(A0,538),mulhiconst(mulloconst(A0,-2118),7921)); /* -3961...4095 */ decode.c: ^ decode.c: decode.c:277:33: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi] decode.c: A0 = sub(mulhiconst(A0,538),mulhiconst(mulloconst(A0,-2118),7921)); /* -3961...4095 */ decode.c: ^ decode.c: ...
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) |
decode.c: decode.c: In function 'add': decode.c: decode.c:23:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi] decode.c: 23 | { decode.c: | ^ decode.c: decode.c: In function 'signedshiftrightconst': decode.c: decode.c:37:23: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6 decode.c: 37 | static inline __m256i signedshiftrightconst(__m256i x,int16 y) 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:5: decode.c: decode.c: In function 'add': decode.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:112:1: error: inlining failed in call to 'always_inline' '_mm256_add_epi16': target specific option mismatch decode.c: 112 | _mm256_add_epi16 (__m256i __A, __m256i __B) decode.c: | ^~~~~~~~~~~~~~~~ decode.c: decode.c:24:10: note: called from here decode.c: 24 | return _mm256_add_epi16(x,y); decode.c: | ^~~~~~~~~~~~~~~~~~~~~
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) |
TIMECOP iterations: 10
Implementation | Compiler |
int16 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
int16 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
int16 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
int16 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
portable | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
portable | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
portable | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
portable | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
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) |