Implementation notes: amd64, h6sandy, crypto_decode/1013x2393
Computer: h6sandy
Microarchitecture: amd64; Sandy Bridge (206a7)
Architecture: amd64
CPU ID: GenuineIntel-000206a7-bfebfbff
SUPERCOP version: 20240808
Operation: crypto_decode
Primitive: 1013x2393
| Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
|---|
| 17235 | 3277 0 0 | 17019 844 896 | int16 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 17256 | 3277 0 0 | 15675 844 896 | int16 | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 17283 | 2407 0 0 | 12133 836 896 | int16 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 17293 | 2829 0 0 | 14627 844 896 | int16 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 18665 | 2587 0 0 | 12691 844 896 | int16 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 18807 | 2645 0 0 | 13452 796 960 | int16 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 21071 | 3515 0 0 | 15861 804 960 | int16 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 21211 | 2526 0 0 | 13621 804 960 | int16 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 21683 | 2515 0 0 | 12344 780 928 | int16 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 24338 | 3153 0 0 | 14253 804 960 | portable | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 24943 | 4395 0 0 | 16749 804 960 | portable | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 25594 | 3067 0 0 | 12789 836 896 | portable | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 26318 | 4287 0 0 | 18027 844 896 | portable | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 26328 | 3562 0 0 | 15363 844 896 | portable | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 26459 | 4337 0 0 | 16731 844 896 | portable | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 27391 | 3260 0 0 | 13371 844 896 | portable | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 50998 | 2812 0 0 | 14619 844 896 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 51079 | 2812 0 0 | 16563 844 896 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 51362 | 2358 0 0 | 14755 844 896 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 52244 | 1788 0 0 | 14101 804 960 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 55926 | 1633 0 0 | 12669 804 960 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 56048 | 1177 0 0 | 10869 836 896 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 56355 | 1976 0 0 | 12804 796 960 | portable | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 56567 | 1165 0 0 | 11267 844 896 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 57952 | 1897 0 0 | 11736 780 928 | portable | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 65340 | 1649 0 0 | 12380 796 960 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
| 71761 | 1524 0 0 | 11240 780 928 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
Compiler output
decode.c: decode.c:270:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S1 = _mm256_srli_epi16(S0,8);
decode.c: ^
decode.c: decode.c:285:10: error: always_inline function '_mm256_unpacklo_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: B0 = _mm256_unpacklo_epi16(A0,A1);
decode.c: ^
decode.c: decode.c:286:10: error: always_inline function '_mm256_unpackhi_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: B1 = _mm256_unpackhi_epi16(A0,A1);
decode.c: ^
decode.c: decode.c:289:10: error: '__builtin_ia32_permti256' needs target feature avx2
decode.c: C0 = _mm256_permute2x128_si256(B0,B1,0x20);
decode.c: ^
decode.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx2intrin.h:821:13: note: expanded from macro '_mm256_permute2x128_si256'
decode.c: ((__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M)))
decode.c: ^
decode.c: decode.c:290:10: error: '__builtin_ia32_permti256' needs target feature avx2
decode.c: C1 = _mm256_permute2x128_si256(B0,B1,0x31);
decode.c: ^
decode.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx2intrin.h:821:13: note: expanded from macro '_mm256_permute2x128_si256'
decode.c: ((__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M)))
decode.c: ^
decode.c: decode.c:306:10: error: always_inline function '_mm256_cvtepu8_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S0 = _mm256_cvtepu8_epi16(_mm_loadu_si128((__m128i *) (s+i)));
decode.c: ^
decode.c: decode.c:318:10: error: always_inline function '_mm256_unpacklo_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: ...
Number of similar (implementation,compiler) pairs: 4, 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) |
Compiler output
decode.c: decode.c:268:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_1013x2393_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:268:15: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:269:10: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_1013x2393_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:269:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:270:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S1 = _mm256_srli_epi16(S0,8);
decode.c: ^
decode.c: decode.c:270:10: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:271:11: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: S0 &= _mm256_set1_epi16(255);
decode.c: ^
decode.c: decode.c:271:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:272:14: 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(A0,412),mulhiconst(mulloconst(A0,-5118),3278)); /* -1639...1742 */
decode.c: ^
decode.c: decode.c:272:44: 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(A0,412),mulhiconst(mulloconst(A0,-5118),3278)); /* -1639...1742 */
decode.c: ^
decode.c: decode.c:272:33: 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(A0,412),mulhiconst(mulloconst(A0,-5118),3278)); /* -1639...1742 */
decode.c: ^
decode.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| avx | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
decode.c: from decode.c:3:
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:22:10: note: called from here
decode.c: 22 | return _mm256_add_epi16(x,y);
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: 27, namely:
| 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) |