Implementation notes: amd64, hydra7, crypto_core/inv3sntrup1277
Computer: hydra7
Microarchitecture: amd64; Sandy Bridge+AES (206a7)
Architecture: amd64
CPU ID: GenuineIntel-000206a7-bfebfbff
SUPERCOP version: 20240808
Operation: crypto_core
Primitive: inv3sntrup1277
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
852712 | 5161 0 0 | 20379 844 928 | bits64 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1143284 | 3321 0 0 | 17333 804 992 | bits64 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1317720 | 8564 0 0 | 22427 844 928 | bits64 | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1344633 | 4441 0 0 | 17707 844 928 | bits64 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1724517 | 2552 0 0 | 13725 836 928 | bits64 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
1958897 | 1890 0 0 | 13435 844 928 | bits64 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
2030104 | 1763 0 0 | 14533 804 992 | bits64 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
2155158 | 1473 0 0 | 12776 780 960 | bits64 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
2176769 | 1670 0 0 | 14164 796 992 | bits64 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
6616681 | 7255 0 0 | 21343 812 992 | bits | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
6972900 | 5507 0 0 | 18853 852 928 | bits | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
7139483 | 7020 0 0 | 22317 852 928 | bits | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
7659522 | 4489 0 0 | 18429 852 928 | bits | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
10027007 | 5736 0 0 | 19791 812 992 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
35802497 | 1700 0 0 | 15045 852 928 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
35858731 | 1700 0 0 | 16989 852 928 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
42097278 | 3022 0 0 | 16973 852 928 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
61281136 | 757 0 0 | 12365 852 928 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
72070911 | 719 0 0 | 11991 844 928 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
97049749 | 1127 0 0 | 12733 852 928 | bits | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
98670473 | 978 0 0 | 13831 812 992 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
98685646 | 1410 0 0 | 14271 812 992 | bits | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
110457804 | 1188 0 0 | 12455 844 928 | bits | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
114277232 | 915 0 0 | 13380 796 992 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
117131902 | 1131 0 0 | 12522 788 960 | bits | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
118693649 | 794 0 0 | 12146 788 960 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
125260556 | 1256 0 0 | 13756 796 992 | bits | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
Compiler output
r3_recip.c: r3_recip.c:41:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c0 = _mm256_unpacklo_epi32(b0,b1); /* 0 1 2 3 32 33 34 35 4 5 6 7 36 37 38 39 ... 55 */
r3_recip.c: ^
r3_recip.c: r3_recip.c:42:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c1 = _mm256_unpackhi_epi32(b0,b1); /* 8 9 10 11 40 41 42 43 ... 63 */
r3_recip.c: ^
r3_recip.c: r3_recip.c:43:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c2 = _mm256_unpacklo_epi32(b2,b3);
r3_recip.c: ^
r3_recip.c: r3_recip.c:44:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c3 = _mm256_unpackhi_epi32(b2,b3);
r3_recip.c: ^
r3_recip.c: r3_recip.c:45:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c4 = _mm256_unpacklo_epi32(b4,b5);
r3_recip.c: ^
r3_recip.c: r3_recip.c:46:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c5 = _mm256_unpackhi_epi32(b4,b5);
r3_recip.c: ^
r3_recip.c: r3_recip.c:47:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c6 = _mm256_unpacklo_epi32(b6,b7);
r3_recip.c: ^
r3_recip.c: r3_recip.c:48:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c7 = _mm256_unpackhi_epi32(b6,b7);
r3_recip.c: ^
r3_recip.c: r3_recip.c:50:22: error: always_inline function '_mm256_slli_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.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
r3_recip.c: r3_recip.c:481:11: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c: F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c: ^
r3_recip.c: r3_recip.c:481:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:482:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c: F0[1] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:482:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:483:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c: F0[2] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:483:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:484:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c: F0[3] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:484:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:485:11: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c: F0[4] = _mm256_set_epi32(0,0,0,0,-2147483648,0,-2147483648,0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:485:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:486:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c: F1[0] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:486:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:487:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.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
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: r3_recip.c: In function 'vec256_frombits':
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:597:1: error: inlining failed in call to 'always_inline' '_mm256_shuffle_epi32': target specific option mismatch
r3_recip.c: 597 | _mm256_shuffle_epi32 (__m256i __A, const int __mask)
r3_recip.c: | ^~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:71:9: note: called from here
r3_recip.c: 71 | h = _mm256_shuffle_epi32(h,0xd8);
r3_recip.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:1071:1: error: inlining failed in call to 'always_inline' '_mm256_permute4x64_epi64': target specific option mismatch
r3_recip.c: 1071 | _mm256_permute4x64_epi64 (__m256i __X, const int __M)
r3_recip.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:70:9: note: called from here
r3_recip.c: 70 | h = _mm256_permute4x64_epi64(h,0xd8);
r3_recip.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:588:1: error: inlining failed in call to 'always_inline' '_mm256_shuffle_epi8': target specific option mismatch
r3_recip.c: 588 | _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
r3_recip.c: | ^~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:69:9: note: called from here
r3_recip.c: 69 | h = _mm256_shuffle_epi8(h,TRANSPOSE);
r3_recip.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.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: 1
Number of similar (implementation,compiler) pairs: 27, namely:
Implementation | Compiler |
bits | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
bits | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
bits | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
bits | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
bits64 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits64 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits64 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits64 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits64 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
bits64 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
bits64 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
bits64 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
bits64 | 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) |