Implementation notes: amd64, kizomba, crypto_kem/ntruhps4096821
Computer: kizomba
Microarchitecture: amd64; Kaby Lake (906e9)
Architecture: amd64
CPU ID: GenuineIntel-000906e9-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: ntruhps4096821
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
114613 | 171329 81120 0 | 228517 81920 1608 | avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
116829 | 183914 81120 0 | 241975 81960 1640 | avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
119087 | 174856 81120 0 | 232647 81960 1576 | avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
137111 | 152290 81120 0 | 207565 81920 1608 | avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
142276 | 151399 81120 0 | 206729 81952 1640 | avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
143844 | 150089 81120 0 | 204703 81960 1576 | avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
146164 | 150213 81120 0 | 204973 81920 1608 | avx2 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
160565 | 144782 81120 0 | 198525 81912 1576 | avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
1043585 | 58918 0 0 | 116729 840 1640 | compact | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
1053207 | 46250 0 0 | 103777 840 1576 | compact | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
1230398 | 28670 0 0 | 86447 800 1608 | compact | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
1733552 | 40471 0 0 | 97193 840 1576 | compact | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
4994355 | 37299 0 0 | 95113 840 1640 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
5046377 | 29684 0 0 | 87257 840 1576 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
5086748 | 19163 0 0 | 76041 840 1576 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
5661012 | 7900 0 0 | 62963 832 1640 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
5726081 | 7299 0 0 | 61937 840 1576 | compact | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
5988973 | 6908 0 0 | 62259 832 1640 | compact | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
6826248 | 21694 0 0 | 78767 800 1608 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
6955117 | 7127 0 0 | 62351 800 1608 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
7252631 | 5337 0 0 | 60983 800 1608 | compact | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
10695252 | 6363 0 0 | 59975 792 1576 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
11516637 | 4076 0 0 | 58215 792 1576 | compact | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
13789440 | 6161 0 0 | 60793 840 1576 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
13872240 | 6816 0 0 | 61445 792 1608 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
14241813 | 4701 0 0 | 59861 792 1608 | compact | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240629 | 20240625 |
Compiler output
poly_s3_inv.c: poly_s3_inv.c:416:11: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function '__poly_S3_inv' that is compiled without support for 'avx'
poly_s3_inv.c: F0[0] = _mm256_set_epi32(-1,-1,-1,-1,-1,-1,-1,-1);
poly_s3_inv.c: ^
poly_s3_inv.c: poly_s3_inv.c:416:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly_s3_inv.c: poly_s3_inv.c:417:11: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function '__poly_S3_inv' that is compiled without support for 'avx'
poly_s3_inv.c: F0[1] = _mm256_set_epi32(-1,-1,-1,-1,-1,-1,-1,-1);
poly_s3_inv.c: ^
poly_s3_inv.c: poly_s3_inv.c:417:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly_s3_inv.c: poly_s3_inv.c:418:11: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function '__poly_S3_inv' that is compiled without support for 'avx'
poly_s3_inv.c: F0[2] = _mm256_set_epi32(-1,-1,-1,-1,-1,-1,-1,-1);
poly_s3_inv.c: ^
poly_s3_inv.c: poly_s3_inv.c:418:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly_s3_inv.c: poly_s3_inv.c:419:11: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function '__poly_S3_inv' that is compiled without support for 'avx'
poly_s3_inv.c: F0[3] = _mm256_set_epi32(0,8191,0,8191,0,8191,0,16383);
poly_s3_inv.c: ^
poly_s3_inv.c: poly_s3_inv.c:419:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly_s3_inv.c: poly_s3_inv.c:420:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function '__poly_S3_inv' that is compiled without support for 'avx'
poly_s3_inv.c: F1[0] = _mm256_set1_epi32(0);
poly_s3_inv.c: ^
poly_s3_inv.c: poly_s3_inv.c:420:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly_s3_inv.c: poly_s3_inv.c:421:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function '__poly_S3_inv' that is compiled without support for 'avx'
poly_s3_inv.c: F1[1] = _mm256_set1_epi32(0);
poly_s3_inv.c: ^
poly_s3_inv.c: poly_s3_inv.c:421:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly_s3_inv.c: poly_s3_inv.c:422:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function '__poly_S3_inv' that is compiled without support for 'avx'
poly_s3_inv.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
owcpa.c: owcpa.c:67:40: warning: argument 3 of type 'const unsigned char[3895]' with mismatched bound [-Warray-parameter=]
owcpa.c: 67 | const unsigned char seed[NTRU_SAMPLE_FG_BYTES])
owcpa.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
owcpa.c: In file included from owcpa.c:1:
owcpa.c: owcpa.h:14:40: note: previously declared as 'const unsigned char[32]'
owcpa.c: 14 | const unsigned char seed[NTRU_SEEDBYTES]);
owcpa.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~
owcpa.c: owcpa.c: In function 'crypto_kem_ntruhps4096821_avx2_constbranchindex_owcpa_keypair':
owcpa.c: <command-line>: warning: 'crypto_kem_ntruhps4096821_avx2_constbranchindex_sample_fg' reading 3895 bytes from a region of size 32 [-Wstringop-overread]
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: owcpa.c:77:3: note: in expansion of macro 'sample_fg'
owcpa.c: 77 | sample_fg(f,g,seed);
owcpa.c: | ^~~~~~~~~
owcpa.c: <command-line>: note: referencing argument 3 of type 'const unsigned char *'
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: owcpa.c:77:3: note: in expansion of macro 'sample_fg'
owcpa.c: 77 | sample_fg(f,g,seed);
owcpa.c: | ^~~~~~~~~
owcpa.c: <command-line>: note: in a call to function 'crypto_kem_ntruhps4096821_avx2_constbranchindex_sample_fg'
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: sample.h:11:6: note: in expansion of macro 'sample_fg'
owcpa.c: 11 | void sample_fg(poly *f, poly *g, const unsigned char uniformbytes[NTRU_SAMPLE_FG_BYTES]);
owcpa.c: | ^~~~~~~~~
pack3.c: pack3.c:3:36: warning: argument 1 of type 'unsigned char[328]' with mismatched bound [-Warray-parameter=]
pack3.c: 3 | void poly_S3_tobytes(unsigned char msg[NTRU_OWCPA_MSGBYTES], const poly *a)
pack3.c: | ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: In file included from pack3.c:1:
pack3.c: poly.h:33:36: note: previously declared as 'unsigned char[164]'
pack3.c: 33 | void poly_S3_tobytes(unsigned char msg[NTRU_PACK_TRINARY_BYTES], const poly *a);
pack3.c: | ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: pack3.c:19:53: warning: argument 2 of type 'const unsigned char[328]' with mismatched bound [-Warray-parameter=]
pack3.c: 19 | void poly_S3_frombytes(poly *r, const unsigned char msg[NTRU_OWCPA_MSGBYTES])
pack3.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: In file included from pack3.c:1:
pack3.c: poly.h:34:53: note: previously declared as 'const unsigned char[164]'
pack3.c: 34 | void poly_S3_frombytes(poly *r, const unsigned char msg[NTRU_PACK_TRINARY_BYTES]);
pack3.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
Number of similar (implementation,compiler) pairs: 4, namely:
Implementation | Compiler |
avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Compiler output
owcpa.c: owcpa.c:67:40: warning: argument 3 of type 'const unsigned char[3895]' with mismatched bound [-Warray-parameter=]
owcpa.c: 67 | const unsigned char seed[NTRU_SAMPLE_FG_BYTES])
owcpa.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
owcpa.c: In file included from owcpa.c:1:
owcpa.c: owcpa.h:14:40: note: previously declared as 'const unsigned char[32]'
owcpa.c: 14 | const unsigned char seed[NTRU_SEEDBYTES]);
owcpa.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~
owcpa.c: owcpa.c: In function 'crypto_kem_ntruhps4096821_ref_constbranchindex_owcpa_keypair':
owcpa.c: <command-line>: warning: 'crypto_kem_ntruhps4096821_ref_constbranchindex_sample_fg' reading 3895 bytes from a region of size 32 [-Wstringop-overread]
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: owcpa.c:77:3: note: in expansion of macro 'sample_fg'
owcpa.c: 77 | sample_fg(f,g,seed);
owcpa.c: | ^~~~~~~~~
owcpa.c: <command-line>: note: referencing argument 3 of type 'const unsigned char *'
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: owcpa.c:77:3: note: in expansion of macro 'sample_fg'
owcpa.c: 77 | sample_fg(f,g,seed);
owcpa.c: | ^~~~~~~~~
owcpa.c: <command-line>: note: in a call to function 'crypto_kem_ntruhps4096821_ref_constbranchindex_sample_fg'
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: sample.h:11:6: note: in expansion of macro 'sample_fg'
owcpa.c: 11 | void sample_fg(poly *f, poly *g, const unsigned char uniformbytes[NTRU_SAMPLE_FG_BYTES]);
owcpa.c: | ^~~~~~~~~
pack3.c: pack3.c:3:36: warning: argument 1 of type 'unsigned char[328]' with mismatched bound [-Warray-parameter=]
pack3.c: 3 | void poly_S3_tobytes(unsigned char msg[NTRU_OWCPA_MSGBYTES], const poly *a)
pack3.c: | ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: In file included from pack3.c:1:
pack3.c: poly.h:32:36: note: previously declared as 'unsigned char[164]'
pack3.c: 32 | void poly_S3_tobytes(unsigned char msg[NTRU_PACK_TRINARY_BYTES], const poly *a);
pack3.c: | ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: pack3.c:19:53: warning: argument 2 of type 'const unsigned char[328]' with mismatched bound [-Warray-parameter=]
pack3.c: 19 | void poly_S3_frombytes(poly *r, const unsigned char msg[NTRU_OWCPA_MSGBYTES])
pack3.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: In file included from pack3.c:1:
pack3.c: poly.h:33:53: note: previously declared as 'const unsigned char[164]'
pack3.c: 33 | void poly_S3_frombytes(poly *r, const unsigned char msg[NTRU_PACK_TRINARY_BYTES]);
pack3.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
Number of similar (implementation,compiler) pairs: 4, namely:
Implementation | Compiler |
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) |
Passed TIMECOP
TIMECOP iterations: 1
Number of similar (implementation,compiler) pairs: 26, namely:
Implementation | Compiler |
avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
compact | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
compact | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
compact | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
compact | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
compact | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
compact | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
compact | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
compact | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
compact | 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) |