Implementation notes: amd64, comet, crypto_kem/ntruhps4096821
Computer: comet
Microarchitecture: amd64; Comet Lake (806ec)
Architecture: amd64
CPU ID: GenuineIntel-000806ec-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: ntruhps4096821
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
112998 | 168800 81120 0 | 230324 81916 1760 | avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
116395 | 174856 81120 0 | 237273 81988 1728 | avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
117841 | 183914 81120 0 | 246617 81988 1792 | avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
138230 | 151664 81120 0 | 211324 81916 1760 | avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
141533 | 151399 81120 0 | 211367 81980 1792 | avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
146524 | 150089 81120 0 | 209281 81988 1728 | avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
150472 | 149136 81120 0 | 208268 81916 1760 | avx2 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
166001 | 143803 81120 0 | 201852 81908 1728 | avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
1099968 | 46250 0 0 | 108359 868 1728 | compact | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
1102349 | 58918 0 0 | 121343 868 1792 | compact | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
1290068 | 27846 0 0 | 89430 796 1760 | compact | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
1881109 | 40471 0 0 | 101775 868 1728 | compact | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
5025562 | 37299 0 0 | 99743 868 1792 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
5070840 | 19163 0 0 | 80639 868 1728 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
5350490 | 29684 0 0 | 91903 868 1728 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
5575646 | 7299 0 0 | 66519 868 1728 | compact | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
5706323 | 7900 0 0 | 67589 860 1792 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
6060655 | 6908 0 0 | 66885 860 1792 | compact | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
6696060 | 19216 0 0 | 80846 796 1760 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
6706165 | 6376 0 0 | 66054 796 1760 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
7181646 | 5379 0 0 | 65110 796 1760 | compact | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
11019079 | 5285 0 0 | 63294 788 1728 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
11630015 | 3770 0 0 | 61918 788 1728 | compact | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
12462898 | 5803 0 0 | 64828 788 1760 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
13727989 | 6161 0 0 | 65375 868 1728 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
14151588 | 4359 0 0 | 63596 788 1760 | compact | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 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 (Debian_Clang_14.0.6) |
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[3895]'
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: | ^~~~~~~~~
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: ...
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: 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 (12.2.0) |
avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
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[3895]'
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: | ^~~~~~~~~
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: ...
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: 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 (12.2.0) |
ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
ref | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
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 (Debian_Clang_14.0.6) |
avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
compact | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
compact | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
compact | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
compact | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
compact | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
compact | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
compact | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
compact | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
compact | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
ref | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
ref | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
ref | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
ref | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
ref | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |
ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |