Implementation notes: amd64, comet, crypto_kem/ntruhps2048677
Computer: comet
Microarchitecture: amd64; Comet Lake (806ec)
Architecture: amd64
CPU ID: GenuineIntel-000806ec-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: ntruhps2048677
| Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
|---|
| 93924 | 125788 56065 0 | 187316 56892 1760 | avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 96890 | 145552 56065 0 | 207993 56964 1728 | avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 97597 | 152304 56065 0 | 215089 56964 1792 | avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 109506 | 119136 56065 0 | 178812 56892 1760 | avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 117320 | 119532 56065 0 | 179495 56956 1792 | avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 119142 | 118625 56065 0 | 177809 56964 1728 | avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 129204 | 118276 56065 0 | 177388 56892 1760 | avx2 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 139516 | 115250 56065 0 | 173276 56884 1728 | avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 878705 | 71662 0 0 | 134079 868 1792 | compact | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 885698 | 48049 0 0 | 110151 868 1728 | compact | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 998433 | 27420 0 0 | 89046 796 1760 | compact | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 1320570 | 41177 0 0 | 102447 868 1728 | compact | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 3402603 | 35588 0 0 | 97919 868 1728 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 3532954 | 21311 0 0 | 82783 868 1728 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 3637149 | 41003 0 0 | 103607 868 1792 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 3905434 | 7345 0 0 | 66583 868 1728 | compact | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 3931383 | 8571 0 0 | 68325 860 1792 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 4165561 | 7014 0 0 | 67013 860 1792 | compact | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 4584740 | 12147 0 0 | 73758 796 1760 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 4604216 | 7234 0 0 | 66926 796 1760 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 4921018 | 5107 0 0 | 64846 796 1760 | compact | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 7365420 | 6097 0 0 | 64126 788 1728 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 7979364 | 3821 0 0 | 61982 788 1728 | compact | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 8659148 | 6642 0 0 | 65668 788 1760 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 9361745 | 6739 0 0 | 65967 868 1728 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 9662312 | 4410 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:360:11: 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:360:11: 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:361:11: 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:361:11: 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:362:11: 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(511,-1,511,-1,511,-1,1023,-1);
poly_s3_inv.c: ^
poly_s3_inv.c: poly_s3_inv.c:362:11: 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:363:11: 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:363:11: 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:364:11: 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:364:11: 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:365:11: 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[2] = _mm256_set1_epi32(0);
poly_s3_inv.c: ^
poly_s3_inv.c: poly_s3_inv.c:365:11: 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:367:11: 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[3211]' 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_ntruhps2048677_avx2_constbranchindex_owcpa_keypair':
owcpa.c: <command-line>: warning: 'crypto_kem_ntruhps2048677_avx2_constbranchindex_sample_fg' reading 3211 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[3211]'
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_ntruhps2048677_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_ntruhps2048677_avx2_constbranchindex_sample_fg' reading 3211 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[272]' 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[136]'
pack3.c: 33 | void poly_S3_tobytes(unsigned char msg[NTRU_PACK_TRINARY_BYTES], const poly *a);
pack3.c: | ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: pack3.c:25:53: warning: argument 2 of type 'const unsigned char[272]' with mismatched bound [-Warray-parameter=]
pack3.c: 25 | 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[136]'
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[3211]' 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_ntruhps2048677_ref_constbranchindex_owcpa_keypair':
owcpa.c: <command-line>: warning: 'crypto_kem_ntruhps2048677_ref_constbranchindex_sample_fg' reading 3211 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[3211]'
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_ntruhps2048677_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_ntruhps2048677_ref_constbranchindex_sample_fg' reading 3211 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[272]' 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[136]'
pack3.c: 32 | void poly_S3_tobytes(unsigned char msg[NTRU_PACK_TRINARY_BYTES], const poly *a);
pack3.c: | ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: pack3.c:25:53: warning: argument 2 of type 'const unsigned char[272]' with mismatched bound [-Warray-parameter=]
pack3.c: 25 | 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[136]'
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) |