Implementation notes: amd64, rumba5, crypto_kem/ntruhps2048677
Computer: rumba5
Microarchitecture: amd64; Zen (800f11)
Architecture: amd64
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20240808
Operation: crypto_kem
Primitive: ntruhps2048677
| Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
|---|
| 118632 | 142605 56065 0 | 201475 56956 1728 | avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 118637 | 135525 56065 0 | 193995 56956 1728 | avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 123159 | 126749 56065 0 | 184237 56916 1760 | avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 136286 | 119648 56065 0 | 175789 56948 1792 | avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 137185 | 120204 56065 0 | 176509 56916 1760 | avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 146163 | 118901 56065 0 | 174379 56956 1728 | avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 148575 | 119840 56065 0 | 175429 56916 1760 | avx2 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 155437 | 116297 56065 0 | 170861 56908 1728 | avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 1005978 | 43582 0 0 | 101749 860 1728 | compact | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 1008542 | 68178 0 0 | 126765 860 1728 | compact | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 1014991 | 21071 0 0 | 78975 820 1760 | compact | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 1090190 | 39234 0 0 | 96845 860 1728 | compact | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 3634107 | 21151 0 0 | 78901 860 1728 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 3883452 | 7181 0 0 | 62685 860 1728 | compact | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 3971070 | 24431 0 0 | 82733 860 1728 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 4018880 | 8607 0 0 | 64487 852 1792 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 4058984 | 29338 0 0 | 87973 860 1728 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 4315105 | 6923 0 0 | 63063 852 1792 | compact | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 4755348 | 12330 0 0 | 69727 820 1760 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 4771730 | 8057 0 0 | 64335 820 1760 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 5040097 | 5225 0 0 | 61927 820 1760 | compact | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 9188186 | 7250 0 0 | 61751 812 1728 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 10022993 | 4164 0 0 | 59151 812 1728 | compact | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 12664177 | 6743 0 0 | 62245 860 1728 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 12680364 | 7726 0 0 | 63245 812 1760 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
| 13055675 | 4782 0 0 | 60781 812 1760 | compact | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
Compiler output
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[0] = _mm256_set_epi32(-1,-1,-1,-1,-1,-1,-1,-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_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: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_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: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[0] = _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:366:11: 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:366:11: 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: F1[2] = _mm256_set1_epi32(0);
poly_s3_inv.c: ^
poly_s3_inv.c: poly_s3_inv.c:367:11: 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:369:11: 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:69:40: warning: argument 3 of type 'const unsigned char[3211]' with mismatched bound [-Warray-parameter=]
owcpa.c: 69 | const unsigned char seed[NTRU_SAMPLE_FG_BYTES])
owcpa.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
owcpa.c: In file included from owcpa.c:2:
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:79:3: note: in expansion of macro 'sample_fg'
owcpa.c: 79 | 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:79:3: note: in expansion of macro 'sample_fg'
owcpa.c: 79 | 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: | ^~~~~~~~~
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: In file included from pack3.c:1:
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 (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:69:40: warning: argument 3 of type 'const unsigned char[3211]' with mismatched bound [-Warray-parameter=]
owcpa.c: 69 | const unsigned char seed[NTRU_SAMPLE_FG_BYTES])
owcpa.c: | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
owcpa.c: In file included from owcpa.c:2:
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:79:3: note: in expansion of macro 'sample_fg'
owcpa.c: 79 | 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:79:3: note: in expansion of macro 'sample_fg'
owcpa.c: 79 | 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: | ^~~~~~~~~
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: In file included from pack3.c:1:
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 (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) |