Implementation notes: amd64, speed2supercop, crypto_kem/lightsaber2
Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240808
Operation: crypto_kem
Primitive: lightsaber2
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
100524 | 70499 0 0 | 90869 800 1568 | T:avx2_nttmul | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
105796 | 58765 0 0 | 78877 800 1568 | T:avx2_nttmul | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
109632 | 153331 0 0 | 169261 800 1568 | T:avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
112944 | 58976 0 0 | 79613 760 1600 | T:avx2_nttmul | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
121640 | 73482 0 0 | 94117 760 1600 | T:avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
121848 | 116872 0 0 | 133173 800 1568 | T:avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
122756 | 25927 0 0 | 44847 792 1632 | T:avx2_nttmul | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
128724 | 26792 0 0 | 45413 760 1600 | T:avx2_nttmul | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
130260 | 28386 0 0 | 46445 800 1568 | T:avx2_nttmul | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
132984 | 27987 0 0 | 46943 792 1632 | T:avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
136128 | 31439 0 0 | 50093 760 1600 | T:avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
136748 | 43859 0 0 | 62005 800 1568 | T:avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
143412 | 24510 0 0 | 41733 752 1568 | T:avx2_nttmul | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
146848 | 25232 0 0 | 43573 760 1600 | T:avx2_nttmul | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
150468 | 27143 0 0 | 45501 760 1600 | T:avx2 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
152808 | 25009 0 0 | 42277 752 1568 | T:avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240812 | 20240808 |
153716 | 77444 0 0 | 97044 808 1568 | T:ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
166980 | 65017 0 0 | 84492 808 1568 | T:ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
169916 | 59967 0 0 | 80684 768 1600 | T:ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
220208 | 92668 0 0 | 113205 808 1568 | T:ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
643168 | 13832 0 0 | 32862 800 1632 | T:ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
675224 | 16338 0 0 | 34533 808 1568 | T:ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
698272 | 14197 0 0 | 32908 768 1600 | T:ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
732280 | 12587 0 0 | 31012 768 1600 | T:ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
870208 | 11702 0 0 | 28996 760 1568 | T:ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
Compiler output
SABER_indcpa.c: In file included from SABER_indcpa.c:9:
SABER_indcpa.c: In file included from ././polymul/toom-cook_4way.c:6:
SABER_indcpa.c: ././polymul/scm_avx.c:40:13: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
SABER_indcpa.c: c_avx[0] = mul_add(a0, b0, c_avx[0]);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:43:9: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new3_acc' that is compiled without support for 'avx2'
SABER_indcpa.c: temp = _mm256_mullo_epi16 (a0, b1);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:43:9: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
SABER_indcpa.c: ././polymul/scm_avx.c:44:7: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
SABER_indcpa.c: temp=mul_add(a1, b0, temp);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:45:13: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new3_acc' that is compiled without support for 'avx2'
SABER_indcpa.c: c_avx[1] = _mm256_add_epi16(temp, c_avx[1]);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:45:13: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
SABER_indcpa.c: ././polymul/scm_avx.c:48:9: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new3_acc' that is compiled without support for 'avx2'
SABER_indcpa.c: temp = _mm256_mullo_epi16 (a0, b2);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:48:9: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
SABER_indcpa.c: ././polymul/scm_avx.c:49:9: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
SABER_indcpa.c: temp = mul_add(a1, b1, temp);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:50:7: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
SABER_indcpa.c: temp=mul_add(a2, b0, temp);
SABER_indcpa.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
T:avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
Compiler output
poly.c: poly.c:16:23: warning: unused function 'reduce' [-Wunused-function]
poly.c: static inline __m256i reduce(const __m256i a, const __m256i p, const int16_t *pdata) {
poly.c: ^
poly.c: 1 warning generated.
Number of similar (implementation,compiler) pairs: 4, namely:
Implementation | Compiler |
T:avx2_nttmul | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2_nttmul | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2_nttmul | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2_nttmul | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
Compiler output
poly.c: poly.c:31:26: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i u_pinv = _mm256_set1_epi16(CRT_U_PINV);
poly.c: ^
poly.c: poly.c:31:26: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:32:21: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i u = _mm256_set1_epi16(CRT_U);
poly.c: ^
poly.c: poly.c:32:21: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:33:22: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i p0 = _mm256_load_si256((__m256i *)&PDATA0[_16XP]);
poly.c: ^
poly.c: poly.c:33:22: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:34:22: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i p1 = _mm256_load_si256((__m256i *)&PDATA1[_16XP]);
poly.c: ^
poly.c: poly.c:34:22: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:35:23: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i mod = _mm256_set1_epi16(KEM_Q-1);
poly.c: ^
poly.c: poly.c:35:23: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:36:30: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i mont0_pinv = _mm256_load_si256((__m256i *)&PDATA0[_16XMONT_PINV]);
poly.c: ^
poly.c: poly.c:36:30: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:37:25: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
T:avx2_nttmul | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
Namespace violations
SABER_indcpa.o BS2POLq T
SABER_indcpa.o GenMatrix T
SABER_indcpa.o GenSecret T
SABER_indcpa.o KARA_eval T
SABER_indcpa.o KARA_interpol T
SABER_indcpa.o POL2MSG T
SABER_indcpa.o TC_eval T
SABER_indcpa.o TC_interpol T
SABER_indcpa.o batch_64coefficient_multiplications_new T
SABER_indcpa.o indcpa_kem_dec T
SABER_indcpa.o indcpa_kem_enc T
SABER_indcpa.o indcpa_kem_keypair T
SABER_indcpa.o matrix_vector_mul T
SABER_indcpa.o schoolbook_avx_new2 T
SABER_indcpa.o schoolbook_avx_new3_acc T
SABER_indcpa.o toom_cook_4way_avx_n1 T
SABER_indcpa.o transpose_n1 T
SABER_indcpa.o vector_vector_mul T
cbd.o cbd T
fips202.o KeccakF1600_StatePermute T
fips202.o cshake128_simple T
fips202.o cshake128_simple_absorb T
fips202.o cshake128_simple_squeezeblocks T
fips202.o sha3_256 T
fips202.o sha3_512 T
fips202.o shake128 T
pack_unpack.o BS2POLVEC T
pack_unpack.o BS2POLVECp T
pack_unpack.o BS2POLVECq T
pack_unpack.o POLVEC2BS T
pack_unpack.o POLVECp2BS T
pack_unpack.o POLVECq2BS T
pack_unpack.o SABER_pack10bit T
pack_unpack.o SABER_pack11bit T
pack_unpack.o SABER_pack13bit T
pack_unpack.o SABER_pack14bit T
pack_unpack.o SABER_pack_3bit T
pack_unpack.o SABER_pack_4bit T
pack_unpack.o SABER_pack_6bit T
pack_unpack.o SABER_poly_un_pack13bit T
pack_unpack.o SABER_un_pack10bit T
pack_unpack.o SABER_un_pack11bit T
pack_unpack.o SABER_un_pack13bit T
pack_unpack.o SABER_un_pack14bit T
pack_unpack.o SABER_un_pack3bit T
pack_unpack.o SABER_un_pack4bit T
pack_unpack.o SABER_un_pack6bit T
poly.o poly_getnoise T
verify.o cmov T
verify.o verify T
Number of similar (implementation,compiler) pairs: 8, namely:
Implementation | Compiler |
T:avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
T:avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
T:avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
T:avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
Namespace violations
SABER_indcpa.o GenMatrix T
SABER_indcpa.o GenSecret T
SABER_indcpa.o indcpa_kem_dec T
SABER_indcpa.o indcpa_kem_enc T
SABER_indcpa.o indcpa_kem_keypair T
basemul256x1.o nttmul_poly_basemul_montgomery T
basemul256x1.o nttmul_polyvec_basemul_acc_montgomery T
cbd.o cbd T
consts256n10753.o nttmul_pdata10753 R
consts256n7681.o nttmul_pdata7681 R
fips202.o KeccakF1600_StatePermute T
fips202.o cshake128_simple T
fips202.o cshake128_simple_absorb T
fips202.o cshake128_simple_squeezeblocks T
fips202.o sha3_256 T
fips202.o sha3_512 T
fips202.o shake128 T
invntt256n.o nttmul_poly_invntt_tomont T
ntt256n.o nttmul_poly_ntt T
pack_unpack.o BS2POLT T
pack_unpack.o BS2POLVEC T
pack_unpack.o BS2POLVECp T
pack_unpack.o BS2POLVECq T
pack_unpack.o BS2POLq T
pack_unpack.o POL2MSG T
pack_unpack.o POLT2BS T
pack_unpack.o POLVEC2BS T
pack_unpack.o POLVECp2BS T
pack_unpack.o POLVECq2BS T
poly.o nttmul_poly_add T
poly.o nttmul_poly_crt T
poly.o nttmul_poly_mul T
poly.o nttmul_poly_sub T
polyvec.o nttmul_polyvec_crt T
polyvec.o nttmul_polyvec_invntt_tomont T
polyvec.o nttmul_polyvec_iprod T
polyvec.o nttmul_polyvec_iprod2 T
polyvec.o nttmul_polyvec_matrix_vector_mul T
polyvec.o nttmul_polyvec_matrix_vector_mul2 T
polyvec.o nttmul_polyvec_ntt T
verify.o cmov T
verify.o verify T
Number of similar (implementation,compiler) pairs: 8, namely:
Implementation | Compiler |
T:avx2_nttmul | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2_nttmul | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2_nttmul | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2_nttmul | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
T:avx2_nttmul | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
T:avx2_nttmul | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
T:avx2_nttmul | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
T:avx2_nttmul | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |