Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
---|---|---|---|---|---|---|
342652 | 183079 0 0 | 205028 824 1640 | T:avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
347886 | 176926 0 0 | 198588 824 1576 | T:avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
389541 | 162569 0 0 | 181414 816 1640 | T:avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
396703 | 258926 0 0 | 280445 792 1608 | T:avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
450478 | 166430 0 0 | 185869 792 1608 | T:avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
457113 | 165067 0 0 | 183164 824 1576 | T:avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
500831 | 161869 0 0 | 179757 784 1576 | T:avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
524948 | 162183 0 0 | 181173 792 1608 | T:avx2 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
720842 | 36858 0 0 | 59124 824 1640 | T:ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
751587 | 33535 0 0 | 55508 824 1576 | T:ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
789875 | 52618 0 0 | 74046 784 1608 | T:ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
825468 | 27333 0 0 | 48172 824 1576 | T:ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
877389 | 16684 0 0 | 35982 816 1640 | T:ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
978212 | 17220 0 0 | 35740 824 1576 | T:ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
1038919 | 18016 0 0 | 37326 784 1608 | T:ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
1120827 | 17632 0 0 | 36486 784 1608 | T:ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
1282141 | 16881 0 0 | 34630 776 1576 | T:ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240720 | 20240716 |
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx' KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 ); KeccakP-1600-times4-SIMD256.c: ^ KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:42: note: expanded from macro 'Xor_In4' KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\ KeccakP-1600-times4-SIMD256.c: ^ KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u' KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a)) KeccakP-1600-times4-SIMD256.c: ^ KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:42: note: expanded from macro 'Xor_In4' KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\ KeccakP-1600-times4-SIMD256.c: ^ KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u' KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a)) KeccakP-1600-times4-SIMD256.c: ^ KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx' KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:136:42: note: expanded from macro 'Xor_In4' KeccakP-1600-times4-SIMD256.c: lanes1 = LOAD256u( curData1[argIndex]),\ KeccakP-1600-times4-SIMD256.c: ^ KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u' KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a)) KeccakP-1600-times4-SIMD256.c: ^ KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:136:42: note: expanded from macro 'Xor_In4' KeccakP-1600-times4-SIMD256.c: ...
Implementation | Compiler |
T:avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
KeccakP-1600-times4-SIMD256.o KeccakF1600times4_FastLoop_Absorb T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_12rounds_FastLoop_Absorb T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_AddBytes T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_AddLanesAll T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractAndAddBytes T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractAndAddLanesAll T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractBytes T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractLanesAll T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_InitializeAll T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_OverwriteBytes T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_OverwriteLanesAll T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_OverwriteWithZeroes T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_PermuteAll_12rounds T KeccakP-1600-times4-SIMD256.o KeccakP1600times4_PermuteAll_24rounds T consts.o neg2 R consts.o neg4 R consts.o q_vector R consts.o qinv_vector R cpapke.o cpapke_dec T cpapke.o cpapke_enc T cpapke.o cpapke_keypair T fips202.o KeccakF1600_StatePermute T fips202.o shake128_absorb T fips202.o shake128_squeezeblocks T fips202.o shake256 T fips202x4.o shake128x4 T fips202x4.o shake256x4 T ntt.o bitrev_vector T ntt.o mul_coefficients T ntt.o ntt T ntt_double.o _ntt_double1024 T ntt_double.o _ntt_double512 T ntt_double.o _pwmul_double1024 T ntt_double.o _pwmul_double512 T ntt_double.o ntt_double1024 T ntt_double.o ntt_double512 T ntt_double.o pwmul_double1024 T ntt_double.o pwmul_double512 T poly.o poly_add T poly.o poly_compress T poly.o poly_decompress T poly.o poly_frombytes T poly.o poly_frommsg T poly.o poly_invntt T poly.o poly_ntt T poly.o poly_pointwise T poly.o poly_sample T poly.o poly_sub T poly.o poly_tobytes T poly.o poly_tomsg T poly.o poly_uniform T precomp.o omegas_double R precomp.o omegas_inv_double R precomp.o psis_bitrev R precomp.o psis_inv R reduce.o barrett_reduce T reduce.o montgomery_reduce T verify.o cmov T verify.o verify T
Implementation | Compiler |
T:avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
cpapke.o cpapke_dec T cpapke.o cpapke_enc T cpapke.o cpapke_keypair T fips202.o KeccakF1600_StatePermute T fips202.o shake128_absorb T fips202.o shake128_squeezeblocks T fips202.o shake256 T ntt.o bitrev_vector T ntt.o mul_coefficients T ntt.o ntt T poly.o poly_add T poly.o poly_compress T poly.o poly_decompress T poly.o poly_frombytes T poly.o poly_frommsg T poly.o poly_invntt T poly.o poly_mul_pointwise T poly.o poly_ntt T poly.o poly_sample T poly.o poly_sub T poly.o poly_tobytes T poly.o poly_tomsg T poly.o poly_uniform T precomp.o omegas_bitrev_montgomery R precomp.o omegas_inv_bitrev_montgomery R precomp.o psis_bitrev_montgomery R precomp.o psis_inv_montgomery R reduce.o montgomery_reduce T verify.o cmov T verify.o verify T
Implementation | Compiler |
T:ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:ref | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:ref | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:ref | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:ref | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:ref | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |