Implementation notes: amd64, speed2supercop, crypto_kem/lac128

Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: lac128

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
225668	30014 39080 620	49197 39952 2144	`T:avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
229536	17118 39080 620	34239 39944 2208	`T:avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
235844	18327 39080 620	34630 39952 2144	`T:avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
242056	14039 39104 664	29828 39944 2208	`T:avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
251728	17417 39104 664	34004 39952 2240	`T:avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
254556	17914 39104 664	34804 39952 2240	`T:avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
262188	31868 39104 664	50132 39952 2240	`T:avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
263808	39288 39080 620	58213 39952 2144	`T:avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
499000	43434 39080 620	62437 39952 2144	`T:opt`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
509488	29061 39080 620	48301 39952 2144	`T:opt`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
542668	17432 39080 620	34623 39944 2208	`T:opt`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
635240	28886 39080 620	46446 39952 2144	`T:opt`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
768424	17951 39104 664	34500 39952 2240	`T:opt`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
873620	18865 39080 620	35206 39952 2144	`T:opt`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
928856	14470 39104 664	30284 39944 2208	`T:opt`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
1681396	34745 0 60	52740 840 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
1701360	20502 39104 664	37388 39952 2240	`T:opt`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
1706656	32916 39104 664	51132 39952 2240	`T:opt`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
2489068	17534 0 60	34156 840 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
2606316	29154 0 60	48125 864 1568	`T:ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
2651616	38148 0 60	56893 864 1568	`T:ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
3372764	16682 0 60	33615 856 1632	`T:ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
4577804	28097 0 60	45398 864 1568	`T:ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
5021820	17220 0 60	33374 864 1568	`T:ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
5405844	16859 0 60	33204 840 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625
5602580	13523 0 60	29124 832 1600	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240711	20240625

Compiler output

bin-lwe.c: bin-lwe.c:91:10: error: always_inline function '_mm256_set_epi16' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.c:         tmp_one=_mm256_set_epi16(1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1);
bin-lwe.c:                 ^
bin-lwe.c: bin-lwe.c:91:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:103:9: error: always_inline function '_mm256_setzero_si256' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.c:                 tmp2 =_mm256_setzero_si256();
bin-lwe.c:                       ^
bin-lwe.c: bin-lwe.c:103:9: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:106:11: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.c:                         tmp0 = _mm256_loadu_si256((__m256i *)(v_p+j));
bin-lwe.c:                                ^
bin-lwe.c: bin-lwe.c:106:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:107:11: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.c:                         tmp1 = _mm256_loadu_si256((__m256i *)(s+j));
bin-lwe.c:                                ^
bin-lwe.c: bin-lwe.c:107:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:108:11: error: always_inline function '_mm256_maddubs_epi16' requires target feature 'avx2', but would be inlined into function 'poly_mul' that is compiled without support for 'avx2'
bin-lwe.c:                         tmp0 = _mm256_maddubs_epi16(tmp0, tmp1);
bin-lwe.c:                                ^
bin-lwe.c: bin-lwe.c:108:11: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:109:11: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'poly_mul' that is compiled without support for 'avx2'
bin-lwe.c:                         tmp2 = _mm256_add_epi16(tmp2, tmp0);
bin-lwe.c:                                ^
bin-lwe.c: bin-lwe.c:109:11: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:111:11: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.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))`