Implementation notes: amd64, zen3, crypto_sign/rainbow3b

Computer: zen3
Architecture: amd64
CPU ID: AuthenticAMD-00a20f10-178bfbff
SUPERCOP version: 20211108
Operation: crypto_sign
Primitive: rainbow3b

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
852538	144836 0 1049684	172860 964 1051416	`T:avx2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
854668	144896 0 1049684	173228 964 1051416	`T:avx2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2044180	253325 0 1049652	281044 964 1051416	`T:portable`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2049685	253325 0 1049652	281012 964 1051416	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2121148	217832 0 1049652	245284 964 1051416	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2123161	217832 0 1049652	245316 964 1051416	`T:portable`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2275006	21831 0 1049732	43020 940 1051512	`T:avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
2337536	48690 0 1049732	71852 940 1051512	`T:avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
2358470	20625 0 1049732	41244 940 1051512	`T:avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
2433440	12388 0 1049732	32024 932 1051480	`T:avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
2585030	18644 0 1049684	39722 956 1051384	`T:avx2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2931340	22048 0 1049684	42700 964 1051384	`T:avx2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
3638018	126226 0 1049700	149484 940 1051512	`T:portable`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
3642007	126226 0 1049700	149484 940 1051512	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
18004920	59837 0 1049652	83532 964 1051384	`T:portable`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
18020844	59837 0 1049652	83516 964 1051384	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
19432822	25656 0 1049652	46698 956 1051384	`T:portable`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
19443213	25656 0 1049652	46698 956 1051384	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
20797977	21525 0 1049652	42804 964 1051384	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
20823319	21525 0 1049652	42820 964 1051384	`T:portable`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
22818042	22087 0 1049700	43356 940 1051512	`T:portable`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
22820866	22087 0 1049700	43356 940 1051512	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
22889240	21875 0 1049700	42572 940 1051512	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
22889796	21875 0 1049700	42572 940 1051512	`T:portable`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
22910704	10950 0 1049700	30656 932 1051480	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
22914245	10950 0 1049700	30688 932 1051480	`T:portable`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

rainbow.c: In file included from rainbow.c:4:
rainbow.c: In file included from ./rainbow.h:7:
rainbow.c: In file included from ./blas.h:17:
rainbow.c: ./blas_avx2.h:265:39: error: always_inline function '_mm256_setzero_si256' requires target feature 'avx', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx'
rainbow.c: for(unsigned i=0;i<n_ymm;i++) r[i] = _mm256_setzero_si256();
rainbow.c: ^
rainbow.c: ./blas_avx2.h:265:39: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:270:16: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx'
rainbow.c: __m256i bi = _mm256_set1_epi16( b_u16[i] );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:270:16: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:273:18: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx'
rainbow.c: __m256i tmp = _mm256_loadu_si256( (__m256i*)(mat+j*32) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:273:18: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:274:36: error: always_inline function '_mm256_maddubs_epi16' requires target feature 'avx2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx2'
rainbow.c: r[j] = _mm256_add_epi16( r[j] , _mm256_maddubs_epi16( tmp , bi ) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:274:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:274:11: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'avx2'
rainbow.c: r[j] = _mm256_add_epi16( r[j] , _mm256_maddubs_epi16( tmp , bi ) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:274:11: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:282:10: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
rainbow.c: r[j] = _gf31v_reduce_u16_avx2( r[j] );
rainbow.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2