Implementation notes: amd64, zen3, crypto_sign/rainbow4a

Computer: zen3
Architecture: amd64
CPU ID: AuthenticAMD-00a20f10-178bfbff
SUPERCOP version: 20211108
Operation: crypto_sign
Primitive: rainbow4a

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
835641	58145 8 1048676	67092 948 1050456	`T:avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
862230	40115 8 1048676	55540 948 1050456	`T:avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
873850	35731 8 1048660	51970 964 1050360	`T:avx2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
880660	39908 8 1048660	55620 972 1050360	`T:avx2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
919156	144285 8 1048660	141316 972 1050392	`T:avx2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
929758	160471 8 1048660	153060 972 1050392	`T:avx2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
1102831	25528 8 1048676	41680 940 1050424	`T:avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
1224148	39185 8 1048676	53540 948 1050456	`T:avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
1749238	151896 0 1048628	180364 964 1050392	`T:portable`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2362868	92716 0 1048644	116012 940 1050456	`T:portable`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
2432691	146828 0 1048628	175692 964 1050392	`T:portable`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2740100	53861 0 1048628	77852 964 1050360	`T:portable`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2834634	32892 0 1048628	53402 956 1050360	`T:portable`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
2944259	28482 0 1048628	49748 964 1050360	`T:portable`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
3174270	21268 0 1048644	42596 940 1050456	`T:portable`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
3550877	21814 0 1048644	42572 940 1050456	`T:portable`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
5808061	9956 0 1048644	29784 932 1050424	`T:portable`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
11027504	114851 0 1048644	138092 940 1050456	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
13923092	83087 0 1048628	105972 964 1050360	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
14932007	108034 0 1048628	134804 964 1050392	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
15223973	103560 0 1048628	130252 964 1050392	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
30928144	22266 0 1048644	43588 940 1050456	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
31683103	21493 0 1048644	42284 940 1050456	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220207	20211108
32013846	33159 0 1048628	54404 964 1050360	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108
35360038	30921 0 1048628	51954 956 1050360	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220207	20211108

Test failure

Implementation: T:ref
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE

error 142

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

Compiler	Implementations
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref

Compiler output

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

mpkc_avx2.c: In file included from mpkc_avx2.c:4:
mpkc_avx2.c: In file included from ./blas.h:21:
mpkc_avx2.c: ./blas_avx2.h:137:19: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'gf16mat_prod_avx2' that is compiled without support for 'avx'
mpkc_avx2.c: __m256i mask_f = _mm256_load_si256( (__m256i*)__mask_low);
mpkc_avx2.c: ^
mpkc_avx2.c: ./blas_avx2.h:137:19: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mpkc_avx2.c: ./blas_avx2.h:142:40: error: always_inline function '_mm256_setzero_si256' requires target feature 'avx', but would be inlined into function 'gf16mat_prod_avx2' that is compiled without support for 'avx'
mpkc_avx2.c: for(unsigned i=0;i<n_ymm;i++) r0[i] = _mm256_setzero_si256();
mpkc_avx2.c: ^
mpkc_avx2.c: ./blas_avx2.h:142:40: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mpkc_avx2.c: ./blas_avx2.h:143:40: error: always_inline function '_mm256_setzero_si256' requires target feature 'avx', but would be inlined into function 'gf16mat_prod_avx2' that is compiled without support for 'avx'
mpkc_avx2.c: for(unsigned i=0;i<n_ymm;i++) r1[i] = _mm256_setzero_si256();
mpkc_avx2.c: ^
mpkc_avx2.c: ./blas_avx2.h:143:40: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mpkc_avx2.c: ./blas_avx2.h:148:32: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'gf16mat_prod_avx2' that is compiled without support for 'avx'
mpkc_avx2.c: __m256i lx = tbl32_gf16_log( _mm256_load_si256((__m256i*)(x+i*32)) );
mpkc_avx2.c: ^
mpkc_avx2.c: ./blas_avx2.h:148:32: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mpkc_avx2.c: ./blas_avx2.h:148:16: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
mpkc_avx2.c: __m256i lx = tbl32_gf16_log( _mm256_load_si256((__m256i*)(x+i*32)) );
mpkc_avx2.c: ^
mpkc_avx2.c: ./blas_avx2.h:149:3: error: always_inline function '_mm256_store_si256' requires target feature 'avx', but would be inlined into function 'gf16mat_prod_avx2' that is compiled without support for 'avx'
mpkc_avx2.c: _mm256_store_si256((__m256i*)(x+i*32),lx);
mpkc_avx2.c: ^
mpkc_avx2.c: ./blas_avx2.h:149:3: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mpkc_avx2.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