Implementation notes: amd64, latour, crypto_sign/rainbow1b

Computer: latour
Architecture: amd64
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20201130
Operation: crypto_sign
Primitive: rainbow1b

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
7298316	317511 0 1049700	338746 848 1051352	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200901	20200826
7347240	317511 0 1049700	338746 848 1051352	`T:portable`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200901	20200826
11168046	27830 0 1049700	46530 848 1051352	`T:portable`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200901	20200826
11176740	27830 0 1049700	46530 848 1051352	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200901	20200826
11421954	98174 0 1049652	116588 896 1051256	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
11422647	98174 0 1049652	116604 896 1051256	`T:portable`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
11424195	98174 0 1049652	116604 896 1051256	`T:portable`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
11437371	98174 0 1049652	116588 896 1051256	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
11447910	98058 0 1049652	117308 896 1051256	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
11453751	98810 0 1049652	118156 896 1051256	`T:portable`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
11455848	98810 0 1049652	118140 896 1051256	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
11468214	98058 0 1049652	117324 896 1051256	`T:portable`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
11471895	28567 0 1049700	47658 848 1051352	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200901	20200826
11477331	28567 0 1049700	47658 848 1051352	`T:portable`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200901	20200826
11952855	21028 0 1049652	38634 888 1051256	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
11960388	21028 0 1049652	38650 888 1051256	`T:portable`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200901	20200826
15558813	10622 0 1049700	28595 848 1051320	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200901	20200826
15582132	10622 0 1049700	28627 848 1051320	`T:portable`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200901	20200826

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -march=native -O2 -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 'xsave', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'xsave'
rainbow.c: for(unsigned i=0;i<n_ymm;i++) r[i] = _mm256_setzero_si256();
rainbow.c: ^
rainbow.c: ./blas_avx2.h:270:16: error: always_inline function '_mm256_set1_epi16' requires target feature 'xsave', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'xsave'
rainbow.c: __m256i bi = _mm256_set1_epi16( b_u16[i] );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:273:18: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'xsave'
rainbow.c: __m256i tmp = _mm256_loadu_si256( (__m256i*)(mat+j*32) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:274:11: error: always_inline function '_mm256_add_epi16' requires target feature 'xsave', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'xsave'
rainbow.c: r[j] = _mm256_add_epi16( r[j] , _mm256_maddubs_epi16( tmp , bi ) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:274:36: error: always_inline function '_mm256_maddubs_epi16' requires target feature 'xsave', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'xsave'
rainbow.c: r[j] = _mm256_add_epi16( r[j] , _mm256_maddubs_epi16( tmp , bi ) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:287:10: error: always_inline function '_mm256_packs_epi16' requires target feature 'xsave', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'xsave'
rainbow.c: r[j] = _mm256_packs_epi16( r[j*2] , r[j*2+1] );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:288:10: error: always_inline function '_mm256_setzero_si256' requires target feature 'xsave', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'xsave'
rainbow.c: r[j] = _mm256_permute4x64_epi64( r[j] , 0xd8 ); // 3,1,2,0
rainbow.c: ^
rainbow.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:877:44: note: expanded from macro '_mm256_permute4x64_epi64'
rainbow.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2

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 'sse4.2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'sse4.2'
rainbow.c: for(unsigned i=0;i<n_ymm;i++) r[i] = _mm256_setzero_si256();
rainbow.c: ^
rainbow.c: ./blas_avx2.h:270:16: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'sse4.2'
rainbow.c: __m256i bi = _mm256_set1_epi16( b_u16[i] );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:273:18: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'sse4.2'
rainbow.c: __m256i tmp = _mm256_loadu_si256( (__m256i*)(mat+j*32) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:274:11: error: always_inline function '_mm256_add_epi16' requires target feature 'sse4.2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'sse4.2'
rainbow.c: r[j] = _mm256_add_epi16( r[j] , _mm256_maddubs_epi16( tmp , bi ) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:274:36: error: always_inline function '_mm256_maddubs_epi16' requires target feature 'sse4.2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'sse4.2'
rainbow.c: r[j] = _mm256_add_epi16( r[j] , _mm256_maddubs_epi16( tmp , bi ) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:287:10: error: always_inline function '_mm256_packs_epi16' requires target feature 'sse4.2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'sse4.2'
rainbow.c: r[j] = _mm256_packs_epi16( r[j*2] , r[j*2+1] );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:288:10: error: always_inline function '_mm256_setzero_si256' requires target feature 'sse4.2', but would be inlined into function 'gf31mat_prod_avx2' that is compiled without support for 'sse4.2'
rainbow.c: r[j] = _mm256_permute4x64_epi64( r[j] , 0xd8 ); // 3,1,2,0
rainbow.c: ^
rainbow.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:877:44: note: expanded from macro '_mm256_permute4x64_epi64'
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

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

blas.c: In file included from blas.h:17:0,
blas.c: from blas.c:1:
blas.c: blas_avx2.h: In function '_gf31v_u8_to_u16_avx2':
blas.c: blas_avx2.h:17:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
blas.c: __m256i _gf31v_u8_to_u16_avx2( __m128i a ) {
blas.c: ^
rainbow.c: In file included from blas.h:17:0,
rainbow.c: from rainbow.h:7,
rainbow.c: from rainbow.c:4:
rainbow.c: blas_avx2.h: In function '_gf31v_u8_to_u16_avx2':
rainbow.c: blas_avx2.h:17:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
rainbow.c: __m256i _gf31v_u8_to_u16_avx2( __m128i a ) {
rainbow.c: ^
rainbow.c: blas_avx2.h: In function '_gf31v_reduce_u16_avx2':
rainbow.c: blas_avx2.h:110:9: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
rainbow.c: __m256i _gf31v_reduce_u16_avx2( __m256i a ){
rainbow.c: ^
rainbow.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
rainbow.c: from blas_avx2.h:8,
rainbow.c: from blas.h:17,
rainbow.c: from rainbow.h:7,
rainbow.c: from rainbow.c:4:
rainbow.c: blas_avx2.h: In function '_gf31v_u8_to_u16_avx2':
rainbow.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:742:1: error: inlining failed in call to always_inline '_mm256_insertf128_si256': target specific option mismatch
rainbow.c: _mm256_insertf128_si256 (__m256i __X, __m128i __Y, const int __O)
rainbow.c: ^
rainbow.c: In file included from blas.h:17:0,
rainbow.c: from rainbow.h:7,
rainbow.c: from rainbow.c:4:
rainbow.c: blas_avx2.h:22:9: error: called from here
rainbow.c: return _mm256_insertf128_si256 ( _mm256_castsi128_si256(a0) , a1 , 1 );
rainbow.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2

Namespace violations

Implementation: T:portable
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

gf31_convert.o gf31_from_digest T
gf31_convert.o gf31_quick_pack T
gf31_convert.o gf31_quick_unpack T
gf31_convert.o gf31_sanity_check T
hash_utils.o sha2_chain T
hash_utils.o sha2_chain_byte T
hash_utils.o sha2_chain_file T
hash_utils.o sha2_chain_msg T
hash_utils.o sha2_file T
prng_utils.o prng_bytes T
prng_utils.o prng_dump T
prng_utils.o prng_dump_set T
prng_utils.o prng_expand_buffer T
prng_utils.o userrand_bytes T
prng_utils.o userrand_dump_generated T
prng_utils.o userrand_source_file T
rainbow.o rainbow_central_map T
rainbow.o rainbow_genkey T
rainbow.o rainbow_genkey_debug T
rainbow.o rainbow_ivs_central_map T
rainbow.o rainbow_pubmap_seckey T
rainbow.o rainbow_secmap T
rainbow.o rainbow_sign T
rainbow.o rainbow_verify T

Number of similar (compiler,implementation) pairs: 18, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:portable
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:portable
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:portable
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:portable
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:portable
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:portable
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:portable
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:portable
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:portable
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref