Implementation notes: amd64, jasper3, crypto_sign/rainbow1c

Computer: jasper3
Microarchitecture: amd64; Tremont (906c0)
Architecture: amd64
CPU ID: GenuineIntel-000906c0-20-bfebfbff
SUPERCOP version: 20231107
Operation: crypto_sign
Primitive: rainbow1c

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
3978620	57116 0 1048628	75090 908 1050360	`T:portable`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
4418630	26971 0 1048644	46052 892 1050424	`T:portable`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
4496156	61598 0 1048628	81420 916 1050360	`T:portable`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
4503359	66448 0 1048628	87180 916 1050360	`T:portable`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
4513331	67382 0 1048628	89460 916 1050360	`T:portable`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
4768450	27117 0 1048644	45796 892 1050424	`T:portable`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
8727959	9239 0 1048644	26997 892 1050424	`T:portable`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
9631536	12180 0 1048628	30978 908 1050360	`T:portable`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
10048216	156141 0 1048644	176452 892 1050424	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
17999557	81269 0 1048628	102316 916 1050360	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
18261190	71309 0 1048628	90084 916 1050360	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
18651916	83983 0 1048628	103844 916 1050360	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230603	20230530
27274456	23639 0 1048644	42772 892 1050424	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
29182421	22451 0 1048644	41132 892 1050424	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
29268992	47377 0 1048628	65266 908 1050360	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
44940769	8344 0 1048644	26045 892 1050424	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
61202870	11156 0 1048628	29906 908 1050360	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530

Test failure

Implementation: T:portable
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

error 111

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

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:portable

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:21:
rainbow.c: ./blas_avx2.h:200:19: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'gf256mat_prod_multab_avx2' that is compiled without support for 'avx'
rainbow.c: __m256i mask_f = _mm256_load_si256((__m256i const *) __mask_low);
rainbow.c: ^
rainbow.c: ./blas_avx2.h:200:19: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:204:39: error: always_inline function '_mm256_setzero_si256' requires target feature 'avx', but would be inlined into function 'gf256mat_prod_multab_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:204:39: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:207:16: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'gf256mat_prod_multab_avx2' that is compiled without support for 'avx'
rainbow.c: __m256i mt = _mm256_load_si256( (__m256i*)( multab + i*32) );
rainbow.c: ^
rainbow.c: ./blas_avx2.h:207:16: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
rainbow.c: ./blas_avx2.h:208:16: error: '__builtin_ia32_permti256' needs target feature avx2
rainbow.c: __m256i ml = _mm256_permute2x128_si256(mt,mt,0x00 );
rainbow.c: ^
rainbow.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:821:12: note: expanded from macro '_mm256_permute2x128_si256'
rainbow.c: (__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M))
rainbow.c: ^
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:21:
rainbow.c: ./blas_avx2.h:209:16: error: '__builtin_ia32_permti256' needs target feature avx2
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:21:
rainbow.c: In file included from ./blas_avx2.h:13:
rainbow.c: ./blas_sse.h:661:24: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function '_gf256mat_gauss_elim_sse' that is compiled without support for 'ssse3'
rainbow.c: __m128i madd_mask = _mm_shuffle_epi8( is_madd , _mm_set1_epi8(i_r) );
rainbow.c: ^
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:21:
rainbow.c: In file included from ./blas_avx2.h:11:
rainbow.c: In file included from ./gf16_avx2.h:8:
rainbow.c: ./gf16_sse.h:78:9: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'tbl_gf16_squ_x8' that is compiled without support for 'ssse3'
rainbow.c: return _mm_shuffle_epi8(tab_l,a);
rainbow.c: ^
rainbow.c: ./gf16_sse.h:118:15: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'tbl_gf16_mul' that is compiled without support for 'ssse3'
rainbow.c: __m128i la = _mm_shuffle_epi8(log_16,a);
rainbow.c: ^
rainbow.c: ./gf16_sse.h:119:15: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'tbl_gf16_mul' that is compiled without support for 'ssse3'
rainbow.c: __m128i lb = _mm_shuffle_epi8(log_16,b);
rainbow.c: ^
rainbow.c: ./gf16_sse.h:122:15: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'tbl_gf16_mul' that is compiled without support for 'ssse3'
rainbow.c: __m128i r0 = _mm_shuffle_epi8(exp_16, _mm_sub_epi8(la_lb, mask_f&_mm_cmpgt_epi8(la_lb,mask_f) ) );
rainbow.c: ^
rainbow.c: ./gf16_sse.h:85:9: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'tbl_gf16_inv' that is compiled without support for 'ssse3'
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_avx2.h:11,
blas.c: from blas.h:21,
blas.c: from blas.c:1:
blas.c: gf16_avx2.h: In function 'tbl32_gf4_x2':
blas.c: gf16_avx2.h:25:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
blas.c: 25 | {
blas.c: | ^
rainbow.c: In file included from blas_avx2.h:11,
rainbow.c: from blas.h:21,
rainbow.c: from rainbow.h:7,
rainbow.c: from rainbow.c:4:
rainbow.c: gf16_avx2.h: In function 'tbl32_gf4_x2':
rainbow.c: gf16_avx2.h:25:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
rainbow.c: 25 | {
rainbow.c: | ^
rainbow.c: gf16_avx2.h: In function 'tbl32_gf16_log':
rainbow.c: gf16_avx2.h:70:23: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
rainbow.c: 70 | static inline __m256i tbl32_gf16_log( __m256i a )
rainbow.c: | ^~~~~~~~~~~~~~
rainbow.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
rainbow.c: from blas_avx2.h:6,
rainbow.c: from blas.h:21,
rainbow.c: from rainbow.h:7,
rainbow.c: from rainbow.c:4:
rainbow.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avx2intrin.h:588:1: error: inlining failed in call to 'always_inline' '_mm256_shuffle_epi8': target specific option mismatch
rainbow.c: 588 | _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
rainbow.c: | ^~~~~~~~~~~~~~~~~~~
rainbow.c: In file included from blas_avx2.h:11,
rainbow.c: from blas.h:21,
rainbow.c: from rainbow.h:7,
rainbow.c: from rainbow.c:4:
rainbow.c: gf16_avx2.h:73:9: note: called from here
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