Implementation notes: amd64, cherry, crypto_sign/rainbow4a

Computer: cherry
Microarchitecture: amd64; Silvermont (406c4)
Architecture: amd64
CPU ID: GenuineIntel-000406c4-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_sign
Primitive: rainbow4a
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
696383842705 0 104862862644 916 1050360T:portableclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070420240625
703659850370 0 104862871956 916 1050360T:portableclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070420240625
720988126406 0 104862844682 908 1050360T:portableclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070420240625
763150420809 0 104864440132 892 1050424T:portablegcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070420240625
770973452875 0 104862874004 916 1050360T:portableclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070420240625
881576221380 0 104864440284 892 1050424T:portablegcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070420240625
156337409087 0 104864427093 892 1050424T:portablegcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070420240625
2019015412316 0 104862831346 908 1050360T:portableclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070420240625

Test failure


error 111

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
T:portablegcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)

Test failure


error 142
Alarm clock

Number of similar (implementation,compiler) pairs: 9, namely:
ImplementationCompiler
T:refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
T:refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
T:refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
T:refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
T:refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
T:refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)

Compiler output


mpkc.c: In file included from mpkc.c:4:
mpkc.c: In file included from ./blas.h:21:
mpkc.c: ./blas_avx2.h:59:18: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'gf16v_madd_avx2' that is compiled without support for 'avx'
mpkc.c:         __m256i m_tab = _mm256_load_si256( (__m256i*) (__gf16_mul + 32*b) );
mpkc.c:                         ^
mpkc.c: ./blas_avx2.h:59:18: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mpkc.c: ./blas_avx2.h:60:15: error: '__builtin_ia32_permti256' needs target feature avx2
mpkc.c:         __m256i ml = _mm256_permute2x128_si256( m_tab , m_tab , 0 );
mpkc.c:                      ^
mpkc.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:821:12: note: expanded from macro '_mm256_permute2x128_si256'
mpkc.c:   (__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M))
mpkc.c:            ^
mpkc.c: In file included from mpkc.c:4:
mpkc.c: In file included from ./blas.h:21:
mpkc.c: ./blas_avx2.h:61:15: error: '__builtin_ia32_permti256' needs target feature avx2
mpkc.c:         __m256i mh = _mm256_permute2x128_si256( m_tab , m_tab , 0x11 );
mpkc.c:                      ^
mpkc.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:821:12: note: expanded from macro '_mm256_permute2x128_si256'
mpkc.c:   (__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M))
mpkc.c:            ^
mpkc.c: In file included from mpkc.c:4:
mpkc.c: In file included from ./blas.h:21:
mpkc.c: ./blas_avx2.h:62:17: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'gf16v_madd_avx2' that is compiled without support for 'avx'
mpkc.c:         __m256i mask = _mm256_load_si256( (__m256i*) __mask_low );
mpkc.c:                        ^
mpkc.c: ...

Number of similar (implementation,compiler) pairs: 5, namely:
ImplementationCompiler
T:avx2clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
T:avx2clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
T:avx2clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
T:avx2clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
T:avx2clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)

Compiler output


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:       | ^
mpkc.c: In file included from blas_avx2.h:11,
mpkc.c:                  from blas.h:21,
mpkc.c:                  from mpkc.c:4:
mpkc.c: gf16_avx2.h: In function 'tbl32_gf4_x2':
mpkc.c: gf16_avx2.h:25:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mpkc.c:    25 | {
mpkc.c:       | ^
mpkc.c: gf16_avx2.h: In function 'tbl32_gf16_log':
mpkc.c: gf16_avx2.h:70:23: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mpkc.c:    70 | static inline __m256i tbl32_gf16_log( __m256i a )
mpkc.c:       |                       ^~~~~~~~~~~~~~
mpkc.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
mpkc.c:                  from blas_avx2.h:6,
mpkc.c:                  from blas.h:21,
mpkc.c:                  from mpkc.c:4:
mpkc.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
mpkc.c:   588 | _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
mpkc.c:       | ^~~~~~~~~~~~~~~~~~~
mpkc.c: In file included from blas_avx2.h:11,
mpkc.c:                  from blas.h:21,
mpkc.c:                  from mpkc.c:4:
mpkc.c: gf16_avx2.h:73:9: note: called from here
mpkc.c:    73 |  return _mm256_shuffle_epi8(tab_l,a);
mpkc.c:       |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
mpkc.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:51,
mpkc.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
T:avx2gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:avx2gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:avx2gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
T:avx2gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)