Implementation notes: amd64, margaux, crypto_kem/mceliece348864f

Computer: margaux
Microarchitecture: amd64; Core 2 65nm (6fb)
Architecture: amd64
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20240425
Operation: crypto_kem
Primitive: mceliece348864f
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
1062564118785 0 0214054 860 1728vecclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
1082858117912 0 0213294 860 1728vecclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
111489089812 0 0184436 820 1760vecgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024051120240425
115164979602 0 0173934 860 1728vecclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
121783147717 0 0140902 860 1728vecclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
128296250310 0 0144292 820 1760vecgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024051120240425
132967748117 0 0141428 820 1760vecgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024051120240425
142689844703 0 0136976 852 1728vecclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
145180242057 0 0134052 812 1728vecgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024051120240425
10284691831821 0 0126686 828 1760refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024051120240425
11174735948892 0 0144488 868 1728refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
11200691430708 0 0125136 868 1728refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
12616515549427 0 0144766 860 1728refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
13467439314976 0 0108232 868 1728refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
13636302313562 0 0105986 860 1728refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024051120240425
14471820615791 0 0109044 820 1760refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024051120240425
15161405616944 0 0110942 828 1760refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024051120240425
15195577112678 0 0104750 820 1728refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024051120240425

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
decrypt.c: decrypt.c:213:11: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c: allone = vec256_set1_16b(0xFFFF);
decrypt.c: ^
decrypt.c: decrypt.c:217:17: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c: error256[i] = vec256_or_reduce(eval[i]);
decrypt.c: ^
decrypt.c: decrypt.c:218:17: warning: AVX vector argument of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c: error256[i] = vec256_xor(error256[i], allone);
decrypt.c: ^
decrypt.c: decrypt.c:146:12: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c: out[i] = vec256_set4x(v[0], v[1], v[2], v[3]);
decrypt.c: ^
decrypt.c: In file included from decrypt.c:8:
decrypt.c: In file included from ./fft_tr.h:10:
decrypt.c: ./vec256.h:37:10: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'vec256_set4x' that is compiled without support for 'avx'
decrypt.c: return _mm256_set_epi64x(a3, a2, a1, a0);
decrypt.c: ^
decrypt.c: ./vec256.h:37:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decrypt.c: decrypt.c:52:15: warning: AVX vector argument of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c: out[i][j] = vec256_and(inv[i][j], recv[i]);
decrypt.c: ^
decrypt.c: In file included from decrypt.c:8:
decrypt.c: In file included from ./fft_tr.h:10:
decrypt.c: ./vec256.h:50:9: error: always_inline function '_mm256_and_si256' requires target feature 'avx2', but would be inlined into function 'vec256_and' that is compiled without support for 'avx2'
decrypt.c: return _mm256_and_si256(a, b);
decrypt.c: ...

Number of similar (compiler,implementation) pairs: 10, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
benes.c: In file included from transpose.h:11,
benes.c: from benes.c:9:
benes.c: vec256.h: In function 'vec256_set1_16b':
benes.c: vec256.h:21:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
benes.c: 21 | {
benes.c: | ^
bm.c: In file included from vec128.h:14,
bm.c: from bm.h:10,
bm.c: from bm.c:13:
bm.c: bm.c: In function 'get_coefs':
bm.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:455:1: error: inlining failed in call to 'always_inline' '_mm_extract_epi64': target specific option mismatch
bm.c: 455 | _mm_extract_epi64 (__m128i __X, const int __N)
bm.c: | ^~~~~~~~~~~~~~~~~
bm.c: In file included from bm.h:10,
bm.c: from bm.c:13:
bm.c: vec128.h:28:42: note: called from here
bm.c: 28 | #define vec128_extract(a, i) ((uint64_t) _mm_extract_epi64((vec128) (a), (i)))
bm.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bm.c: bm.c:133:44: note: in expansion of macro 'vec128_extract'
bm.c: 133 | out[ (4*1 + k)*16 + i ] = (vec128_extract(buf[i], 1) >> (k*16)) & GFMASK;
bm.c: | ^~~~~~~~~~~~~~
bm.c: In file included from vec128.h:14,
bm.c: from bm.h:10,
bm.c: from bm.c:13:
bm.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:455:1: error: inlining failed in call to 'always_inline' '_mm_extract_epi64': target specific option mismatch
bm.c: 455 | _mm_extract_epi64 (__m128i __X, const int __N)
bm.c: | ^~~~~~~~~~~~~~~~~
bm.c: In file included from bm.h:10,
bm.c: from bm.c:13:
bm.c: vec128.h:28:42: note: called from here
bm.c: 28 | #define vec128_extract(a, i) ((uint64_t) _mm_extract_epi64((vec128) (a), (i)))
bm.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE avx T:avx
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE avx T:avx
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE avx T:avx
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE avx T:avx

Compiler output

Implementation: sse
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
decrypt.c: In file included from decrypt.c:8:
decrypt.c: In file included from ./fft_tr.h:10:
decrypt.c: ./vec128.h:39:9: error: always_inline function '_mm_testz_si128' requires target feature 'sse4.1', but would be inlined into function 'vec128_testz' that is compiled without support for 'sse4.1'
decrypt.c: return _mm_testz_si128(a, a);
decrypt.c: ^
decrypt.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse

Compiler output

Implementation: sse
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
bm.c: In file included from vec128.h:16,
bm.c: from bm.h:13,
bm.c: from bm.c:13:
bm.c: bm.c: In function 'get_coefs':
bm.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:455:1: error: inlining failed in call to 'always_inline' '_mm_extract_epi64': target specific option mismatch
bm.c: 455 | _mm_extract_epi64 (__m128i __X, const int __N)
bm.c: | ^~~~~~~~~~~~~~~~~
bm.c: In file included from bm.h:13,
bm.c: from bm.c:13:
bm.c: vec128.h:35:42: note: called from here
bm.c: 35 | #define vec128_extract(a, i) ((uint64_t) _mm_extract_epi64((vec128) (a), (i)))
bm.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bm.c: bm.c:133:44: note: in expansion of macro 'vec128_extract'
bm.c: 133 | out[ (4*1 + k)*16 + i ] = (vec128_extract(buf[i], 1) >> (k*16)) & GFMASK;
bm.c: | ^~~~~~~~~~~~~~
bm.c: In file included from vec128.h:16,
bm.c: from bm.h:13,
bm.c: from bm.c:13:
bm.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:455:1: error: inlining failed in call to 'always_inline' '_mm_extract_epi64': target specific option mismatch
bm.c: 455 | _mm_extract_epi64 (__m128i __X, const int __N)
bm.c: | ^~~~~~~~~~~~~~~~~
bm.c: In file included from bm.h:13,
bm.c: from bm.c:13:
bm.c: vec128.h:35:42: note: called from here
bm.c: 35 | #define vec128_extract(a, i) ((uint64_t) _mm_extract_epi64((vec128) (a), (i)))
bm.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE sse
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE sse
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE sse
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE sse