Implementation notes: amd64, h9trinity, crypto_kem/mceliece6960119f

Computer: h9trinity
Architecture: amd64
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20200618
Operation: crypto_kem
Primitive: mceliece6960119f
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
1199694175724 0 0229525 792 1608ssegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
1253745132251 0 0186996 792 1576sseclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
1265531105979 0 0159140 792 1576sseclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
1289467105979 0 0159140 792 1576sseclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
130642382632 0 0134637 792 1608ssegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
133280482215 0 0134077 792 1608ssegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
134437872981 0 0124138 784 1576sseclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
138396075095 0 0126053 784 1576ssegcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
3065336193575 0 0249517 792 1608vecgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
3119215109933 0 0165788 792 1576vecclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
452066667908 0 0122277 792 1608vecgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
458476753380 0 0106725 784 1576vecgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
474370355328 0 0108146 784 1576vecclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
485343969260 0 0123541 792 1608vecgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
5826617115106 0 0172236 792 1576vecclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
582744480911 0 0136332 792 1576vecclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
582930280911 0 0136332 792 1576vecclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
59494897598760 0 0155063 800 1608refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
69679982337739 0 093644 792 1576refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
73201382741753 0 098956 792 1576refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
73787372929291 0 084908 792 1576refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
73807765029291 0 084908 792 1576refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
77229892713610 0 066490 784 1576refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020060220200601
80785880417080 0 071349 792 1608refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
81394498613505 0 066781 784 1576refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601
81432795116957 0 071333 792 1608refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020060220200601

Compiler output

Implementation: crypto_kem/mceliece6960119f/avx
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
bm.c: bm.c:68:2: error: always_inline function '_mm256_slli_epi64' requires target feature 'avx2', but would be inlined into function 'interleave' that is compiled without support for 'avx2'
bm.c: vec256_sll_4x(vec256_and(in[idx1], mask[0]), s));
bm.c: ^
bm.c: ./vec256.h:63:39: note: expanded from macro 'vec256_sll_4x'
bm.c: #define vec256_sll_4x(a, s) ((vec256) _mm256_slli_epi64((vec256) (a), (s)))
bm.c: ^
bm.c: bm.c:70:16: error: always_inline function '_mm256_srli_epi64' requires target feature 'avx2', but would be inlined into function 'interleave' that is compiled without support for 'avx2'
bm.c: y = vec256_or(vec256_srl_4x(vec256_and(in[idx0], mask[1]), s),
bm.c: ^
bm.c: ./vec256.h:64:39: note: expanded from macro 'vec256_srl_4x'
bm.c: #define vec256_srl_4x(a, s) ((vec256) _mm256_srli_epi64((vec256) (a), (s)))
bm.c: ^
bm.c: ./vec256.h:60:9: error: always_inline function '_mm256_or_si256' requires target feature 'avx2', but would be inlined into function 'vec256_or' that is compiled without support for 'avx2'
bm.c: return _mm256_or_si256(a, b);
bm.c: ^
bm.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'
bm.c: return _mm256_and_si256(a, b);
bm.c: ^
bm.c: 4 errors generated.

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx

Compiler output

Implementation: crypto_kem/mceliece6960119f/avx
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
bm.c: bm.c:136:44: error: always_inline function '_mm256_extract_epi64' requires target feature 'sse4.2', but would be inlined into function 'get_coefs' that is compiled without support for 'sse4.2'
bm.c: out[ (4*0 + k)*16 + i ] = (vec256_extract(buf[i], 0) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: bm.c:137:44: error: always_inline function '_mm256_extract_epi64' requires target feature 'sse4.2', but would be inlined into function 'get_coefs' that is compiled without support for 'sse4.2'
bm.c: out[ (4*1 + k)*16 + i ] = (vec256_extract(buf[i], 1) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: bm.c:138:44: error: always_inline function '_mm256_extract_epi64' requires target feature 'sse4.2', but would be inlined into function 'get_coefs' that is compiled without support for 'sse4.2'
bm.c: out[ (4*2 + k)*16 + i ] = (vec256_extract(buf[i], 2) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: bm.c:139:44: error: always_inline function '_mm256_extract_epi64' requires target feature 'sse4.2', but would be inlined into function 'get_coefs' that is compiled without support for 'sse4.2'
bm.c: out[ (4*3 + k)*16 + i ] = (vec256_extract(buf[i], 3) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: ./vec256.h:32:10: error: always_inline function '_mm256_setzero_si256' requires target feature 'sse4.2', but would be inlined into function 'vec256_setzero' that is compiled without support for 'sse4.2'
bm.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx

Compiler output

Implementation: crypto_kem/mceliece6960119f/sse
Compiler: clang -mcpu=native -O3 -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:40:9: error: always_inline function '_mm_testz_si128' requires target feature 'ssse3', but would be inlined into function 'vec128_testz' that is compiled without support for 'ssse3'
decrypt.c: return _mm_testz_si128(a, a);
decrypt.c: ^
decrypt.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse

Compiler output

Implementation: crypto_kem/mceliece6960119f/avx
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
bm.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
bm.c: from vec256.h:16,
bm.c: from bm.h:11,
bm.c: from bm.c:10:
bm.c: vec256.h: In function 'vec256_and':
bm.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:179:1: error: inlining failed in call to always_inline '_mm256_and_si256': target specific option mismatch
bm.c: _mm256_and_si256 (__m256i __A, __m256i __B)
bm.c: ^~~~~~~~~~~~~~~~
bm.c: In file included from bm.h:11:0,
bm.c: from bm.c:10:
bm.c: vec256.h:50:9: note: called from here
bm.c: return _mm256_and_si256(a, b);
bm.c: ^~~~~~~~~~~~~~~~~~~~~~

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