Implementation notes: amd64, h8atom, crypto_kem/mceliece6960119f

Computer: h8atom
Architecture: amd64
CPU ID: GenuineIntel-00030661-bfebfbff
SUPERCOP version: 20191221
Operation: crypto_kem
Primitive: mceliece6960119f

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
6526471	160593 0 0	253405 864 1608	`vec`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191221	20191221
8398005	110849 0 0	203459 848 1576	`vec`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
8593501	110156 0 0	202915 848 1576	`vec`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
9580872	68763 0 0	160109 864 1608	`vec`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191221	20191221
9589923	54949 0 0	144625 840 1576	`vec`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
9617720	80891 0 0	172291 848 1576	`vec`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
9746184	80891 0 0	172291 848 1576	`vec`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
10388483	53474 0 0	143669 856 1576	`vec`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191221	20191221
11430587	70302 0 0	161805 864 1608	`vec`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191221	20191221
2060594165	40674 0 0	133483 848 1576	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191210	20191017
2061909465	33878 0 0	125339 848 1576	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191210	20191017
2065043932	33878 0 0	125339 848 1576	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191210	20191017
2068876761	41164 0 0	133867 848 1576	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191210	20191017
2111808622	72816 0 0	166079 872 1608	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191210	20191017
2485763336	13637 0 0	103353 840 1576	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191210	20191017
2575920641	13627 0 0	103741 856 1576	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191210	20191017
2616499025	17401 0 0	108733 864 1608	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191210	20191017
2672832862	17556 0 0	109013 864 1608	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191210	20191017

Compiler output

Implementation: crypto_kem/mceliece6960119f/sse
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:9:
decrypt.c: ./vec128.h:30:9: 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: 4, namely:

Compiler	Implementations
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

Compiler output

Implementation: crypto_kem/mceliece6960119f/avx
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

bm.c: bm.c:133:30: error: always_inline function '_mm256_extract_epi64' requires target feature 'xsave', but would be inlined into function 'get_coefs' that is compiled without support for 'xsave'
bm.c: out[ (4*j + k)*16 + i ] = (vec256_extract(buf[i], j) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:31:41: 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:22:10: error: always_inline function '_mm256_setzero_si256' requires target feature 'xsave', but would be inlined into function 'vec256_setzero' that is compiled without support for 'xsave'
bm.c: return _mm256_setzero_si256();
bm.c: ^
bm.c: ./vec256.h:17:9: error: always_inline function '_mm256_set1_epi16' requires target feature 'xsave', but would be inlined into function 'vec256_set1_16b' that is compiled without support for 'xsave'
bm.c: return _mm256_set1_epi16(a);
bm.c: ^
bm.c: bm.c:64:2: error: always_inline function '_mm256_slli_epi64' requires target feature 'xsave', but would be inlined into function 'interleave' that is compiled without support for 'xsave'
bm.c: vec256_sll_4x(vec256_and(in[idx1], mask[0]), s));
bm.c: ^
bm.c: ./vec256.h:53:39: 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:66:16: error: always_inline function '_mm256_srli_epi64' requires target feature 'xsave', but would be inlined into function 'interleave' that is compiled without support for 'xsave'
bm.c: y = vec256_or(vec256_srl_4x(vec256_and(in[idx0], mask[1]), s),
bm.c: ^
bm.c: ./vec256.h:54:39: 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:50:9: error: always_inline function '_mm256_or_si256' requires target feature 'xsave', but would be inlined into function 'vec256_or' that is compiled without support for 'xsave'
bm.c: ...

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

Compiler	Implementations
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/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:9:
decrypt.c: ./vec128.h:30:9: 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:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse

Compiler output

Implementation: crypto_kem/mceliece6960119f/avx
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

bm.c: bm.c:133:30: 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*j + k)*16 + i ] = (vec256_extract(buf[i], j) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:31:41: 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:22:10: 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: return _mm256_setzero_si256();
bm.c: ^
bm.c: ./vec256.h:17:9: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'vec256_set1_16b' that is compiled without support for 'sse4.2'
bm.c: return _mm256_set1_epi16(a);
bm.c: ^
bm.c: bm.c:64:2: 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:53:39: 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:66:16: 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:54:39: 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:50:9: 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: ...

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

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx

Compiler output

Implementation: crypto_kem/mceliece6960119f/sse
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

bm.c: In file included from vec128.h:12:0,
bm.c: from bm.h:10,
bm.c: from bm.c:6:
bm.c: bm.c: In function 'get_coefs':
bm.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/smmintrin.h:454:1: error: inlining failed in call to always_inline '_mm_extract_epi64': target specific option mismatch
bm.c: _mm_extract_epi64 (__m128i __X, const int __N)
bm.c: ^~~~~~~~~~~~~~~~~
bm.c: In file included from bm.h:10:0,
bm.c: from bm.c:6:
bm.c: vec128.h:26:42: note: called from here
bm.c: #define vec128_extract(a, i) ((uint64_t) _mm_extract_epi64((vec128) (a), (i)))
bm.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bm.c: bm.c:129:30: note: in expansion of macro 'vec128_extract'
bm.c: out[ (4*j + k)*16 + i ] = (vec128_extract(buf[i], j) >> (k*16)) & GFMASK;
bm.c: ^~~~~~~~~~~~~~
bm.c: In file included from vec128.h:12:0,
bm.c: from bm.h:10,
bm.c: from bm.c:6:
bm.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/smmintrin.h:454:1: error: inlining failed in call to always_inline '_mm_extract_epi64': target specific option mismatch
bm.c: _mm_extract_epi64 (__m128i __X, const int __N)
bm.c: ^~~~~~~~~~~~~~~~~
bm.c: In file included from bm.h:10:0,
bm.c: from bm.c:6:
bm.c: vec128.h:26:42: note: called from here
bm.c: #define vec128_extract(a, i) ((uint64_t) _mm_extract_epi64((vec128) (a), (i)))
bm.c: ...

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

Compiler	Implementations
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

Compiler output

Implementation: crypto_kem/mceliece6960119f/avx
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

benes.c: In file included from transpose.h:9:0,
benes.c: from benes.c:8:
benes.c: vec256.h: In function 'vec256_set1_16b':
benes.c: vec256.h:16:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
benes.c: {
benes.c: ^
bm.c: In file included from bm.h:10:0,
bm.c: from bm.c:6:
bm.c: vec256.h: In function 'vec256_set1_16b':
bm.c: vec256.h:16:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
bm.c: {
bm.c: ^
bm.c: vec256.h: In function 'vec256_and':
bm.c: vec256.h:38:22: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
bm.c: static inline vec256 vec256_and(vec256 a, vec256 b)
bm.c: ^~~~~~~~~~
bm.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
bm.c: from vec256.h:11,
bm.c: from bm.h:10,
bm.c: from bm.c:6:
bm.c: vec256.h: In function 'vec256_set1_16b':
bm.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1325:1: error: inlining failed in call to always_inline '_mm256_set1_epi16': target specific option mismatch
bm.c: _mm256_set1_epi16 (short __A)
bm.c: ^~~~~~~~~~~~~~~~~
bm.c: In file included from bm.h:10:0,
bm.c: from bm.c:6:
bm.c: vec256.h:17:9: note: called from here
bm.c: return _mm256_set1_epi16(a);
bm.c: ^~~~~~~~~~~~~~~~~~~~

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

Compiler	Implementations
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