Implementation notes: amd64, gpu, crypto_core/multsntrup653

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: multsntrup653

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
353748	3656 0 0	16878 776 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190822	20190816
358332	3814 0 0	17134 776 832	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190822	20190816
362960	3814 0 0	17134 776 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190822	20190816
367780	3814 0 0	17134 776 832	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190822	20190816
396992	3974 0 0	17078 776 832	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190822	20190816
402580	3974 0 0	17166 776 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190822	20190816
408216	3974 0 0	17230 776 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190822	20190816
416632	4694 0 0	17934 776 832	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190822	20190816
524943	3878 0 0	19093 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
541179	3875 0 0	19733 760 1128	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
553554	3878 0 0	19093 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
610844	3875 0 0	19733 760 1128	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
951644	3635 0 0	21877 760 776	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
956214	3635 0 0	20549 760 776	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
967323	3635 0 0	21877 760 776	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
987744	3635 0 0	21877 760 776	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
1085912	3600 0 0	19270 776 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190822	20190816
1097001	3600 0 0	19270 776 832	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190822	20190816
1100808	6231 0 0	22502 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1117698	6287 0 0	22670 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1123340	2223 0 0	16493 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190822	20190816
1123560	2223 0 0	16493 768 832	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190822	20190816
1129532	3600 0 0	19270 776 832	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190822	20190816
1132347	2400 0 0	16717 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1140036	6287 0 0	22670 776 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1154384	2336 0 0	16517 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1154980	6231 0 0	22502 776 832	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1164000	3971 0 0	19534 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1164624	2400 0 0	16717 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1168242	2336 0 0	16517 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1176636	1967 0 0	16077 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1182620	3971 0 0	19534 776 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1183800	2223 0 0	16493 768 832	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190822	20190816
1192716	1967 0 0	16077 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1463524	2170 0 0	16549 768 832	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190822	20190816
1483485	2170 0 0	16549 768 832	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190822	20190816
1485792	2151 0 0	16525 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
1486131	2170 0 0	16549 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190822	20190816
1498008	2151 0 0	16325 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
1520496	2211 0 0	16709 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
1538284	2151 0 0	16525 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
1542192	2211 0 0	16709 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
1587072	2151 0 0	16325 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
1722171	4659 0 0	18286 776 832	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1741152	715 0 0	11717 768 832	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1748016	4763 0 0	18550 776 832	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1755282	715 0 0	11717 768 832	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1770428	2229 0 0	15582 776 832	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190822	20190816
1771660	4659 0 0	18286 776 832	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1773564	669 0 0	11653 768 832	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190822	20190816
1780614	677 0 0	11605 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190822	20190816
1782336	677 0 0	11613 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190822	20190816
1783528	2229 0 0	15582 776 832	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190822	20190816
1784720	1558 0 0	12045 768 832	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1788780	677 0 0	11605 768 832	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190822	20190816
1797696	669 0 0	11653 768 832	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190822	20190816
1797824	779 0 0	12045 768 832	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1799808	677 0 0	11613 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190822	20190816
1799844	677 0 0	11605 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190822	20190816
1804076	677 0 0	11613 768 832	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190822	20190816
1806285	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190822	20190816
1808108	2229 0 0	15582 776 832	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190822	20190816
1812400	677 0 0	11605 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190822	20190816
1815080	9526 0 0	18550 776 832	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1821104	669 0 0	11653 768 832	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190822	20190816
1825312	856 0 0	11693 768 832	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1825452	856 0 0	11693 768 832	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1837416	2744 0 0	15958 776 832	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1839150	2744 0 0	15958 776 832	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1843172	1058 0 0	10557 760 800	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
1871244	529 0 0	10557 760 800	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190822	20190816
1884486	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190822	20190816
1895169	1174 0 0	11493 768 832	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
1912172	529 0 0	10557 760 800	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
1914764	592 0 0	11525 768 832	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190822	20190816
1921587	529 0 0	10557 760 800	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
1925994	529 0 0	10573 760 800	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190822	20190816
1927744	529 0 0	10557 760 800	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190822	20190816
1928253	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190822	20190816
1928733	633 0 0	11749 768 832	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
1929159	592 0 0	11525 768 832	`ref`	`gcc_-O_-fomit-frame-pointer`	20190822	20190816
1930047	587 0 0	11493 768 832	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
1931178	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190822	20190816
1933208	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
1934034	529 0 0	10573 760 800	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190822	20190816
1934848	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190822	20190816
1939659	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190822	20190816
1939836	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
1945047	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
1945389	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190822	20190816
1946184	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190822	20190816
1946768	592 0 0	11525 768 832	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190822	20190816
1948588	529 0 0	10557 760 800	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
1950420	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190822	20190816
1955272	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190822	20190816
1955832	529 0 0	10557 760 800	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190822	20190816
1955871	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190822	20190816
1956456	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190822	20190816
1960572	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
1967264	592 0 0	11445 768 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190822	20190816
1970988	633 0 0	11749 768 832	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
1973824	661 0 0	11589 768 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190822	20190816
1974368	529 0 0	10573 760 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190822	20190816
1978792	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190822	20190816
1988109	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
1989357	587 0 0	11549 768 832	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2010212	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
2023696	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
2032684	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190822	20190816
2042360	587 0 0	11549 768 832	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2071972	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
2266180	527 0 0	10557 760 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190822	20190816
5901424	1004 0 0	13238 760 792	`ref`	`cc`	20190822	20190816
6210821	1004 0 0	13238 760 792	`ref`	`gcc`	20190822	20190816
6277434	1004 0 0	13238 760 792	`ref`	`gcc_-funroll-loops`	20190822	20190816

Test failure

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	avx
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	avx
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	ref

Compiler output

Implementation: avx
Security model: unknown
Compiler: cc

mult768.c: mult768.c: In function 'squeeze_4621_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: mult768.c:18:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult768.c: static int16x16 squeeze_4621_x16(int16x16 x)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'freeze_4621_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:207:1: error: inlining failed in call to always_inline '_mm256_blendv_epi8': target specific option mismatch
mult768.c: _mm256_blendv_epi8 (__m256i __X, __m256i __Y, __m256i __M)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:253:5: note: called from here
mult768.c: x = _mm256_blendv_epi8(xq,x,mask);
mult768.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:252:6: note: called from here
mult768.c: xq = sub_x16(x,const_x16(q));
mult768.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult768.c: ...

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
cc	avx
gcc	avx
gcc -funroll-loops	avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

mult768.c: mult768.c:266:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup653_avx' that is compiled without support for 'sse4.2'
mult768.c: x = const_x16(0);
mult768.c: ^
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c: ^
mult768.c: mult768.c:267:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup653_avx' that is compiled without support for 'sse4.2'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&f[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:268:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup653_avx' that is compiled without support for 'sse4.2'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&g[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:273:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup653_avx' that is compiled without support for 'sse4.2'
mult768.c: x = load_x16(&f[i]);
mult768.c: ^
mult768.c: mult768.c:8:21: note: expanded from macro 'load_x16'
mult768.c: #define load_x16(p) _mm256_loadu_si256((int16x16 *) (p))
mult768.c: ^
mult768.c: mult768.c:275:5: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup653_avx' that is compiled without support for 'sse4.2'
mult768.c: ...

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	avx
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

mult768.c: mult768.c:290:9: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_multsntrup653_avx' that is compiled without support for 'avx2'
mult768.c: x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c: ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c: ^
mult768.c: mult768.c:290:21: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_multsntrup653_avx' that is compiled without support for 'avx2'
mult768.c: x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c: ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c: ^
mult768.c: 2 errors generated.

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

Compiler	Implementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	avx
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	avx
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 84, namely:

Compiler	Implementations
gcc -O2 -fomit-frame-pointer	avx
gcc -O3 -fomit-frame-pointer	avx
gcc -O -fomit-frame-pointer	avx
gcc -Os -fomit-frame-pointer	avx
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	avx
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	avx
gcc -fno-schedule-insns -O -fomit-frame-pointer	avx
gcc -fno-schedule-insns -Os -fomit-frame-pointer	avx
gcc -funroll-loops -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -O -fomit-frame-pointer	avx
gcc -funroll-loops -Os -fomit-frame-pointer	avx
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	avx
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	avx
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	avx
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	avx
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	avx
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	avx
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	avx
gcc -m64 -O2 -fomit-frame-pointer	avx
gcc -m64 -O3 -fomit-frame-pointer	avx
gcc -m64 -O -fomit-frame-pointer	avx
gcc -m64 -Os -fomit-frame-pointer	avx
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -O -fomit-frame-pointer	avx
gcc -m64 -march=core2 -Os -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	avx
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=corei7 -O -fomit-frame-pointer	avx
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	avx
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=k8 -O -fomit-frame-pointer	avx
gcc -m64 -march=k8 -Os -fomit-frame-pointer	avx
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	avx
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	avx
gcc -m64 -march=nocona -O -fomit-frame-pointer	avx
gcc -m64 -march=nocona -Os -fomit-frame-pointer	avx
gcc -march=barcelona -O2 -fomit-frame-pointer	avx
gcc -march=barcelona -O3 -fomit-frame-pointer	avx
gcc -march=barcelona -O -fomit-frame-pointer	avx
gcc -march=barcelona -Os -fomit-frame-pointer	avx
gcc -march=k8 -O2 -fomit-frame-pointer	avx
gcc -march=k8 -O3 -fomit-frame-pointer	avx
gcc -march=k8 -O -fomit-frame-pointer	avx
gcc -march=k8 -Os -fomit-frame-pointer	avx
gcc -march=nocona -O2 -fomit-frame-pointer	avx
gcc -march=nocona -O3 -fomit-frame-pointer	avx
gcc -march=nocona -O -fomit-frame-pointer	avx
gcc -march=nocona -Os -fomit-frame-pointer	avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

mult768.c: mult768.c: In function 'squeeze_4621_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: mult768.c: In function 'squeeze_7681_x16':
mult768.c: mult768.c:23:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult768.c: static int16x16 squeeze_7681_x16(int16x16 x)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'squeeze_4621_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4621)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: ...
mult768.c: mult768.c: In function 'squeeze_4621_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: mult768.c: In function 'squeeze_7681_x16':
mult768.c: mult768.c:23:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult768.c: static int16x16 squeeze_7681_x16(int16x16 x)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'squeeze_4621_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4621)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: ...

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	avx
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	avx
gcc -m64 -march=barcelona -O -fomit-frame-pointer	avx
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'squeeze_4621_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4621)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4621)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: ...

Number of similar (compiler,implementation) pairs: 16, namely:

Compiler	Implementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	avx
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	avx
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	avx
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	avx
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	avx
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	avx
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	avx
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	avx
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	avx
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	avx
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	avx
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	avx
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	avx
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	avx
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	avx