Implementation notes: amd64, gpu, crypto_core/mult3sntrup653

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: mult3sntrup653

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
344460	4117 0 0	19205 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
372636	4226 0 0	19957 760 1128	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
373576	4117 0 0	19205 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
412220	4226 0 0	19957 760 1128	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
458984	4616 0 0	17710 776 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190822	20190816
529548	4930 0 0	23045 760 776	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
573480	4930 0 0	21717 760 776	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
603748	4930 0 0	23045 760 776	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
621284	4930 0 0	23045 760 776	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
1051540	3253 0 0	18694 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1074804	4710 0 0	20862 776 832	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1082296	2156 0 0	16293 768 832	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190822	20190816
1085316	4710 0 0	20862 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1097922	2156 0 0	16293 768 832	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190822	20190816
1099840	3253 0 0	18694 776 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1100300	3302 0 0	18846 776 832	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190822	20190816
1104548	2013 0 0	15989 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1110612	4790 0 0	21046 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1131916	2013 0 0	15989 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1134936	2156 0 0	16341 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1143028	4790 0 0	21046 776 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1151628	3302 0 0	18846 776 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190822	20190816
1152276	2156 0 0	16293 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190822	20190816
1157912	2108 0 0	16157 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1157956	2108 0 0	16157 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1157964	3302 0 0	18846 776 832	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190822	20190816
1165896	2156 0 0	16341 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1551672	2975 0 0	16166 776 832	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190822	20190816
1711684	2603 0 0	16845 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190822	20190816
1769524	601 0 0	11477 768 832	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1774496	1314 0 0	11805 768 832	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1787992	3637 0 0	17134 776 832	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1790680	1989 0 0	15214 776 832	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190822	20190816
1791144	634 0 0	11429 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190822	20190816
1791580	3637 0 0	17134 776 832	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1794620	634 0 0	11437 768 832	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190822	20190816
1794872	634 0 0	11493 768 832	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190822	20190816
1798696	3302 0 0	16438 776 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190822	20190816
1800796	3446 0 0	16566 776 832	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190822	20190816
1804268	1989 0 0	15214 776 832	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190822	20190816
1810776	2975 0 0	16166 776 832	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190822	20190816
1820872	3669 0 0	17334 776 832	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1823780	3302 0 0	16374 776 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190822	20190816
1825196	634 0 0	11493 768 832	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190822	20190816
1830100	634 0 0	11429 768 832	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190822	20190816
1834484	3302 0 0	16286 776 832	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190822	20190816
1834976	657 0 0	11805 768 832	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1836440	611 0 0	11325 768 832	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1841028	1989 0 0	15214 776 832	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190822	20190816
1841056	611 0 0	11325 768 832	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1844260	634 0 0	11437 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190822	20190816
1846800	2139 0 0	15222 776 832	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1859064	634 0 0	11429 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190822	20190816
1872552	601 0 0	11477 768 832	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1880576	634 0 0	11437 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190822	20190816
1891580	634 0 0	11493 768 832	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190822	20190816
1894960	2975 0 0	16166 776 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190822	20190816
1898932	7338 0 0	17334 776 832	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1923124	634 0 0	11429 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190822	20190816
1943444	2139 0 0	15222 776 832	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1952404	2451 0 0	16813 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
2005908	2451 0 0	16813 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
2027877	578 0 0	10409 752 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190822	20190816
2029540	2603 0 0	16845 768 832	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190822	20190816
2041408	2568 0 0	16605 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
2045092	2603 0 0	16845 768 832	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190822	20190816
2069532	2568 0 0	16605 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
2093084	2568 0 0	16805 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2096452	2568 0 0	16805 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2232300	561 0 0	10353 752 800	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190822	20190816
2291487	561 0 0	10353 752 800	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190822	20190816
2324684	561 0 0	10353 752 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190822	20190816
2328720	578 0 0	10409 752 800	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190822	20190816
2348048	575 0 0	10393 752 800	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
2355084	591 0 0	11381 768 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190822	20190816
2372364	561 0 0	10369 752 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190822	20190816
2373636	561 0 0	10369 752 800	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190822	20190816
2401456	561 0 0	10353 752 800	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190822	20190816
2407768	578 0 0	10409 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
2414352	561 0 0	10369 752 800	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190822	20190816
2421880	661 0 0	11373 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190822	20190816
2431508	578 0 0	10409 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
2432872	561 0 0	10353 752 800	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190822	20190816
2444252	575 0 0	10393 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
2461980	561 0 0	10353 752 800	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190822	20190816
2473164	561 0 0	10353 752 800	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190822	20190816
2496280	578 0 0	10409 752 800	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
2500064	578 0 0	10409 752 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
2501768	546 0 0	10345 752 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190822	20190816
2505484	561 0 0	10353 752 800	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
2508344	578 0 0	10409 752 800	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190822	20190816
2514580	561 0 0	10353 752 800	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
2539572	661 0 0	11373 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190822	20190816
2539768	561 0 0	10353 752 800	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
2550256	558 0 0	10353 752 800	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
2576160	1122 0 0	10353 752 800	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
2578828	661 0 0	11373 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190822	20190816
2579888	661 0 0	11453 768 832	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190822	20190816
2594376	558 0 0	10353 752 800	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
2594392	650 0 0	11477 768 832	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2603432	661 0 0	11373 768 832	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190822	20190816
2607280	1300 0 0	11421 768 832	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
2632884	658 0 0	11381 768 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190822	20190816
2647176	690 0 0	11661 768 832	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
2657484	661 0 0	11453 768 832	`ref`	`gcc_-O_-fomit-frame-pointer`	20190822	20190816
2662836	661 0 0	11453 768 832	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190822	20190816
2688028	661 0 0	11373 768 832	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190822	20190816
2720528	690 0 0	11661 768 832	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
2731260	650 0 0	11477 768 832	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2734540	661 0 0	11373 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190822	20190816
2739696	661 0 0	11373 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190822	20190816
2798196	650 0 0	11421 768 832	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
6325240	1096 0 0	13206 760 792	`ref`	`cc`	20190822	20190816
6411896	1096 0 0	13206 760 792	`ref`	`gcc`	20190822	20190816
6757564	1096 0 0	13206 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_3_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_3_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_3_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:195:5: note: called from here
mult768.c: x = _mm256_blendv_epi8(x3,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:194:6: note: called from here
mult768.c: x3 = sub_x16(x,const_x16(3));
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:208:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup653_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:209:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup653_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:210:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup653_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:227:20: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup653_avx' that is compiled without support for 'sse4.2'
mult768.c: int16x16 fgi = load_x16(&fg[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:228:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup653_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:230:9: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup653_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:230:21: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup653_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_3_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_3_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(10923)),const_x16(3)));
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_3_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_3_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(10923)),const_x16(3)));
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_3_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(10923)),const_x16(3)));
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(10923)),const_x16(3)));
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