Implementation notes: x86, gpu, crypto_core/multsntrup761

Computer: gpu
Architecture: x86
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: multsntrup761

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
480570	3582 0 0	20034 400 768	`ref`	`gcc_-m32_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190822	20190816
481464	3582 0 0	20034 400 768	`ref`	`gcc_-m32_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190822	20190816
485040	3582 0 0	20034 400 768	`ref`	`gcc_-m32_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190822	20190816
519444	3678 0 0	19862 400 768	`ref`	`gcc_-m32_-march=corei7_-O3_-fomit-frame-pointer`	20190822	20190816
520172	3678 0 0	19810 400 768	`ref`	`gcc_-m32_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190822	20190816
543320	3678 0 0	19862 400 768	`ref`	`gcc_-m32_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190822	20190816
550941	4302 0 0	20482 400 768	`ref`	`gcc_-m32_-march=core2_-O3_-fomit-frame-pointer`	20190822	20190816
1465017	4903 0 0	23606 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1466514	1859 0 0	19057 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer`	20190822	20190816
1484847	1672 0 0	18061 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=i386_-O2_-fomit-frame-pointer`	20190822	20190816
1486098	1802 0 0	18477 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=athlon_-O2_-fomit-frame-pointer`	20190822	20190816
1487696	3003 0 0	21414 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-2_-O3_-fomit-frame-pointer`	20190822	20190816
1489032	2245 0 0	20398 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=athlon_-O3_-fomit-frame-pointer`	20190822	20190816
1491582	1831 0 0	18569 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1492404	1826 0 0	18505 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1500813	1815 0 0	18569 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-3_-O2_-fomit-frame-pointer`	20190822	20190816
1502793	1691 0 0	18374 400 768	`ref`	`gcc_-m32_-march=k6-2_-O3_-fomit-frame-pointer`	20190822	20190816
1505040	1859 0 0	19057 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium3_-O2_-fomit-frame-pointer`	20190822	20190816
1505868	4954 0 0	24414 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1509348	1691 0 0	18374 400 768	`ref`	`gcc_-m32_-march=k6-3_-O3_-fomit-frame-pointer`	20190822	20190816
1509932	2210 0 0	20166 400 768	`ref`	`gcc_-funroll-loops_-m32_-O3_-fomit-frame-pointer`	20190822	20190816
1511292	1815 0 0	18569 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6_-O2_-fomit-frame-pointer`	20190822	20190816
1515789	1815 0 0	18569 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-2_-O2_-fomit-frame-pointer`	20190822	20190816
1521939	3166 0 0	20486 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=prescott_-O3_-fomit-frame-pointer`	20190822	20190816
1522080	1859 0 0	19869 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-m_-O2_-fomit-frame-pointer`	20190822	20190816
1525600	2202 0 0	20006 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6_-O3_-fomit-frame-pointer`	20190822	20190816
1532397	3200 0 0	20466 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium4_-O3_-fomit-frame-pointer`	20190822	20190816
1533360	3135 0 0	22337 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-m_-O3_-fomit-frame-pointer`	20190822	20190816
1536644	3003 0 0	21414 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-3_-O3_-fomit-frame-pointer`	20190822	20190816
1539480	2302 0 0	21441 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium2_-O3_-fomit-frame-pointer`	20190822	20190816
1549804	2160 0 0	19869 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=i486_-O3_-fomit-frame-pointer`	20190822	20190816
1559508	2302 0 0	21649 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium3_-O3_-fomit-frame-pointer`	20190822	20190816
1560604	2302 0 0	21441 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer`	20190822	20190816
1562852	1859 0 0	19057 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium2_-O2_-fomit-frame-pointer`	20190822	20190816
1567732	1836 0 0	18853 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer`	20190822	20190816
1568948	1817 0 0	18721 396 768	`ref`	`gcc_-funroll-loops_-m32_-O2_-fomit-frame-pointer`	20190822	20190816
1579648	2253 0 0	20277 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium_-O3_-fomit-frame-pointer`	20190822	20190816
1581156	2114 0 0	18469 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=i386_-O3_-fomit-frame-pointer`	20190822	20190816
1584012	1831 0 0	18569 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=prescott_-O2_-fomit-frame-pointer`	20190822	20190816
1590064	3166 0 0	20486 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1594620	1885 0 0	19337 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1601268	1836 0 0	18853 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium_-O2_-fomit-frame-pointer`	20190822	20190816
1608921	1617 0 0	18413 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-2_-O_-fomit-frame-pointer`	20190822	20190816
1609348	1860 0 0	18453 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium4_-O2_-fomit-frame-pointer`	20190822	20190816
1617684	1718 0 0	18937 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=i486_-O2_-fomit-frame-pointer`	20190822	20190816
1617720	2253 0 0	20277 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer`	20190822	20190816
1624581	1617 0 0	18413 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6_-O_-fomit-frame-pointer`	20190822	20190816
1635636	1617 0 0	18413 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-3_-O_-fomit-frame-pointer`	20190822	20190816
1721397	1705 0 0	18325 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=i386_-O_-fomit-frame-pointer`	20190822	20190816
1736392	1749 0 0	18881 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
1798515	1724 0 0	18529 396 768	`ref`	`gcc_-funroll-loops_-m32_-O_-fomit-frame-pointer`	20190822	20190816
1802343	1644 0 0	18549 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
1825464	1666 0 0	18757 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
1837296	1659 0 0	19101 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium3_-O_-fomit-frame-pointer`	20190822	20190816
1846208	1659 0 0	19221 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-m_-O_-fomit-frame-pointer`	20190822	20190816
1854316	1749 0 0	18881 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=prescott_-O_-fomit-frame-pointer`	20190822	20190816
1862844	1659 0 0	19101 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentiumpro_-O_-fomit-frame-pointer`	20190822	20190816
1874352	1659 0 0	19101 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium2_-O_-fomit-frame-pointer`	20190822	20190816
1902588	1700 0 0	18465 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer`	20190822	20190816
1919320	1755 0 0	18897 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium4_-O_-fomit-frame-pointer`	20190822	20190816
1919658	1649 0 0	18321 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=athlon_-O_-fomit-frame-pointer`	20190822	20190816
1941930	1705 0 0	18645 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=i486_-O_-fomit-frame-pointer`	20190822	20190816
1956696	1700 0 0	18465 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium_-O_-fomit-frame-pointer`	20190822	20190816
2178885	4093 0 0	20658 400 768	`ref`	`gcc_-m32_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
2193924	1380 0 0	17889 396 768	`ref`	`gcc_-m32_-march=pentium_-O3_-fomit-frame-pointer`	20190822	20190816
2247033	1025 0 0	17526 400 768	`ref`	`gcc_-m32_-march=k6_-O3_-fomit-frame-pointer`	20190822	20190816
2251803	611 0 0	12821 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=i386_-Os_-fomit-frame-pointer`	20190822	20190816
2255923	654 0 0	13809 396 768	`ref`	`gcc_-m32_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190822	20190816
2270601	627 0 0	13917 396 768	`ref`	`gcc_-m32_-march=pentium2_-O_-fomit-frame-pointer`	20190822	20190816
2294448	680 0 0	13921 396 768	`ref`	`gcc_-m32_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
2315961	750 0 0	14325 396 768	`ref`	`gcc_-m32_-march=corei7_-O2_-fomit-frame-pointer`	20190822	20190816
2327884	1417 0 0	16337 396 768	`ref`	`gcc_-m32_-march=i386_-O3_-fomit-frame-pointer`	20190822	20190816
2336264	947 0 0	14469 396 768	`ref`	`gcc_-m32_-march=pentium_-O2_-fomit-frame-pointer`	20190822	20190816
2340684	1993 0 0	18849 396 768	`ref`	`gcc_-m32_-march=pentium-m_-O3_-fomit-frame-pointer`	20190822	20190816
2345151	1622 0 0	15021 396 768	`ref`	`gcc_-m32_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
2360253	1056 0 0	17022 400 768	`ref`	`gcc_-m32_-march=athlon_-O3_-fomit-frame-pointer`	20190822	20190816
2364540	1284 0 0	13937 396 768	`ref`	`gcc_-m32_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
2371860	1081 0 0	17521 396 768	`ref`	`gcc_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer`	20190822	20190816
2389652	749 0 0	14325 396 768	`ref`	`gcc_-m32_-O2_-fomit-frame-pointer`	20190822	20190816
2391252	910 0 0	14149 396 768	`ref`	`gcc_-m32_-march=prescott_-O2_-fomit-frame-pointer`	20190822	20190816
2391441	2237 0 0	18114 400 768	`ref`	`gcc_-m32_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
2394225	1081 0 0	17521 396 768	`ref`	`gcc_-m32_-march=pentium2_-O3_-fomit-frame-pointer`	20190822	20190816
2395086	2237 0 0	18114 400 768	`ref`	`gcc_-m32_-march=prescott_-O3_-fomit-frame-pointer`	20190822	20190816
2395148	744 0 0	14217 396 768	`ref`	`gcc_-m32_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
2396540	764 0 0	14453 396 768	`ref`	`gcc_-m32_-march=k6-3_-O2_-fomit-frame-pointer`	20190822	20190816
2397057	764 0 0	14453 396 768	`ref`	`gcc_-m32_-march=k6-2_-O2_-fomit-frame-pointer`	20190822	20190816
2402048	781 0 0	14373 396 768	`ref`	`gcc_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer`	20190822	20190816
2403016	756 0 0	14013 396 768	`ref`	`gcc_-m32_-march=athlon_-O2_-fomit-frame-pointer`	20190822	20190816
2404516	8336 0 0	21170 400 768	`ref`	`gcc_-m32_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
2404984	697 0 0	13697 396 768	`ref`	`gcc_-m32_-march=i386_-O_-fomit-frame-pointer`	20190822	20190816
2405916	627 0 0	13957 396 768	`ref`	`gcc_-m32_-march=pentium-m_-O_-fomit-frame-pointer`	20190822	20190816
2410068	781 0 0	14729 396 768	`ref`	`gcc_-m32_-march=pentium-m_-O2_-fomit-frame-pointer`	20190822	20190816
2410440	654 0 0	13809 396 768	`ref`	`gcc_-m32_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190822	20190816
2411928	654 0 0	13805 396 768	`ref`	`gcc_-m32_-O_-fomit-frame-pointer`	20190822	20190816
2413311	633 0 0	12949 388 768	`ref`	`gcc_-m32_-march=k6-3_-Os_-fomit-frame-pointer`	20190822	20190816
2415321	1003 0 0	17078 400 768	`ref`	`gcc_-m32_-O3_-fomit-frame-pointer`	20190822	20190816
2415540	764 0 0	14453 396 768	`ref`	`gcc_-m32_-march=k6_-O2_-fomit-frame-pointer`	20190822	20190816
2415904	654 0 0	13809 396 768	`ref`	`gcc_-m32_-march=core2_-O_-fomit-frame-pointer`	20190822	20190816
2416280	637 0 0	13881 396 768	`ref`	`gcc_-m32_-march=k6-3_-O_-fomit-frame-pointer`	20190822	20190816
2417692	750 0 0	14325 396 768	`ref`	`gcc_-m32_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190822	20190816
2420847	654 0 0	13809 396 768	`ref`	`gcc_-m32_-march=corei7-avx_-O_-fomit-frame-pointer`	20190822	20190816
2421632	654 0 0	13809 396 768	`ref`	`gcc_-m32_-march=core-avx-i_-O_-fomit-frame-pointer`	20190822	20190816
2421933	1455 0 0	17725 396 768	`ref`	`gcc_-m32_-march=i486_-O3_-fomit-frame-pointer`	20190822	20190816
2422524	2295 0 0	18154 400 768	`ref`	`gcc_-m32_-march=pentium4_-O3_-fomit-frame-pointer`	20190822	20190816
2424132	1081 0 0	17729 396 768	`ref`	`gcc_-m32_-march=pentium3_-O3_-fomit-frame-pointer`	20190822	20190816
2425988	618 0 0	13669 396 768	`ref`	`gcc_-m32_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2430080	654 0 0	13809 396 768	`ref`	`gcc_-m32_-march=corei7_-O_-fomit-frame-pointer`	20190822	20190816
2430164	750 0 0	14309 396 768	`ref`	`gcc_-m32_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190822	20190816
2431772	617 0 0	13505 396 768	`ref`	`gcc_-m32_-march=athlon_-O_-fomit-frame-pointer`	20190822	20190816
2432556	637 0 0	13881 396 768	`ref`	`gcc_-m32_-march=k6_-O_-fomit-frame-pointer`	20190822	20190816
2433200	750 0 0	14309 396 768	`ref`	`gcc_-m32_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190822	20190816
2442100	750 0 0	14309 396 768	`ref`	`gcc_-m32_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190822	20190816
2444784	910 0 0	14149 396 768	`ref`	`gcc_-m32_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
2446188	637 0 0	13881 396 768	`ref`	`gcc_-m32_-march=k6-2_-O_-fomit-frame-pointer`	20190822	20190816
2448208	750 0 0	14325 396 768	`ref`	`gcc_-m32_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190822	20190816
2448244	627 0 0	13917 396 768	`ref`	`gcc_-m32_-march=pentium3_-O_-fomit-frame-pointer`	20190822	20190816
2448468	947 0 0	14469 396 768	`ref`	`gcc_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer`	20190822	20190816
2449308	750 0 0	14341 396 768	`ref`	`gcc_-m32_-march=core2_-O2_-fomit-frame-pointer`	20190822	20190816
2459792	781 0 0	14373 396 768	`ref`	`gcc_-m32_-march=pentium3_-O2_-fomit-frame-pointer`	20190822	20190816
2460288	781 0 0	14373 396 768	`ref`	`gcc_-m32_-march=pentium2_-O2_-fomit-frame-pointer`	20190822	20190816
2472228	1380 0 0	17889 396 768	`ref`	`gcc_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer`	20190822	20190816
2480600	967 0 0	14033 396 768	`ref`	`gcc_-m32_-march=i386_-O2_-fomit-frame-pointer`	20190822	20190816
2482849	654 0 0	13809 396 768	`ref`	`gcc_-m32_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190822	20190816
2489888	997 0 0	14793 396 768	`ref`	`gcc_-m32_-march=i486_-O2_-fomit-frame-pointer`	20190822	20190816
2494276	627 0 0	13917 396 768	`ref`	`gcc_-m32_-march=pentiumpro_-O_-fomit-frame-pointer`	20190822	20190816
2494443	690 0 0	13821 396 768	`ref`	`gcc_-m32_-march=pentium_-O_-fomit-frame-pointer`	20190822	20190816
2501552	680 0 0	13921 396 768	`ref`	`gcc_-m32_-march=prescott_-O_-fomit-frame-pointer`	20190822	20190816
2503844	689 0 0	13953 396 768	`ref`	`gcc_-m32_-march=pentium4_-O_-fomit-frame-pointer`	20190822	20190816
2530920	690 0 0	13821 396 768	`ref`	`gcc_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer`	20190822	20190816
2543811	610 0 0	12837 388 768	`ref`	`gcc_-m32_-march=pentium_-Os_-fomit-frame-pointer`	20190822	20190816
2549823	610 0 0	12837 388 768	`ref`	`gcc_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer`	20190822	20190816
2560200	633 0 0	12949 388 768	`ref`	`gcc_-m32_-march=k6-2_-Os_-fomit-frame-pointer`	20190822	20190816
2561688	939 0 0	14165 396 768	`ref`	`gcc_-m32_-march=pentium4_-O2_-fomit-frame-pointer`	20190822	20190816
2569650	611 0 0	12853 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
2575524	610 0 0	12853 388 768	`ref`	`gcc_-m32_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190822	20190816
2575616	697 0 0	13985 396 768	`ref`	`gcc_-m32_-march=i486_-O_-fomit-frame-pointer`	20190822	20190816
2576076	610 0 0	12869 388 768	`ref`	`gcc_-m32_-march=core2_-Os_-fomit-frame-pointer`	20190822	20190816
2594019	1220 0 0	12869 388 768	`ref`	`gcc_-m32_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
2596612	610 0 0	12853 388 768	`ref`	`gcc_-m32_-march=corei7_-Os_-fomit-frame-pointer`	20190822	20190816
2598381	611 0 0	12853 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
2614257	610 0 0	12837 388 768	`ref`	`gcc_-m32_-march=athlon_-Os_-fomit-frame-pointer`	20190822	20190816
2614965	610 0 0	12869 388 768	`ref`	`gcc_-m32_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
2626668	610 0 0	12869 388 768	`ref`	`gcc_-m32_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
2627020	610 0 0	12853 388 768	`ref`	`gcc_-m32_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190822	20190816
2636374	610 0 0	12869 388 768	`ref`	`gcc_-m32_-march=pentium4_-Os_-fomit-frame-pointer`	20190822	20190816
2638647	634 0 0	12933 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6_-Os_-fomit-frame-pointer`	20190822	20190816
2641203	611 0 0	12821 388 768	`ref`	`gcc_-funroll-loops_-m32_-Os_-fomit-frame-pointer`	20190822	20190816
2644232	610 0 0	12837 388 768	`ref`	`gcc_-m32_-Os_-fomit-frame-pointer`	20190822	20190816
2649480	610 0 0	12869 388 768	`ref`	`gcc_-m32_-march=prescott_-Os_-fomit-frame-pointer`	20190822	20190816
2652879	610 0 0	12837 388 768	`ref`	`gcc_-m32_-march=i386_-Os_-fomit-frame-pointer`	20190822	20190816
2653184	610 0 0	12837 388 768	`ref`	`gcc_-m32_-march=i486_-Os_-fomit-frame-pointer`	20190822	20190816
2660349	611 0 0	12821 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium_-Os_-fomit-frame-pointer`	20190822	20190816
2660520	611 0 0	12821 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=i486_-Os_-fomit-frame-pointer`	20190822	20190816
2661618	634 0 0	12933 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-3_-Os_-fomit-frame-pointer`	20190822	20190816
2661924	633 0 0	12949 388 768	`ref`	`gcc_-m32_-march=k6_-Os_-fomit-frame-pointer`	20190822	20190816
2681172	634 0 0	12933 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-2_-Os_-fomit-frame-pointer`	20190822	20190816
2689140	611 0 0	12853 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
2701980	611 0 0	12821 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=athlon_-Os_-fomit-frame-pointer`	20190822	20190816
2717420	611 0 0	12821 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer`	20190822	20190816
2824092	611 0 0	12853 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium4_-Os_-fomit-frame-pointer`	20190822	20190816
2833772	611 0 0	12853 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=prescott_-Os_-fomit-frame-pointer`	20190822	20190816
2974784	610 0 0	12853 388 768	`ref`	`gcc_-m32_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190822	20190816
2980016	610 0 0	12853 388 768	`ref`	`gcc_-m32_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190822	20190816
2999392	610 0 0	12853 388 768	`ref`	`gcc_-m32_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190822	20190816
3314796	609 0 0	12745 388 768	`ref`	`gcc_-m32_-march=pentium3_-Os_-fomit-frame-pointer`	20190822	20190816
3316660	609 0 0	12745 388 768	`ref`	`gcc_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer`	20190822	20190816
3320799	609 0 0	12745 388 768	`ref`	`gcc_-m32_-march=pentium2_-Os_-fomit-frame-pointer`	20190822	20190816
3347796	609 0 0	12793 388 768	`ref`	`gcc_-m32_-march=pentium-m_-Os_-fomit-frame-pointer`	20190822	20190816
3433340	611 0 0	12729 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer`	20190822	20190816
3459544	611 0 0	12729 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium3_-Os_-fomit-frame-pointer`	20190822	20190816
3465168	611 0 0	12777 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-m_-Os_-fomit-frame-pointer`	20190822	20190816
3467688	611 0 0	12729 388 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium2_-Os_-fomit-frame-pointer`	20190822	20190816

Test failure

Implementation: avx
Security model: unknown
Compiler: gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer

error 111

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

Compiler	Implementations
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	avx
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	avx
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	ref
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	ref

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 156, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	avx
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	avx
gcc -m32 -O2 -fomit-frame-pointer	avx
gcc -m32 -O3 -fomit-frame-pointer	avx
gcc -m32 -O -fomit-frame-pointer	avx
gcc -m32 -Os -fomit-frame-pointer	avx
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	avx
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	avx
gcc -m32 -march=athlon -O -fomit-frame-pointer	avx
gcc -m32 -march=athlon -Os -fomit-frame-pointer	avx
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=core2 -O -fomit-frame-pointer	avx
gcc -m32 -march=core2 -Os -fomit-frame-pointer	avx
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	avx
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	avx
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	avx
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	avx
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=corei7 -O -fomit-frame-pointer	avx
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	avx
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=i386 -O -fomit-frame-pointer	avx
gcc -m32 -march=i386 -Os -fomit-frame-pointer	avx
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=i486 -O -fomit-frame-pointer	avx
gcc -m32 -march=i486 -Os -fomit-frame-pointer	avx
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	avx
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	avx
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	avx
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	avx
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=k6 -O -fomit-frame-pointer	avx
gcc -m32 -march=k6 -Os -fomit-frame-pointer	avx
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=k8 -O -fomit-frame-pointer	avx
gcc -m32 -march=k8 -Os -fomit-frame-pointer	avx
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	avx
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	avx
gcc -m32 -march=nocona -O -fomit-frame-pointer	avx
gcc -m32 -march=nocona -Os -fomit-frame-pointer	avx
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	avx
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	avx
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	avx
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	avx
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	avx
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	avx
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	avx
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	avx
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	avx
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	avx
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	avx
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	avx
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	avx
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	avx
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	avx
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	avx
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	avx
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	avx
gcc -m32 -march=pentium -O -fomit-frame-pointer	avx
gcc -m32 -march=pentium -Os -fomit-frame-pointer	avx
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	avx
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	avx
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	avx
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	avx
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	avx
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	avx
gcc -m32 -march=prescott -O -fomit-frame-pointer	avx
gcc -m32 -march=prescott -Os -fomit-frame-pointer	avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

mult768.c: mult768.c: In function 'squeeze_4591_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
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: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(4591)));
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(4591)));
mult768.c: ...
mult768.c: mult768.c: In function 'squeeze_4591_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
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: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(4591)));
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(4591)));
mult768.c: ...

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

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	avx
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	avx
gcc -m32 -march=barcelona -O -fomit-frame-pointer	avx
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m32 -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_4591_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(4591)));
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(4591)));
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: 12, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	avx
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer	avx
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	avx
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	avx
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	avx
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer	avx
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	avx
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	avx
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	avx
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	avx
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	avx
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	avx

Compiler output

Implementation: round1
Security model: unknown
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

mult.c: mult.c: In function '_mm_load_cvtepi8_epi16':
mult.c: mult.c:58:1: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
mult.c: {
mult.c: ^
mult.c: mult.c: In function 'add':
mult.c: mult.c:81:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult.c: {
mult.c: ^
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult.c: from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1310:1: error: inlining failed in call to always_inline '_mm256_set1_ps': target specific option mismatch
mult.c: _mm256_set1_ps (float __A)
mult.c: ^~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 88, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	round1
gcc -m32 -O2 -fomit-frame-pointer	round1
gcc -m32 -O3 -fomit-frame-pointer	round1
gcc -m32 -O -fomit-frame-pointer	round1
gcc -m32 -Os -fomit-frame-pointer	round1
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	round1
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	round1
gcc -m32 -march=athlon -O -fomit-frame-pointer	round1
gcc -m32 -march=athlon -Os -fomit-frame-pointer	round1
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=i386 -O -fomit-frame-pointer	round1
gcc -m32 -march=i386 -Os -fomit-frame-pointer	round1
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=i486 -O -fomit-frame-pointer	round1
gcc -m32 -march=i486 -Os -fomit-frame-pointer	round1
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	round1
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	round1
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	round1
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	round1
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=k6 -O -fomit-frame-pointer	round1
gcc -m32 -march=k6 -Os -fomit-frame-pointer	round1
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	round1
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	round1
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	round1
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	round1
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	round1
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	round1
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	round1
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	round1
gcc -m32 -march=pentium -O -fomit-frame-pointer	round1
gcc -m32 -march=pentium -Os -fomit-frame-pointer	round1
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	round1
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	round1
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	round1
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	round1

Compiler output

Implementation: round1
Security model: unknown
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 68, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	round1
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	round1
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=core2 -O -fomit-frame-pointer	round1
gcc -m32 -march=core2 -Os -fomit-frame-pointer	round1
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	round1
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	round1
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	round1
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	round1
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=corei7 -O -fomit-frame-pointer	round1
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	round1
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=k8 -O -fomit-frame-pointer	round1
gcc -m32 -march=k8 -Os -fomit-frame-pointer	round1
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	round1
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	round1
gcc -m32 -march=nocona -O -fomit-frame-pointer	round1
gcc -m32 -march=nocona -Os -fomit-frame-pointer	round1
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	round1
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	round1
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	round1
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	round1
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	round1
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	round1
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	round1
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	round1
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	round1
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	round1
gcc -m32 -march=prescott -O -fomit-frame-pointer	round1
gcc -m32 -march=prescott -Os -fomit-frame-pointer	round1

Compiler output

Implementation: round1
Security model: unknown
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

mult.c: mult.c: In function 'add':
mult.c: mult.c:81:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult.c: {
mult.c: ^
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult.c: from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1310:1: error: inlining failed in call to always_inline '_mm256_set1_ps': target specific option mismatch
mult.c: _mm256_set1_ps (float __A)
mult.c: ^~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: mult.c: In function 'add':
mult.c: mult.c:81:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult.c: {
mult.c: ^
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult.c: from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1310:1: error: inlining failed in call to always_inline '_mm256_set1_ps': target specific option mismatch
mult.c: _mm256_set1_ps (float __A)
mult.c: ^~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

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

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	round1
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	round1
gcc -m32 -march=barcelona -O -fomit-frame-pointer	round1
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	round1

Compiler output

Implementation: round1
Security model: unknown
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer

mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 12, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	round1
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer	round1
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	round1
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	round1
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	round1
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer	round1
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	round1
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	round1
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	round1
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	round1
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	round1
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	round1

Compiler output

Implementation: round1
Security model: unknown
Compiler: gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer

mult.c: mult.c: In function 'mult24x8_float':
mult.c: mult.c:46:3: error: 'asm' operand has impossible constraints
mult.c: __asm__( \
mult.c: ^
mult.c: mult.c:146:3: note: in expansion of macro 'MULSTEP_fromzero'
mult.c: MULSTEP_fromzero(0,h0,h1,h2,h3,h4)
mult.c: ^~~~~~~~~~~~~~~~
mult.c: mult.c:33:3: error: 'asm' operand has impossible constraints
mult.c: __asm__( \
mult.c: ^
mult.c: mult.c:148:5: note: in expansion of macro 'MULSTEP_noload'
mult.c: MULSTEP_noload(j + 1,h1,h2,h3,h4,h0)
mult.c: ^~~~~~~~~~~~~~
mult.c: mult.c:33:3: error: 'asm' operand has impossible constraints
mult.c: __asm__( \
mult.c: ^
mult.c: mult.c:149:5: note: in expansion of macro 'MULSTEP_noload'
mult.c: MULSTEP_noload(j + 2,h2,h3,h4,h0,h1)
mult.c: ^~~~~~~~~~~~~~
mult.c: mult.c:33:3: error: 'asm' operand has impossible constraints
mult.c: __asm__( \
mult.c: ^
mult.c: mult.c:150:5: note: in expansion of macro 'MULSTEP_noload'
mult.c: MULSTEP_noload(j + 3,h3,h4,h0,h1,h2)
mult.c: ^~~~~~~~~~~~~~
mult.c: ...

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

Compiler	Implementations
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	round1
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	round1