Implementation notes: x86, gpu, crypto_core/mult3sntrup761

Computer: gpu
Architecture: x86
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: mult3sntrup761

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1369376	3006 0 0	19789 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=prescott_-O3_-fomit-frame-pointer`	20190822	20190816
1417818	3006 0 0	19789 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1440906	2900 0 0	19669 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium4_-O3_-fomit-frame-pointer`	20190822	20190816
1458279	1711 0 0	18157 396 768	`ref`	`gcc_-funroll-loops_-m32_-O2_-fomit-frame-pointer`	20190822	20190816
1467309	1618 0 0	17856 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
1493244	1618 0 0	17856 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=prescott_-O2_-fomit-frame-pointer`	20190822	20190816
1499040	1680 0 0	17856 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1500392	1743 0 0	17973 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=athlon_-O2_-fomit-frame-pointer`	20190822	20190816
1507380	1666 0 0	18696 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer`	20190822	20190816
1514192	3680 0 0	21881 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1521618	1641 0 0	17724 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium4_-O2_-fomit-frame-pointer`	20190822	20190816
1537965	3695 0 0	22617 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1555059	1666 0 0	18696 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium3_-O2_-fomit-frame-pointer`	20190822	20190816
1555320	1776 0 0	19282 400 768	`ref`	`gcc_-funroll-loops_-m32_-O3_-fomit-frame-pointer`	20190822	20190816
1555848	2346 0 0	21484 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium3_-O3_-fomit-frame-pointer`	20190822	20190816
1558119	1744 0 0	18692 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1568226	1666 0 0	19508 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-m_-O2_-fomit-frame-pointer`	20190822	20190816
1584585	1798 0 0	19494 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=athlon_-O3_-fomit-frame-pointer`	20190822	20190816
1591962	2346 0 0	21276 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer`	20190822	20190816
1594029	2346 0 0	21276 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium2_-O3_-fomit-frame-pointer`	20190822	20190816
1609431	1666 0 0	18696 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium2_-O2_-fomit-frame-pointer`	20190822	20190816
1622862	3404 0 0	22408 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-m_-O3_-fomit-frame-pointer`	20190822	20190816
2011428	1714 0 0	17820 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=i386_-O_-fomit-frame-pointer`	20190822	20190816
2069676	1966 0 0	18305 396 768	`ref`	`gcc_-funroll-loops_-m32_-O_-fomit-frame-pointer`	20190822	20190816
2201415	592 0 0	13713 396 768	`ref`	`gcc_-m32_-O2_-fomit-frame-pointer`	20190822	20190816
2320776	2572 0 0	18234 400 768	`ref`	`gcc_-m32_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190822	20190816
2329986	590 0 0	13397 396 768	`ref`	`gcc_-m32_-march=athlon_-O2_-fomit-frame-pointer`	20190822	20190816
2348433	2467 0 0	18434 400 768	`ref`	`gcc_-m32_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190822	20190816
2367762	582 0 0	13552 392 768	`ref`	`gcc_-m32_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
2372844	620 0 0	13340 392 768	`ref`	`gcc_-m32_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
2383011	2467 0 0	18434 400 768	`ref`	`gcc_-m32_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190822	20190816
2385552	592 0 0	13701 396 768	`ref`	`gcc_-m32_-march=corei7_-O2_-fomit-frame-pointer`	20190822	20190816
2390532	6734 0 0	19853 396 768	`ref`	`gcc_-m32_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
2396439	592 0 0	13701 396 768	`ref`	`gcc_-m32_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190822	20190816
2397216	592 0 0	13701 396 768	`ref`	`gcc_-m32_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190822	20190816
2399416	3231 0 0	19229 396 768	`ref`	`gcc_-m32_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
2413953	2467 0 0	18434 400 768	`ref`	`gcc_-m32_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190822	20190816
2415468	856 0 0	16358 400 768	`ref`	`gcc_-m32_-march=athlon_-O3_-fomit-frame-pointer`	20190822	20190816
2418552	592 0 0	13685 396 768	`ref`	`gcc_-m32_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190822	20190816
2424510	1941 0 0	18285 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-2_-O_-fomit-frame-pointer`	20190822	20190816
2432817	592 0 0	13685 396 768	`ref`	`gcc_-m32_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190822	20190816
2433924	1979 0 0	18173 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=athlon_-O_-fomit-frame-pointer`	20190822	20190816
2438624	2572 0 0	18234 400 768	`ref`	`gcc_-m32_-march=corei7_-O3_-fomit-frame-pointer`	20190822	20190816
2453250	1711 0 0	17013 396 768	`ref`	`gcc_-m32_-march=pentium4_-O3_-fomit-frame-pointer`	20190822	20190816
2461684	2767 0 0	18422 400 768	`ref`	`gcc_-m32_-march=core2_-O3_-fomit-frame-pointer`	20190822	20190816
2466720	1927 0 0	18320 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2469093	1814 0 0	17161 396 768	`ref`	`gcc_-m32_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
2469678	1792 0 0	18105 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer`	20190822	20190816
2470239	819 0 0	16434 400 768	`ref`	`gcc_-m32_-O3_-fomit-frame-pointer`	20190822	20190816
2478399	558 0 0	13292 392 768	`ref`	`gcc_-m32_-march=pentium4_-O2_-fomit-frame-pointer`	20190822	20190816
2482905	1918 0 0	18548 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=prescott_-O_-fomit-frame-pointer`	20190822	20190816
2482947	620 0 0	13340 392 768	`ref`	`gcc_-m32_-march=prescott_-O2_-fomit-frame-pointer`	20190822	20190816
2488836	2572 0 0	18182 400 768	`ref`	`gcc_-m32_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190822	20190816
2488896	1918 0 0	18548 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
2490660	1714 0 0	18140 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=i486_-O_-fomit-frame-pointer`	20190822	20190816
2512713	1308 0 0	14360 392 768	`ref`	`gcc_-m32_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
2515056	1941 0 0	18285 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-3_-O_-fomit-frame-pointer`	20190822	20190816
2521152	1792 0 0	18105 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium_-O_-fomit-frame-pointer`	20190822	20190816
2527725	1927 0 0	18500 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
2547084	1977 0 0	18596 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium4_-O_-fomit-frame-pointer`	20190822	20190816
2554002	917 0 0	16680 392 768	`ref`	`gcc_-m32_-march=i486_-O3_-fomit-frame-pointer`	20190822	20190816
2574116	592 0 0	13685 396 768	`ref`	`gcc_-m32_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190822	20190816
2578938	1941 0 0	18285 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6_-O_-fomit-frame-pointer`	20190822	20190816
2607222	1634 0 0	17937 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-2_-O2_-fomit-frame-pointer`	20190822	20190816
2609124	1810 0 0	19746 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-3_-O3_-fomit-frame-pointer`	20190822	20190816
2623482	1814 0 0	17161 396 768	`ref`	`gcc_-m32_-march=prescott_-O3_-fomit-frame-pointer`	20190822	20190816
2630766	1433 0 0	18148 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=i486_-O2_-fomit-frame-pointer`	20190822	20190816
2638476	1634 0 0	17937 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6_-O2_-fomit-frame-pointer`	20190822	20190816
2655135	1810 0 0	19138 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6_-O3_-fomit-frame-pointer`	20190822	20190816
2659710	1520 0 0	18093 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer`	20190822	20190816
2690313	592 0 0	13717 396 768	`ref`	`gcc_-m32_-march=core2_-O2_-fomit-frame-pointer`	20190822	20190816
2703420	1897 0 0	19441 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium_-O3_-fomit-frame-pointer`	20190822	20190816
2705112	1835 0 0	19112 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentiumpro_-O_-fomit-frame-pointer`	20190822	20190816
2717142	1897 0 0	19441 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer`	20190822	20190816
2725962	1810 0 0	19746 400 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-2_-O3_-fomit-frame-pointer`	20190822	20190816
2733219	1520 0 0	18093 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium_-O2_-fomit-frame-pointer`	20190822	20190816
2745651	1634 0 0	17937 396 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-3_-O2_-fomit-frame-pointer`	20190822	20190816
2774307	1373 0 0	17256 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=i386_-O2_-fomit-frame-pointer`	20190822	20190816
2785488	1550 0 0	17392 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=i386_-O3_-fomit-frame-pointer`	20190822	20190816
2800710	1587 0 0	18792 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=i486_-O3_-fomit-frame-pointer`	20190822	20190816
2819808	1835 0 0	19112 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium2_-O_-fomit-frame-pointer`	20190822	20190816
2879721	593 0 0	13164 392 768	`ref`	`gcc_-m32_-march=i386_-O2_-fomit-frame-pointer`	20190822	20190816
2888925	1835 0 0	19112 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium3_-O_-fomit-frame-pointer`	20190822	20190816
2914764	1835 0 0	19232 392 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-m_-O_-fomit-frame-pointer`	20190822	20190816
2926458	629 0 0	13693 396 768	`ref`	`gcc_-m32_-march=pentium_-O2_-fomit-frame-pointer`	20190822	20190816
2935815	538 0 0	12228 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium4_-Os_-fomit-frame-pointer`	20190822	20190816
2943291	601 0 0	13837 396 768	`ref`	`gcc_-m32_-march=k6-3_-O2_-fomit-frame-pointer`	20190822	20190816
2957073	875 0 0	16898 400 768	`ref`	`gcc_-m32_-march=k6_-O3_-fomit-frame-pointer`	20190822	20190816
2973624	621 0 0	13924 392 768	`ref`	`gcc_-m32_-march=i486_-O2_-fomit-frame-pointer`	20190822	20190816
3003927	532 0 0	12196 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=i386_-Os_-fomit-frame-pointer`	20190822	20190816
3019338	627 0 0	13417 396 768	`ref`	`gcc_-m32_-march=k6-2_-O_-fomit-frame-pointer`	20190822	20190816
3028767	1230 0 0	13408 392 768	`ref`	`gcc_-m32_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
3029532	627 0 0	13417 396 768	`ref`	`gcc_-m32_-march=k6_-O_-fomit-frame-pointer`	20190822	20190816
3031104	601 0 0	13837 396 768	`ref`	`gcc_-m32_-march=k6-2_-O2_-fomit-frame-pointer`	20190822	20190816
3037530	675 0 0	13412 392 768	`ref`	`gcc_-m32_-march=prescott_-O_-fomit-frame-pointer`	20190822	20190816
3043812	591 0 0	12372 384 768	`ref`	`gcc_-m32_-march=k6-2_-Os_-fomit-frame-pointer`	20190822	20190816
3049632	629 0 0	13693 396 768	`ref`	`gcc_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer`	20190822	20190816
3055696	619 0 0	13301 396 768	`ref`	`gcc_-m32_-march=corei7_-O_-fomit-frame-pointer`	20190822	20190816
3056775	540 0 0	12260 384 768	`ref`	`gcc_-m32_-march=core2_-Os_-fomit-frame-pointer`	20190822	20190816
3056871	834 0 0	15244 392 768	`ref`	`gcc_-m32_-march=i386_-O3_-fomit-frame-pointer`	20190822	20190816
3067401	540 0 0	12244 384 768	`ref`	`gcc_-m32_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190822	20190816
3079434	601 0 0	13837 396 768	`ref`	`gcc_-m32_-march=k6_-O2_-fomit-frame-pointer`	20190822	20190816
3080319	927 0 0	16957 396 768	`ref`	`gcc_-m32_-march=pentium_-O3_-fomit-frame-pointer`	20190822	20190816
3091332	627 0 0	13417 396 768	`ref`	`gcc_-m32_-march=k6-3_-O_-fomit-frame-pointer`	20190822	20190816
3102633	585 0 0	12340 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-2_-Os_-fomit-frame-pointer`	20190822	20190816
3103170	875 0 0	17090 400 768	`ref`	`gcc_-m32_-march=k6-3_-O3_-fomit-frame-pointer`	20190822	20190816
3106725	619 0 0	13301 396 768	`ref`	`gcc_-m32_-march=corei7-avx_-O_-fomit-frame-pointer`	20190822	20190816
3115844	619 0 0	13293 396 768	`ref`	`gcc_-m32_-O_-fomit-frame-pointer`	20190822	20190816
3123696	591 0 0	12372 384 768	`ref`	`gcc_-m32_-march=k6-3_-Os_-fomit-frame-pointer`	20190822	20190816
3128404	540 0 0	12244 384 768	`ref`	`gcc_-m32_-march=corei7_-Os_-fomit-frame-pointer`	20190822	20190816
3131436	619 0 0	13301 396 768	`ref`	`gcc_-m32_-march=core2_-O_-fomit-frame-pointer`	20190822	20190816
3135570	540 0 0	12228 384 768	`ref`	`gcc_-m32_-march=pentium_-Os_-fomit-frame-pointer`	20190822	20190816
3149337	617 0 0	13037 396 768	`ref`	`gcc_-m32_-march=athlon_-O_-fomit-frame-pointer`	20190822	20190816
3151104	650 0 0	13317 396 768	`ref`	`gcc_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer`	20190822	20190816
3153920	540 0 0	12244 384 768	`ref`	`gcc_-m32_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190822	20190816
3154407	538 0 0	12196 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer`	20190822	20190816
3161964	650 0 0	13317 396 768	`ref`	`gcc_-m32_-march=pentium_-O_-fomit-frame-pointer`	20190822	20190816
3164184	619 0 0	13301 396 768	`ref`	`gcc_-m32_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190822	20190816
3190564	591 0 0	12372 384 768	`ref`	`gcc_-m32_-march=k6_-Os_-fomit-frame-pointer`	20190822	20190816
3194442	606 0 0	13724 392 768	`ref`	`gcc_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer`	20190822	20190816
3194845	619 0 0	13301 396 768	`ref`	`gcc_-m32_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190822	20190816
3195768	538 0 0	12196 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium_-Os_-fomit-frame-pointer`	20190822	20190816
3198687	875 0 0	17090 400 768	`ref`	`gcc_-m32_-march=k6-2_-O3_-fomit-frame-pointer`	20190822	20190816
3202980	540 0 0	12228 384 768	`ref`	`gcc_-m32_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190822	20190816
3211128	652 0 0	13416 392 768	`ref`	`gcc_-m32_-march=i486_-O_-fomit-frame-pointer`	20190822	20190816
3219603	540 0 0	12228 384 768	`ref`	`gcc_-m32_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190822	20190816
3219666	585 0 0	12340 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6-3_-Os_-fomit-frame-pointer`	20190822	20190816
3219699	540 0 0	12228 384 768	`ref`	`gcc_-m32_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190822	20190816
3221286	652 0 0	13144 392 768	`ref`	`gcc_-m32_-march=i386_-O_-fomit-frame-pointer`	20190822	20190816
3223652	540 0 0	12228 384 768	`ref`	`gcc_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer`	20190822	20190816
3230640	619 0 0	13301 396 768	`ref`	`gcc_-m32_-march=core-avx-i_-O_-fomit-frame-pointer`	20190822	20190816
3234243	619 0 0	13301 396 768	`ref`	`gcc_-m32_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190822	20190816
3251982	675 0 0	13412 392 768	`ref`	`gcc_-m32_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
3252989	585 0 0	12340 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=k6_-Os_-fomit-frame-pointer`	20190822	20190816
3259086	927 0 0	16957 396 768	`ref`	`gcc_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer`	20190822	20190816
3263844	540 0 0	12260 384 768	`ref`	`gcc_-m32_-march=pentium4_-Os_-fomit-frame-pointer`	20190822	20190816
3275448	540 0 0	12260 384 768	`ref`	`gcc_-m32_-march=prescott_-Os_-fomit-frame-pointer`	20190822	20190816
3280572	540 0 0	12212 384 768	`ref`	`gcc_-m32_-march=athlon_-Os_-fomit-frame-pointer`	20190822	20190816
3283434	540 0 0	12260 384 768	`ref`	`gcc_-m32_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
3302748	540 0 0	12260 384 768	`ref`	`gcc_-m32_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
3304077	538 0 0	12244 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
3314502	538 0 0	12228 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=prescott_-Os_-fomit-frame-pointer`	20190822	20190816
3325803	615 0 0	13152 392 768	`ref`	`gcc_-m32_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
3330459	536 0 0	12212 384 768	`ref`	`gcc_-m32_-march=i486_-Os_-fomit-frame-pointer`	20190822	20190816
3373788	1080 0 0	12260 384 768	`ref`	`gcc_-m32_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
3398604	538 0 0	12196 384 768	`ref`	`gcc_-funroll-loops_-m32_-Os_-fomit-frame-pointer`	20190822	20190816
3401496	538 0 0	12228 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
3414744	538 0 0	12196 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=athlon_-Os_-fomit-frame-pointer`	20190822	20190816
3414798	617 0 0	13364 392 768	`ref`	`gcc_-m32_-march=pentium4_-O_-fomit-frame-pointer`	20190822	20190816
3416032	540 0 0	12212 384 768	`ref`	`gcc_-m32_-Os_-fomit-frame-pointer`	20190822	20190816
3419070	532 0 0	12196 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=i486_-Os_-fomit-frame-pointer`	20190822	20190816
3435690	536 0 0	12212 384 768	`ref`	`gcc_-m32_-march=i386_-Os_-fomit-frame-pointer`	20190822	20190816
3445653	538 0 0	12244 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
3519477	961 0 0	16936 392 768	`ref`	`gcc_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer`	20190822	20190816
3520530	606 0 0	14080 392 768	`ref`	`gcc_-m32_-march=pentium-m_-O2_-fomit-frame-pointer`	20190822	20190816
3648129	1879 0 0	18232 392 768	`ref`	`gcc_-m32_-march=pentium-m_-O3_-fomit-frame-pointer`	20190822	20190816
3674529	606 0 0	13724 392 768	`ref`	`gcc_-m32_-march=pentium3_-O2_-fomit-frame-pointer`	20190822	20190816
3697278	606 0 0	13724 392 768	`ref`	`gcc_-m32_-march=pentium2_-O2_-fomit-frame-pointer`	20190822	20190816
3751323	961 0 0	17144 392 768	`ref`	`gcc_-m32_-march=pentium3_-O3_-fomit-frame-pointer`	20190822	20190816
3753255	961 0 0	16936 392 768	`ref`	`gcc_-m32_-march=pentium2_-O3_-fomit-frame-pointer`	20190822	20190816
3814872	606 0 0	13400 392 768	`ref`	`gcc_-m32_-march=pentium3_-O_-fomit-frame-pointer`	20190822	20190816
3822459	606 0 0	13400 392 768	`ref`	`gcc_-m32_-march=pentiumpro_-O_-fomit-frame-pointer`	20190822	20190816
4093071	606 0 0	13440 392 768	`ref`	`gcc_-m32_-march=pentium-m_-O_-fomit-frame-pointer`	20190822	20190816
4109376	606 0 0	13400 392 768	`ref`	`gcc_-m32_-march=pentium2_-O_-fomit-frame-pointer`	20190822	20190816
4177752	521 0 0	12132 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium2_-Os_-fomit-frame-pointer`	20190822	20190816
4245135	521 0 0	12132 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer`	20190822	20190816
4318776	518 0 0	12148 384 768	`ref`	`gcc_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer`	20190822	20190816
4412727	518 0 0	12148 384 768	`ref`	`gcc_-m32_-march=pentium2_-Os_-fomit-frame-pointer`	20190822	20190816
4505862	518 0 0	12180 384 768	`ref`	`gcc_-m32_-march=pentium-m_-Os_-fomit-frame-pointer`	20190822	20190816
4511751	518 0 0	12148 384 768	`ref`	`gcc_-m32_-march=pentium3_-Os_-fomit-frame-pointer`	20190822	20190816
4582953	521 0 0	12132 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium3_-Os_-fomit-frame-pointer`	20190822	20190816
4594434	521 0 0	12164 384 768	`ref`	`gcc_-funroll-loops_-m32_-march=pentium-m_-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_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: 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(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: 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: 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(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: ...

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_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: 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