Implementation notes: x86, titan0, crypto_core/mult3sntrup761

Computer: titan0
Architecture: x86
CPU ID: GenuineIntel-000306c3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_core
Primitive: mult3sntrup761

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
10116	`avx`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20190731	20190729
10164	`avx`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20190731	20190729
15488	`avx`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20190731	20190729
15516	`avx`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20190731	20190729
16916	`avx`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20190731	20190729
16960	`avx`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20190731	20190729
29208	`avx`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20190731	20190729
29484	`avx`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20190731	20190729
645380	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20190731	20190729
645968	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190731	20190729
646708	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190731	20190729
649400	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20190731	20190729
652372	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20190731	20190729
659916	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20190731	20190729
660812	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20190731	20190729
663416	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20190731	20190729
664400	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20190731	20190729
666388	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20190731	20190729
678232	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20190731	20190729
686772	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190731	20190729
688112	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20190731	20190729
688164	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190731	20190729
910088	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190731	20190729
911988	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190731	20190729
912100	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190731	20190729
913084	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190731	20190729
917020	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190731	20190729
922392	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190731	20190729
922716	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190731	20190729
923064	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190731	20190729
1073548	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20190731	20190729
1073944	`ref`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20190731	20190729
1086436	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20190731	20190729
1086676	`ref`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20190731	20190729
1106564	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190731	20190729
1111284	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190731	20190729
1113548	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190731	20190729
1122124	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190731	20190729
1123924	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20190731	20190729
1128512	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20190731	20190729
1129108	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20190731	20190729
1132220	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20190731	20190729
1136516	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20190731	20190729
1136884	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20190731	20190729
1138624	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20190731	20190729
1166992	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20190731	20190729
1167040	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20190731	20190729
1194512	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20190731	20190729
1201588	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20190731	20190729
1235620	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20190731	20190729
1242976	`ref`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20190731	20190729
1243184	`ref`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20190731	20190729
1244588	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20190731	20190729
1245280	`ref`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20190731	20190729
1246576	`ref`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20190731	20190729
1249668	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20190731	20190729
1257276	`ref`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20190731	20190729
1257664	`ref`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20190731	20190729
1285132	`ref`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20190731	20190729
1304216	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20190731	20190729
1745184	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20190731	20190729
1745336	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20190731	20190729
1745424	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20190731	20190729
1758412	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20190731	20190729
1758948	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20190731	20190729
1760796	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20190731	20190729
1760836	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190731	20190729
1763012	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20190731	20190729
1771784	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20190731	20190729
1771808	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20190731	20190729
1773372	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20190731	20190729
1776476	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20190731	20190729
1776612	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20190731	20190729
1777100	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20190731	20190729
1874216	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190731	20190729
1878764	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190731	20190729
1878776	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190731	20190729
1880020	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190731	20190729
1888220	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190731	20190729
1888672	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190731	20190729
1888776	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190731	20190729
1888984	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190731	20190729
2008280	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190731	20190729
2008376	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20190731	20190729
2008900	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20190731	20190729
2009608	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20190731	20190729
2051960	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20190731	20190729
2052644	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190731	20190729
2052712	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20190731	20190729
2053936	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20190731	20190729
2054348	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20190731	20190729
2065936	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20190731	20190729
2066172	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20190731	20190729
2067052	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190731	20190729
2067312	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20190731	20190729
2067368	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20190731	20190729
2126032	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20190731	20190729
2126072	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190731	20190729
2126120	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190731	20190729
2129132	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20190731	20190729
2129160	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20190731	20190729
2130612	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20190731	20190729
2131512	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20190731	20190729
2132784	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20190731	20190729
2132916	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20190731	20190729
2142296	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20190731	20190729
2142448	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20190731	20190729
2163876	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20190731	20190729
2164240	`ref`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20190731	20190729
2172268	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190731	20190729
2172544	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20190731	20190729
2181020	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20190731	20190729
2181356	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20190731	20190729
2181392	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20190731	20190729
2184048	`ref`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20190731	20190729
2184684	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190731	20190729
2184824	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20190731	20190729
2185124	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20190731	20190729
2186780	`ref`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20190731	20190729
2380532	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20190731	20190729
2382936	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20190731	20190729
2382940	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190731	20190729
2384772	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20190731	20190729
2388012	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20190731	20190729
2391184	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20190731	20190729
2391240	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190731	20190729
2393888	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20190731	20190729
2397628	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190731	20190729
2397676	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190731	20190729
2397736	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20190731	20190729
2418492	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20190731	20190729
2418628	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190731	20190729
2418672	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190731	20190729
2430772	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20190731	20190729
2430844	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20190731	20190729
2430868	`ref`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20190731	20190729
2430892	`ref`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20190731	20190729
2430912	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20190731	20190729
2430940	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20190731	20190729
2431692	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20190731	20190729
2432216	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20190731	20190729
2432376	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20190731	20190729
2432444	`ref`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20190731	20190729
2433008	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20190731	20190729
2433072	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20190731	20190729
2434464	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20190731	20190729
2434492	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20190731	20190729
2434540	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20190731	20190729
2454288	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20190731	20190729
2457140	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20190731	20190729
2465428	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20190731	20190729
2468184	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20190731	20190729
2469172	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20190731	20190729
2471840	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20190731	20190729
2482168	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190731	20190729
2482196	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20190731	20190729
2482216	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20190731	20190729
2482472	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20190731	20190729
2484232	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20190731	20190729
2597060	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190731	20190729
2597528	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190731	20190729
2597716	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190731	20190729
2597904	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190731	20190729
2597956	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190731	20190729
2598008	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190731	20190729
2598088	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190731	20190729
2598308	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190731	20190729
2662548	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190731	20190729
2662976	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20190731	20190729
2663408	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190731	20190729
2685348	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20190731	20190729
2691452	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190731	20190729
2700196	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190731	20190729
2700280	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20190731	20190729
2709328	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190731	20190729
2709396	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190731	20190729
2711284	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20190731	20190729
2753320	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190731	20190729
2753588	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20190731	20190729
2753792	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190731	20190729
3035840	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20190731	20190729
3035908	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20190731	20190729
3036216	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20190731	20190729
3038964	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190731	20190729

Compiler output

Implementation: crypto_core/mult3sntrup761/round1
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: crypto_core/mult3sntrup761/avx
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: crypto_core/mult3sntrup761/round1
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: crypto_core/mult3sntrup761/round1
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: crypto_core/mult3sntrup761/avx
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: crypto_core/mult3sntrup761/round1
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: 8, 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

Compiler output

Implementation: crypto_core/mult3sntrup761/avx
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: 8, 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

Compiler output

Implementation: crypto_core/mult3sntrup761/round1
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: 8, namely:

Compiler	Implementations
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	round1
gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer	round1
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	round1
gcc -m32 -march=core-avx2 -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