Implementation notes: x86, samba, crypto_core/mult3sntrup761

Computer: samba
Architecture: x86
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_core
Primitive: mult3sntrup761

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
8448	`avx`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20190730	20190729
8455	`avx`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20190730	20190729
14230	`avx`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20190730	20190729
14542	`avx`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20190730	20190729
15317	`avx`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20190730	20190729
15477	`avx`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20190730	20190729
26760	`avx`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20190730	20190729
26820	`avx`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20190730	20190729
649668	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20190730	20190729
650645	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20190730	20190729
660504	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20190730	20190729
664401	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20190730	20190729
673484	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190730	20190729
683343	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190730	20190729
688724	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20190730	20190729
689030	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20190730	20190729
689148	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20190730	20190729
690415	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20190730	20190729
700040	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190730	20190729
721268	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20190730	20190729
724532	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20190730	20190729
735554	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190730	20190729
962324	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190730	20190729
966084	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190730	20190729
966295	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190730	20190729
969133	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190730	20190729
970418	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190730	20190729
971498	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190730	20190729
971561	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190730	20190729
972532	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190730	20190729
1009566	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190730	20190729
1042313	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190730	20190729
1065653	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20190730	20190729
1078333	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20190730	20190729
1078627	`ref`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20190730	20190729
1079893	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190730	20190729
1082830	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20190730	20190729
1086953	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20190730	20190729
1109667	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20190730	20190729
1111683	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20190730	20190729
1112538	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20190730	20190729
1112771	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20190730	20190729
1161087	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20190730	20190729
1166179	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20190730	20190729
1194075	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20190730	20190729
1194097	`ref`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20190730	20190729
1198942	`ref`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20190730	20190729
1200218	`ref`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20190730	20190729
1206899	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190730	20190729
1209421	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20190730	20190729
1214208	`ref`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20190730	20190729
1214464	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20190730	20190729
1218351	`ref`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20190730	20190729
1235316	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20190730	20190729
1236897	`ref`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20190730	20190729
1237230	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20190730	20190729
1237674	`ref`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20190730	20190729
1240329	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20190730	20190729
1271056	`ref`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20190730	20190729
1287321	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20190730	20190729
1729778	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20190730	20190729
1730197	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20190730	20190729
1730482	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20190730	20190729
1739531	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20190730	20190729
1740690	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20190730	20190729
1744212	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20190730	20190729
1746564	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190730	20190729
1746645	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20190730	20190729
1752135	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20190730	20190729
1752229	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20190730	20190729
1753216	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20190730	20190729
1753610	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20190730	20190729
1757787	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20190730	20190729
1760379	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20190730	20190729
1880032	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190730	20190729
1889492	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190730	20190729
1889536	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190730	20190729
1889597	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190730	20190729
1893449	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190730	20190729
1893528	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190730	20190729
1894079	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190730	20190729
1900583	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190730	20190729
1982832	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20190730	20190729
1982877	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20190730	20190729
1982905	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190730	20190729
1983082	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20190730	20190729
2000655	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20190730	20190729
2001479	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20190730	20190729
2003770	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20190730	20190729
2003780	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190730	20190729
2003908	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20190730	20190729
2010697	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20190730	20190729
2012558	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20190730	20190729
2013748	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190730	20190729
2014234	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20190730	20190729
2015471	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20190730	20190729
2027323	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20190730	20190729
2027573	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20190730	20190729
2028898	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20190730	20190729
2028994	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20190730	20190729
2035255	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20190730	20190729
2037373	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20190730	20190729
2045230	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20190730	20190729
2045472	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20190730	20190729
2049782	`ref`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20190730	20190729
2049848	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20190730	20190729
2065994	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20190730	20190729
2065996	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190730	20190729
2066455	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190730	20190729
2080902	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20190730	20190729
2083186	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190730	20190729
2096548	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20190730	20190729
2096591	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20190730	20190729
2096613	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20190730	20190729
2106679	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190730	20190729
2106915	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20190730	20190729
2107326	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20190730	20190729
2107597	`ref`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20190730	20190729
2107754	`ref`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20190730	20190729
2386649	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20190730	20190729
2388594	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20190730	20190729
2389353	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190730	20190729
2389440	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20190730	20190729
2394959	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20190730	20190729
2395438	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190730	20190729
2395575	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190730	20190729
2395887	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190730	20190729
2396409	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20190730	20190729
2396426	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20190730	20190729
2404423	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20190730	20190729
2410140	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20190730	20190729
2410180	`ref`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20190730	20190729
2410703	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20190730	20190729
2410742	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20190730	20190729
2410748	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20190730	20190729
2410958	`ref`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20190730	20190729
2411266	`ref`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20190730	20190729
2411623	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20190730	20190729
2413203	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20190730	20190729
2413314	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20190730	20190729
2413676	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20190730	20190729
2415025	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20190730	20190729
2415359	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20190730	20190729
2415948	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20190730	20190729
2415996	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20190730	20190729
2416018	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190730	20190729
2416062	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190730	20190729
2416169	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20190730	20190729
2430293	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20190730	20190729
2430996	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20190730	20190729
2441421	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20190730	20190729
2442623	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20190730	20190729
2471297	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20190730	20190729
2481227	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20190730	20190729
2482762	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20190730	20190729
2482891	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20190730	20190729
2483879	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190730	20190729
2484222	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20190730	20190729
2484976	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20190730	20190729
2574129	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190730	20190729
2574173	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190730	20190729
2574603	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190730	20190729
2574726	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190730	20190729
2576345	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190730	20190729
2579180	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190730	20190729
2579236	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190730	20190729
2579278	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190730	20190729
2611964	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20190730	20190729
2612157	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190730	20190729
2617151	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190730	20190729
2617403	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20190730	20190729
2645166	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20190730	20190729
2645206	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190730	20190729
2645242	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190730	20190729
2660468	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190730	20190729
2660638	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190730	20190729
2660664	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20190730	20190729
2670857	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190730	20190729
2671083	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190730	20190729
2671120	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20190730	20190729
3069700	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20190730	20190729
3078276	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20190730	20190729
3082016	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20190730	20190729
3083931	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190730	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