Implementation notes: x86, samba, crypto_core/multsntrup761

Computer: samba
Architecture: x86
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_core
Primitive: multsntrup761

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
16670	`avx`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20190730	20190729
16671	`avx`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20190730	20190729
18931	`avx`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20190730	20190729
18943	`avx`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20190730	20190729
18948	`avx`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20190730	20190729
18980	`avx`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20190730	20190729
23427	`avx`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20190730	20190729
23961	`avx`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20190730	20190729
226296	`ref`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20190730	20190729
226625	`ref`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20190730	20190729
229950	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20190730	20190729
229960	`ref`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20190730	20190729
235985	`ref`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20190730	20190729
235993	`ref`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20190730	20190729
236063	`ref`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20190730	20190729
255760	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20190730	20190729
709246	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190730	20190729
709573	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190730	20190729
750966	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20190730	20190729
760404	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20190730	20190729
760607	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20190730	20190729
765435	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20190730	20190729
766954	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190730	20190729
767678	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20190730	20190729
769716	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190730	20190729
772111	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190730	20190729
773439	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190730	20190729
773839	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20190730	20190729
781623	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20190730	20190729
782572	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190730	20190729
784184	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20190730	20190729
784349	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20190730	20190729
785413	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190730	20190729
786589	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190730	20190729
789956	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190730	20190729
791121	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20190730	20190729
793707	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190730	20190729
794474	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190730	20190729
795412	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190730	20190729
796095	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190730	20190729
796244	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190730	20190729
796619	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20190730	20190729
796790	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190730	20190729
797970	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20190730	20190729
798686	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20190730	20190729
803320	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190730	20190729
804220	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20190730	20190729
813710	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20190730	20190729
815339	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20190730	20190729
815937	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20190730	20190729
826088	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190730	20190729
826615	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20190730	20190729
949206	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20190730	20190729
951170	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20190730	20190729
952801	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20190730	20190729
988250	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20190730	20190729
988315	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20190730	20190729
989494	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20190730	20190729
989655	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20190730	20190729
990250	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20190730	20190729
990853	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20190730	20190729
991970	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190730	20190729
994768	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20190730	20190729
1005353	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20190730	20190729
1016797	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20190730	20190729
1017504	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20190730	20190729
1024553	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190730	20190729
1025958	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190730	20190729
1045895	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20190730	20190729
1046593	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190730	20190729
1055867	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20190730	20190729
1058919	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20190730	20190729
1149990	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20190730	20190729
1151165	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20190730	20190729
1170070	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20190730	20190729
1178875	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190730	20190729
1199811	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190730	20190729
1200412	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20190730	20190729
1200528	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20190730	20190729
1200571	`ref`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20190730	20190729
1200820	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20190730	20190729
1201028	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20190730	20190729
1201071	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20190730	20190729
1201077	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20190730	20190729
1201097	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20190730	20190729
1201278	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190730	20190729
1202081	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20190730	20190729
1202182	`ref`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20190730	20190729
1202769	`ref`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20190730	20190729
1203033	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20190730	20190729
1204096	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20190730	20190729
1204411	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190730	20190729
1204437	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20190730	20190729
1204988	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20190730	20190729
1205066	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190730	20190729
1205091	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20190730	20190729
1205191	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20190730	20190729
1205787	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190730	20190729
1206114	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190730	20190729
1206756	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190730	20190729
1207443	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20190730	20190729
1208020	`ref`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20190730	20190729
1208058	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20190730	20190729
1208073	`ref`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20190730	20190729
1208078	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20190730	20190729
1208089	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20190730	20190729
1208232	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190730	20190729
1208887	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20190730	20190729
1209010	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190730	20190729
1210411	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20190730	20190729
1210982	`ref`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20190730	20190729
1211274	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20190730	20190729
1211430	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20190730	20190729
1211958	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20190730	20190729
1212099	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20190730	20190729
1212113	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20190730	20190729
1212277	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20190730	20190729
1212343	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20190730	20190729
1212462	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190730	20190729
1212553	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190730	20190729
1212621	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20190730	20190729
1212629	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20190730	20190729
1213351	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20190730	20190729
1213449	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190730	20190729
1214155	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20190730	20190729
1214416	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20190730	20190729
1215280	`ref`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20190730	20190729
1215456	`ref`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20190730	20190729
1215777	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190730	20190729
1215948	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20190730	20190729
1215956	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20190730	20190729
1216016	`ref`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20190730	20190729
1216051	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20190730	20190729
1216149	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20190730	20190729
1217418	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20190730	20190729
1217423	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20190730	20190729
1217754	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20190730	20190729
1218047	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20190730	20190729
1218248	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20190730	20190729
1221168	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190730	20190729
1221582	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190730	20190729
1221664	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190730	20190729
1221868	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20190730	20190729
1222036	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190730	20190729
1222186	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20190730	20190729
1222389	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190730	20190729
1222540	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20190730	20190729
1223427	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20190730	20190729
1223774	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20190730	20190729
1223774	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20190730	20190729
1224391	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20190730	20190729
1224574	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20190730	20190729
1225947	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20190730	20190729
1226284	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20190730	20190729
1226607	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20190730	20190729
1227443	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190730	20190729
1227526	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20190730	20190729
1227665	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20190730	20190729
1230665	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20190730	20190729
1230795	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190730	20190729
1231143	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20190730	20190729
1231202	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20190730	20190729
1231597	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190730	20190729
1231666	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20190730	20190729
1232161	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190730	20190729
1232430	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20190730	20190729
1233893	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190730	20190729
1234137	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20190730	20190729
1235331	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20190730	20190729
1237303	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20190730	20190729
1237596	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20190730	20190729
1240833	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20190730	20190729
1272391	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20190730	20190729
1277423	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190730	20190729
1287597	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190730	20190729
1290228	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20190730	20190729
1299615	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190730	20190729
1305309	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190730	20190729
1307148	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190730	20190729
1307286	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190730	20190729
1307990	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190730	20190729
1311843	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190730	20190729
1312109	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190730	20190729
1313316	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190730	20190729

Compiler output

Implementation: crypto_core/multsntrup761/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/multsntrup761/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/multsntrup761/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/multsntrup761/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/multsntrup761/avx
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

mult768.c: mult768.c: In function 'squeeze_4591_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4591)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4591)));
mult768.c: ...
mult768.c: mult768.c: In function 'squeeze_4591_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4591)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4591)));
mult768.c: ...

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

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

Compiler output

Implementation: crypto_core/multsntrup761/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/multsntrup761/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_4591_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4591)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(7)),const_x16(4591)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: ...

Number of similar (compiler,implementation) pairs: 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/multsntrup761/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