Implementation notes: x86, bolero, crypto_kem/ntskem1264

Computer: bolero
Architecture: x86
CPU ID: GenuineIntel-000406f1-bfebfbff
SUPERCOP version: 20190110
Operation: crypto_kem
Primitive: ntskem1264

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
1920728	`opt`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20181123	20181113
1934352	`opt`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20181123	20181113
2030432	`opt`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20181123	20181113
2031028	`opt`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20181123	20181113
2037232	`opt`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20181123	20181113
2040356	`opt`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20181123	20181113
2040732	`opt`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20181123	20181113
2043284	`opt`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20181123	20181113
2051552	`opt`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20181123	20181113
2053052	`opt`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20181123	20181113
2053324	`opt`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20181123	20181113
2061728	`opt`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20181123	20181113
2063188	`opt`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20181123	20181113
2069624	`opt`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20181123	20181113
2074424	`opt`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20181123	20181113
2075964	`opt`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20181123	20181113
2077408	`opt`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20181123	20181113
2089064	`opt`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20181123	20181113
2092776	`opt`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20181123	20181113
2095192	`opt`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20181123	20181113
2102804	`opt`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20181123	20181113
2105868	`opt`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20181123	20181113
2109324	`opt`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20181123	20181113
2114844	`opt`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20181123	20181113
2120652	`opt`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20181123	20181113
2124296	`opt`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20181123	20181113
2128036	`opt`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20181123	20181113
2128788	`opt`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20181123	20181113
2131300	`opt`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20181123	20181113
2132564	`opt`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20181123	20181113
2133416	`opt`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20181123	20181113
2133620	`opt`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20181123	20181113
2134436	`opt`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20181123	20181113
2137420	`opt`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20181123	20181113
2138024	`opt`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20181123	20181113
2140868	`opt`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20181123	20181113
2142888	`opt`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20181123	20181113
2142956	`opt`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20181123	20181113
2142988	`opt`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20181123	20181113
2147716	`opt`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20181123	20181113
2148708	`opt`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20181123	20181113
2149120	`opt`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20181123	20181113
2150832	`opt`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20181123	20181113
2153964	`opt`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20181123	20181113
2154124	`opt`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20181123	20181113
2154628	`opt`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20181123	20181113
2154708	`opt`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20181123	20181113
2155200	`opt`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20181123	20181113
2157208	`opt`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20181123	20181113
2157824	`opt`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20181123	20181113
2159292	`opt`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20181123	20181113
2159932	`opt`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20181123	20181113
2161104	`opt`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20181123	20181113
2162348	`opt`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20181123	20181113
2163384	`opt`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20181123	20181113
2163724	`opt`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20181123	20181113
2164648	`opt`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20181123	20181113
2165084	`opt`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20181123	20181113
2165684	`opt`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20181123	20181113
2165844	`opt`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20181123	20181113
2167372	`opt`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20181123	20181113
2167828	`opt`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20181123	20181113
2167908	`opt`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20181123	20181113
2169028	`opt`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20181123	20181113
2169520	`opt`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20181123	20181113
2169560	`opt`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20181123	20181113
2169856	`opt`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20181123	20181113
2172404	`opt`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20181123	20181113
2172900	`opt`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20181123	20181113
2173748	`opt`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20181123	20181113
2173836	`opt`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20181123	20181113
2175544	`opt`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20181123	20181113
2175820	`opt`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20181123	20181113
2175832	`opt`	`gcc -m32 -O3 -fomit-frame-pointer`	20181123	20181113
2176520	`opt`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20181123	20181113
2176880	`opt`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20181123	20181113
2177128	`opt`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20181123	20181113
2177156	`opt`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20181123	20181113
2177172	`opt`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20181123	20181113
2177536	`opt`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20181123	20181113
2177916	`opt`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20181123	20181113
2178356	`opt`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20181123	20181113
2178492	`opt`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20181123	20181113
2179904	`opt`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20181123	20181113
2180824	`opt`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20181123	20181113
2181452	`opt`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20181123	20181113
2181940	`opt`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20181123	20181113
2182268	`opt`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20181123	20181113
2182648	`opt`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20181123	20181113
2182920	`opt`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20181123	20181113
2183340	`opt`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20181123	20181113
2183680	`opt`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20181123	20181113
2183888	`opt`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20181123	20181113
2183976	`opt`	`gcc -m32 -O -fomit-frame-pointer`	20181123	20181113
2184804	`opt`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20181123	20181113
2184968	`opt`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20181123	20181113
2187296	`opt`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20181123	20181113
2188404	`opt`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20181123	20181113
2188964	`opt`	`gcc -m32 -Os -fomit-frame-pointer`	20181123	20181113
2189716	`opt`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20181123	20181113
2190208	`opt`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20181123	20181113
2190508	`opt`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20181123	20181113
2192560	`opt`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20181123	20181113
2194484	`opt`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20181123	20181113
2195360	`opt`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20181123	20181113
2195544	`opt`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20181123	20181113
2195800	`opt`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20181123	20181113
2195828	`opt`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20181123	20181113
2199636	`opt`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20181123	20181113
2200692	`opt`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20181123	20181113
2200700	`opt`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20181123	20181113
2201672	`opt`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20181123	20181113
2202808	`opt`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20181123	20181113
2203040	`opt`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20181123	20181113
2203640	`opt`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20181123	20181113
2206148	`opt`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20181123	20181113
2207584	`opt`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20181123	20181113
2207704	`opt`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20181123	20181113
2209284	`opt`	`gcc -m32 -O2 -fomit-frame-pointer`	20181123	20181113
2209724	`opt`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20181123	20181113
2210060	`opt`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20181123	20181113
2210684	`opt`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20181123	20181113
2211676	`opt`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20181123	20181113
2212132	`opt`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20181123	20181113
2214960	`opt`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20181123	20181113
2215260	`opt`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20181123	20181113
2216468	`opt`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20181123	20181113
2216928	`opt`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20181123	20181113
2217456	`opt`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20181123	20181113
2217964	`opt`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20181123	20181113
2218288	`opt`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20181123	20181113
2219004	`opt`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20181123	20181113
2219800	`opt`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20181123	20181113
2220840	`opt`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20181123	20181113
2221452	`opt`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20181123	20181113
2223964	`opt`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20181123	20181113
2226036	`opt`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20181123	20181113
2227328	`opt`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20181123	20181113
2227564	`opt`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20181123	20181113
2229836	`opt`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20181123	20181113
2229868	`opt`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20181123	20181113
2230996	`opt`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20181123	20181113
2233404	`opt`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20181123	20181113
2234508	`opt`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20181123	20181113
2235128	`opt`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20181123	20181113
2235800	`opt`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20181123	20181113
2238012	`opt`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20181123	20181113
2244272	`opt`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20181123	20181113
2253144	`opt`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20181123	20181113
2264040	`opt`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20181123	20181113
2265976	`opt`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20181123	20181113
2271028	`opt`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20181123	20181113
2273868	`opt`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20181123	20181113
2275396	`opt`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20181123	20181113
2276632	`opt`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20181123	20181113
2279164	`opt`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20181123	20181113
2283592	`opt`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20181123	20181113
2285176	`opt`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20181123	20181113
2287776	`opt`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20181123	20181113
2291672	`opt`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20181123	20181113
2296376	`opt`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20181123	20181113
2297212	`opt`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20181123	20181113
2322820	`opt`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20181123	20181113
2325264	`opt`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20181123	20181113
2325676	`opt`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20181123	20181113
2325844	`opt`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20181123	20181113
2332696	`opt`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20181123	20181113
2355640	`opt`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20181123	20181113
2356380	`opt`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20181123	20181113
2359136	`opt`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20181123	20181113
2360308	`opt`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20181123	20181113
2363528	`opt`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20181123	20181113
2375548	`opt`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20181123	20181113
2390272	`opt`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20181123	20181113
2393296	`opt`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20181123	20181113
2402028	`opt`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20181123	20181113

Test failure

Implementation: crypto_kem/ntskem1264/ref
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

error 111
crypto_kem_dec returns nonzero

Number of similar (compiler,implementation) pairs: 172, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	ref
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	ref
gcc -m32 -O2 -fomit-frame-pointer	ref
gcc -m32 -O3 -fomit-frame-pointer	ref
gcc -m32 -O -fomit-frame-pointer	ref
gcc -m32 -Os -fomit-frame-pointer	ref
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	ref
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	ref
gcc -m32 -march=athlon -O -fomit-frame-pointer	ref
gcc -m32 -march=athlon -Os -fomit-frame-pointer	ref
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	ref
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer	ref
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	ref
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	ref
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	ref
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	ref
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=core2 -O -fomit-frame-pointer	ref
gcc -m32 -march=core2 -Os -fomit-frame-pointer	ref
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	ref
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	ref
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	ref
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	ref
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	ref
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer	ref
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	ref
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	ref
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=corei7 -O -fomit-frame-pointer	ref
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	ref
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=i386 -O -fomit-frame-pointer	ref
gcc -m32 -march=i386 -Os -fomit-frame-pointer	ref
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=i486 -O -fomit-frame-pointer	ref
gcc -m32 -march=i486 -Os -fomit-frame-pointer	ref
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	ref
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	ref
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	ref
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	ref
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=k6 -O -fomit-frame-pointer	ref
gcc -m32 -march=k6 -Os -fomit-frame-pointer	ref
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=k8 -O -fomit-frame-pointer	ref
gcc -m32 -march=k8 -Os -fomit-frame-pointer	ref
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	ref
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	ref
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	ref
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	ref
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	ref
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	ref
gcc -m32 -march=nocona -O -fomit-frame-pointer	ref
gcc -m32 -march=nocona -Os -fomit-frame-pointer	ref
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	ref
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	ref
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	ref
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	ref
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	ref
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	ref
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	ref
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	ref
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	ref
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	ref
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	ref
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	ref
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	ref
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	ref
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	ref
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	ref
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	ref
gcc -m32 -march=pentium -O -fomit-frame-pointer	ref
gcc -m32 -march=pentium -Os -fomit-frame-pointer	ref
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	ref
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	ref
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	ref
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	ref
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	ref
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	ref
gcc -m32 -march=prescott -O -fomit-frame-pointer	ref
gcc -m32 -march=prescott -Os -fomit-frame-pointer	ref

Test failure

Implementation: crypto_kem/ntskem1264/ref
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

error 111
crypto_kem_dec returns nonzero
error 111
crypto_kem_dec returns nonzero

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

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

Compiler output

Implementation: crypto_kem/ntskem1264/sse2
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

bitslice_bma_128.c: In file included from bitslice_bma_128.c:20:0:
bitslice_bma_128.c: bits.h: In function 'vector_popcount':
bitslice_bma_128.c: bits.h:99:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: bits.h:93:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c: In function 'vMUX':
bitslice_bma_128.c: bitslice_bma_128.c:47:1: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
bitslice_bma_128.c: {
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
bitslice_bma_128.c: from bitslice_bma_128.h:18,
bitslice_bma_128.c: from bitslice_bma_128.c:18:
bitslice_bma_128.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
bitslice_bma_128.c: _mm_xor_si128 (__m128i __A, __m128i __B)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:48:12: error: called from here
bitslice_bma_128.c: return _mm_xor_si128(b,
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
bitslice_bma_128.c: from bitslice_bma_128.h:18,
bitslice_bma_128.c: ...

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

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	sse2
gcc -m32 -O2 -fomit-frame-pointer	sse2
gcc -m32 -O3 -fomit-frame-pointer	sse2
gcc -m32 -O -fomit-frame-pointer	sse2
gcc -m32 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=athlon -O -fomit-frame-pointer	sse2
gcc -m32 -march=athlon -Os -fomit-frame-pointer	sse2
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=i386 -O -fomit-frame-pointer	sse2
gcc -m32 -march=i386 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=i486 -O -fomit-frame-pointer	sse2
gcc -m32 -march=i486 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	sse2
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	sse2
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=k6 -O -fomit-frame-pointer	sse2
gcc -m32 -march=k6 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	sse2
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	sse2
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	sse2
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium -O -fomit-frame-pointer	sse2
gcc -m32 -march=pentium -Os -fomit-frame-pointer	sse2
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	sse2
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	sse2

Compiler output

Implementation: crypto_kem/ntskem1264/avx2
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

bitslice_bma_128.c: bitslice_bma_128.c: In function 'vMUX':
bitslice_bma_128.c: bitslice_bma_128.c:46:1: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
bitslice_bma_128.c: {
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:0:
bitslice_bma_128.c: bitslice_bma_128.c: In function 'vector_popcount_128':
bitslice_bma_128.c: bitslice_bma_128.c:55:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: bits.h:97:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
bitslice_bma_128.c: from bitslice_bma_128.h:18,
bitslice_bma_128.c: from bitslice_bma_128.c:17:
bitslice_bma_128.c: bitslice_bma_128.c: In function 'vMUX':
bitslice_bma_128.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
bitslice_bma_128.c: _mm_xor_si128 (__m128i __A, __m128i __B)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:47:12: error: called from here
bitslice_bma_128.c: return _mm_xor_si128(b,
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
bitslice_bma_128.c: ...

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

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	avx2
gcc -m32 -O2 -fomit-frame-pointer	avx2
gcc -m32 -O3 -fomit-frame-pointer	avx2
gcc -m32 -O -fomit-frame-pointer	avx2
gcc -m32 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=athlon -O -fomit-frame-pointer	avx2
gcc -m32 -march=athlon -Os -fomit-frame-pointer	avx2
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=i386 -O -fomit-frame-pointer	avx2
gcc -m32 -march=i386 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=i486 -O -fomit-frame-pointer	avx2
gcc -m32 -march=i486 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	avx2
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	avx2
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=k6 -O -fomit-frame-pointer	avx2
gcc -m32 -march=k6 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	avx2
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	avx2
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	avx2
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium -O -fomit-frame-pointer	avx2
gcc -m32 -march=pentium -Os -fomit-frame-pointer	avx2
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	avx2
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	avx2

Compiler output

Implementation: crypto_kem/ntskem1264/avx2
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	avx2
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	avx2
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	avx2
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -O -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	avx2
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	avx2
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	avx2
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=corei7 -O -fomit-frame-pointer	avx2
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=k8 -O -fomit-frame-pointer	avx2
gcc -m32 -march=k8 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=nocona -O -fomit-frame-pointer	avx2
gcc -m32 -march=nocona -Os -fomit-frame-pointer	avx2
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	avx2
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	avx2
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	avx2
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=prescott -O -fomit-frame-pointer	avx2
gcc -m32 -march=prescott -Os -fomit-frame-pointer	avx2

Compiler output

Implementation: crypto_kem/ntskem1264/sse2
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 76, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -O -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	sse2
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	sse2
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=corei7 -O -fomit-frame-pointer	sse2
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=k8 -O -fomit-frame-pointer	sse2
gcc -m32 -march=k8 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	sse2
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	sse2
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=nocona -O -fomit-frame-pointer	sse2
gcc -m32 -march=nocona -Os -fomit-frame-pointer	sse2
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	sse2
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	sse2
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	sse2
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=prescott -O -fomit-frame-pointer	sse2
gcc -m32 -march=prescott -Os -fomit-frame-pointer	sse2

Compiler output

Implementation: crypto_kem/ntskem1264/avx2
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer

bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:0:
bitslice_bma_128.c: bitslice_bma_128.c: In function 'vector_popcount_128':
bitslice_bma_128.c: bitslice_bma_128.c:55:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: bits.h:97:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
bitslice_bma_128.c: from bitslice_bma_128.h:18,
bitslice_bma_128.c: from bitslice_bma_128.c:17:
bitslice_bma_128.c: bitslice_bma_128.c: In function 'vMUX':
bitslice_bma_128.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
bitslice_bma_128.c: _mm_xor_si128 (__m128i __A, __m128i __B)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:47:12: error: called from here
bitslice_bma_128.c: return _mm_xor_si128(b,
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
bitslice_bma_128.c: from bitslice_bma_128.h:18,
bitslice_bma_128.c: from bitslice_bma_128.c:17:
bitslice_bma_128.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1268:1: error: inlining failed in call to always_inline '_mm_and_si128': target specific option mismatch
bitslice_bma_128.c: _mm_and_si128 (__m128i __A, __m128i __B)
bitslice_bma_128.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	avx2
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	avx2

Compiler output

Implementation: crypto_kem/ntskem1264/sse2
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer

bitslice_bma_128.c: In file included from bitslice_bma_128.c:20:0:
bitslice_bma_128.c: bits.h: In function 'vector_popcount':
bitslice_bma_128.c: bits.h:99:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: bits.h:93:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
bitslice_bma_128.c: from bitslice_bma_128.h:18,
bitslice_bma_128.c: from bitslice_bma_128.c:18:
bitslice_bma_128.c: bitslice_bma_128.c: In function 'vMUX':
bitslice_bma_128.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
bitslice_bma_128.c: _mm_xor_si128 (__m128i __A, __m128i __B)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:48:12: error: called from here
bitslice_bma_128.c: return _mm_xor_si128(b,
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
bitslice_bma_128.c: from bitslice_bma_128.h:18,
bitslice_bma_128.c: from bitslice_bma_128.c:18:
bitslice_bma_128.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1268:1: error: inlining failed in call to always_inline '_mm_and_si128': target specific option mismatch
bitslice_bma_128.c: _mm_and_si128 (__m128i __A, __m128i __B)
bitslice_bma_128.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	sse2
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	sse2

Compiler output

Implementation: crypto_kem/ntskem1264/avx2
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:0:
bitslice_bma_128.c: bits.h: In function 'vector_popcount':
bitslice_bma_128.c: bits.h:124:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: bits.h:97:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c: Assembler messages:
bitslice_bma_128.c: bitslice_bma_128.c:165: Error: invalid instruction suffix for `bsr'
bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:0:
bitslice_bma_128.c: bits.h: In function 'vector_popcount':
bitslice_bma_128.c: bits.h:124:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: bits.h:97:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c: Assembler messages:
bitslice_bma_128.c: bitslice_bma_128.c:165: Error: invalid instruction suffix for `bsr'

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

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=barcelona -O -fomit-frame-pointer	avx2
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	avx2

Compiler output

Implementation: crypto_kem/ntskem1264/sse2
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

bitslice_bma_128.c: In file included from bitslice_bma_128.c:20:0:
bitslice_bma_128.c: bits.h: In function 'vector_popcount':
bitslice_bma_128.c: bits.h:99:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: bits.h:93:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c: Assembler messages:
bitslice_bma_128.c: bitslice_bma_128.c:166: Error: invalid instruction suffix for `bsr'
bitslice_bma_128.c: In file included from bitslice_bma_128.c:20:0:
bitslice_bma_128.c: bits.h: In function 'vector_popcount':
bitslice_bma_128.c: bits.h:99:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: bits.h:93:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c: Assembler messages:
bitslice_bma_128.c: bitslice_bma_128.c:166: Error: invalid instruction suffix for `bsr'

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

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=barcelona -O -fomit-frame-pointer	sse2
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	sse2

Compiler output

Implementation: crypto_kem/ntskem1264/avx2
Compiler: gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer

bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:0:
bitslice_bma_128.c: bits.h: In function 'vector_popcount':
bitslice_bma_128.c: bits.h:118:22: warning: implicit declaration of function '_mm256_extract_epi64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return (int32_t)(_mm256_extract_epi64(popcnt, 3) +
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c: In function 'vector_popcount_128':
bitslice_bma_128.c: bitslice_bma_128.c:55:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: bits.h:97:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c: Assembler messages:
bitslice_bma_128.c: bitslice_bma_128.c:165: Error: invalid instruction suffix for `bsr'

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	avx2
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	avx2
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	avx2
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	avx2