Implementation notes: x86, samba, crypto_kem/ntskem1264

Computer: samba
Architecture: x86
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_kem
Primitive: ntskem1264

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
1529923	`opt`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20190724	20190110
1530323	`opt`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20190724	20190110
1549274	`opt`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20190724	20190110
1550325	`opt`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20190724	20190110
1568563	`opt`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190724	20190110
1571022	`opt`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190724	20190110
1573033	`opt`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20190724	20190110
1574030	`opt`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20190724	20190110
1629915	`opt`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20190724	20190110
1630305	`opt`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20190724	20190110
1641939	`opt`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20190724	20190110
1642703	`opt`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190724	20190110
1647435	`opt`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20190724	20190110
1648080	`opt`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20190724	20190110
1648929	`opt`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20190724	20190110
1648976	`opt`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20190724	20190110
1653708	`opt`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20190724	20190110
1654949	`opt`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20190724	20190110
1655964	`opt`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190724	20190110
1662968	`opt`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190724	20190110
1664052	`opt`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20190724	20190110
1664629	`opt`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20190724	20190110
1664811	`opt`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20190724	20190110
1670304	`opt`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20190724	20190110
1670411	`opt`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20190724	20190110
1671554	`opt`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20190724	20190110
1679638	`opt`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20190724	20190110
1679719	`opt`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20190724	20190110
1680973	`opt`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20190724	20190110
1681242	`opt`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20190724	20190110
1681925	`opt`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20190724	20190110
1682311	`opt`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20190724	20190110
1683132	`opt`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190724	20190110
1691103	`opt`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190724	20190110
1696173	`opt`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20190724	20190110
1697369	`opt`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20190724	20190110
1698715	`opt`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190724	20190110
1731911	`opt`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190724	20190110
1740837	`opt`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190724	20190110
1742710	`opt`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20190724	20190110
1748053	`opt`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20190724	20190110
1750156	`opt`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20190724	20190110
1765661	`opt`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190724	20190110
1769214	`opt`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20190724	20190110
1785690	`opt`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20190724	20190110
1795109	`opt`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20190724	20190110
1802766	`opt`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20190724	20190110
1811542	`opt`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20190724	20190110
1812968	`opt`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20190724	20190110
1824948	`opt`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190724	20190110
1953268	`opt`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20190724	20190110
1956020	`opt`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20190724	20190110
1970033	`opt`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20190724	20190110
1975028	`opt`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20190724	20190110
1975230	`opt`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20190724	20190110
1977389	`opt`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20190724	20190110
1980202	`opt`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20190724	20190110
1983077	`opt`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20190724	20190110
1983298	`opt`	`gcc -m32 -O3 -fomit-frame-pointer`	20190724	20190110
1986033	`opt`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20190724	20190110
1986839	`opt`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190724	20190110
1990482	`opt`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20190724	20190110
1993782	`opt`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190724	20190110
1994011	`opt`	`gcc -m32 -O2 -fomit-frame-pointer`	20190724	20190110
1994490	`opt`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20190724	20190110
1995304	`opt`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190724	20190110
1995800	`opt`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190724	20190110
1996935	`opt`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20190724	20190110
1997607	`opt`	`gcc -m32 -Os -fomit-frame-pointer`	20190724	20190110
1998174	`opt`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190724	20190110
1998191	`opt`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190724	20190110
2000796	`opt`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190724	20190110
2000978	`opt`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20190724	20190110
2002496	`opt`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20190724	20190110
2002716	`opt`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20190724	20190110
2003254	`opt`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190724	20190110
2003331	`opt`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190724	20190110
2003897	`opt`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20190724	20190110
2005831	`opt`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190724	20190110
2007307	`opt`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20190724	20190110
2007369	`opt`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190724	20190110
2007980	`opt`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190724	20190110
2008088	`opt`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20190724	20190110
2008817	`opt`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20190724	20190110
2008844	`opt`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20190724	20190110
2008905	`opt`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20190724	20190110
2009220	`opt`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190724	20190110
2009346	`opt`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190724	20190110
2009411	`opt`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20190724	20190110
2012836	`opt`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20190724	20190110
2013186	`opt`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20190724	20190110
2013542	`opt`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20190724	20190110
2014754	`opt`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20190724	20190110
2016236	`opt`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20190724	20190110
2018105	`opt`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20190724	20190110
2024082	`opt`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20190724	20190110
2025536	`opt`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20190724	20190110
2026200	`opt`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20190724	20190110
2028528	`opt`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20190724	20190110
2029056	`opt`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190724	20190110
2029986	`opt`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190724	20190110
2030103	`opt`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20190724	20190110
2035169	`opt`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190724	20190110
2039572	`opt`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20190724	20190110
2039754	`opt`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20190724	20190110
2039780	`opt`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20190724	20190110
2040444	`opt`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20190724	20190110
2046980	`opt`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190724	20190110
2048677	`opt`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190724	20190110
2053049	`opt`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20190724	20190110
2053683	`opt`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20190724	20190110
2057802	`opt`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20190724	20190110
2059470	`opt`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20190724	20190110
2061931	`opt`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190724	20190110
2063355	`opt`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20190724	20190110
2063814	`opt`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20190724	20190110
2064528	`opt`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20190724	20190110
2065652	`opt`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20190724	20190110
2068448	`opt`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20190724	20190110
2069516	`opt`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20190724	20190110
2070811	`opt`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20190724	20190110
2072486	`opt`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20190724	20190110
2072531	`opt`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20190724	20190110
2072921	`opt`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20190724	20190110
2073524	`opt`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20190724	20190110
2073718	`opt`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20190724	20190110
2073968	`opt`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20190724	20190110
2074577	`opt`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20190724	20190110
2074694	`opt`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20190724	20190110
2075488	`opt`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20190724	20190110
2077937	`opt`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20190724	20190110
2079748	`opt`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20190724	20190110
2084786	`opt`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20190724	20190110
2085583	`opt`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20190724	20190110
2086105	`opt`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190724	20190110
2086116	`opt`	`gcc -m32 -O -fomit-frame-pointer`	20190724	20190110
2089044	`opt`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190724	20190110
2091539	`opt`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20190724	20190110
2096000	`opt`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20190724	20190110
2098139	`opt`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190724	20190110
2105209	`opt`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20190724	20190110
2105677	`opt`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20190724	20190110
2118066	`opt`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20190724	20190110
2121161	`opt`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190724	20190110
2121647	`opt`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20190724	20190110
2129042	`opt`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20190724	20190110
2133246	`opt`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20190724	20190110
2187413	`opt`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190724	20190110
2193302	`opt`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190724	20190110
2194401	`opt`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190724	20190110
2195056	`opt`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190724	20190110
2208903	`opt`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190724	20190110
2215780	`opt`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20190724	20190110
2217415	`opt`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190724	20190110
2220801	`opt`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190724	20190110
2222866	`opt`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190724	20190110
2225147	`opt`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190724	20190110
2228024	`opt`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20190724	20190110
2239260	`opt`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190724	20190110
2243733	`opt`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190724	20190110
2256387	`opt`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190724	20190110
2259445	`opt`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20190724	20190110
2260068	`opt`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190724	20190110
2261021	`opt`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190724	20190110
2268643	`opt`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190724	20190110
2272167	`opt`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20190724	20190110
2274583	`opt`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190724	20190110
2277305	`opt`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190724	20190110
2286421	`opt`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190724	20190110
2287696	`opt`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20190724	20190110
2458613	`opt`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190724	20190110
2533647	`opt`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190724	20190110
2964049	`opt`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20190724	20190110
2984117	`opt`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20190724	20190110
3039891	`opt`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20190724	20190110
3048423	`opt`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20190724	20190110

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'; did you mean '_mm_cvtsi128_si32'? [-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/7/include/xmmintrin.h:1252:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/7/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/7/include/emmintrin.h:1291:1: 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: note: called from here
bitslice_bma_128.c: return _mm_xor_si128(b,
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~
bitslice_bma_128.c: _mm_and_si128(_mm_set1_epi64x(-ctl),
bitslice_bma_128.c: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: _mm_xor_si128(a, b)));
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'; did you mean '_mm_cvtsi128_si32'? [-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/7/include/xmmintrin.h:1252:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/7/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/7/include/emmintrin.h:1291:1: 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: note: called from here
bitslice_bma_128.c: return _mm_xor_si128(b,
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~
bitslice_bma_128.c: _mm_and_si128(_mm_set1_epi64x(-ctl),
bitslice_bma_128.c: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
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: 35, 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=pentium-m -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m32 -march=pentium-m -O3 -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=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 -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 -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=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 -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=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=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=pentium-m -O -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=prescott -O2 -fomit-frame-pointer	avx2
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	avx2
gcc -m32 -march=prescott -O -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: 41, 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=pentium-m -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-m -O3 -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-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=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 -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 -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=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 -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=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=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=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=pentium-m -O -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=prescott -O2 -fomit-frame-pointer	sse2
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	sse2
gcc -m32 -march=prescott -O -fomit-frame-pointer	sse2

Compiler output

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

Number of similar (compiler,implementation) pairs: 14, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O -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=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=pentium-m -O -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=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

Compiler output

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

Number of similar (compiler,implementation) pairs: 14, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O -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=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=pentium-m -O -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=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

Compiler output

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

Number of similar (compiler,implementation) pairs: 19, namely:

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

Number of similar (compiler,implementation) pairs: 21, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	sse2
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=k8 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=native -mtune=native -Os -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 -Os -fomit-frame-pointer	sse2
gcc -m32 -march=pentium4 -Os -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'; did you mean '_mm_cvtsi128_si32'? [-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/7/include/xmmintrin.h:1252:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/7/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/7/include/emmintrin.h:1291:1: 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: note: called from here
bitslice_bma_128.c: return _mm_xor_si128(b,
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~
bitslice_bma_128.c: _mm_and_si128(_mm_set1_epi64x(-ctl),
bitslice_bma_128.c: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: _mm_xor_si128(a, b)));
bitslice_bma_128.c: ~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/xmmintrin.h:1252:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:29,
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'; did you mean '_mm_cvtsi128_si32'? [-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/7/include/xmmintrin.h:1252:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/7/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/7/include/emmintrin.h:1291:1: 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: note: called from here
bitslice_bma_128.c: return _mm_xor_si128(b,
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~
bitslice_bma_128.c: _mm_and_si128(_mm_set1_epi64x(-ctl),
bitslice_bma_128.c: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: _mm_xor_si128(a, b)));
bitslice_bma_128.c: ~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/xmmintrin.h:1252:0,
bitslice_bma_128.c: from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:29,
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'; did you mean '_mm_cvtsi128_si32'? [-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: In function 'bitslice_bma':
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
bitslice_bma_128.c: }
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
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'; did you mean '_mm_cvtsi128_si32'? [-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: In function 'bitslice_bma':
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
bitslice_bma_128.c: }
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
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: 3, 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 -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'; did you mean '_mm_cvtsi128_si32'? [-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 'bitslice_bma':
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
bitslice_bma_128.c: }
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
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'; did you mean '_mm_cvtsi128_si32'? [-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 'bitslice_bma':
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
bitslice_bma_128.c: }
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
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: 3, 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 -Os -fomit-frame-pointer	sse2

Compiler output

Implementation: crypto_kem/ntskem1264/avx2
Compiler: gcc -m32 -march=barcelona -O -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'; did you mean '_mm_cvtsi128_si32'? [-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: In function 'bitslice_bma':
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
bitslice_bma_128.c: }
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
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'; did you mean '_mm_cvtsi128_si32'? [-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: In function 'bitslice_bma':
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
bitslice_bma_128.c: }
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
bitslice_bma_128.c: bitslice_bma_128.c:180:1: warning: unsupported size for integer register
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: 1, namely:

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

Compiler output

Implementation: crypto_kem/ntskem1264/sse2
Compiler: gcc -m32 -march=barcelona -O -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'; did you mean '_mm_cvtsi128_si32'? [-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 'bitslice_bma':
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
bitslice_bma_128.c: }
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
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'; did you mean '_mm_cvtsi128_si32'? [-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 'bitslice_bma':
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
bitslice_bma_128.c: }
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
bitslice_bma_128.c: bitslice_bma_128.c:181:1: warning: unsupported size for integer register
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: 1, namely:

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

Compiler output

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

Number of similar (compiler,implementation) pairs: 6, 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=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

Compiler output

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

Number of similar (compiler,implementation) pairs: 2, namely:

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