Implementation notes: x86, hydra1, crypto_aead/iscream14v1

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: iscream14v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
729181	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20161016	20161009
737170	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20161016	20161009
754557	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161016	20161009
756285	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161016	20161009
756493	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161016	20161009
757723	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161016	20161009
759251	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20161016	20161009
759787	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161016	20161009
762783	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20161016	20161009
762790	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161016	20161009
763080	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161016	20161009
772642	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161016	20161009
823740	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
825768	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
828182	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
828182	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20161016	20161009
835757	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20161016	20161009
835919	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
836712	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
837355	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
837654	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161016	20161009
861142	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20161016	20161009
861256	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161016	20161009
862755	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161016	20161009
891504	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20161016	20161009
891620	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161016	20161009
891908	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161016	20161009
911355	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20161016	20161009
913435	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20161016	20161009
918213	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161016	20161009
929901	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20161016	20161009
935595	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161016	20161009
936328	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161016	20161009
937155	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20161016	20161009
946154	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20161016	20161009
958364	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161016	20161009
958724	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20161016	20161009
1261102	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161016	20161009
1261142	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20161016	20161009
1261163	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161016	20161009
1295456	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20161016	20161009
1296472	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
1311701	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20161016	20161009
1315670	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20161016	20161009
1317796	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161016	20161009
1327844	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
1423256	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
1423320	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20161016	20161009
1462733	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161016	20161009
1496727	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161016	20161009
1497085	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161016	20161009
1497248	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161016	20161009
1497294	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161016	20161009
1501730	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20161016	20161009
1521725	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20161016	20161009
1572621	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
1574301	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20161016	20161009
1594658	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20161016	20161009
1608915	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20161016	20161009
1609720	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
1615951	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20161016	20161009
1623208	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
1637726	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20161016	20161009
1671475	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161016	20161009
1677231	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20161016	20161009
1678856	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20161016	20161009
1679088	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161016	20161009
1695214	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
1695326	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20161016	20161009
1696650	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20161016	20161009
1696674	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20161016	20161009
1697811	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20161016	20161009
1704003	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20161016	20161009
1712772	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
1715582	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20161016	20161009
1723638	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20161016	20161009
1734804	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
1742014	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20161016	20161009
1742194	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161016	20161009
1742899	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20161016	20161009
1748036	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161016	20161009
1756230	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
1756415	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161016	20161009
1756528	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161016	20161009
1758235	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20161016	20161009
1758867	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161016	20161009
1759200	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20161016	20161009
1759373	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20161016	20161009
1759386	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20161016	20161009
1760989	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20161016	20161009
1765774	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161016	20161009
1767590	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20161016	20161009
1767606	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
1767728	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20161016	20161009
1768170	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
1768485	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
1769555	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20161016	20161009
1770199	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
1771365	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20161016	20161009
1771757	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161016	20161009
1772360	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20161016	20161009
1775174	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
1777712	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20161016	20161009
1783275	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20161016	20161009
1785990	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20161016	20161009
1787191	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20161016	20161009
1787194	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20161016	20161009
1793781	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20161016	20161009
1799372	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20161016	20161009
1802008	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161016	20161009
1803213	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20161016	20161009
1805007	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161016	20161009
1805067	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20161016	20161009
1806033	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20161016	20161009
1807877	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161016	20161009
1807979	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161016	20161009
1808037	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161016	20161009
1808141	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20161016	20161009
1808159	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20161016	20161009
1808166	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161016	20161009
1808277	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
1808384	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
1812615	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161016	20161009
1812997	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
1813051	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161016	20161009
1814605	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20161016	20161009
1816485	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161016	20161009
1818952	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161016	20161009
1819312	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20161016	20161009
1827819	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161016	20161009
1830567	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161016	20161009
1830667	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20161016	20161009
1836616	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20161016	20161009
1841538	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20161016	20161009
1842293	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161016	20161009
1848643	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20161016	20161009
1848768	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20161016	20161009
1848978	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161016	20161009
1851754	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161016	20161009
1855200	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161016	20161009
1857142	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161016	20161009
1857166	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161016	20161009
1857522	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161016	20161009
1866220	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20161016	20161009
1872619	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161016	20161009
1880301	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20161016	20161009
1901877	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161016	20161009
1902253	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161016	20161009
1902336	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20161016	20161009
1906490	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161016	20161009
1906928	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161016	20161009
1908034	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161016	20161009
1908101	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161016	20161009
1909019	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161016	20161009
1920144	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161016	20161009
1921460	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161016	20161009
1922645	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20161016	20161009
1992304	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161016	20161009
2013888	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20161016	20161009
2041621	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20161016	20161009

Test failure

Implementation: crypto_aead/iscream14v1/ref
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 32, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	ref sse
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	ref sse
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	ref sse
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	ref sse
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	ref sse
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	ref sse
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	ref sse
gcc -m32 -march=core2 -O -fomit-frame-pointer	sse
gcc -m32 -march=core2 -Os -fomit-frame-pointer	sse
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	sse
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	sse
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	sse
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	sse
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	ref sse
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	ref sse
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	ref sse
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=corei7 -O -fomit-frame-pointer	sse
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	sse

Compiler output

Implementation: crypto_aead/iscream14v1/sse
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

iscream.c: iscream.c: In function 'LBox16P':
iscream.c: iscream.c:17:32: warning: implicit declaration of function '__builtin_ia32_psrldi128' [-Wimplicit-function-declaration]
iscream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
iscream.c: ^
iscream.c: iscream.c:200:10: note: in expansion of macro 'shift_right'
iscream.c: t0 = shift_right(in[0]) & V(0xf);
iscream.c: ^
iscream.c: iscream.c:200:5: error: can't convert between vector values of different size
iscream.c: t0 = shift_right(in[0]) & V(0xf);
iscream.c: ^
iscream.c: iscream.c:201:5: error: can't convert between vector values of different size
iscream.c: t1 = shift_right(in[2]) & V(0xf);
iscream.c: ^
iscream.c: iscream.c:203:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
iscream.c: A = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: iscream.c:203:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: A = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: iscream.c:204:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: C = __builtin_ia32_pshufb128(table, t1);
iscream.c: ^
iscream.c: iscream.c:208:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: B = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: ...

Number of similar (compiler,implementation) pairs: 96, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	sse
gcc -m32 -O2 -fomit-frame-pointer	sse
gcc -m32 -O3 -fomit-frame-pointer	sse
gcc -m32 -O -fomit-frame-pointer	sse
gcc -m32 -Os -fomit-frame-pointer	sse
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	sse
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	sse
gcc -m32 -march=athlon -O -fomit-frame-pointer	sse
gcc -m32 -march=athlon -Os -fomit-frame-pointer	sse
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	sse
gcc -m32 -march=i386 -O -fomit-frame-pointer	sse
gcc -m32 -march=i386 -Os -fomit-frame-pointer	sse
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	sse
gcc -m32 -march=i486 -O -fomit-frame-pointer	sse
gcc -m32 -march=i486 -Os -fomit-frame-pointer	sse
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	sse
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	sse
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	sse
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	sse
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	sse
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	sse
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	sse
gcc -m32 -march=k6 -O -fomit-frame-pointer	sse
gcc -m32 -march=k6 -Os -fomit-frame-pointer	sse
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	sse
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	sse
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	sse
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	sse
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	sse
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	sse
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	sse
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	sse
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	sse
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	sse
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	sse
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	sse
gcc -m32 -march=pentium -O -fomit-frame-pointer	sse
gcc -m32 -march=pentium -Os -fomit-frame-pointer	sse
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	sse
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	sse
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	sse
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	sse

Compiler output

Implementation: crypto_aead/iscream14v1/sse
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 48, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	sse
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	sse
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	sse
gcc -m32 -march=k8 -O -fomit-frame-pointer	sse
gcc -m32 -march=k8 -Os -fomit-frame-pointer	sse
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	sse
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	sse
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	sse
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	sse
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	sse
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	sse
gcc -m32 -march=nocona -O -fomit-frame-pointer	sse
gcc -m32 -march=nocona -Os -fomit-frame-pointer	sse
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	sse
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	sse
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	sse
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	sse
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	sse
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	sse
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	sse
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	sse
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	sse
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	sse
gcc -m32 -march=prescott -O -fomit-frame-pointer	sse
gcc -m32 -march=prescott -Os -fomit-frame-pointer	sse

Compiler output

Implementation: crypto_aead/iscream14v1/sse
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

iscream.c: iscream.c: In function 'LBox16P':
iscream.c: iscream.c:203:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
iscream.c: A = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: iscream.c:203:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: A = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: iscream.c:204:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: C = __builtin_ia32_pshufb128(table, t1);
iscream.c: ^
iscream.c: iscream.c:208:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: B = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: iscream.c:209:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: D = __builtin_ia32_pshufb128(table, t1);
iscream.c: ^
iscream.c: iscream.c:216:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
iscream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
iscream.c: ^
iscream.c: iscream.c:217:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
iscream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
iscream.c: ^
iscream.c: iscream.c:221:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
iscream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
iscream.c: ^
iscream.c: ...
iscream.c: iscream.c: In function 'LBox16P':
iscream.c: iscream.c:203:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
iscream.c: A = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: iscream.c:203:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: A = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: iscream.c:204:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: C = __builtin_ia32_pshufb128(table, t1);
iscream.c: ^
iscream.c: iscream.c:208:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: B = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: iscream.c:209:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
iscream.c: D = __builtin_ia32_pshufb128(table, t1);
iscream.c: ^
iscream.c: iscream.c:216:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
iscream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
iscream.c: ^
iscream.c: iscream.c:217:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
iscream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
iscream.c: ^
iscream.c: iscream.c:221:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
iscream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
iscream.c: ^
iscream.c: ...

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

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