Implementation notes: x86, hydra1, crypto_aead/iscream14v2

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: iscream14v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
730821	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20161016	20161009
738112	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20161016	20161009
755025	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161016	20161009
757347	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161016	20161009
757584	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161016	20161009
758346	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161016	20161009
758691	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20161016	20161009
761010	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161016	20161009
764573	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161016	20161009
764597	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161016	20161009
764848	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20161016	20161009
772989	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161016	20161009
823629	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
825650	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
829309	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
829325	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20161016	20161009
837595	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
838671	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
838915	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161016	20161009
851360	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20161016	20161009
851446	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
860253	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20161016	20161009
860445	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161016	20161009
862426	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161016	20161009
891379	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161016	20161009
891829	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161016	20161009
892151	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20161016	20161009
903735	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161016	20161009
905392	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161016	20161009
910694	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20161016	20161009
913571	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20161016	20161009
932008	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20161016	20161009
939578	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161016	20161009
939651	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20161016	20161009
945960	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20161016	20161009
958990	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20161016	20161009
961678	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161016	20161009
1261341	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161016	20161009
1261570	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20161016	20161009
1269760	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161016	20161009
1295846	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20161016	20161009
1296277	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
1311176	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20161016	20161009
1315944	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20161016	20161009
1316102	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161016	20161009
1325390	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
1426100	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161016	20161009
1457384	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
1457429	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20161016	20161009
1498554	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161016	20161009
1498997	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161016	20161009
1499366	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161016	20161009
1499414	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161016	20161009
1501218	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20161016	20161009
1503296	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20161016	20161009
1569727	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20161016	20161009
1575659	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
1590757	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20161016	20161009
1598496	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20161016	20161009
1599176	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
1632824	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
1645109	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20161016	20161009
1671822	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20161016	20161009
1687632	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20161016	20161009
1695649	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161016	20161009
1698963	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
1703093	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20161016	20161009
1703099	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20161016	20161009
1703232	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20161016	20161009
1703336	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20161016	20161009
1707726	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
1713011	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161016	20161009
1713539	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20161016	20161009
1717434	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20161016	20161009
1717989	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161016	20161009
1723354	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
1726688	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161016	20161009
1726760	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20161016	20161009
1726771	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161016	20161009
1731615	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20161016	20161009
1735612	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
1736189	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
1740685	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20161016	20161009
1743877	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161016	20161009
1750317	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20161016	20161009
1755454	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20161016	20161009
1756206	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161016	20161009
1759648	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20161016	20161009
1761203	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161016	20161009
1762146	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
1762211	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20161016	20161009
1765893	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20161016	20161009
1766509	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20161016	20161009
1767252	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20161016	20161009
1768968	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
1769062	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161016	20161009
1769247	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20161016	20161009
1769247	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20161016	20161009
1769664	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
1770286	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20161016	20161009
1771445	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20161016	20161009
1772441	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20161016	20161009
1773393	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20161016	20161009
1774645	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20161016	20161009
1790744	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20161016	20161009
1794168	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161016	20161009
1800933	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
1801326	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161016	20161009
1801634	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20161016	20161009
1802208	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161016	20161009
1802223	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20161016	20161009
1803471	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161016	20161009
1803490	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161016	20161009
1803728	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161016	20161009
1803904	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161016	20161009
1804135	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20161016	20161009
1806258	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
1807678	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161016	20161009
1808190	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20161016	20161009
1808437	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20161016	20161009
1811102	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20161016	20161009
1811840	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20161016	20161009
1813575	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20161016	20161009
1813789	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161016	20161009
1813837	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
1815779	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20161016	20161009
1816296	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20161016	20161009
1816717	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20161016	20161009
1818173	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161016	20161009
1818402	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161016	20161009
1818477	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20161016	20161009
1820349	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20161016	20161009
1820877	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161016	20161009
1825672	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161016	20161009
1825680	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161016	20161009
1827158	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161016	20161009
1828144	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
1829151	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20161016	20161009
1835941	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20161016	20161009
1848381	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161016	20161009
1850627	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20161016	20161009
1853224	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20161016	20161009
1855736	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161016	20161009
1858923	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161016	20161009
1877167	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161016	20161009
1878965	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20161016	20161009
1883867	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161016	20161009
1884425	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161016	20161009
1900208	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20161016	20161009
1918933	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161016	20161009
1923456	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161016	20161009
1928283	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161016	20161009
1928565	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161016	20161009
1929682	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161016	20161009
1929688	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161016	20161009
1940920	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161016	20161009
1946445	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161016	20161009
1997994	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20161016	20161009
2000555	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161016	20161009
2021626	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20161016	20161009

Test failure

Implementation: crypto_aead/iscream14v2/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/iscream14v2/sse
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

iscream.c: iscream.c: In function 'LBox16P':
iscream.c: iscream.c:16:32: 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:181:10: note: in expansion of macro 'shift_right'
iscream.c: t0 = shift_right(in[0]) & V(0xf);
iscream.c: ^
iscream.c: iscream.c:181:5: 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:182:5: 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:184:10: 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:184:8: 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:185:8: 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:189:8: 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/iscream14v2/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/iscream14v2/sse
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

iscream.c: iscream.c: In function 'LBox16P':
iscream.c: iscream.c:184:10: 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:184:8: 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:185:8: 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:189:8: 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:190:8: 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:197:7: 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:198:7: 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:202:7: 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:184:10: 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:184:8: 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:185:8: 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:189:8: 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:190:8: 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:197:7: 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:198:7: 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:202:7: 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