Implementation notes: x86, hydra1, crypto_aead/iscream12v1

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: iscream12v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
637506	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20161016	20161009
644157	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20161016	20161009
658149	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161016	20161009
659934	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161016	20161009
660669	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161016	20161009
664803	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20161016	20161009
665339	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161016	20161009
666150	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161016	20161009
670789	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161016	20161009
672101	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161016	20161009
675494	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161016	20161009
686672	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20161016	20161009
716312	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
716698	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
722320	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
722477	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
722546	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
722877	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20161016	20161009
723408	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161016	20161009
729475	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20161016	20161009
729477	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
767621	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20161016	20161009
767864	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161016	20161009
769959	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161016	20161009
771671	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161016	20161009
771677	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161016	20161009
773450	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20161016	20161009
786780	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20161016	20161009
787112	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161016	20161009
798776	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161016	20161009
809909	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20161016	20161009
811893	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20161016	20161009
813045	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161016	20161009
814573	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161016	20161009
818654	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20161016	20161009
886128	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20161016	20161009
888464	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20161016	20161009
1092066	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161016	20161009
1092786	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20161016	20161009
1094000	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161016	20161009
1118688	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20161016	20161009
1120197	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
1130911	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20161016	20161009
1138435	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161016	20161009
1138509	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20161016	20161009
1146283	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
1230520	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
1230540	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20161016	20161009
1246459	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161016	20161009
1293017	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161016	20161009
1293043	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161016	20161009
1293177	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161016	20161009
1293445	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161016	20161009
1297168	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20161016	20161009
1313995	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20161016	20161009
1356766	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
1359272	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20161016	20161009
1375661	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20161016	20161009
1390213	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20161016	20161009
1390269	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
1397704	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20161016	20161009
1399398	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20161016	20161009
1399944	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
1399965	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20161016	20161009
1400349	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20161016	20161009
1419885	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20161016	20161009
1444653	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20161016	20161009
1445806	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161016	20161009
1447584	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20161016	20161009
1449391	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20161016	20161009
1449448	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161016	20161009
1466528	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20161016	20161009
1476347	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
1481251	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
1491680	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20161016	20161009
1495720	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20161016	20161009
1499192	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20161016	20161009
1505557	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20161016	20161009
1507206	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20161016	20161009
1516823	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
1517509	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161016	20161009
1517510	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
1517699	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161016	20161009
1519607	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20161016	20161009
1519939	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20161016	20161009
1520600	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20161016	20161009
1523307	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161016	20161009
1526056	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20161016	20161009
1526968	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161016	20161009
1527066	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
1528224	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
1528797	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20161016	20161009
1528848	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20161016	20161009
1528888	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20161016	20161009
1529744	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
1530402	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20161016	20161009
1531243	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161016	20161009
1532312	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161016	20161009
1532406	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20161016	20161009
1536158	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
1536701	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20161016	20161009
1542144	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20161016	20161009
1542381	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20161016	20161009
1548365	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20161016	20161009
1553949	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161016	20161009
1555488	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
1557610	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20161016	20161009
1557760	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20161016	20161009
1558822	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20161016	20161009
1560034	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161016	20161009
1560584	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161016	20161009
1560639	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161016	20161009
1561043	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20161016	20161009
1561640	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20161016	20161009
1562520	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161016	20161009
1562534	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161016	20161009
1562587	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161016	20161009
1562780	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20161016	20161009
1562826	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
1562885	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
1562976	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161016	20161009
1564109	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161016	20161009
1565291	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161016	20161009
1565692	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20161016	20161009
1566295	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161016	20161009
1566576	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
1569213	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161016	20161009
1569302	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161016	20161009
1572701	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161016	20161009
1572787	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161016	20161009
1575920	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20161016	20161009
1577163	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161016	20161009
1578706	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161016	20161009
1578712	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20161016	20161009
1584283	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20161016	20161009
1587054	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20161016	20161009
1588160	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20161016	20161009
1589480	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20161016	20161009
1591017	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20161016	20161009
1595366	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161016	20161009
1596157	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20161016	20161009
1604243	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161016	20161009
1604347	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161016	20161009
1604490	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161016	20161009
1607819	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20161016	20161009
1611118	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20161016	20161009
1619823	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20161016	20161009
1620338	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161016	20161009
1644067	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161016	20161009
1644237	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161016	20161009
1647570	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161016	20161009
1647709	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161016	20161009
1648840	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161016	20161009
1649669	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161016	20161009
1661084	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161016	20161009
1662099	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20161016	20161009
1677555	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161016	20161009
1722099	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161016	20161009
1741093	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20161016	20161009
1763139	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20161016	20161009

Test failure

Implementation: crypto_aead/iscream12v1/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/iscream12v1/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/iscream12v1/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/iscream12v1/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