Implementation notes: x86, h9trinity, crypto_aead/scream12v2

Computer: h9trinity
Architecture: x86
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream12v2
TimeImplementationCompilerBenchmark dateSUPERCOP version
673452refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121320171020
685379refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017121320171020
691698refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017121320171020
694278refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017121320171020
699887refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017121320171020
701941refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017121320171020
702485refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017121320171020
702619refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017121320171020
702668refgcc -m32 -O3 -fomit-frame-pointer2017121320171020
710002refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017121320171020
711656refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121320171020
712904refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017121320171020
713135refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017121320171020
715456refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017121320171020
715602refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017121320171020
715736refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017121320171020
718007refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121320171020
719180refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2017121320171020
719655refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017121320171020
719812refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2017121320171020
722401refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017121320171020
723002refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2017121320171020
723433refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017121320171020
724932refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017121320171020
725267refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017121320171020
725328refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017121320171020
727535refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017121320171020
728251refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017121320171020
728356refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017121320171020
729302refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2017121320171020
744946refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017121320171020
744953refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017121320171020
746601refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017121320171020
752384refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121320171020
756748refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121320171020
757527refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121320171020
757666refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121320171020
758229refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121320171020
765944refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121320171020
769792refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121320171020
770579refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121320171020
774931refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121320171020
781069refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017121320171020
782583refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121320171020
782631refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121320171020
797862refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121320171020
804506refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017121320171020
824414refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017121320171020
824569refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017121320171020
825180refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017121320171020
826218refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017121320171020
965856refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121320171020
972691refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017121320171020
972761refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017121320171020
973553refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017121320171020
973925refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017121320171020
982084refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017121320171020
984911refgcc -m32 -march=prescott -O -fomit-frame-pointer2017121320171020
987845refgcc -m32 -O2 -fomit-frame-pointer2017121320171020
987875refgcc -m32 -march=nocona -O -fomit-frame-pointer2017121320171020
991246refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017121320171020
993699refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2017121320171020
993926refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017121320171020
994702refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017121320171020
995631refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017121320171020
995702refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017121320171020
997625refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2017121320171020
1009885refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2017121320171020
1012143refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2017121320171020
1012971refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017121320171020
1018220refgcc -m32 -march=athlon -O -fomit-frame-pointer2017121320171020
1024889refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017121320171020
1026164refgcc -m32 -O -fomit-frame-pointer2017121320171020
1027925refgcc -m32 -march=core2 -O -fomit-frame-pointer2017121320171020
1028080refgcc -m32 -march=k8 -O -fomit-frame-pointer2017121320171020
1031526refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017121320171020
1033900refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017121320171020
1039390refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017121320171020
1039661refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017121320171020
1056663refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121320171020
1073412refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121320171020
1075013refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121320171020
1075851refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017121320171020
1076196refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121320171020
1079861refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017121320171020
1081777refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017121320171020
1081808refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017121320171020
1102914refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017121320171020
1105492refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017121320171020
1107232refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017121320171020
1108192refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017121320171020
1109483refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017121320171020
1120212refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017121320171020
1128187refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017121320171020
1133758refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121320171020
1136950refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017121320171020
1139504refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017121320171020
1140077refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017121320171020
1141611refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121320171020
1147250refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121320171020
1147694refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017121320171020
1147897refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121320171020
1157723refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017121320171020
1170111refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121320171020
1170594refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017121320171020
1172181refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121320171020
1172954refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121320171020
1173718refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121320171020
1181224refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017121320171020
1182269refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017121320171020
1185227refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121320171020
1199268refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017121320171020
1199471refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121320171020
1204858refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017121320171020
1228607refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017121320171020
1245012refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017121320171020
1247484refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017121320171020
1247636refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121320171020
1249150refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017121320171020
1257704refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121320171020
1260762refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017121320171020
1267124refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017121320171020
1274963refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017121320171020
1399712refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017121320171020
1402213refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017121320171020
1413194refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017121320171020
1414043refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121320171020
1427399refgcc -m32 -march=i386 -O -fomit-frame-pointer2017121320171020
1439719refgcc -m32 -march=i486 -O -fomit-frame-pointer2017121320171020
1462331refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121320171020
1468304refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121320171020
1470986refgcc -m32 -march=pentium -O -fomit-frame-pointer2017121320171020
1471023refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121320171020
1471311refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017121320171020
1471797refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017121320171020
1474557refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017121320171020
1474613refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017121320171020
1475464refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017121320171020
1477151refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017121320171020
1479590refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017121320171020
1482871refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017121320171020
1484910refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017121320171020
1489812refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017121320171020
1490114refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017121320171020
1491084refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017121320171020
1492144refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017121320171020
1493141refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017121320171020
1494713refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017121320171020
1497415refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017121320171020
1497623refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017121320171020
1498489refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017121320171020
1498885refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017121320171020
1499472refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017121320171020
1500931refgcc -m32 -Os -fomit-frame-pointer2017121320171020
1502309refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121320171020
1502450refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017121320171020
1503440refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017121320171020
1503479refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017121320171020
1504113refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017121320171020
1507110refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017121320171020
1511680refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2017121320171020
1512673refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2017121320171020
1512735refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017121320171020
1514666refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017121320171020
1521395refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017121320171020
1521469refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017121320171020
1521884refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017121320171020
1521940refgcc -m32 -march=k6 -O -fomit-frame-pointer2017121320171020
1523807refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121320171020
1536674refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017121320171020
1537303refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017121320171020
1540272refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017121320171020

Test failure

Implementation: crypto_aead/scream12v2/sse
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 34, namely:
CompilerImplementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer sse
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer sse
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer sse
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer 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 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 -O3 -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 -O3 -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 sse
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer sse
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer sse
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer sse
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer sse
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer sse
gcc -m32 -march=corei7 -O -fomit-frame-pointer sse
gcc -m32 -march=corei7 -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

Compiler output

Implementation: crypto_aead/scream12v2/sse
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:16:32: warning: implicit declaration of function '__builtin_ia32_psrldi128' [-Wimplicit-function-declaration]
scream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
scream.c: ^
scream.c: scream.c:182:10: note: in expansion of macro 'shift_right'
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:182:5: error: can't convert between vector values of different size
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:183:5: error: can't convert between vector values of different size
scream.c: t1 = shift_right(in[2]) & V(0xf);
scream.c: ^
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 96, namely:
CompilerImplementations
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/scream12v2/sse
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 44, namely:
CompilerImplementations
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=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/scream12v2/sse
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...

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