Implementation notes: x86, hydra1, crypto_aead/scream12v3

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: scream12v3
TimeImplementationCompilerBenchmark dateSUPERCOP version
701779refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
708440refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016102320161009
709000refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2016102320161009
712896refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2016102320161009
720372refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2016102320161009
735358refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2016102320161009
736941refgcc -m32 -O3 -fomit-frame-pointer2016102320161009
737176refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016102320161009
737920refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2016102320161009
742939refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016102320161009
742943refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016102320161009
743289refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016102320161009
743382refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
747981refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2016102320161009
748661refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016102320161009
749126refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2016102320161009
749715refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016102320161009
754989refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2016102320161009
755381refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016102320161009
756223refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016102320161009
757587refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2016102320161009
758390refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
758440refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016102320161009
760551refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2016102320161009
763594refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016102320161009
770923refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2016102320161009
776274refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016102320161009
783501refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2016102320161009
785530refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016102320161009
785947refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016102320161009
796770refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016102320161009
800456refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2016102320161009
801240refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2016102320161009
811702refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016102320161009
813626refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016102320161009
814037refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016102320161009
821781refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2016102320161009
822716refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016102320161009
823442refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2016102320161009
823525refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016102320161009
823784refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016102320161009
824736refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2016102320161009
825203refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2016102320161009
830869refgcc -funroll-loops -m32 -O -fomit-frame-pointer2016102320161009
848968refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016102320161009
913704refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2016102320161009
932030refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2016102320161009
932362refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016102320161009
936984refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2016102320161009
938357refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2016102320161009
938472refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2016102320161009
946569refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2016102320161009
946837refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2016102320161009
947318refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2016102320161009
951338refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2016102320161009
952137refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2016102320161009
952300refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2016102320161009
959135refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2016102320161009
959463refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016102320161009
965129refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016102320161009
965864refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2016102320161009
978184refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2016102320161009
987923refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2016102320161009
1005932refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2016102320161009
1006773refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2016102320161009
1007916refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2016102320161009
1017910refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2016102320161009
1018982refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2016102320161009
1019456refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2016102320161009
1034152refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2016102320161009
1035165refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2016102320161009
1047640refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2016102320161009
1058779refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2016102320161009
1141027refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2016102320161009
1144467refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2016102320161009
1149974refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
1150173refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016102320161009
1164230refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2016102320161009
1168642refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2016102320161009
1177662refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016102320161009
1184552refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016102320161009
1187982refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016102320161009
1193853refgcc -m32 -O2 -fomit-frame-pointer2016102320161009
1194699refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016102320161009
1196445refgcc -m32 -O -fomit-frame-pointer2016102320161009
1198290refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016102320161009
1198556refgcc -m32 -march=barcelona -O -fomit-frame-pointer2016102320161009
1203274refgcc -m32 -march=core2 -O -fomit-frame-pointer2016102320161009
1203485refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016102320161009
1203651refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016102320161009
1206155refgcc -m32 -march=k8 -O -fomit-frame-pointer2016102320161009
1206354refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2016102320161009
1214400refgcc -m32 -march=athlon -O -fomit-frame-pointer2016102320161009
1235026refgcc -m32 -march=corei7 -O -fomit-frame-pointer2016102320161009
1237219refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2016102320161009
1237872refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016102320161009
1241008refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2016102320161009
1242594refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2016102320161009
1242696refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2016102320161009
1243096refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016102320161009
1245261refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2016102320161009
1249074refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2016102320161009
1268445refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2016102320161009
1269640refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2016102320161009
1270649refgcc -m32 -march=prescott -O -fomit-frame-pointer2016102320161009
1270925refgcc -m32 -march=nocona -O -fomit-frame-pointer2016102320161009
1282445refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2016102320161009
1286782refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2016102320161009
1287149refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2016102320161009
1287467refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2016102320161009
1289877refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2016102320161009
1294622refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2016102320161009
1302307refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2016102320161009
1303016refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2016102320161009
1303118refgcc -m32 -march=i486 -O -fomit-frame-pointer2016102320161009
1304744refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2016102320161009
1306778refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2016102320161009
1313893refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2016102320161009
1316397refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2016102320161009
1318754refgcc -m32 -march=i386 -O -fomit-frame-pointer2016102320161009
1319827refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2016102320161009
1320386refgcc -m32 -march=prescott -Os -fomit-frame-pointer2016102320161009
1320605refgcc -m32 -march=nocona -Os -fomit-frame-pointer2016102320161009
1322022refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2016102320161009
1325448refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2016102320161009
1325968refgcc -m32 -march=pentium -O -fomit-frame-pointer2016102320161009
1326376refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2016102320161009
1335778refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016102320161009
1336007refgcc -m32 -march=i486 -Os -fomit-frame-pointer2016102320161009
1338301refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2016102320161009
1346599refgcc -m32 -march=i386 -Os -fomit-frame-pointer2016102320161009
1348018refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016102320161009
1348365refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2016102320161009
1350981refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016102320161009
1354269refgcc -m32 -march=pentium -Os -fomit-frame-pointer2016102320161009
1355471refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2016102320161009
1355512refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2016102320161009
1356576refgcc -m32 -march=k6 -O -fomit-frame-pointer2016102320161009
1366357refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1366440refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2016102320161009
1369120refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2016102320161009
1369170refgcc -m32 -march=core2 -Os -fomit-frame-pointer2016102320161009
1369352refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2016102320161009
1373596refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016102320161009
1376134refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1376862refgcc -m32 -march=athlon -Os -fomit-frame-pointer2016102320161009
1378374refgcc -m32 -Os -fomit-frame-pointer2016102320161009
1380066refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2016102320161009
1381378refgcc -m32 -march=k8 -Os -fomit-frame-pointer2016102320161009
1384750refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2016102320161009
1384936refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2016102320161009
1385373refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2016102320161009
1400391refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2016102320161009
1424530refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2016102320161009
1428376refgcc -m32 -march=k6 -Os -fomit-frame-pointer2016102320161009
1429256refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2016102320161009
1433839refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2016102320161009
1433957refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2016102320161009
1434395refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2016102320161009
1435344refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2016102320161009

Test failure

Implementation: crypto_aead/scream12v3/ref
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 32, namely:
CompilerImplementations
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/scream12v3/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:199:10: note: in expansion of macro 'shift_right'
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:199:5: 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:200:5: 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:202:10: 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:202:8: 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:203:8: 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:207:8: 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/scream12v3/sse
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:202:10: 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:202:8: 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:203:8: 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:207:8: 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:208:8: 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:215:7: 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:216:7: 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:220:7: 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: 48, 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=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/scream12v3/sse
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:202:10: 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:202:8: 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:203:8: 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:207:8: 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:208:8: 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:215:7: 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:216:7: 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:220:7: 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:202:10: 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:202:8: 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:203:8: 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:207:8: 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:208:8: 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:215:7: 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:216:7: 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:220:7: 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