Implementation notes: x86, h9trinity, crypto_aead/scream12v1

Computer: h9trinity
Architecture: x86
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream12v1
TimeImplementationCompilerBenchmark dateSUPERCOP version
678139refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121320171020
685383refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017121320171020
693921refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017121320171020
695692refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017121320171020
699177refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017121320171020
701911refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017121320171020
702286refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017121320171020
702383refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017121320171020
702982refgcc -m32 -O3 -fomit-frame-pointer2017121320171020
707742refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017121320171020
708352refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121320171020
710248refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121320171020
713809refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017121320171020
714447refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017121320171020
715391refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017121320171020
716581refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017121320171020
718146refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017121320171020
718744refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2017121320171020
719712refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017121320171020
720793refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2017121320171020
722679refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017121320171020
723407refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017121320171020
723431refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2017121320171020
723432refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017121320171020
724234refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017121320171020
726252refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017121320171020
726564refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017121320171020
726720refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017121320171020
727447refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2017121320171020
727899refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017121320171020
744780refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017121320171020
745496refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017121320171020
745716refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017121320171020
752116refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121320171020
755795refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121320171020
756975refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121320171020
757283refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121320171020
758174refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121320171020
764848refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121320171020
769049refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121320171020
774352refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121320171020
775343refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121320171020
780134refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017121320171020
781964refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121320171020
782687refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121320171020
788663refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121320171020
804424refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017121320171020
823840refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017121320171020
824126refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017121320171020
827538refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017121320171020
848344refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017121320171020
963742refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017121320171020
966500refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017121320171020
969445refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017121320171020
969869refgcc -m32 -march=nocona -O -fomit-frame-pointer2017121320171020
971511refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017121320171020
971628refgcc -m32 -march=prescott -O -fomit-frame-pointer2017121320171020
973296refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017121320171020
978220refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121320171020
983571refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2017121320171020
985007refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017121320171020
987820refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2017121320171020
987964refgcc -m32 -O2 -fomit-frame-pointer2017121320171020
988383refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017121320171020
989650refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017121320171020
990167refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017121320171020
991977refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017121320171020
1004618refgcc -m32 -O -fomit-frame-pointer2017121320171020
1013196refgcc -m32 -march=k8 -O -fomit-frame-pointer2017121320171020
1013241refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2017121320171020
1014460refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2017121320171020
1017421refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017121320171020
1022501refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017121320171020
1025121refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017121320171020
1025461refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017121320171020
1034913refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017121320171020
1035861refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017121320171020
1037852refgcc -m32 -march=core2 -O -fomit-frame-pointer2017121320171020
1050898refgcc -m32 -march=athlon -O -fomit-frame-pointer2017121320171020
1064682refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121320171020
1074581refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017121320171020
1074596refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017121320171020
1074736refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017121320171020
1075429refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121320171020
1075479refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121320171020
1075522refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121320171020
1081007refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017121320171020
1085552refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017121320171020
1094030refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017121320171020
1094830refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017121320171020
1095053refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017121320171020
1108329refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017121320171020
1118947refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017121320171020
1131856refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017121320171020
1132485refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017121320171020
1132622refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121320171020
1132634refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121320171020
1136790refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017121320171020
1139123refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017121320171020
1139487refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121320171020
1146650refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121320171020
1146994refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017121320171020
1147029refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121320171020
1148975refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017121320171020
1164945refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017121320171020
1171097refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121320171020
1172455refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017121320171020
1172778refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121320171020
1174234refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017121320171020
1175882refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121320171020
1181339refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017121320171020
1199231refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017121320171020
1199443refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121320171020
1204479refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121320171020
1230127refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017121320171020
1241626refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121320171020
1242651refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017121320171020
1248698refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121320171020
1250954refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017121320171020
1257825refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017121320171020
1257874refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017121320171020
1277166refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017121320171020
1282116refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017121320171020
1399778refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017121320171020
1405848refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017121320171020
1410519refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121320171020
1415609refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017121320171020
1436706refgcc -m32 -march=i486 -O -fomit-frame-pointer2017121320171020
1440464refgcc -m32 -march=i386 -O -fomit-frame-pointer2017121320171020
1462160refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017121320171020
1462204refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121320171020
1468346refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121320171020
1468947refgcc -m32 -march=pentium -O -fomit-frame-pointer2017121320171020
1470857refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121320171020
1471471refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017121320171020
1477657refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017121320171020
1490433refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017121320171020
1492508refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017121320171020
1492991refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017121320171020
1494721refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017121320171020
1495937refgcc -m32 -Os -fomit-frame-pointer2017121320171020
1496449refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017121320171020
1496525refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017121320171020
1497093refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017121320171020
1500515refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017121320171020
1501770refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017121320171020
1504505refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017121320171020
1505380refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017121320171020
1505392refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121320171020
1508104refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017121320171020
1508161refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017121320171020
1508168refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017121320171020
1508529refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121320171020
1508993refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017121320171020
1509320refgcc -m32 -march=k6 -O -fomit-frame-pointer2017121320171020
1509540refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017121320171020
1512082refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017121320171020
1512264refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017121320171020
1512411refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017121320171020
1512830refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017121320171020
1513426refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017121320171020
1516617refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2017121320171020
1517679refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017121320171020
1521228refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017121320171020
1521836refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2017121320171020
1527225refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017121320171020
1529068refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017121320171020
1530113refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017121320171020
1530655refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017121320171020
1541250refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017121320171020
1542318refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017121320171020
1546763refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017121320171020

Test failure

Implementation: crypto_aead/scream12v1/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/scream12v1/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/scream12v1/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/scream12v1/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