Implementation notes: x86, h4e450, crypto_aead/scream12v1

Computer: h4e450
Architecture: x86
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream12v1
TimeImplementationCompilerBenchmark dateSUPERCOP version
873145refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017101020170725
875045refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017101020170725
875102refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017101020170725
880033refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017101020170725
881096refgcc -m32 -O3 -fomit-frame-pointer2017101020170725
882341refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017101020170725
886778refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017101020170725
891860refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017101020170725
893646refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017101020170725
896553refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017101020170725
897042refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017101020170725
897066refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017101020170725
900947refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017101020170725
901089refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017101020170725
901427refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017101020170725
902115refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017101020170725
903750refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017101020170725
907620refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017101020170725
907653refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017101020170725
907711refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017101020170725
913786refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017101020170725
913990refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017101020170725
917601refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017101020170725
921719refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017101020170725
924326refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017101020170725
925708refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017101020170725
926397refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017101020170725
927642refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017101020170725
927907refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017101020170725
928526refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017101020170725
928753refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017101020170725
928920refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017101020170725
931869refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017101020170725
932131refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017101020170725
932976refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017101020170725
934952refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017101020170725
935104refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017101020170725
937835refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017101020170725
937854refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017101020170725
938063refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017101020170725
941036refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017101020170725
941089refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017101020170725
943169refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017101020170725
943231refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017101020170725
944828refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017101020170725
946794refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017101020170725
947041refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017101020170725
960108refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017101020170725
961205refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017101020170725
966635refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017101020170725
967964refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017101020170725
971831refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017101020170725
973056refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017101020170725
974833refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017101020170725
975090refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017101020170725
977014refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017101020170725
981498refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017101020170725
981507refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017101020170725
983597refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017101020170725
984647refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017101020170725
987720refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017101020170725
998203refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017101020170725
1033272refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017101020170725
1033472refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017101020170725
1034612refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017101020170725
1048771refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017101020170725
1053863refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017101020170725
1058020refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017101020170725
1058247refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017101020170725
1065235refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017101020170725
1068071refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017101020170725
1068461refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017101020170725
1068907refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017101020170725
1069919refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017101020170725
1112612refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017101020170725
1116335refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017101020170725
1116606refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017101020170725
1120368refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017101020170725
1121475refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017101020170725
1122976refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017101020170725
1124757refgcc -m32 -O2 -fomit-frame-pointer2017101020170725
1131037refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017101020170725
1132547refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017101020170725
1139487refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017101020170725
1144080refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017101020170725
1161964refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017101020170725
1164976refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017101020170725
1195077refgcc -m32 -march=athlon -O -fomit-frame-pointer2017101020170725
1198601refgcc -m32 -march=nocona -O -fomit-frame-pointer2017101020170725
1198928refgcc -m32 -march=prescott -O -fomit-frame-pointer2017101020170725
1218632refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017101020170725
1225315refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017101020170725
1232686refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017101020170725
1232701refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017101020170725
1232715refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017101020170725
1235380refgcc -m32 -O -fomit-frame-pointer2017101020170725
1236283refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017101020170725
1240805refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017101020170725
1243227refgcc -m32 -march=k8 -O -fomit-frame-pointer2017101020170725
1243793refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017101020170725
1244509refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017101020170725
1261377refgcc -m32 -march=core2 -O -fomit-frame-pointer2017101020170725
1261648refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017101020170725
1261857refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017101020170725
1264697refgcc -m32 -march=i386 -O -fomit-frame-pointer2017101020170725
1272354refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017101020170725
1274487refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017101020170725
1276339refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017101020170725
1279266refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017101020170725
1279313refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017101020170725
1280923refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017101020170725
1287820refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017101020170725
1295458refgcc -m32 -march=i486 -O -fomit-frame-pointer2017101020170725
1299363refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017101020170725
1301485refgcc -m32 -march=pentium -O -fomit-frame-pointer2017101020170725
1301576refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017101020170725
1302384refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017101020170725
1314653refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017101020170725
1314710refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017101020170725
1314762refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017101020170725
1322732refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017101020170725
1326224refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017101020170725
1326500refgcc -m32 -march=k6 -O -fomit-frame-pointer2017101020170725
1330157refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017101020170725
1330670refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017101020170725
1331529refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017101020170725
1331610refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017101020170725
1332708refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017101020170725
1332945refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017101020170725
1333391refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017101020170725
1335781refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017101020170725
1336379refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017101020170725
1342488refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017101020170725
1343362refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017101020170725
1346535refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017101020170725
1346791refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017101020170725
1350952refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017101020170725
1351029refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017101020170725
1356035refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017101020170725
1356216refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017101020170725
1356305refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017101020170725
1360448refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017101020170725
1362689refgcc -m32 -Os -fomit-frame-pointer2017101020170725
1365554refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017101020170725
1365781refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017101020170725
1366603refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017101020170725
1388268refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017101020170725
1389584refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017101020170725
1390017refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017101020170725
1390591refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017101020170725
1395137refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017101020170725
1395541refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017101020170725
1395635refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017101020170725
1464805refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017101020170725
1466202refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017101020170725
1466786refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017101020170725
1475327refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017101020170725
1476594refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017101020170725
1480062refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017101020170725
1488551refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017101020170725
1488992refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017101020170725

Test failure

Implementation: crypto_aead/scream12v1/ref
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 35, 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 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
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