Implementation notes: x86, h4e450, crypto_aead/scream12v2

Computer: h4e450
Architecture: x86
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream12v2
TimeImplementationCompilerBenchmark dateSUPERCOP version
874076refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017101020170725
875696refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017101020170725
876817refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017101020170725
880255refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017101020170725
882242refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017101020170725
884046refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017101020170725
886084refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017101020170725
886127refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017101020170725
886673refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017101020170725
887082refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017101020170725
894031refgcc -m32 -O3 -fomit-frame-pointer2017101020170725
896819refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017101020170725
897270refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017101020170725
900490refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017101020170725
900576refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017101020170725
903231refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017101020170725
907330refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017101020170725
908557refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017101020170725
909388refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017101020170725
912560refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017101020170725
918598refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017101020170725
918655refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017101020170725
919077refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017101020170725
921210refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017101020170725
921580refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017101020170725
922350refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017101020170725
923542refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017101020170725
924525refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017101020170725
924707refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017101020170725
925371refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017101020170725
927651refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017101020170725
927969refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017101020170725
928192refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017101020170725
928454refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017101020170725
931251refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017101020170725
934971refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017101020170725
935470refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017101020170725
937218refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017101020170725
941840refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017101020170725
941887refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017101020170725
942291refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017101020170725
948418refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017101020170725
949230refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017101020170725
949411refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017101020170725
949724refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017101020170725
949948refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017101020170725
950133refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017101020170725
959319refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017101020170725
960649refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017101020170725
960744refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017101020170725
961946refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017101020170725
969513refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017101020170725
969689refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017101020170725
970839refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017101020170725
982528refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017101020170725
983987refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017101020170725
984960refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017101020170725
985326refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017101020170725
986457refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017101020170725
986969refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017101020170725
989515refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017101020170725
995453refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017101020170725
1027425refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017101020170725
1035419refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017101020170725
1035819refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017101020170725
1036360refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017101020170725
1041974refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017101020170725
1042008refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017101020170725
1054747refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017101020170725
1066607refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017101020170725
1068797refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017101020170725
1070631refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017101020170725
1071615refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017101020170725
1072441refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017101020170725
1112099refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017101020170725
1112635refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017101020170725
1122163refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017101020170725
1122421refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017101020170725
1123095refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017101020170725
1123883refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017101020170725
1124168refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017101020170725
1124947refgcc -m32 -O2 -fomit-frame-pointer2017101020170725
1147415refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017101020170725
1154007refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017101020170725
1157780refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017101020170725
1157913refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017101020170725
1161878refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017101020170725
1208258refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017101020170725
1209155refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017101020170725
1209839refgcc -m32 -march=prescott -O -fomit-frame-pointer2017101020170725
1210461refgcc -m32 -march=nocona -O -fomit-frame-pointer2017101020170725
1222247refgcc -m32 -march=athlon -O -fomit-frame-pointer2017101020170725
1228279refgcc -m32 -march=i486 -O -fomit-frame-pointer2017101020170725
1232982refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017101020170725
1234525refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017101020170725
1234530refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017101020170725
1234920refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017101020170725
1235100refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017101020170725
1235195refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017101020170725
1235974refgcc -m32 -O -fomit-frame-pointer2017101020170725
1242500refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017101020170725
1242790refgcc -m32 -march=k8 -O -fomit-frame-pointer2017101020170725
1254603refgcc -m32 -march=core2 -O -fomit-frame-pointer2017101020170725
1254836refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017101020170725
1256010refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017101020170725
1257225refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017101020170725
1268986refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017101020170725
1269291refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017101020170725
1270530refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017101020170725
1270900refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017101020170725
1271950refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017101020170725
1275413refgcc -m32 -march=i386 -O -fomit-frame-pointer2017101020170725
1278971refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017101020170725
1279360refgcc -m32 -march=k6 -O -fomit-frame-pointer2017101020170725
1279394refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017101020170725
1293796refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017101020170725
1295097refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017101020170725
1296641refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017101020170725
1301429refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017101020170725
1307742refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017101020170725
1316895refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017101020170725
1317251refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017101020170725
1322215refgcc -m32 -march=pentium -O -fomit-frame-pointer2017101020170725
1322433refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017101020170725
1334308refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017101020170725
1334327refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017101020170725
1334679refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017101020170725
1334693refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017101020170725
1335500refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017101020170725
1335505refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017101020170725
1336441refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017101020170725
1344387refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017101020170725
1344407refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017101020170725
1353028refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017101020170725
1353237refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017101020170725
1356799refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017101020170725
1356819refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017101020170725
1357545refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017101020170725
1365996refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017101020170725
1366214refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017101020170725
1366224refgcc -m32 -Os -fomit-frame-pointer2017101020170725
1366456refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017101020170725
1367169refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017101020170725
1373994refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017101020170725
1374626refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017101020170725
1397720refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017101020170725
1399388refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017101020170725
1399445refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017101020170725
1403958refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017101020170725
1403995refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017101020170725
1404413refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017101020170725
1408190refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017101020170725
1409268refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017101020170725
1440898refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017101020170725
1440927refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017101020170725
1464634refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017101020170725
1475355refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017101020170725
1475373refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017101020170725
1475422refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017101020170725
1495091refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017101020170725
1496597refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017101020170725

Test failure

Implementation: crypto_aead/scream12v2/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/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