Implementation notes: x86, h9trinity, crypto_aead/scream12v3

Computer: h9trinity
Architecture: x86
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream12v3
TimeImplementationCompilerBenchmark dateSUPERCOP version
783602refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017121320171020
783900refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017121320171020
784048refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121320171020
789082refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017121320171020
790132refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017121320171020
790719refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017121320171020
790869refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017121320171020
794604refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017121320171020
795162refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121320171020
795235refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017121320171020
796336refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017121320171020
801533refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017121320171020
805725refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017121320171020
805805refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017121320171020
806955refgcc -m32 -O3 -fomit-frame-pointer2017121320171020
809522refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121320171020
815684refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017121320171020
819301refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017121320171020
819940refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017121320171020
823255refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2017121320171020
826030refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017121320171020
826416refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2017121320171020
826458refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017121320171020
830562refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2017121320171020
830599refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2017121320171020
831202refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017121320171020
832713refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017121320171020
836594refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121320171020
840838refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121320171020
858891refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121320171020
859866refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017121320171020
860308refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121320171020
862687refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121320171020
862886refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121320171020
863986refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017121320171020
864008refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121320171020
864028refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017121320171020
866370refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121320171020
868915refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121320171020
871896refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121320171020
873642refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121320171020
874715refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121320171020
880763refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017121320171020
882133refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017121320171020
884634refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017121320171020
902837refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017121320171020
918045refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017121320171020
925699refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017121320171020
926460refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017121320171020
926659refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017121320171020
927597refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017121320171020
1068152refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017121320171020
1069137refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017121320171020
1069367refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2017121320171020
1070864refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2017121320171020
1070874refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017121320171020
1072550refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017121320171020
1076096refgcc -m32 -O2 -fomit-frame-pointer2017121320171020
1080589refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017121320171020
1082365refgcc -m32 -march=core2 -O -fomit-frame-pointer2017121320171020
1085537refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017121320171020
1085964refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017121320171020
1087165refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017121320171020
1091898refgcc -m32 -O -fomit-frame-pointer2017121320171020
1095498refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017121320171020
1096455refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121320171020
1096470refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017121320171020
1105108refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017121320171020
1107602refgcc -m32 -march=k8 -O -fomit-frame-pointer2017121320171020
1109399refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2017121320171020
1110915refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2017121320171020
1112282refgcc -m32 -march=prescott -O -fomit-frame-pointer2017121320171020
1113093refgcc -m32 -march=nocona -O -fomit-frame-pointer2017121320171020
1120280refgcc -m32 -march=athlon -O -fomit-frame-pointer2017121320171020
1132604refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017121320171020
1137276refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017121320171020
1138894refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017121320171020
1142044refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017121320171020
1149108refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017121320171020
1179414refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121320171020
1179709refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121320171020
1182343refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121320171020
1184230refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121320171020
1202862refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017121320171020
1203010refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017121320171020
1211400refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017121320171020
1219536refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017121320171020
1303543refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017121320171020
1328913refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017121320171020
1330015refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121320171020
1332386refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017121320171020
1337250refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017121320171020
1338669refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121320171020
1339269refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121320171020
1340405refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017121320171020
1341117refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017121320171020
1343434refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121320171020
1344665refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121320171020
1344900refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017121320171020
1345418refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017121320171020
1345858refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017121320171020
1349352refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017121320171020
1350222refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121320171020
1351661refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121320171020
1365149refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121320171020
1369490refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017121320171020
1388835refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121320171020
1389191refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017121320171020
1402623refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017121320171020
1415668refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017121320171020
1423733refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121320171020
1423843refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017121320171020
1436148refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121320171020
1454321refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017121320171020
1462739refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017121320171020
1475254refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017121320171020
1477555refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017121320171020
1477623refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121320171020
1480924refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017121320171020
1482240refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017121320171020
1484554refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017121320171020
1552245refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017121320171020
1596841refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017121320171020
1596920refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121320171020
1597601refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017121320171020
1598368refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017121320171020
1598589refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017121320171020
1614634refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017121320171020
1615890refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017121320171020
1616000refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017121320171020
1617972refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017121320171020
1618579refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017121320171020
1618894refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017121320171020
1619001refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017121320171020
1620528refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017121320171020
1625399refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121320171020
1626803refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017121320171020
1627614refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017121320171020
1628004refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017121320171020
1638620refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017121320171020
1642955refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017121320171020
1644443refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017121320171020
1647236refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2017121320171020
1647403refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017121320171020
1648214refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017121320171020
1649639refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017121320171020
1651167refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017121320171020
1651837refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017121320171020
1653299refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2017121320171020
1653736refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017121320171020
1653932refgcc -m32 -Os -fomit-frame-pointer2017121320171020
1655713refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121320171020
1660482refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017121320171020
1670168refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017121320171020
1675575refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017121320171020
1677737refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017121320171020
1682879refgcc -m32 -march=i386 -O -fomit-frame-pointer2017121320171020
1689401refgcc -m32 -march=pentium -O -fomit-frame-pointer2017121320171020
1689999refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121320171020
1695347refgcc -m32 -march=i486 -O -fomit-frame-pointer2017121320171020
1732650refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121320171020
1732652refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017121320171020
1733302refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017121320171020
1736141refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017121320171020
1736586refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121320171020
1742930refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017121320171020
1766619refgcc -m32 -march=k6 -O -fomit-frame-pointer2017121320171020
1767598refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017121320171020
1770845refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017121320171020
1777513refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017121320171020
1787419refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017121320171020
1790642refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017121320171020

Test failure

Implementation: crypto_aead/scream12v3/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/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: 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/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