Implementation notes: x86, h9trinity, crypto_aead/scream10v3

Computer: h9trinity
Architecture: x86
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream10v3
TimeImplementationCompilerBenchmark dateSUPERCOP version
656445refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017121220171020
660116refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017121220171020
662414refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017121220171020
663996refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017121220171020
664295refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121220171020
666234refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017121220171020
666810refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017121220171020
667327refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017121220171020
668524refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017121220171020
669852refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017121220171020
672521refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017121220171020
676847refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121220171020
677835refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017121220171020
681856refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017121220171020
682340refgcc -m32 -O3 -fomit-frame-pointer2017121220171020
684270refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017121220171020
691809refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017121220171020
694645refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017121220171020
694785refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017121220171020
695543refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2017121220171020
696728refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2017121220171020
697789refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2017121220171020
697840refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2017121220171020
699119refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017121220171020
699974refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017121220171020
700649refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017121220171020
701158refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121220171020
704437refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121220171020
708811refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121220171020
726586refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121220171020
726843refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121220171020
727124refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017121220171020
728885refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017121220171020
731221refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017121220171020
731241refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121220171020
732102refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121220171020
735175refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121220171020
738848refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121220171020
739515refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121220171020
739731refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121220171020
740651refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121220171020
743565refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017121220171020
744468refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017121220171020
745133refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121220171020
745640refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017121220171020
755408refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017121220171020
771730refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017121220171020
784675refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017121220171020
785346refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017121220171020
786022refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017121220171020
786151refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017121220171020
909535refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017121220171020
910463refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017121220171020
911170refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017121220171020
911582refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017121220171020
912756refgcc -m32 -O2 -fomit-frame-pointer2017121220171020
915023refgcc -m32 -march=core2 -O -fomit-frame-pointer2017121220171020
915637refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017121220171020
915667refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2017121220171020
915998refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017121220171020
918452refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2017121220171020
918485refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017121220171020
920349refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017121220171020
922638refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017121220171020
930709refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121220171020
933190refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2017121220171020
937775refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2017121220171020
938031refgcc -m32 -march=k8 -O -fomit-frame-pointer2017121220171020
947207refgcc -m32 -march=prescott -O -fomit-frame-pointer2017121220171020
947369refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017121220171020
947682refgcc -m32 -march=athlon -O -fomit-frame-pointer2017121220171020
948421refgcc -m32 -O -fomit-frame-pointer2017121220171020
948567refgcc -m32 -march=nocona -O -fomit-frame-pointer2017121220171020
954278refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017121220171020
965588refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017121220171020
968513refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017121220171020
969257refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017121220171020
977425refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017121220171020
979138refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017121220171020
996998refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121220171020
997550refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121220171020
998910refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121220171020
1001927refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121220171020
1013447refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017121220171020
1015668refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017121220171020
1019458refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017121220171020
1036117refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017121220171020
1051103refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017121220171020
1074889refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017121220171020
1131291refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121220171020
1131333refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121220171020
1131688refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017121220171020
1131746refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121220171020
1132296refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017121220171020
1132581refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017121220171020
1132995refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017121220171020
1135456refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121220171020
1135622refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017121220171020
1135854refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017121220171020
1136609refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017121220171020
1136836refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121220171020
1138224refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017121220171020
1159162refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121220171020
1159208refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017121220171020
1162671refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121220171020
1163612refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017121220171020
1170078refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121220171020
1175673refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017121220171020
1175997refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121220171020
1177330refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121220171020
1183671refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017121220171020
1195617refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017121220171020
1196441refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121220171020
1197114refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121220171020
1197229refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017121220171020
1228437refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017121220171020
1231854refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017121220171020
1240285refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017121220171020
1242220refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017121220171020
1242331refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017121220171020
1270488refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017121220171020
1294400refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017121220171020
1295693refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017121220171020
1351261refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017121220171020
1353721refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017121220171020
1354197refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017121220171020
1362652refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121220171020
1365942refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121220171020
1366463refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017121220171020
1366915refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017121220171020
1367307refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017121220171020
1367687refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017121220171020
1368181refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017121220171020
1368289refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017121220171020
1368937refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017121220171020
1369832refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017121220171020
1370720refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017121220171020
1372222refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017121220171020
1376327refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2017121220171020
1378772refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017121220171020
1383049refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2017121220171020
1383257refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017121220171020
1383905refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017121220171020
1386536refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017121220171020
1386829refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017121220171020
1387097refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017121220171020
1387213refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017121220171020
1387927refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017121220171020
1388000refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017121220171020
1389757refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017121220171020
1392014refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017121220171020
1396892refgcc -m32 -Os -fomit-frame-pointer2017121220171020
1397876refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017121220171020
1403413refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121220171020
1413234refgcc -m32 -march=i386 -O -fomit-frame-pointer2017121220171020
1413774refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017121220171020
1415189refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017121220171020
1423353refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121220171020
1429214refgcc -m32 -march=pentium -O -fomit-frame-pointer2017121220171020
1429941refgcc -m32 -march=i486 -O -fomit-frame-pointer2017121220171020
1464036refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017121220171020
1464930refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121220171020
1470341refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121220171020
1476901refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017121220171020
1480725refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017121220171020
1484061refgcc -m32 -march=k6 -O -fomit-frame-pointer2017121220171020
1486295refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017121220171020
1486884refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017121220171020
1487056refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017121220171020
1507790refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017121220171020
1515650refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017121220171020
1516661refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017121220171020

Test failure

Implementation: crypto_aead/scream10v3/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/scream10v3/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/scream10v3/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/scream10v3/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