Implementation notes: x86, rumba7, crypto_aead/scream12v3

Computer: rumba7
Architecture: x86
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream12v3
TimeImplementationCompilerBenchmark dateSUPERCOP version
529260refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2018052920171218
531480refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2018052920171218
532080refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2018052920171218
533070refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2018052920171218
534480refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2018052920171218
534510refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018052920171218
535500refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2018052920171218
540030refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2018052920171218
542010refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2018052920171218
542670refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2018052920171218
542700refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2018052920171218
542910refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018052920171218
543960refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2018052920171218
544800refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2018052920171218
544800refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2018052920171218
545310refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2018052920171218
545640refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2018052920171218
546450refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2018052920171218
546720refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2018052920171218
546870refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018052920171218
547050refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2018052920171218
547110refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2018052920171218
547590refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2018052920171218
548160refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2018052920171218
548550refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2018052920171218
548700refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018052920171218
549780refgcc -m32 -O3 -fomit-frame-pointer2018052920171218
550680refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2018052920171218
552450refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2018052920171218
552630refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2018052920171218
552960refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018052920171218
553050refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2018052920171218
553260refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2018052920171218
553620refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2018052920171218
554040refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2018052920171218
554220refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2018052920171218
554310refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2018052920171218
555720refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2018052920171218
556170refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2018052920171218
556350refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2018052920171218
557100refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2018052920171218
557850refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2018052920171218
558120refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2018052920171218
558480refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2018052920171218
559020refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2018052920171218
560940refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2018052920171218
560970refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2018052920171218
570060refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018052920171218
573540refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2018052920171218
583950refgcc -funroll-loops -m32 -O -fomit-frame-pointer2018052920171218
590070refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2018052920171218
591870refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2018052920171218
685950refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2018052920171218
686370refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2018052920171218
686400refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2018052920171218
686670refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018052920171218
687300refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2018052920171218
687300refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2018052920171218
687390refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2018052920171218
688410refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2018052920171218
688650refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2018052920171218
689040refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018052920171218
690660refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2018052920171218
691350refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2018052920171218
691770refgcc -m32 -O2 -fomit-frame-pointer2018052920171218
691980refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2018052920171218
694710refgcc -m32 -march=prescott -O -fomit-frame-pointer2018052920171218
695220refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018052920171218
695670refgcc -m32 -march=nocona -O -fomit-frame-pointer2018052920171218
695850refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2018052920171218
696570refgcc -m32 -march=athlon -O -fomit-frame-pointer2018052920171218
697200refgcc -m32 -march=barcelona -O -fomit-frame-pointer2018052920171218
697740refgcc -m32 -O -fomit-frame-pointer2018052920171218
699480refgcc -m32 -march=core2 -O -fomit-frame-pointer2018052920171218
700380refgcc -m32 -march=k8 -O -fomit-frame-pointer2018052920171218
700530refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018052920171218
700950refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2018052920171218
700980refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2018052920171218
701040refgcc -m32 -march=corei7 -O -fomit-frame-pointer2018052920171218
703110refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2018052920171218
704610refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018052920171218
715440refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2018052920171218
751260refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2018052920171218
751260refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2018052920171218
751380refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2018052920171218
752880refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2018052920171218
753750refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2018052920171218
753930refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018052920171218
756900refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2018052920171218
757110refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2018052920171218
758190refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2018052920171218
758310refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2018052920171218
759330refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2018052920171218
759840refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2018052920171218
767880refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2018052920171218
769290refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2018052920171218
776040refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2018052920171218
776370refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2018052920171218
892050refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2018052920171218
957210refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2018052920171218
958110refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2018052920171218
970860refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2018052920171218
971040refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2018052920171218
971070refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018052920171218
971400refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018052920171218
974280refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2018052920171218
978390refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2018052920171218
984810refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2018052920171218
985770refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2018052920171218
986640refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2018052920171218
999030refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2018052920171218
1000470refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2018052920171218
1001610refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2018052920171218
1004040refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2018052920171218
1008450refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2018052920171218
1008900refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2018052920171218
1025490refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2018052920171218
1025550refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018052920171218
1026450refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2018052920171218
1027260refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2018052920171218
1027290refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2018052920171218
1028220refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2018052920171218
1029240refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2018052920171218
1030140refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018052920171218
1030410refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2018052920171218
1035870refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2018052920171218
1036230refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018052920171218
1036350refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2018052920171218
1046730refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2018052920171218
1046820refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2018052920171218
1046880refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2018052920171218
1047060refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2018052920171218
1048110refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2018052920171218
1049430refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2018052920171218
1054890refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2018052920171218
1067760refgcc -m32 -march=i386 -O -fomit-frame-pointer2018052920171218
1068930refgcc -m32 -march=pentium -Os -fomit-frame-pointer2018052920171218
1069410refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018052920171218
1072650refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2018052920171218
1072740refgcc -m32 -march=nocona -Os -fomit-frame-pointer2018052920171218
1073460refgcc -m32 -march=prescott -Os -fomit-frame-pointer2018052920171218
1074030refgcc -m32 -march=i486 -Os -fomit-frame-pointer2018052920171218
1074090refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2018052920171218
1074300refgcc -m32 -march=i386 -Os -fomit-frame-pointer2018052920171218
1074810refgcc -m32 -march=i486 -O -fomit-frame-pointer2018052920171218
1074840refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2018052920171218
1074960refgcc -m32 -march=pentium -O -fomit-frame-pointer2018052920171218
1076160refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2018052920171218
1076610refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2018052920171218
1081470refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2018052920171218
1081920refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2018052920171218
1082220refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2018052920171218
1083150refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018052920171218
1083540refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2018052920171218
1083900refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2018052920171218
1084410refgcc -m32 -march=k8 -Os -fomit-frame-pointer2018052920171218
1084620refgcc -m32 -march=core2 -Os -fomit-frame-pointer2018052920171218
1084710refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018052920171218
1085130refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018052920171218
1085640refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2018052920171218
1086900refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2018052920171218
1087560refgcc -m32 -Os -fomit-frame-pointer2018052920171218
1087620refgcc -m32 -march=athlon -Os -fomit-frame-pointer2018052920171218
1096260refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2018052920171218
1125810refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2018052920171218
1125840refgcc -m32 -march=k6 -Os -fomit-frame-pointer2018052920171218
1127040refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2018052920171218
1142520refgcc -m32 -march=k6 -O -fomit-frame-pointer2018052920171218
1143810refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2018052920171218
1144230refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2018052920171218
1210080refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2018052920171218
1210380refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2018052920171218
1210980refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2018052920171218
1210980refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2018052920171218
1211040refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2018052920171218
1211670refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2018052920171218

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: 32, 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 sse
gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer sse
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer sse
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer 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