Implementation notes: x86, latour, crypto_aead/scream10v1

Computer: latour
Architecture: x86
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream10v1
TimeImplementationCompilerBenchmark dateSUPERCOP version
548955refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017072520170718
550710refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017072520170718
551907refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017072520170718
552501refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017072520170718
556848refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017072520170718
557073refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017072520170718
559188refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017072520170718
559296refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017072520170718
566856refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017072520170718
568125refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017072520170718
575766refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017072520170718
576171refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017072520170718
577989refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017072520170718
578502refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017072520170718
587556refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017072520170718
587979refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017072520170718
622053refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017072520170718
624123refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017072520170718
624258refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017072520170718
628911refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017072520170718
636300refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017072520170718
639882refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017072520170718
640062refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017072520170718
640251refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017072520170718
640620refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017072520170718
641169refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017072520170718
641754refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017072520170718
644409refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017072520170718
644652refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017072520170718
647622refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017072520170718
648288refgcc -m32 -O3 -fomit-frame-pointer2017072520170718
650592refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017072520170718
656127refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017072520170718
657126refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017072520170718
658881refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017072520170718
660195refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017072520170718
660366refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017072520170718
660870refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017072520170718
661572refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017072520170718
662958refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017072520170718
663588refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017072520170718
664542refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017072520170718
665235refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017072520170718
665856refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017072520170718
669150refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017072520170718
699768refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017072520170718
709596refgcc -m32 -march=prescott -O -fomit-frame-pointer2017072520170718
709641refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017072520170718
712215refgcc -m32 -march=nocona -O -fomit-frame-pointer2017072520170718
715257refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017072520170718
716049refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017072520170718
716526refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017072520170718
717138refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017072520170718
717543refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017072520170718
720333refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017072520170718
721143refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017072520170718
722124refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017072520170718
722439refgcc -m32 -march=core2 -O -fomit-frame-pointer2017072520170718
722682refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2017072520170718
722916refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017072520170718
723348refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017072520170718
723627refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2017072520170718
723762refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017072520170718
723834refgcc -m32 -O -fomit-frame-pointer2017072520170718
724311refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2017072520170718
724455refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017072520170718
725040refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017072520170718
725679refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017072520170718
726327refgcc -m32 -O2 -fomit-frame-pointer2017072520170718
727209refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017072520170718
730026refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2017072520170718
738810refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017072520170718
739620refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017072520170718
741087refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017072520170718
743742refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017072520170718
743940refgcc -m32 -march=athlon -O -fomit-frame-pointer2017072520170718
743940refgcc -m32 -march=k8 -O -fomit-frame-pointer2017072520170718
755874refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017072520170718
756387refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017072520170718
756522refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017072520170718
756549refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017072520170718
756549refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017072520170718
761985refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017072520170718
766755refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017072520170718
769833refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017072520170718
769896refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017072520170718
781497refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017072520170718
782352refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017072520170718
782433refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017072520170718
783639refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017072520170718
795897refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017072520170718
803601refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017072520170718
805050refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017072520170718
805644refgcc -m32 -march=i386 -O -fomit-frame-pointer2017072520170718
808992refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017072520170718
810828refgcc -m32 -march=i486 -O -fomit-frame-pointer2017072520170718
811962refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017072520170718
813762refgcc -m32 -march=pentium -O -fomit-frame-pointer2017072520170718
817749refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017072520170718
824427refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017072520170718
826020refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017072520170718
836397refgcc -m32 -march=k6 -O -fomit-frame-pointer2017072520170718
836559refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017072520170718
838827refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017072520170718
842634refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017072520170718
843795refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017072520170718
848043refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017072520170718
848844refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017072520170718
849123refgcc -m32 -Os -fomit-frame-pointer2017072520170718
850671refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2017072520170718
851544refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017072520170718
852453refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017072520170718
853020refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017072520170718
854127refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017072520170718
855315refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017072520170718
855819refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017072520170718
858654refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017072520170718
859455refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017072520170718
859869refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017072520170718
860454refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017072520170718
863388refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017072520170718
864558refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017072520170718
870543refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017072520170718
882963refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017072520170718
883377refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017072520170718
887913refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017072520170718
892170refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017072520170718
894870refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017072520170718
896688refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017072520170718
897714refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017072520170718
898047refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017072520170718
901845refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017072520170718
903114refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017072520170718
903510refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017072520170718
908253refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017072520170718
908613refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017072520170718
909234refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017072520170718
909585refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017072520170718
910107refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017072520170718
911151refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017072520170718
911898refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2017072520170718
911925refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017072520170718
914022refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017072520170718
915408refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017072520170718
915759refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017072520170718
916956refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017072520170718
923094refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017072520170718
923994refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017072520170718
944478refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017072520170718
955278refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017072520170718
968130refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017072520170718
968985refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017072520170718
978750refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017072520170718
997056refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017072520170718
1034154refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017072520170718
1055142refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017072520170718
1056204refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017072520170718
1062531refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017072520170718
1065807refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017072520170718
1333656refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017072520170718
1333728refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017072520170718
1334196refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017072520170718
1335348refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017072520170718
1344753refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017072520170718
1345590refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017072520170718
1346355refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017072520170718
1349136refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017072520170718

Test failure

Implementation: crypto_aead/scream10v1/sse
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 29, namely:
CompilerImplementations
gcc -m32 -march=core-avx-i -O2 -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 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer sse
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer 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 -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/scream10v1/sse
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:182:5: error: can't convert between vector values of different size
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:183:5: error: can't convert between vector values of different size
scream.c: t1 = shift_right(in[2]) & V(0xf);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
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/scream10v1/sse
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:204:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
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/scream10v1/sse
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:204:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: ...
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:204:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
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