Implementation notes: x86, margaux, crypto_aead/scream12v1

Computer: margaux
Architecture: x86
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream12v1
TimeImplementationCompilerBenchmark dateSUPERCOP version
646254refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017080220170725
647586refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017080220170725
648891refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017080220170725
649008refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017080220170725
652050refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017080220170725
657423refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017080220170725
671760refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017080220170725
671832refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017080220170725
672138refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017080220170725
672795refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017080220170725
675441refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017080220170725
675486refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017080220170725
676584refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017080220170725
676800refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017080220170725
677637refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017080220170725
678897refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017080220170725
726687refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017080220170725
726894refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017080220170725
726993refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017080220170725
733203refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017080220170725
746262refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017080220170725
746397refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017080220170725
747360refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017080220170725
756675refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017080220170725
757026refgcc -m32 -O3 -fomit-frame-pointer2017080220170725
757305refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017080220170725
757764refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017080220170725
758322refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017080220170725
759537refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017080220170725
760500refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017080220170725
760725refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017080220170725
761535refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017080220170725
762138refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017080220170725
763434refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017080220170725
764172refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017080220170725
765621refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017080220170725
765630refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017080220170725
766071refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017080220170725
766116refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017080220170725
777654refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017080220170725
780966refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017080220170725
782118refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017080220170725
782235refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017080220170725
786807refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017080220170725
788643refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017080220170725
821574refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017080220170725
822024refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017080220170725
822816refgcc -m32 -march=nocona -O -fomit-frame-pointer2017080220170725
828612refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017080220170725
828891refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017080220170725
829872refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017080220170725
830178refgcc -m32 -march=prescott -O -fomit-frame-pointer2017080220170725
832608refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017080220170725
837099refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017080220170725
839952refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2017080220170725
840807refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017080220170725
840924refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017080220170725
841329refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017080220170725
841410refgcc -m32 -O -fomit-frame-pointer2017080220170725
841752refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017080220170725
841860refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017080220170725
841950refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017080220170725
842004refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017080220170725
842373refgcc -m32 -march=core2 -O -fomit-frame-pointer2017080220170725
842913refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2017080220170725
842994refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017080220170725
843399refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2017080220170725
848286refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2017080220170725
849429refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017080220170725
849609refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017080220170725
850185refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017080220170725
850950refgcc -m32 -O2 -fomit-frame-pointer2017080220170725
855711refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017080220170725
858060refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017080220170725
859617refgcc -m32 -march=k8 -O -fomit-frame-pointer2017080220170725
860454refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017080220170725
863127refgcc -m32 -march=athlon -O -fomit-frame-pointer2017080220170725
875736refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017080220170725
875862refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017080220170725
877653refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017080220170725
880992refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017080220170725
903060refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017080220170725
903645refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017080220170725
904104refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017080220170725
904185refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017080220170725
909432refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017080220170725
919755refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017080220170725
920952refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017080220170725
921069refgcc -m32 -march=i386 -O -fomit-frame-pointer2017080220170725
927063refgcc -m32 -march=i486 -O -fomit-frame-pointer2017080220170725
930942refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017080220170725
932328refgcc -m32 -march=pentium -O -fomit-frame-pointer2017080220170725
934677refgcc -m32 -march=k6 -O -fomit-frame-pointer2017080220170725
940050refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017080220170725
954207refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017080220170725
956304refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017080220170725
981000refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017080220170725
987174refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017080220170725
987363refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017080220170725
988038refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017080220170725
988038refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017080220170725
990585refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017080220170725
993258refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017080220170725
993852refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017080220170725
994923refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2017080220170725
995283refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017080220170725
997542refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017080220170725
1000674refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017080220170725
1002258refgcc -m32 -Os -fomit-frame-pointer2017080220170725
1004580refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017080220170725
1005192refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017080220170725
1009206refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017080220170725
1017711refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017080220170725
1018791refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017080220170725
1020051refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017080220170725
1021923refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017080220170725
1024542refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017080220170725
1033164refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017080220170725
1034757refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017080220170725
1036566refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017080220170725
1038429refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017080220170725
1042416refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017080220170725
1043379refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017080220170725
1044117refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017080220170725
1045926refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017080220170725
1051092refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017080220170725
1051542refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017080220170725
1056816refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017080220170725
1057122refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2017080220170725
1057860refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017080220170725
1059183refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017080220170725
1061523refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017080220170725
1062774refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017080220170725
1066554refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017080220170725
1066680refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017080220170725
1069119refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017080220170725
1071756refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017080220170725
1074114refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017080220170725
1078020refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017080220170725
1078569refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017080220170725
1092231refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017080220170725
1093005refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017080220170725
1094832refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017080220170725
1097901refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017080220170725
1143027refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017080220170725
1159677refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017080220170725
1160991refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017080220170725
1165464refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017080220170725
1172898refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017080220170725
1175247refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017080220170725
1188666refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017080220170725
1199754refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017080220170725
1199979refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017080220170725
1212975refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017080220170725
1217799refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017080220170725
1219689refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017080220170725
1226304refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017080220170725
1252395refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017080220170725
1530126refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017080220170725
1559493refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017080220170725
1559772refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017080220170725
1560348refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017080220170725
1560888refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017080220170725
1577259refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017080220170725
1577619refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017080220170725
1590489refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017080220170725
1601280refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017080220170725

Test failure

Implementation: crypto_aead/scream12v1/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/scream12v1/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/scream12v1/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/scream12v1/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