Implementation notes: x86, hydra1, crypto_aead/scream10v3

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: scream10v3
TimeImplementationCompilerBenchmark dateSUPERCOP version
598082refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
601899refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016102320161009
603669refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2016102320161009
608579refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2016102320161009
612789refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2016102320161009
617371refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2016102320161009
619051refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2016102320161009
623361refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2016102320161009
627251refgcc -m32 -O3 -fomit-frame-pointer2016102320161009
629261refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016102320161009
629277refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2016102320161009
629323refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016102320161009
629811refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016102320161009
629974refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2016102320161009
631067refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2016102320161009
632061refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
632252refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2016102320161009
634191refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016102320161009
637344refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016102320161009
637967refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016102320161009
638763refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2016102320161009
639075refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016102320161009
640139refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016102320161009
645208refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
646767refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016102320161009
647086refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2016102320161009
647706refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016102320161009
659437refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016102320161009
663003refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016102320161009
663552refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016102320161009
663552refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016102320161009
669848refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016102320161009
674474refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2016102320161009
674749refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2016102320161009
691158refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016102320161009
691253refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016102320161009
699446refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016102320161009
699651refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2016102320161009
699928refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016102320161009
700842refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2016102320161009
701965refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2016102320161009
702059refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016102320161009
702525refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2016102320161009
710158refgcc -funroll-loops -m32 -O -fomit-frame-pointer2016102320161009
720669refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016102320161009
746934refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016102320161009
749029refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2016102320161009
750851refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2016102320161009
759747refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2016102320161009
782800refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2016102320161009
784144refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2016102320161009
784820refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2016102320161009
788061refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016102320161009
791272refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2016102320161009
819728refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2016102320161009
819896refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2016102320161009
820134refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2016102320161009
821856refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2016102320161009
822598refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016102320161009
827643refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2016102320161009
828104refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2016102320161009
831086refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2016102320161009
833079refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2016102320161009
833157refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2016102320161009
834494refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2016102320161009
837520refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2016102320161009
838000refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2016102320161009
856770refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2016102320161009
857064refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2016102320161009
881725refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2016102320161009
881760refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2016102320161009
882278refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2016102320161009
885928refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2016102320161009
962512refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2016102320161009
966749refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2016102320161009
974947refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
975088refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016102320161009
980704refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2016102320161009
980899refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2016102320161009
998798refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016102320161009
1002736refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016102320161009
1004136refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2016102320161009
1009263refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016102320161009
1009898refgcc -m32 -O2 -fomit-frame-pointer2016102320161009
1012501refgcc -m32 -O -fomit-frame-pointer2016102320161009
1017702refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016102320161009
1018472refgcc -m32 -march=barcelona -O -fomit-frame-pointer2016102320161009
1020235refgcc -m32 -march=k8 -O -fomit-frame-pointer2016102320161009
1020725refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016102320161009
1020928refgcc -m32 -march=core2 -O -fomit-frame-pointer2016102320161009
1021562refgcc -m32 -march=athlon -O -fomit-frame-pointer2016102320161009
1027514refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016102320161009
1032810refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016102320161009
1040104refgcc -m32 -march=corei7 -O -fomit-frame-pointer2016102320161009
1046210refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016102320161009
1046432refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2016102320161009
1050120refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2016102320161009
1050261refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016102320161009
1055224refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2016102320161009
1055661refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2016102320161009
1062365refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2016102320161009
1067597refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2016102320161009
1074325refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2016102320161009
1075128refgcc -m32 -march=nocona -O -fomit-frame-pointer2016102320161009
1077989refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2016102320161009
1080053refgcc -m32 -march=prescott -O -fomit-frame-pointer2016102320161009
1086061refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2016102320161009
1088452refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2016102320161009
1093310refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2016102320161009
1093771refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2016102320161009
1095545refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2016102320161009
1100013refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2016102320161009
1102164refgcc -m32 -march=i486 -O -fomit-frame-pointer2016102320161009
1103312refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2016102320161009
1103973refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2016102320161009
1113702refgcc -m32 -march=i386 -O -fomit-frame-pointer2016102320161009
1115653refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2016102320161009
1117214refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2016102320161009
1118179refgcc -m32 -march=nocona -Os -fomit-frame-pointer2016102320161009
1118237refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2016102320161009
1118293refgcc -m32 -march=prescott -Os -fomit-frame-pointer2016102320161009
1118683refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2016102320161009
1119870refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2016102320161009
1121175refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2016102320161009
1121469refgcc -m32 -march=pentium -O -fomit-frame-pointer2016102320161009
1121640refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2016102320161009
1127019refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2016102320161009
1133349refgcc -m32 -march=i486 -Os -fomit-frame-pointer2016102320161009
1134365refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016102320161009
1134602refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2016102320161009
1135652refgcc -m32 -march=i386 -Os -fomit-frame-pointer2016102320161009
1141048refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016102320161009
1143229refgcc -m32 -march=pentium -Os -fomit-frame-pointer2016102320161009
1145867refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016102320161009
1146208refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2016102320161009
1146883refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2016102320161009
1146949refgcc -m32 -march=k6 -O -fomit-frame-pointer2016102320161009
1147110refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2016102320161009
1154069refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2016102320161009
1155084refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1155808refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016102320161009
1158813refgcc -m32 -march=core2 -Os -fomit-frame-pointer2016102320161009
1159560refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2016102320161009
1159678refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2016102320161009
1161392refgcc -m32 -Os -fomit-frame-pointer2016102320161009
1162230refgcc -m32 -march=k8 -Os -fomit-frame-pointer2016102320161009
1162962refgcc -m32 -march=athlon -Os -fomit-frame-pointer2016102320161009
1165723refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1169566refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2016102320161009
1174019refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2016102320161009
1176560refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2016102320161009
1176603refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2016102320161009
1183336refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2016102320161009
1184293refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2016102320161009
1206974refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2016102320161009
1207563refgcc -m32 -march=k6 -Os -fomit-frame-pointer2016102320161009
1207765refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2016102320161009
1215200refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2016102320161009
1215255refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2016102320161009
1215579refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2016102320161009

Test failure

Implementation: crypto_aead/scream10v3/ref
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 ref sse
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer ref 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 ref 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 ref sse
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer ref sse
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer ref 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

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: 48, 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=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
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