Implementation notes: x86, hydra1, crypto_aead/scream10v1

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: scream10v1
TimeImplementationCompilerBenchmark dateSUPERCOP version
544389refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2016102320161009
546576refgcc -m32 -O3 -fomit-frame-pointer2016102320161009
569096refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016102320161009
570283refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2016102320161009
571215refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2016102320161009
572080refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
572749refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2016102320161009
577691refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
579810refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016102320161009
581464refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2016102320161009
585006refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2016102320161009
586650refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2016102320161009
588842refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016102320161009
589875refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
590472refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016102320161009
590525refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016102320161009
591573refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016102320161009
591606refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2016102320161009
592280refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2016102320161009
592293refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2016102320161009
593733refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016102320161009
593797refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2016102320161009
594104refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016102320161009
594216refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016102320161009
594309refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016102320161009
594878refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2016102320161009
595844refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016102320161009
602889refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016102320161009
604931refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016102320161009
609666refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016102320161009
616121refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016102320161009
617753refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016102320161009
624789refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2016102320161009
626341refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2016102320161009
627104refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2016102320161009
650292refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2016102320161009
650331refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2016102320161009
651879refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2016102320161009
652641refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016102320161009
653512refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2016102320161009
659997refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016102320161009
662953refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2016102320161009
663096refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2016102320161009
664004refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2016102320161009
665152refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016102320161009
665733refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2016102320161009
667653refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2016102320161009
668557refgcc -funroll-loops -m32 -O -fomit-frame-pointer2016102320161009
669927refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016102320161009
669947refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016102320161009
677522refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2016102320161009
678269refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2016102320161009
679869refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2016102320161009
680432refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2016102320161009
681403refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2016102320161009
681550refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2016102320161009
682293refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016102320161009
682926refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016102320161009
683201refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016102320161009
683605refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2016102320161009
694411refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2016102320161009
702264refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2016102320161009
702421refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2016102320161009
702596refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2016102320161009
702654refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2016102320161009
709584refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2016102320161009
722606refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2016102320161009
722763refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2016102320161009
728325refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016102320161009
728984refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2016102320161009
744526refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2016102320161009
748176refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2016102320161009
775774refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2016102320161009
961429refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2016102320161009
961805refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2016102320161009
962000refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016102320161009
965228refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2016102320161009
971501refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016102320161009
972830refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016102320161009
985368refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2016102320161009
985696refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016102320161009
985917refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2016102320161009
986336refgcc -m32 -O2 -fomit-frame-pointer2016102320161009
991939refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
999675refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016102320161009
1005939refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2016102320161009
1009291refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2016102320161009
1011290refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2016102320161009
1011632refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016102320161009
1018976refgcc -m32 -march=prescott -O -fomit-frame-pointer2016102320161009
1021530refgcc -m32 -march=athlon -O -fomit-frame-pointer2016102320161009
1023589refgcc -m32 -march=k8 -O -fomit-frame-pointer2016102320161009
1026677refgcc -m32 -march=barcelona -O -fomit-frame-pointer2016102320161009
1027144refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016102320161009
1027325refgcc -m32 -march=nocona -O -fomit-frame-pointer2016102320161009
1027533refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016102320161009
1031043refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2016102320161009
1031165refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016102320161009
1032011refgcc -m32 -march=i386 -O -fomit-frame-pointer2016102320161009
1032975refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2016102320161009
1036805refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2016102320161009
1039261refgcc -m32 -march=i486 -O -fomit-frame-pointer2016102320161009
1041565refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2016102320161009
1043891refgcc -m32 -march=core2 -O -fomit-frame-pointer2016102320161009
1044068refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2016102320161009
1048114refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016102320161009
1049912refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016102320161009
1050276refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2016102320161009
1052335refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2016102320161009
1052784refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2016102320161009
1055613refgcc -m32 -O -fomit-frame-pointer2016102320161009
1055663refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2016102320161009
1056115refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2016102320161009
1056602refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2016102320161009
1058573refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2016102320161009
1058768refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2016102320161009
1059067refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2016102320161009
1061098refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2016102320161009
1061704refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2016102320161009
1062459refgcc -m32 -march=prescott -Os -fomit-frame-pointer2016102320161009
1063008refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1063573refgcc -m32 -march=nocona -Os -fomit-frame-pointer2016102320161009
1065117refgcc -m32 -march=corei7 -O -fomit-frame-pointer2016102320161009
1065671refgcc -m32 -march=k6 -O -fomit-frame-pointer2016102320161009
1066361refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016102320161009
1066808refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2016102320161009
1067096refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2016102320161009
1068808refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2016102320161009
1069440refgcc -m32 -march=athlon -Os -fomit-frame-pointer2016102320161009
1070525refgcc -m32 -march=i386 -Os -fomit-frame-pointer2016102320161009
1071541refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2016102320161009
1071622refgcc -m32 -march=i486 -Os -fomit-frame-pointer2016102320161009
1078800refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2016102320161009
1079947refgcc -m32 -Os -fomit-frame-pointer2016102320161009
1080517refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1081901refgcc -m32 -march=k6 -Os -fomit-frame-pointer2016102320161009
1082634refgcc -m32 -march=k8 -Os -fomit-frame-pointer2016102320161009
1084779refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2016102320161009
1085405refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2016102320161009
1085688refgcc -m32 -march=pentium -O -fomit-frame-pointer2016102320161009
1086629refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2016102320161009
1086694refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2016102320161009
1086718refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2016102320161009
1086939refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2016102320161009
1088920refgcc -m32 -march=core2 -Os -fomit-frame-pointer2016102320161009
1090067refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2016102320161009
1090570refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2016102320161009
1090682refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2016102320161009
1090808refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2016102320161009
1091282refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2016102320161009
1093040refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2016102320161009
1093163refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2016102320161009
1093184refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016102320161009
1094392refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2016102320161009
1098261refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2016102320161009
1106157refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016102320161009
1106206refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2016102320161009
1106680refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2016102320161009
1110994refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2016102320161009
1113419refgcc -m32 -march=pentium -Os -fomit-frame-pointer2016102320161009

Test failure

Implementation: crypto_aead/scream10v1/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/scream10v1/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:182:10: note: in expansion of macro 'shift_right'
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
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:185:10: 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:185:8: 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:186:8: 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:190:8: 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/scream10v1/sse
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: 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:185:8: 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:186:8: 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:190:8: 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:191:8: 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:198:7: 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:199:7: 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:203:7: 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/scream10v1/sse
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: 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:185:8: 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:186:8: 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:190:8: 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:191:8: 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:198:7: 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:199:7: 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:203:7: 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:185:10: 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:185:8: 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:186:8: 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:190:8: 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:191:8: 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:198:7: 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:199:7: 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:203:7: 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