Implementation notes: x86, h9trinity, crypto_aead/scream10v2

Computer: h9trinity
Architecture: x86
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream10v2
TimeImplementationCompilerBenchmark dateSUPERCOP version
576837refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121220171020
584380refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017121220171020
585752refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017121220171020
585956refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017121220171020
586264refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017121220171020
587053refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017121220171020
589413refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121220171020
595291refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017121220171020
596715refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017121220171020
598181refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017121220171020
605749refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017121220171020
606176refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017121220171020
608306refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017121220171020
608440refgcc -m32 -O3 -fomit-frame-pointer2017121220171020
608964refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017121220171020
609986refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017121220171020
610363refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017121220171020
611333refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017121220171020
612345refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017121220171020
614151refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017121220171020
617687refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2017121220171020
621506refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2017121220171020
631690refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121220171020
633447refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121220171020
633475refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121220171020
634437refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121220171020
634660refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121220171020
636412refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017121220171020
637967refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017121220171020
638054refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017121220171020
638077refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017121220171020
639948refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2017121220171020
641246refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017121220171020
641400refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2017121220171020
641768refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017121220171020
646273refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121220171020
652127refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121220171020
653946refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017121220171020
655691refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017121220171020
655804refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121220171020
656184refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017121220171020
656434refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017121220171020
661791refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017121220171020
662802refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017121220171020
663942refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017121220171020
669278refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017121220171020
679380refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017121220171020
695309refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017121220171020
695729refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017121220171020
696730refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017121220171020
697447refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017121220171020
822793refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017121220171020
823193refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017121220171020
826089refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017121220171020
826577refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017121220171020
827175refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017121220171020
828887refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017121220171020
833968refgcc -m32 -O2 -fomit-frame-pointer2017121220171020
835829refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017121220171020
838502refgcc -m32 -march=prescott -O -fomit-frame-pointer2017121220171020
842138refgcc -m32 -march=nocona -O -fomit-frame-pointer2017121220171020
842220refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017121220171020
842495refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017121220171020
843081refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017121220171020
843475refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017121220171020
843721refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2017121220171020
846055refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2017121220171020
856424refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2017121220171020
859236refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017121220171020
861135refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2017121220171020
861354refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017121220171020
864326refgcc -m32 -march=athlon -O -fomit-frame-pointer2017121220171020
865282refgcc -m32 -O -fomit-frame-pointer2017121220171020
868928refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017121220171020
870471refgcc -m32 -march=core2 -O -fomit-frame-pointer2017121220171020
873521refgcc -m32 -march=k8 -O -fomit-frame-pointer2017121220171020
875140refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017121220171020
883901refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017121220171020
887275refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017121220171020
900514refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017121220171020
900928refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017121220171020
912827refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017121220171020
915161refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017121220171020
915726refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017121220171020
916252refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017121220171020
916667refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017121220171020
918182refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017121220171020
918950refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017121220171020
927799refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017121220171020
929197refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017121220171020
931407refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017121220171020
943465refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017121220171020
955954refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121220171020
956167refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017121220171020
959913refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017121220171020
962531refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017121220171020
968971refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121220171020
969255refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017121220171020
969526refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121220171020
973250refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017121220171020
974013refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017121220171020
975113refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121220171020
984961refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017121220171020
985258refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017121220171020
985505refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017121220171020
988842refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121220171020
988867refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121220171020
993047refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017121220171020
1002208refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017121220171020
1006575refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017121220171020
1031184refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121220171020
1032389refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017121220171020
1044808refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017121220171020
1056158refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121220171020
1056776refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017121220171020
1058112refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017121220171020
1059400refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017121220171020
1060110refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017121220171020
1062972refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017121220171020
1064274refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017121220171020
1069335refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017121220171020
1086824refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017121220171020
1086987refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017121220171020
1185340refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017121220171020
1189156refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017121220171020
1195998refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017121220171020
1200274refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017121220171020
1210576refgcc -m32 -march=i386 -O -fomit-frame-pointer2017121220171020
1220217refgcc -m32 -march=i486 -O -fomit-frame-pointer2017121220171020
1239071refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017121220171020
1239078refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017121220171020
1239775refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017121220171020
1240749refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017121220171020
1241628refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017121220171020
1243983refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017121220171020
1246487refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017121220171020
1246868refgcc -m32 -march=pentium -O -fomit-frame-pointer2017121220171020
1248096refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017121220171020
1248276refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017121220171020
1248648refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017121220171020
1250576refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017121220171020
1251419refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017121220171020
1255196refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017121220171020
1259761refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017121220171020
1261638refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017121220171020
1262423refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017121220171020
1262567refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017121220171020
1263589refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017121220171020
1264115refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017121220171020
1265416refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017121220171020
1265930refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017121220171020
1266256refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017121220171020
1266597refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017121220171020
1266659refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017121220171020
1267257refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017121220171020
1268577refgcc -m32 -Os -fomit-frame-pointer2017121220171020
1270646refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017121220171020
1270754refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017121220171020
1271908refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121220171020
1274613refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017121220171020
1275644refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2017121220171020
1276763refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2017121220171020
1280206refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017121220171020
1282290refgcc -m32 -march=k6 -O -fomit-frame-pointer2017121220171020
1282973refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017121220171020
1283035refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017121220171020
1283593refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017121220171020
1284007refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017121220171020
1284654refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017121220171020
1296715refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017121220171020
1299933refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017121220171020
1300009refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017121220171020

Test failure

Implementation: crypto_aead/scream10v2/sse
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 34, namely:
CompilerImplementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer sse
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer sse
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer sse
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer sse
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer 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 -O3 -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer sse
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer sse
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer sse
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer sse
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer sse
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer sse
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer sse
gcc -m32 -march=corei7 -O -fomit-frame-pointer sse
gcc -m32 -march=corei7 -Os -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream10v2/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/scream10v2/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: 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/scream10v2/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