Implementation notes: x86, h2atom, crypto_aead/scream10v2

Computer: h2atom
Architecture: x86
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20161009
Operation: crypto_aead
Primitive: scream10v2
TimeImplementationCompilerBenchmark dateSUPERCOP version
1034040refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016120420161009
1068980refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2016120420161009
1076580refgcc -m32 -O3 -fomit-frame-pointer2016120420161009
1091400refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016120420161009
1091960refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016120420161009
1093350refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2016120420161009
1096360refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016120420161009
1097720refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2016120420161009
1099120refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2016120420161009
1100160refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016120420161009
1100720refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2016120420161009
1101490refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016120420161009
1102600refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016120420161009
1102630refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2016120420161009
1118550refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2016120420161009
1119420refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016120420161009
1131710refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016120420161009
1131910refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2016120420161009
1133090refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2016120420161009
1156060refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2016120420161009
1156110refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2016120420161009
1156130refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2016120420161009
1157180refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2016120420161009
1158100refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2016120420161009
1158300refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2016120420161009
1172860refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2016120420161009
1172900refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2016120420161009
1174220refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2016120420161009
1175660refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2016120420161009
1182370refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016120420161009
1185270refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016120420161009
1185460refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2016120420161009
1188180refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2016120420161009
1188790refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016120420161009
1190000refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016120420161009
1190030refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2016120420161009
1194550refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2016120420161009
1194730refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016120420161009
1205220refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2016120420161009
1205380refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2016120420161009
1206010refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2016120420161009
1210420refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016120420161009
1211010refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016120420161009
1211900refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016120420161009
1215760refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016120420161009
1223780refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2016120420161009
1235630refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016120420161009
1239230refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2016120420161009
1242280refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2016120420161009
1244930refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2016120420161009
1245850refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016120420161009
1249430refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2016120420161009
1251000refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016120420161009
1253800refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016120420161009
1260520refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2016120420161009
1261840refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2016120420161009
1263510refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016120420161009
1266420refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016120420161009
1293440refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2016120420161009
1299100refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2016120420161009
1301720refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2016120420161009
1315850refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2016120420161009
1319820refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2016120420161009
1335010refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2016120420161009
1335710refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016120420161009
1339660refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016120420161009
1418410refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016120420161009
1419020refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2016120420161009
1419030refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2016120420161009
1420020refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2016120420161009
1465160refgcc -funroll-loops -m32 -O -fomit-frame-pointer2016120420161009
1481560refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016120420161009
1523500refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2016120420161009
1523520refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2016120420161009
1751600refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016120420161009
1966940refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016120420161009
1973030refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2016120420161009
1973320refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016120420161009
1981360refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016120420161009
1984080refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2016120420161009
1984150refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016120420161009
1984280refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016120420161009
1985970refgcc -m32 -O2 -fomit-frame-pointer2016120420161009
2010670refgcc -m32 -march=k6 -Os -fomit-frame-pointer2016120420161009
2010700refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2016120420161009
2010740refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2016120420161009
2016640refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2016120420161009
2025180refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016120420161009
2026670refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2016120420161009
2034020refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2016120420161009
2038110refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2016120420161009
2038190refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2016120420161009
2055830refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2016120420161009
2055880refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2016120420161009
2056370refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2016120420161009
2075670refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016120420161009
2075860refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2016120420161009
2076360refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2016120420161009
2076410refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016120420161009
2093820refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2016120420161009
2094020refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016120420161009
2124050refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2016120420161009
2124210refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2016120420161009
2124550refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2016120420161009
2127960refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2016120420161009
2131760refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2016120420161009
2136370refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2016120420161009
2141030refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2016120420161009
2145470refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2016120420161009
2147970refgcc -m32 -march=athlon -Os -fomit-frame-pointer2016120420161009
2148180refgcc -m32 -Os -fomit-frame-pointer2016120420161009
2151190refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2016120420161009
2151190refgcc -m32 -march=k8 -Os -fomit-frame-pointer2016120420161009
2158100refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2016120420161009
2158110refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016120420161009
2158130refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2016120420161009
2158360refgcc -m32 -march=core2 -Os -fomit-frame-pointer2016120420161009
2163100refgcc -m32 -march=i486 -O -fomit-frame-pointer2016120420161009
2165300refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2016120420161009
2165520refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2016120420161009
2165570refgcc -m32 -march=k6 -O -fomit-frame-pointer2016120420161009
2168530refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016120420161009
2173360refgcc -m32 -march=nocona -O -fomit-frame-pointer2016120420161009
2173540refgcc -m32 -march=prescott -O -fomit-frame-pointer2016120420161009
2180250refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016120420161009
2180790refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2016120420161009
2183460refgcc -m32 -march=pentium -Os -fomit-frame-pointer2016120420161009
2189830refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2016120420161009
2189900refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2016120420161009
2192550refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2016120420161009
2192820refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2016120420161009
2193020refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2016120420161009
2193210refgcc -m32 -march=k8 -O -fomit-frame-pointer2016120420161009
2197250refgcc -m32 -march=i386 -Os -fomit-frame-pointer2016120420161009
2198120refgcc -m32 -march=barcelona -O -fomit-frame-pointer2016120420161009
2199530refgcc -m32 -march=i486 -Os -fomit-frame-pointer2016120420161009
2200130refgcc -m32 -march=nocona -Os -fomit-frame-pointer2016120420161009
2200620refgcc -m32 -march=prescott -Os -fomit-frame-pointer2016120420161009
2202100refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2016120420161009
2209660refgcc -m32 -march=i386 -O -fomit-frame-pointer2016120420161009
2239750refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2016120420161009
2239800refgcc -m32 -march=corei7 -O -fomit-frame-pointer2016120420161009
2241220refgcc -m32 -march=athlon -O -fomit-frame-pointer2016120420161009
2241960refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2016120420161009
2243240refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2016120420161009
2246910refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2016120420161009
2249270refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2016120420161009
2260160refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2016120420161009
2260450refgcc -m32 -march=pentium -O -fomit-frame-pointer2016120420161009
2273700refgcc -m32 -march=core2 -O -fomit-frame-pointer2016120420161009
2273950refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016120420161009
2274010refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016120420161009
2275650refgcc -m32 -O -fomit-frame-pointer2016120420161009
2312800refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2016120420161009
2312860refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2016120420161009
2322940refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2016120420161009
2325640refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2016120420161009
2381050refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2016120420161009
2381090refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2016120420161009
2417980refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2016120420161009
2421850refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2016120420161009

Test failure

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

Number of similar (compiler,implementation) pairs: 35, 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 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
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