Implementation notes: x86, h2atom, crypto_aead/scream10v3

Computer: h2atom
Architecture: x86
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20161009
Operation: crypto_aead
Primitive: scream10v3
TimeImplementationCompilerBenchmark dateSUPERCOP version
1067110refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016120420161009
1115940refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2016120420161009
1130750refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2016120420161009
1138970refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2016120420161009
1140070refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016120420161009
1140440refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016120420161009
1155300refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2016120420161009
1156110refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016120420161009
1156120refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2016120420161009
1156180refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016120420161009
1165030refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2016120420161009
1170860refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2016120420161009
1178900refgcc -m32 -O3 -fomit-frame-pointer2016120420161009
1180530refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2016120420161009
1182980refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016120420161009
1183480refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016120420161009
1184350refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2016120420161009
1184440refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016120420161009
1206270refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2016120420161009
1206330refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2016120420161009
1206360refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2016120420161009
1217920refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2016120420161009
1218020refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016120420161009
1219190refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016120420161009
1219700refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2016120420161009
1227770refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016120420161009
1235190refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2016120420161009
1235490refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016120420161009
1236800refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2016120420161009
1236890refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2016120420161009
1238200refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2016120420161009
1241920refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2016120420161009
1251020refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016120420161009
1251980refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2016120420161009
1259340refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016120420161009
1259440refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016120420161009
1280650refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2016120420161009
1281310refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2016120420161009
1281500refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2016120420161009
1282710refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2016120420161009
1282710refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2016120420161009
1282750refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2016120420161009
1283730refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2016120420161009
1299440refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016120420161009
1299580refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016120420161009
1299860refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2016120420161009
1301350refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016120420161009
1309980refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016120420161009
1316840refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2016120420161009
1321180refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2016120420161009
1321470refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2016120420161009
1322590refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2016120420161009
1323050refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016120420161009
1325890refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016120420161009
1330420refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016120420161009
1341440refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2016120420161009
1350130refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2016120420161009
1354950refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016120420161009
1355000refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016120420161009
1361790refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2016120420161009
1371610refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2016120420161009
1409270refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2016120420161009
1412490refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2016120420161009
1481990refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016120420161009
1482490refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2016120420161009
1482510refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2016120420161009
1483690refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2016120420161009
1491960refgcc -funroll-loops -m32 -O -fomit-frame-pointer2016120420161009
1497150refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2016120420161009
1498970refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016120420161009
1500020refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016120420161009
1619920refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2016120420161009
1619950refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2016120420161009
1625380refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016120420161009
1758480refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016120420161009
1907080refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016120420161009
1907810refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2016120420161009
1908430refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2016120420161009
1939450refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2016120420161009
1939450refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016120420161009
1939570refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016120420161009
1940670refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016120420161009
1943670refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016120420161009
1948510refgcc -m32 -O2 -fomit-frame-pointer2016120420161009
2039820refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2016120420161009
2039820refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2016120420161009
2043120refgcc -m32 -march=k6 -Os -fomit-frame-pointer2016120420161009
2069490refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2016120420161009
2069920refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016120420161009
2103170refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2016120420161009
2107070refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2016120420161009
2107490refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2016120420161009
2139170refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2016120420161009
2140190refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2016120420161009
2140370refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2016120420161009
2143410refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2016120420161009
2151850refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2016120420161009
2151930refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016120420161009
2155300refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2016120420161009
2155590refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016120420161009
2155810refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2016120420161009
2156000refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2016120420161009
2157410refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2016120420161009
2157440refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2016120420161009
2157450refgcc -m32 -march=k6 -O -fomit-frame-pointer2016120420161009
2162470refgcc -m32 -march=athlon -O -fomit-frame-pointer2016120420161009
2165870refgcc -m32 -march=barcelona -O -fomit-frame-pointer2016120420161009
2166420refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2016120420161009
2168280refgcc -m32 -O -fomit-frame-pointer2016120420161009
2169370refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016120420161009
2169830refgcc -m32 -march=corei7 -O -fomit-frame-pointer2016120420161009
2170330refgcc -m32 -march=k8 -O -fomit-frame-pointer2016120420161009
2173740refgcc -m32 -march=nocona -O -fomit-frame-pointer2016120420161009
2173790refgcc -m32 -march=prescott -O -fomit-frame-pointer2016120420161009
2175070refgcc -m32 -march=core2 -O -fomit-frame-pointer2016120420161009
2176590refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016120420161009
2176860refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016120420161009
2179580refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016120420161009
2182410refgcc -m32 -march=i486 -O -fomit-frame-pointer2016120420161009
2183720refgcc -m32 -march=pentium -Os -fomit-frame-pointer2016120420161009
2184400refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016120420161009
2186850refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2016120420161009
2192610refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2016120420161009
2193110refgcc -m32 -march=core2 -Os -fomit-frame-pointer2016120420161009
2195340refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2016120420161009
2195710refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016120420161009
2198610refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2016120420161009
2199180refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2016120420161009
2199200refgcc -m32 -march=pentium -O -fomit-frame-pointer2016120420161009
2199670refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2016120420161009
2201580refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2016120420161009
2201820refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2016120420161009
2201850refgcc -m32 -march=k8 -Os -fomit-frame-pointer2016120420161009
2201890refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2016120420161009
2202660refgcc -m32 -Os -fomit-frame-pointer2016120420161009
2202810refgcc -m32 -march=i486 -Os -fomit-frame-pointer2016120420161009
2202820refgcc -m32 -march=i386 -Os -fomit-frame-pointer2016120420161009
2202910refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2016120420161009
2204430refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2016120420161009
2205130refgcc -m32 -march=prescott -Os -fomit-frame-pointer2016120420161009
2205700refgcc -m32 -march=athlon -Os -fomit-frame-pointer2016120420161009
2206130refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2016120420161009
2206500refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2016120420161009
2207440refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2016120420161009
2208080refgcc -m32 -march=nocona -Os -fomit-frame-pointer2016120420161009
2208740refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2016120420161009
2213630refgcc -m32 -march=i386 -O -fomit-frame-pointer2016120420161009
2227340refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2016120420161009
2233500refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2016120420161009
2248920refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2016120420161009
2251600refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2016120420161009
2253710refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2016120420161009
2257150refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2016120420161009
2266130refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2016120420161009
2266560refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2016120420161009
2268730refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2016120420161009
2269030refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2016120420161009
2419920refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2016120420161009
2421940refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2016120420161009
2421970refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2016120420161009
2424030refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2016120420161009

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: 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/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: 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/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