Implementation notes: x86, h3neo, crypto_aead/scream12v3

Computer: h3neo
Architecture: x86
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream12v3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
701735? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016111020161009
707947? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O2_-fomit-frame-pointer2016111020161009
708885? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O2_-fomit-frame-pointer2016111020161009
711858? ? ?? ? ?refgcc_-funroll-loops_-m32_-O2_-fomit-frame-pointer2016111020161009
720978? ? ?? ? ?refgcc_-funroll-loops_-m32_-O3_-fomit-frame-pointer2016111020161009
734305? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016111020161009
736797? ? ?? ? ?refgcc_-m32_-O3_-fomit-frame-pointer2016111020161009
737754? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016111020161009
737941? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016111020161009
742553? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016111020161009
742805? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O2_-fomit-frame-pointer2016111020161009
742905? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O2_-fomit-frame-pointer2016111020161009
744386? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O3_-fomit-frame-pointer2016111020161009
746162? ? ?? ? ?refgcc_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016111020161009
748746? ? ?? ? ?refgcc_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016111020161009
749041? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016111020161009
751910? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016111020161009
754737? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016111020161009
755975? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016111020161009
756248? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016111020161009
757330? ? ?? ? ?refgcc_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016111020161009
757379? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016111020161009
757715? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016111020161009
758064? ? ?? ? ?refgcc_-m32_-march=k8_-O3_-fomit-frame-pointer2016111020161009
766161? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016111020161009
771436? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O3_-fomit-frame-pointer2016111020161009
776288? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016111020161009
784533? ? ?? ? ?refgcc_-m32_-march=athlon_-O3_-fomit-frame-pointer2016111020161009
787243? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O3_-fomit-frame-pointer2016111020161009
788211? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O3_-fomit-frame-pointer2016111020161009
796987? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016111020161009
798468? ? ?? ? ?refgcc_-m32_-march=nocona_-O3_-fomit-frame-pointer2016111020161009
798653? ? ?? ? ?refgcc_-m32_-march=prescott_-O3_-fomit-frame-pointer2016111020161009
812245? ? ?? ? ?refgcc_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016111020161009
813307? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O_-fomit-frame-pointer2016111020161009
813865? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O_-fomit-frame-pointer2016111020161009
822879? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O_-fomit-frame-pointer2016111020161009
823077? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016111020161009
823340? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O_-fomit-frame-pointer2016111020161009
823582? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016111020161009
824052? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O_-fomit-frame-pointer2016111020161009
824282? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O_-fomit-frame-pointer2016111020161009
824993? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O_-fomit-frame-pointer2016111020161009
831183? ? ?? ? ?refgcc_-funroll-loops_-m32_-O_-fomit-frame-pointer2016111020161009
848528? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O_-fomit-frame-pointer2016111020161009
911644? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O2_-fomit-frame-pointer2016111020161009
931760? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016111020161009
932707? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O3_-fomit-frame-pointer2016111020161009
937029? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O2_-fomit-frame-pointer2016111020161009
937943? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016111020161009
938272? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016111020161009
946567? ? ?? ? ?refgcc_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016111020161009
946699? ? ?? ? ?refgcc_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016111020161009
946912? ? ?? ? ?refgcc_-m32_-march=k6_-O3_-fomit-frame-pointer2016111020161009
952070? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016111020161009
952401? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016111020161009
953031? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O3_-fomit-frame-pointer2016111020161009
959596? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O2_-fomit-frame-pointer2016111020161009
959951? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016111020161009
965350? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016111020161009
965417? ? ?? ? ?refgcc_-m32_-march=pentium_-O3_-fomit-frame-pointer2016111020161009
978605? ? ?? ? ?refgcc_-m32_-march=i486_-O3_-fomit-frame-pointer2016111020161009
986888? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O3_-fomit-frame-pointer2016111020161009
1005693? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O_-fomit-frame-pointer2016111020161009
1007263? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O3_-fomit-frame-pointer2016111020161009
1007296? ? ?? ? ?refgcc_-m32_-march=i386_-O3_-fomit-frame-pointer2016111020161009
1017902? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O_-fomit-frame-pointer2016111020161009
1018882? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O_-fomit-frame-pointer2016111020161009
1018971? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O_-fomit-frame-pointer2016111020161009
1033998? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016111020161009
1034227? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O_-fomit-frame-pointer2016111020161009
1048353? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O_-fomit-frame-pointer2016111020161009
1058714? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O2_-fomit-frame-pointer2016111020161009
1144422? ? ?? ? ?refgcc_-m32_-march=k8_-O2_-fomit-frame-pointer2016111020161009
1152622? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016111020161009
1152816? ? ?? ? ?refgcc_-m32_-march=athlon_-O2_-fomit-frame-pointer2016111020161009
1168607? ? ?? ? ?refgcc_-m32_-march=nocona_-O2_-fomit-frame-pointer2016111020161009
1171773? ? ?? ? ?refgcc_-m32_-march=prescott_-O2_-fomit-frame-pointer2016111020161009
1174804? ? ?? ? ?refgcc_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016111020161009
1175646? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O2_-fomit-frame-pointer2016111020161009
1176373? ? ?? ? ?refgcc_-m32_-march=core2_-O2_-fomit-frame-pointer2016111020161009
1187734? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016111020161009
1196231? ? ?? ? ?refgcc_-m32_-O_-fomit-frame-pointer2016111020161009
1201469? ? ?? ? ?refgcc_-m32_-O2_-fomit-frame-pointer2016111020161009
1203315? ? ?? ? ?refgcc_-m32_-march=corei7_-O2_-fomit-frame-pointer2016111020161009
1205244? ? ?? ? ?refgcc_-m32_-march=barcelona_-O_-fomit-frame-pointer2016111020161009
1205909? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016111020161009
1206169? ? ?? ? ?refgcc_-m32_-march=core2_-O_-fomit-frame-pointer2016111020161009
1207165? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O_-fomit-frame-pointer2016111020161009
1208375? ? ?? ? ?refgcc_-m32_-march=corei7_-O_-fomit-frame-pointer2016111020161009
1208991? ? ?? ? ?refgcc_-m32_-march=k8_-O_-fomit-frame-pointer2016111020161009
1209652? ? ?? ? ?refgcc_-m32_-march=athlon_-O_-fomit-frame-pointer2016111020161009
1213785? ? ?? ? ?refgcc_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016111020161009
1228559? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O_-fomit-frame-pointer2016111020161009
1237172? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016111020161009
1237422? ? ?? ? ?refgcc_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016111020161009
1240789? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016111020161009
1241422? ? ?? ? ?refgcc_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016111020161009
1242935? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016111020161009
1243365? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016111020161009
1246993? ? ?? ? ?refgcc_-m32_-march=i486_-O2_-fomit-frame-pointer2016111020161009
1250267? ? ?? ? ?refgcc_-m32_-march=pentium4_-O_-fomit-frame-pointer2016111020161009
1269167? ? ?? ? ?refgcc_-m32_-march=prescott_-O_-fomit-frame-pointer2016111020161009
1269171? ? ?? ? ?refgcc_-m32_-march=nocona_-O_-fomit-frame-pointer2016111020161009
1269390? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016111020161009
1271180? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016111020161009
1272824? ? ?? ? ?refgcc_-m32_-march=i386_-O2_-fomit-frame-pointer2016111020161009
1287171? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016111020161009
1287345? ? ?? ? ?refgcc_-m32_-march=pentium3_-O_-fomit-frame-pointer2016111020161009
1293098? ? ?? ? ?refgcc_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016111020161009
1294800? ? ?? ? ?refgcc_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016111020161009
1296548? ? ?? ? ?refgcc_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016111020161009
1305733? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016111020161009
1305753? ? ?? ? ?refgcc_-m32_-march=i486_-O_-fomit-frame-pointer2016111020161009
1310386? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-Os_-fomit-frame-pointer2016111020161009
1310661? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-Os_-fomit-frame-pointer2016111020161009
1316897? ? ?? ? ?refgcc_-m32_-march=i386_-O_-fomit-frame-pointer2016111020161009
1317101? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016111020161009
1319872? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016111020161009
1320507? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-Os_-fomit-frame-pointer2016111020161009
1320725? ? ?? ? ?refgcc_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016111020161009
1321146? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-Os_-fomit-frame-pointer2016111020161009
1321179? ? ?? ? ?refgcc_-m32_-march=prescott_-Os_-fomit-frame-pointer2016111020161009
1321332? ? ?? ? ?refgcc_-m32_-march=nocona_-Os_-fomit-frame-pointer2016111020161009
1321645? ? ?? ? ?refgcc_-m32_-march=pentium2_-O_-fomit-frame-pointer2016111020161009
1330048? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016111020161009
1330070? ? ?? ? ?refgcc_-m32_-march=pentium_-O_-fomit-frame-pointer2016111020161009
1337974? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016111020161009
1343726? ? ?? ? ?refgcc_-m32_-march=pentium_-O2_-fomit-frame-pointer2016111020161009
1350222? ? ?? ? ?refgcc_-m32_-march=i486_-Os_-fomit-frame-pointer2016111020161009
1355356? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016111020161009
1355988? ? ?? ? ?refgcc_-m32_-march=i386_-Os_-fomit-frame-pointer2016111020161009
1356343? ? ?? ? ?refgcc_-m32_-march=k6-3_-O_-fomit-frame-pointer2016111020161009
1356418? ? ?? ? ?refgcc_-m32_-march=k6-2_-O_-fomit-frame-pointer2016111020161009
1357036? ? ?? ? ?refgcc_-m32_-march=k6_-O_-fomit-frame-pointer2016111020161009
1359162? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-Os_-fomit-frame-pointer2016111020161009
1362574? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016111020161009
1367278? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016111020161009
1367570? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-Os_-fomit-frame-pointer2016111020161009
1370497? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016111020161009
1372750? ? ?? ? ?refgcc_-m32_-march=pentium_-Os_-fomit-frame-pointer2016111020161009
1375401? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-Os_-fomit-frame-pointer2016111020161009
1375597? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016111020161009
1375650? ? ?? ? ?refgcc_-m32_-march=core2_-Os_-fomit-frame-pointer2016111020161009
1375950? ? ?? ? ?refgcc_-m32_-march=corei7_-Os_-fomit-frame-pointer2016111020161009
1376109? ? ?? ? ?refgcc_-m32_-march=k8_-Os_-fomit-frame-pointer2016111020161009
1381709? ? ?? ? ?refgcc_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016111020161009
1386867? ? ?? ? ?refgcc_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016111020161009
1386945? ? ?? ? ?refgcc_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016111020161009
1387972? ? ?? ? ?refgcc_-m32_-march=k6_-O2_-fomit-frame-pointer2016111020161009
1393843? ? ?? ? ?refgcc_-m32_-Os_-fomit-frame-pointer2016111020161009
1396224? ? ?? ? ?refgcc_-funroll-loops_-m32_-Os_-fomit-frame-pointer2016111020161009
1396696? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-Os_-fomit-frame-pointer2016111020161009
1396983? ? ?? ? ?refgcc_-m32_-march=athlon_-Os_-fomit-frame-pointer2016111020161009
1424504? ? ?? ? ?refgcc_-m32_-march=k6_-Os_-fomit-frame-pointer2016111020161009
1431219? ? ?? ? ?refgcc_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016111020161009
1431252? ? ?? ? ?refgcc_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016111020161009
1439894? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016111020161009
1458195? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-Os_-fomit-frame-pointer2016111020161009
1461058? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016111020161009

Test failure

Implementation: crypto_aead/scream12v3/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/scream12v3/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/scream12v3/sse
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:202:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:202:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:203:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:207:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:208:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:215:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:216:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:220:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 48, namely:
CompilerImplementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer sse
gcc -m32 -march=k8 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k8 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k8 -O -fomit-frame-pointer sse
gcc -m32 -march=k8 -Os -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer sse
gcc -m32 -march=nocona -O2 -fomit-frame-pointer sse
gcc -m32 -march=nocona -O3 -fomit-frame-pointer sse
gcc -m32 -march=nocona -O -fomit-frame-pointer sse
gcc -m32 -march=nocona -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -O -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -O -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer sse
gcc -m32 -march=prescott -O2 -fomit-frame-pointer sse
gcc -m32 -march=prescott -O3 -fomit-frame-pointer sse
gcc -m32 -march=prescott -O -fomit-frame-pointer sse
gcc -m32 -march=prescott -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream12v3/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