Implementation notes: x86, h2atom, crypto_aead/scream10v1

Computer: h2atom
Architecture: x86
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20161009
Operation: crypto_aead
Primitive: scream10v1
TimeImplementationCompilerBenchmark dateSUPERCOP version
1035400refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016120420161009
1073930refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2016120420161009
1077770refgcc -m32 -O3 -fomit-frame-pointer2016120420161009
1088660refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016120420161009
1092150refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016120420161009
1093560refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2016120420161009
1095460refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016120420161009
1097500refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016120420161009
1099420refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2016120420161009
1099620refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016120420161009
1099740refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2016120420161009
1100020refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2016120420161009
1101780refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2016120420161009
1102700refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016120420161009
1119000refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2016120420161009
1120030refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016120420161009
1129570refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016120420161009
1131060refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2016120420161009
1133380refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2016120420161009
1154110refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2016120420161009
1154240refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2016120420161009
1155110refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2016120420161009
1157010refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2016120420161009
1157370refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2016120420161009
1157460refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2016120420161009
1172770refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2016120420161009
1172830refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2016120420161009
1172920refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2016120420161009
1174140refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2016120420161009
1183270refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016120420161009
1183550refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016120420161009
1187760refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2016120420161009
1188830refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016120420161009
1188960refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2016120420161009
1189290refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2016120420161009
1190680refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016120420161009
1192720refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016120420161009
1192800refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2016120420161009
1205470refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2016120420161009
1205480refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2016120420161009
1205670refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2016120420161009
1209450refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016120420161009
1210810refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016120420161009
1211500refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016120420161009
1215600refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016120420161009
1225910refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2016120420161009
1235310refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2016120420161009
1236270refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016120420161009
1243860refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2016120420161009
1244790refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2016120420161009
1246270refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016120420161009
1250900refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016120420161009
1251280refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2016120420161009
1253730refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016120420161009
1260540refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2016120420161009
1261030refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016120420161009
1261830refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2016120420161009
1263990refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016120420161009
1291940refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2016120420161009
1298160refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2016120420161009
1302920refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2016120420161009
1316050refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2016120420161009
1319420refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2016120420161009
1334570refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016120420161009
1335390refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2016120420161009
1338700refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016120420161009
1417770refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2016120420161009
1418260refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2016120420161009
1418280refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2016120420161009
1421100refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016120420161009
1465190refgcc -funroll-loops -m32 -O -fomit-frame-pointer2016120420161009
1479920refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016120420161009
1524360refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2016120420161009
1524370refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2016120420161009
1752180refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016120420161009
1936270refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016120420161009
1936480refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2016120420161009
1957010refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016120420161009
1976020refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016120420161009
1976250refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016120420161009
1978600refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2016120420161009
1980530refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016120420161009
1981680refgcc -m32 -O2 -fomit-frame-pointer2016120420161009
2001760refgcc -m32 -march=k6 -Os -fomit-frame-pointer2016120420161009
2005020refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2016120420161009
2005020refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2016120420161009
2010820refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2016120420161009
2011320refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2016120420161009
2013610refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2016120420161009
2019140refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2016120420161009
2019200refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2016120420161009
2019350refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016120420161009
2030440refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2016120420161009
2036210refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2016120420161009
2046230refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2016120420161009
2077650refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016120420161009
2094380refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2016120420161009
2097390refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016120420161009
2114850refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016120420161009
2115250refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2016120420161009
2118080refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2016120420161009
2123100refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2016120420161009
2123470refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2016120420161009
2126970refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2016120420161009
2129920refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2016120420161009
2130260refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2016120420161009
2137900refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2016120420161009
2138010refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2016120420161009
2138180refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2016120420161009
2142940refgcc -m32 -Os -fomit-frame-pointer2016120420161009
2144810refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2016120420161009
2144810refgcc -m32 -march=k8 -Os -fomit-frame-pointer2016120420161009
2145700refgcc -m32 -march=athlon -Os -fomit-frame-pointer2016120420161009
2151270refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016120420161009
2151280refgcc -m32 -march=core2 -Os -fomit-frame-pointer2016120420161009
2151300refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2016120420161009
2153870refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2016120420161009
2155930refgcc -m32 -march=i486 -O -fomit-frame-pointer2016120420161009
2168060refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016120420161009
2169560refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2016120420161009
2169560refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2016120420161009
2169570refgcc -m32 -march=k6 -O -fomit-frame-pointer2016120420161009
2174130refgcc -m32 -march=prescott -O -fomit-frame-pointer2016120420161009
2176680refgcc -m32 -march=nocona -O -fomit-frame-pointer2016120420161009
2181450refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2016120420161009
2182910refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016120420161009
2183120refgcc -m32 -march=pentium -Os -fomit-frame-pointer2016120420161009
2188460refgcc -m32 -march=i486 -Os -fomit-frame-pointer2016120420161009
2191110refgcc -m32 -march=barcelona -O -fomit-frame-pointer2016120420161009
2191210refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2016120420161009
2191970refgcc -m32 -march=i386 -Os -fomit-frame-pointer2016120420161009
2192300refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2016120420161009
2192590refgcc -m32 -march=prescott -Os -fomit-frame-pointer2016120420161009
2192700refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2016120420161009
2193810refgcc -m32 -march=k8 -O -fomit-frame-pointer2016120420161009
2194290refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2016120420161009
2194780refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2016120420161009
2195450refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2016120420161009
2196290refgcc -m32 -march=nocona -Os -fomit-frame-pointer2016120420161009
2201430refgcc -m32 -march=i386 -O -fomit-frame-pointer2016120420161009
2234600refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2016120420161009
2238870refgcc -m32 -march=athlon -O -fomit-frame-pointer2016120420161009
2239400refgcc -m32 -march=corei7 -O -fomit-frame-pointer2016120420161009
2245140refgcc -m32 -march=pentium -O -fomit-frame-pointer2016120420161009
2245520refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2016120420161009
2246830refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2016120420161009
2246880refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2016120420161009
2255610refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2016120420161009
2255620refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2016120420161009
2277370refgcc -m32 -O -fomit-frame-pointer2016120420161009
2279580refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016120420161009
2283050refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016120420161009
2283480refgcc -m32 -march=core2 -O -fomit-frame-pointer2016120420161009
2321820refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2016120420161009
2324420refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2016120420161009
2329170refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2016120420161009
2330440refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2016120420161009
2374300refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2016120420161009
2380790refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2016120420161009
2420280refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2016120420161009
2420520refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2016120420161009

Test failure

Implementation: crypto_aead/scream10v1/ref
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 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/scream10v1/sse
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:16:32: warning: implicit declaration of function '__builtin_ia32_psrldi128' [-Wimplicit-function-declaration]
scream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
scream.c: ^
scream.c: scream.c:182:10: note: in expansion of macro 'shift_right'
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:182:5: error: can't convert between vector values of different size
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:183:5: error: can't convert between vector values of different size
scream.c: t1 = shift_right(in[2]) & V(0xf);
scream.c: ^
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 96, namely:
CompilerImplementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer sse
gcc -m32 -O2 -fomit-frame-pointer sse
gcc -m32 -O3 -fomit-frame-pointer sse
gcc -m32 -O -fomit-frame-pointer sse
gcc -m32 -Os -fomit-frame-pointer sse
gcc -m32 -march=athlon -O2 -fomit-frame-pointer sse
gcc -m32 -march=athlon -O3 -fomit-frame-pointer sse
gcc -m32 -march=athlon -O -fomit-frame-pointer sse
gcc -m32 -march=athlon -Os -fomit-frame-pointer sse
gcc -m32 -march=i386 -O2 -fomit-frame-pointer sse
gcc -m32 -march=i386 -O3 -fomit-frame-pointer sse
gcc -m32 -march=i386 -O -fomit-frame-pointer sse
gcc -m32 -march=i386 -Os -fomit-frame-pointer sse
gcc -m32 -march=i486 -O2 -fomit-frame-pointer sse
gcc -m32 -march=i486 -O3 -fomit-frame-pointer sse
gcc -m32 -march=i486 -O -fomit-frame-pointer sse
gcc -m32 -march=i486 -Os -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -O -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -O -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer sse
gcc -m32 -march=k6 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k6 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k6 -O -fomit-frame-pointer sse
gcc -m32 -march=k6 -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -O -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -O -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium -O -fomit-frame-pointer sse
gcc -m32 -march=pentium -Os -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream10v1/sse
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 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/scream10v1/sse
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer sse
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer sse
gcc -m32 -march=barcelona -O -fomit-frame-pointer sse
gcc -m32 -march=barcelona -Os -fomit-frame-pointer sse