Implementation notes: x86, h2atom, crypto_aead/scream12v1

Computer: h2atom
Architecture: x86
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20161009
Operation: crypto_aead
Primitive: scream12v1
TimeImplementationCompilerBenchmark dateSUPERCOP version
1232870refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2016120420161009
1249660refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016120420161009
1259650refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016120420161009
1260430refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016120420161009
1263010refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2016120420161009
1267640refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2016120420161009
1282140refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016120420161009
1282730refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2016120420161009
1282850refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016120420161009
1285180refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2016120420161009
1286310refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016120420161009
1287150refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016120420161009
1289370refgcc -m32 -O3 -fomit-frame-pointer2016120420161009
1292150refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2016120420161009
1292340refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2016120420161009
1296780refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016120420161009
1296860refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2016120420161009
1314570refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2016120420161009
1314600refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016120420161009
1357620refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2016120420161009
1357620refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2016120420161009
1357750refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2016120420161009
1360360refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2016120420161009
1361210refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2016120420161009
1361220refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2016120420161009
1361370refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2016120420161009
1369180refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016120420161009
1374770refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2016120420161009
1374770refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2016120420161009
1375320refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2016120420161009
1375330refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016120420161009
1375560refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2016120420161009
1375920refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016120420161009
1376010refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2016120420161009
1389250refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016120420161009
1389990refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016120420161009
1391700refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2016120420161009
1393010refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016120420161009
1398750refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2016120420161009
1398970refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016120420161009
1416780refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2016120420161009
1430570refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2016120420161009
1437300refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2016120420161009
1437340refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2016120420161009
1438110refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2016120420161009
1451480refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2016120420161009
1456070refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2016120420161009
1459520refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2016120420161009
1459740refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016120420161009
1465410refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016120420161009
1468410refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016120420161009
1468490refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2016120420161009
1471840refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016120420161009
1483970refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016120420161009
1486760refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016120420161009
1490710refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016120420161009
1490740refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016120420161009
1499130refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2016120420161009
1501760refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2016120420161009
1563250refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2016120420161009
1577370refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2016120420161009
1581270refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2016120420161009
1586430refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2016120420161009
1642850refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016120420161009
1670000refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2016120420161009
1670090refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2016120420161009
1672350refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2016120420161009
1673050refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016120420161009
1673430refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016120420161009
1674260refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2016120420161009
1677620refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016120420161009
1727120refgcc -funroll-loops -m32 -O -fomit-frame-pointer2016120420161009
1793480refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2016120420161009
1793650refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2016120420161009
2060490refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016120420161009
2261600refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016120420161009
2274980refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2016120420161009
2275040refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016120420161009
2327770refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2016120420161009
2327830refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016120420161009
2327910refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016120420161009
2329630refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016120420161009
2329840refgcc -m32 -O2 -fomit-frame-pointer2016120420161009
2354350refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2016120420161009
2354460refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2016120420161009
2354650refgcc -m32 -march=k6 -Os -fomit-frame-pointer2016120420161009
2370310refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2016120420161009
2370320refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2016120420161009
2370460refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2016120420161009
2374270refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2016120420161009
2374660refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2016120420161009
2384590refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016120420161009
2389590refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2016120420161009
2389800refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2016120420161009
2394710refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2016120420161009
2447990refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016120420161009
2466540refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2016120420161009
2466560refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016120420161009
2491380refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016120420161009
2491960refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2016120420161009
2494440refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2016120420161009
2499810refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2016120420161009
2499850refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2016120420161009
2503170refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2016120420161009
2503550refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2016120420161009
2510930refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2016120420161009
2517020refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2016120420161009
2517780refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2016120420161009
2517830refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2016120420161009
2523730refgcc -m32 -march=athlon -Os -fomit-frame-pointer2016120420161009
2523750refgcc -m32 -Os -fomit-frame-pointer2016120420161009
2525490refgcc -m32 -march=k8 -Os -fomit-frame-pointer2016120420161009
2525530refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2016120420161009
2533330refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2016120420161009
2533420refgcc -m32 -march=core2 -Os -fomit-frame-pointer2016120420161009
2533500refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2016120420161009
2535770refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016120420161009
2543200refgcc -m32 -march=i486 -O -fomit-frame-pointer2016120420161009
2554850refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016120420161009
2560180refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2016120420161009
2560210refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2016120420161009
2560350refgcc -m32 -march=k6 -O -fomit-frame-pointer2016120420161009
2562030refgcc -m32 -march=nocona -O -fomit-frame-pointer2016120420161009
2564730refgcc -m32 -march=prescott -O -fomit-frame-pointer2016120420161009
2568750refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016120420161009
2568910refgcc -m32 -march=pentium -Os -fomit-frame-pointer2016120420161009
2570110refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2016120420161009
2578270refgcc -m32 -march=i386 -Os -fomit-frame-pointer2016120420161009
2578340refgcc -m32 -march=i486 -Os -fomit-frame-pointer2016120420161009
2580440refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2016120420161009
2580950refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2016120420161009
2581880refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2016120420161009
2582170refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2016120420161009
2582200refgcc -m32 -march=nocona -Os -fomit-frame-pointer2016120420161009
2582400refgcc -m32 -march=prescott -Os -fomit-frame-pointer2016120420161009
2583560refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2016120420161009
2584100refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2016120420161009
2585080refgcc -m32 -march=barcelona -O -fomit-frame-pointer2016120420161009
2590490refgcc -m32 -march=k8 -O -fomit-frame-pointer2016120420161009
2595750refgcc -m32 -march=i386 -O -fomit-frame-pointer2016120420161009
2638300refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2016120420161009
2641530refgcc -m32 -march=corei7 -O -fomit-frame-pointer2016120420161009
2643590refgcc -m32 -march=athlon -O -fomit-frame-pointer2016120420161009
2644120refgcc -m32 -march=pentium -O -fomit-frame-pointer2016120420161009
2644210refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2016120420161009
2647990refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2016120420161009
2648350refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2016120420161009
2655260refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2016120420161009
2655820refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2016120420161009
2687840refgcc -m32 -O -fomit-frame-pointer2016120420161009
2691150refgcc -m32 -march=core2 -O -fomit-frame-pointer2016120420161009
2694320refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016120420161009
2697990refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016120420161009
2737080refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2016120420161009
2737410refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2016120420161009
2742720refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2016120420161009
2742860refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2016120420161009
2804260refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2016120420161009
2805180refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2016120420161009
2853100refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2016120420161009
2853620refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2016120420161009

Test failure

Implementation: crypto_aead/scream12v1/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/scream12v1/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/scream12v1/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/scream12v1/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