Implementation notes: x86, hydra1, crypto_aead/scream12v1

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: scream12v1
TimeImplementationCompilerBenchmark dateSUPERCOP version
644478refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
645192refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016102320161009
646408refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2016102320161009
660589refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2016102320161009
669013refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2016102320161009
669854refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2016102320161009
674133refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
677016refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2016102320161009
677971refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016102320161009
681722refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2016102320161009
687034refgcc -m32 -O3 -fomit-frame-pointer2016102320161009
689472refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016102320161009
690185refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
693031refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2016102320161009
695342refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2016102320161009
696360refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016102320161009
696696refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2016102320161009
697437refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016102320161009
698003refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016102320161009
698910refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2016102320161009
699088refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2016102320161009
699501refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2016102320161009
700325refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016102320161009
708486refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016102320161009
709339refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016102320161009
712358refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016102320161009
717474refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016102320161009
718214refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016102320161009
743384refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016102320161009
744738refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2016102320161009
749945refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016102320161009
750031refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016102320161009
750787refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2016102320161009
752199refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016102320161009
752424refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016102320161009
752580refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016102320161009
753050refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2016102320161009
753273refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2016102320161009
758555refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2016102320161009
759832refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016102320161009
767083refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2016102320161009
767397refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2016102320161009
769355refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2016102320161009
774574refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2016102320161009
776853refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2016102320161009
776880refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2016102320161009
776944refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2016102320161009
777042refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016102320161009
777070refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2016102320161009
784869refgcc -funroll-loops -m32 -O -fomit-frame-pointer2016102320161009
790515refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016102320161009
791461refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016102320161009
794189refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016102320161009
796581refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2016102320161009
797613refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2016102320161009
797685refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2016102320161009
798883refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016102320161009
803850refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2016102320161009
817115refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016102320161009
817611refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2016102320161009
818738refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2016102320161009
827427refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2016102320161009
828000refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2016102320161009
828190refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2016102320161009
847304refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2016102320161009
848130refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2016102320161009
848418refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2016102320161009
848834refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2016102320161009
855192refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2016102320161009
863526refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2016102320161009
863545refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2016102320161009
863914refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2016102320161009
943880refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2016102320161009
1136203refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2016102320161009
1137618refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2016102320161009
1137642refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016102320161009
1138670refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2016102320161009
1142320refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016102320161009
1144878refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016102320161009
1157211refgcc -m32 -O2 -fomit-frame-pointer2016102320161009
1160781refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
1161352refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2016102320161009
1161544refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2016102320161009
1163792refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016102320161009
1171725refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016102320161009
1184152refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2016102320161009
1184552refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016102320161009
1190509refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2016102320161009
1196571refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2016102320161009
1203368refgcc -m32 -march=nocona -O -fomit-frame-pointer2016102320161009
1203389refgcc -m32 -march=prescott -O -fomit-frame-pointer2016102320161009
1210507refgcc -m32 -march=athlon -O -fomit-frame-pointer2016102320161009
1212853refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016102320161009
1213323refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016102320161009
1214675refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2016102320161009
1215871refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016102320161009
1216109refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2016102320161009
1216415refgcc -m32 -march=barcelona -O -fomit-frame-pointer2016102320161009
1219528refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2016102320161009
1221133refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2016102320161009
1221807refgcc -m32 -march=i486 -O -fomit-frame-pointer2016102320161009
1221853refgcc -m32 -march=i386 -O -fomit-frame-pointer2016102320161009
1222367refgcc -m32 -march=k8 -O -fomit-frame-pointer2016102320161009
1225269refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2016102320161009
1233403refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016102320161009
1233835refgcc -m32 -march=core2 -O -fomit-frame-pointer2016102320161009
1234096refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016102320161009
1242375refgcc -m32 -O -fomit-frame-pointer2016102320161009
1242703refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2016102320161009
1242704refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2016102320161009
1244701refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2016102320161009
1244917refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2016102320161009
1245493refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2016102320161009
1248685refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2016102320161009
1249461refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2016102320161009
1249541refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2016102320161009
1249568refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2016102320161009
1252131refgcc -m32 -march=corei7 -O -fomit-frame-pointer2016102320161009
1254180refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1254367refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016102320161009
1254851refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2016102320161009
1255048refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2016102320161009
1257182refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2016102320161009
1257680refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2016102320161009
1257735refgcc -m32 -march=nocona -Os -fomit-frame-pointer2016102320161009
1257741refgcc -m32 -march=k6 -O -fomit-frame-pointer2016102320161009
1259383refgcc -m32 -march=prescott -Os -fomit-frame-pointer2016102320161009
1263563refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2016102320161009
1263690refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2016102320161009
1263891refgcc -m32 -march=athlon -Os -fomit-frame-pointer2016102320161009
1264074refgcc -m32 -Os -fomit-frame-pointer2016102320161009
1267224refgcc -m32 -march=i486 -Os -fomit-frame-pointer2016102320161009
1269597refgcc -m32 -march=i386 -Os -fomit-frame-pointer2016102320161009
1271189refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2016102320161009
1272279refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2016102320161009
1276522refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2016102320161009
1276600refgcc -m32 -march=k6 -Os -fomit-frame-pointer2016102320161009
1279002refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2016102320161009
1279565refgcc -m32 -march=pentium -O -fomit-frame-pointer2016102320161009
1281410refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1281526refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2016102320161009
1283974refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2016102320161009
1284291refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2016102320161009
1284384refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2016102320161009
1284642refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2016102320161009
1285869refgcc -m32 -march=k8 -Os -fomit-frame-pointer2016102320161009
1286189refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2016102320161009
1289035refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2016102320161009
1289410refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016102320161009
1292667refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2016102320161009
1292739refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2016102320161009
1294790refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2016102320161009
1294798refgcc -m32 -march=core2 -Os -fomit-frame-pointer2016102320161009
1298056refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2016102320161009
1299079refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2016102320161009
1300379refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2016102320161009
1308890refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2016102320161009
1310984refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2016102320161009
1311592refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016102320161009
1312606refgcc -m32 -march=pentium -Os -fomit-frame-pointer2016102320161009

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: 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/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: 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/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