Implementation notes: x86, h4e450, crypto_aead/scream12v3

Computer: h4e450
Architecture: x86
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream12v3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
905099	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20171010	20170725
933816	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20171010	20170725
934615	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20171010	20170725
939579	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20171010	20170725
941032	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20171010	20170725
941730	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20171010	20170725
950309	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20171010	20170725
951463	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20171010	20170725
955942	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20171010	20170725
956375	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20171010	20170725
956840	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20171010	20170725
958407	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20171010	20170725
961685	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20171010	20170725
962650	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20171010	20170725
963813	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20171010	20170725
963841	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20171010	20170725
970277	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20171010	20170725
971370	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20171010	20170725
972249	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20171010	20170725
973108	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20171010	20170725
975754	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20171010	20170725
976425	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20171010	20170725
976961	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20171010	20170725
977355	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20171010	20170725
980081	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20171010	20170725
981008	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20171010	20170725
987800	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20171010	20170725
987919	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20171010	20170725
1012457	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20171010	20170725
1012477	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20171010	20170725
1014363	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20171010	20170725
1016248	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20171010	20170725
1017322	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20171010	20170725
1017336	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20171010	20170725
1018847	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20171010	20170725
1019787	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20171010	20170725
1027453	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20171010	20170725
1035609	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20171010	20170725
1037732	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20171010	20170725
1039718	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20171010	20170725
1041561	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20171010	20170725
1041732	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20171010	20170725
1042259	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20171010	20170725
1061221	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20171010	20170725
1062742	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20171010	20170725
1065283	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20171010	20170725
1065952	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20171010	20170725
1080948	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20171010	20170725
1080948	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20171010	20170725
1083299	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20171010	20170725
1083760	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20171010	20170725
1090610	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20171010	20170725
1100432	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20171010	20170725
1109287	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20171010	20170725
1115771	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20171010	20170725
1116953	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20171010	20170725
1117846	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20171010	20170725
1119708	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20171010	20170725
1120605	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20171010	20170725
1125479	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20171010	20170725
1126876	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20171010	20170725
1127541	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20171010	20170725
1142346	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20171010	20170725
1159983	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20171010	20170725
1160231	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20171010	20170725
1160264	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20171010	20170725
1161228	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20171010	20170725
1161717	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20171010	20170725
1166220	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20171010	20170725
1167351	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20171010	20170725
1171692	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20171010	20170725
1172984	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20171010	20170725
1173065	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20171010	20170725
1175135	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20171010	20170725
1181207	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20171010	20170725
1182513	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20171010	20170725
1183914	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20171010	20170725
1187600	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20171010	20170725
1188265	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20171010	20170725
1189818	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20171010	20170725
1189975	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20171010	20170725
1195105	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20171010	20170725
1199793	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20171010	20170725
1214181	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20171010	20170725
1225614	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20171010	20170725
1226796	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20171010	20170725
1227243	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20171010	20170725
1228355	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20171010	20170725
1234896	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20171010	20170725
1234905	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20171010	20170725
1245080	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20171010	20170725
1255482	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20171010	20170725
1265043	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20171010	20170725
1276914	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20171010	20170725
1281336	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20171010	20170725
1281393	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20171010	20170725
1281778	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20171010	20170725
1297410	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20171010	20170725
1302707	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20171010	20170725
1344948	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20171010	20170725
1345870	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20171010	20170725
1347052	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20171010	20170725
1351622	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20171010	20170725
1376218	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20171010	20170725
1376645	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20171010	20170725
1377286	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20171010	20170725
1377382	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20171010	20170725
1378056	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20171010	20170725
1378070	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20171010	20170725
1380768	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20171010	20170725
1382316	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20171010	20170725
1384393	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20171010	20170725
1384478	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20171010	20170725
1384535	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20171010	20170725
1385252	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20171010	20170725
1388201	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20171010	20170725
1388492	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20171010	20170725
1390073	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20171010	20170725
1397645	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20171010	20170725
1397806	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20171010	20170725
1403525	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20171010	20170725
1404452	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20171010	20170725
1424259	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20171010	20170725
1425157	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20171010	20170725
1430942	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20171010	20170725
1431375	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20171010	20170725
1439834	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20171010	20170725
1440357	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20171010	20170725
1443036	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20171010	20170725
1443074	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20171010	20170725
1443492	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20171010	20170725
1447030	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20171010	20170725
1453956	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20171010	20170725
1458483	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20171010	20170725
1458506	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20171010	20170725
1461670	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20171010	20170725
1461812	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20171010	20170725
1463893	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20171010	20170725
1464117	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20171010	20170725
1464197	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20171010	20170725
1471474	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20171010	20170725
1472681	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20171010	20170725
1472728	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20171010	20170725
1473198	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20171010	20170725
1499722	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20171010	20170725
1501541	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20171010	20170725
1504358	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20171010	20170725
1504762	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20171010	20170725
1506733	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20171010	20170725
1506928	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20171010	20170725
1507052	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20171010	20170725
1507227	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20171010	20170725
1507323	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20171010	20170725
1507768	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20171010	20170725
1508438	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20171010	20170725
1508990	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20171010	20170725
1509098	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20171010	20170725
1529072	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20171010	20170725
1538111	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20171010	20170725
1540031	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20171010	20170725
1540278	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20171010	20170725

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: 35, namely:

Compiler	Implementations
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/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:

Compiler	Implementations
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

Number of similar (compiler,implementation) pairs: 44, namely:

Compiler	Implementations
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/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:

Compiler	Implementations
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