Implementation notes: x86, latour, crypto_aead/scream12v3

Computer: latour
Architecture: x86
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream12v3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
726003	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20170725	20170718
726993	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20170725	20170718
727191	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20170725	20170718
730566	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20170725	20170718
794592	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20170725	20170718
795321	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20170725	20170718
796896	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20170725	20170718
798831	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20170725	20170718
800658	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20170725	20170718
806013	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20170725	20170718
807165	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20170725	20170718
807183	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20170725	20170718
810981	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20170725	20170718
812484	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20170725	20170718
815796	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20170725	20170718
823194	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20170725	20170718
854982	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20170725	20170718
855783	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20170725	20170718
858600	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20170725	20170718
858843	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20170725	20170718
859392	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20170725	20170718
860247	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20170725	20170718
861426	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20170725	20170718
863982	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20170725	20170718
893781	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20170725	20170718
894213	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170725	20170718
897327	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20170725	20170718
898398	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20170725	20170718
898596	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20170725	20170718
898713	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20170725	20170718
899478	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20170725	20170718
900054	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20170725	20170718
901440	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20170725	20170718
901485	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20170725	20170718
903564	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20170725	20170718
904401	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20170725	20170718
904527	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20170725	20170718
904761	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20170725	20170718
904905	`ref`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20170725	20170718
904941	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20170725	20170718
905643	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20170725	20170718
907200	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20170725	20170718
907479	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20170725	20170718
907776	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170725	20170718
908271	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20170725	20170718
908361	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20170725	20170718
911880	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20170725	20170718
912978	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20170725	20170718
914265	`ref`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20170725	20170718
914544	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20170725	20170718
915849	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20170725	20170718
916443	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20170725	20170718
920835	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20170725	20170718
921060	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20170725	20170718
921843	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20170725	20170718
921978	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20170725	20170718
922086	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20170725	20170718
922509	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20170725	20170718
929997	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20170725	20170718
932220	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20170725	20170718
932346	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20170725	20170718
933840	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20170725	20170718
934173	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20170725	20170718
934803	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20170725	20170718
939276	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20170725	20170718
948600	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20170725	20170718
953433	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20170725	20170718
955404	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20170725	20170718
958554	`ref`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20170725	20170718
959850	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20170725	20170718
960354	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20170725	20170718
961506	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20170725	20170718
962199	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20170725	20170718
962235	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170725	20170718
962631	`ref`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20170725	20170718
962802	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20170725	20170718
963342	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20170725	20170718
963396	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20170725	20170718
966879	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20170725	20170718
968283	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20170725	20170718
977670	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170725	20170718
978750	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170725	20170718
1009575	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20170725	20170718
1009872	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20170725	20170718
1025379	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20170725	20170718
1027107	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20170725	20170718
1035126	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20170725	20170718
1043199	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20170725	20170718
1074213	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20170725	20170718
1128843	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20170725	20170718
1131066	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20170725	20170718
1139715	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20170725	20170718
1146321	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20170725	20170718
1186641	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20170725	20170718
1192761	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20170725	20170718
1193832	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20170725	20170718
1214991	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20170725	20170718
1221093	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20170725	20170718
1230201	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170725	20170718
1230642	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20170725	20170718
1231335	`ref`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20170725	20170718
1232289	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20170725	20170718
1237788	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20170725	20170718
1239678	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20170725	20170718
1242072	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20170725	20170718
1242234	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20170725	20170718
1243314	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20170725	20170718
1245672	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20170725	20170718
1247382	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20170725	20170718
1249938	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20170725	20170718
1252350	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20170725	20170718
1259712	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20170725	20170718
1260801	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20170725	20170718
1265742	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20170725	20170718
1265877	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20170725	20170718
1265958	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170725	20170718
1267614	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20170725	20170718
1272555	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20170725	20170718
1275669	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20170725	20170718
1277397	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20170725	20170718
1278225	`ref`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20170725	20170718
1279494	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20170725	20170718
1280844	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20170725	20170718
1284138	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20170725	20170718
1284192	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20170725	20170718
1284507	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20170725	20170718
1285965	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20170725	20170718
1286172	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20170725	20170718
1288683	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20170725	20170718
1289286	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20170725	20170718
1289916	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20170725	20170718
1292760	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20170725	20170718
1294965	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20170725	20170718
1296999	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20170725	20170718
1298196	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20170725	20170718
1300275	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20170725	20170718
1302174	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20170725	20170718
1303704	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20170725	20170718
1306458	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20170725	20170718
1307943	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20170725	20170718
1310112	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20170725	20170718
1316007	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20170725	20170718
1317690	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20170725	20170718
1322640	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20170725	20170718
1324809	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20170725	20170718
1326789	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20170725	20170718
1327194	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20170725	20170718
1333863	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20170725	20170718
1334421	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20170725	20170718
1335717	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20170725	20170718
1351215	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20170725	20170718
1351539	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20170725	20170718
1357434	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20170725	20170718
1364940	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20170725	20170718
1369917	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20170725	20170718
1381122	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20170725	20170718
1435284	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20170725	20170718
1438785	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20170725	20170718
1464111	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20170725	20170718
1501830	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20170725	20170718
1640790	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20170725	20170718
1641267	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20170725	20170718
1645803	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20170725	20170718
1645839	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20170725	20170718
1656909	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20170725	20170718
1669941	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20170725	20170718
2849895	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20170725	20170718

Test failure

Implementation: crypto_aead/scream12v3/sse
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 29, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	sse
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	sse
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	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	sse
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	sse
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	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: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:202:8: error: incompatible types when assigning to type 'v16qi' 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' 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' 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' 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' 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' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
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:202:8: error: incompatible types when assigning to type 'v16qi' 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' 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' 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' 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' 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' 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' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:221:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: ...
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:202:8: error: incompatible types when assigning to type 'v16qi' 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' 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' 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' 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' 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' 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' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:221:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
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