Implementation notes: amd64, glyme, crypto_aead/scream12v1

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: scream12v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
96420	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170205	20170105
96476	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170205	20170105
96488	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170205	20170105
96792	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
96896	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170205	20170105
100484	`sse`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
104480	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
104584	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170205	20170105
104600	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170205	20170105
104880	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170205	20170105
105080	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170205	20170105
108332	`sse`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
113008	`sse`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
113048	`sse`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
115720	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170205	20170105
115792	`sse`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
115936	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170205	20170105
115996	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170205	20170105
116040	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
116624	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170205	20170105
157544	`sse`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170205	20170105
157552	`sse`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170205	20170105
157596	`sse`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105
158388	`sse`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
158728	`sse`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170205	20170105
158760	`sse`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170205	20170105
577324	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
577640	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
577640	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
579232	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
588096	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
588736	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
588736	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
589124	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
593504	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
593668	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
594392	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
594516	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
598388	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
604500	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170205	20170105
604500	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
604940	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170205	20170105
605108	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170205	20170105
605724	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170205	20170105
606932	`ref`	`gcc -O3 -fomit-frame-pointer`	20170205	20170105
606932	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
606932	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170205	20170105
610252	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
610252	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170205	20170105
610904	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170205	20170105
672452	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
672640	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
672908	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
673752	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
676752	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
678148	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
678568	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
678648	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
678648	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
678816	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170205	20170105
678988	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
678992	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
679120	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170205	20170105
679532	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
679704	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
692276	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170205	20170105
692940	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170205	20170105
696960	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170205	20170105
697244	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170205	20170105
697248	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170205	20170105
697268	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
697388	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
697664	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170205	20170105
700992	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
785976	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
789308	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
791620	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170205	20170105
793908	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
795320	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20170205	20170105
796372	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
796728	`ref`	`gcc -O2 -fomit-frame-pointer`	20170205	20170105
796728	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170205	20170105
796740	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
797728	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
798148	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
798168	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
798624	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170205	20170105
798700	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170205	20170105
799860	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
801384	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170205	20170105
803628	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
803824	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170205	20170105
803872	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170205	20170105
803872	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
804652	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
805416	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170205	20170105
806000	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170205	20170105
806888	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170205	20170105
808204	`ref`	`gcc -O -fomit-frame-pointer`	20170205	20170105
808376	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170205	20170105
809016	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170205	20170105
812336	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
813696	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170205	20170105
814616	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
912704	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
927236	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
932824	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
934884	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
935924	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170205	20170105
936380	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
937000	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170205	20170105
937092	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105
938176	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170205	20170105
938492	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
938660	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170205	20170105
938828	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170205	20170105
939376	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
940548	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170205	20170105
940832	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170205	20170105
940972	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
941052	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
941068	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
941656	`ref`	`gcc -Os -fomit-frame-pointer`	20170205	20170105
946612	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
947380	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
948580	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
949584	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
950000	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
3120528	`ref`	`cc`	20170205	20170105
3354928	`ref`	`gcc -funroll-loops`	20170205	20170105
3369484	`ref`	`gcc`	20170205	20170105

Compiler output

Implementation: crypto_aead/scream12v1/sse
Compiler: cc

scream.c: scream.c:185:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:204:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:211:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
cc	sse
clang -O3 -fomit-frame-pointer -Qunused-arguments	sse
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	sse
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	sse
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	sse

Compiler output

Implementation: crypto_aead/scream12v1/sse
Compiler: gcc

Number of similar (compiler,implementation) pairs: 70, namely:

Compiler	Implementations
gcc	sse
gcc -O2 -fomit-frame-pointer	sse
gcc -O3 -fomit-frame-pointer	sse
gcc -O -fomit-frame-pointer	sse
gcc -Os -fomit-frame-pointer	sse
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	sse
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	sse
gcc -fno-schedule-insns -O -fomit-frame-pointer	sse
gcc -fno-schedule-insns -Os -fomit-frame-pointer	sse
gcc -funroll-loops	sse
gcc -funroll-loops -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -O -fomit-frame-pointer	sse
gcc -funroll-loops -Os -fomit-frame-pointer	sse
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	sse
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	sse
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	sse
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	sse
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	sse
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	sse
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	sse
gcc -m64 -O2 -fomit-frame-pointer	sse
gcc -m64 -O3 -fomit-frame-pointer	sse
gcc -m64 -O -fomit-frame-pointer	sse
gcc -m64 -Os -fomit-frame-pointer	sse
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	sse
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	sse
gcc -m64 -march=k8 -O -fomit-frame-pointer	sse
gcc -m64 -march=k8 -Os -fomit-frame-pointer	sse
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	sse
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	sse
gcc -m64 -march=nocona -O -fomit-frame-pointer	sse
gcc -m64 -march=nocona -Os -fomit-frame-pointer	sse
gcc -march=barcelona -O2 -fomit-frame-pointer	sse
gcc -march=barcelona -O3 -fomit-frame-pointer	sse
gcc -march=barcelona -O -fomit-frame-pointer	sse
gcc -march=barcelona -Os -fomit-frame-pointer	sse
gcc -march=k8 -O2 -fomit-frame-pointer	sse
gcc -march=k8 -O3 -fomit-frame-pointer	sse
gcc -march=k8 -O -fomit-frame-pointer	sse
gcc -march=k8 -Os -fomit-frame-pointer	sse
gcc -march=nocona -O2 -fomit-frame-pointer	sse
gcc -march=nocona -O3 -fomit-frame-pointer	sse
gcc -march=nocona -O -fomit-frame-pointer	sse
gcc -march=nocona -Os -fomit-frame-pointer	sse

Compiler output

Implementation: crypto_aead/scream12v1/sse
Compiler: gcc -m64 -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:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	sse
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	sse
gcc -m64 -march=barcelona -O -fomit-frame-pointer	sse
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	sse