Implementation notes: amd64, glyme, crypto_aead/scream12v2

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: scream12v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
95892	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170205	20170105
95896	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170205	20170105
95904	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170205	20170105
96004	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170205	20170105
96008	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
100036	`sse`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
103752	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
103852	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170205	20170105
103876	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170205	20170105
103876	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170205	20170105
105420	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170205	20170105
107468	`sse`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
111308	`sse`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
111376	`sse`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
116412	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170205	20170105
116416	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170205	20170105
116416	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170205	20170105
116556	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170205	20170105
116652	`sse`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
116676	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
155584	`sse`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170205	20170105
156172	`sse`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105
156364	`sse`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170205	20170105
156440	`sse`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
156784	`sse`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170205	20170105
156992	`sse`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170205	20170105
579916	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
581448	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
584084	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
584084	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
587628	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
587996	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
587996	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
590744	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
593456	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
593460	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
593892	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
594048	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
598980	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
604412	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170205	20170105
604416	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170205	20170105
604624	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170205	20170105
604676	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
604696	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170205	20170105
606860	`ref`	`gcc -O3 -fomit-frame-pointer`	20170205	20170105
606860	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170205	20170105
606884	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
609784	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
609784	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170205	20170105
610768	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170205	20170105
672716	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
672816	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
673204	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
674808	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
677760	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
677764	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
678744	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170205	20170105
678808	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
679388	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
679884	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
679892	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
681352	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170205	20170105
681984	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
682248	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
684956	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
691780	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170205	20170105
692364	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170205	20170105
697228	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
697420	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170205	20170105
698084	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170205	20170105
699732	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
701780	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
701868	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170205	20170105
701868	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170205	20170105
783480	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
783584	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
786744	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
789864	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
791256	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170205	20170105
792380	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
794104	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
795948	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170205	20170105
796720	`ref`	`gcc -O2 -fomit-frame-pointer`	20170205	20170105
796772	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
796776	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170205	20170105
797468	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
797760	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
798120	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170205	20170105
798328	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170205	20170105
798712	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170205	20170105
800580	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170205	20170105
801356	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
801484	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20170205	20170105
802492	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
804896	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170205	20170105
805680	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170205	20170105
806244	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
807400	`ref`	`gcc -O -fomit-frame-pointer`	20170205	20170105
808100	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170205	20170105
808100	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
810116	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170205	20170105
811460	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
812344	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170205	20170105
823708	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170205	20170105
929680	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
929680	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
931220	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
931552	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105
931564	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170205	20170105
932564	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170205	20170105
932608	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
933088	`ref`	`gcc -Os -fomit-frame-pointer`	20170205	20170105
933168	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
933844	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
936284	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
937816	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
940796	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
941932	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
942000	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170205	20170105
942000	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
942136	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170205	20170105
942264	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
942380	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
942812	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
942956	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170205	20170105
944028	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
950032	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170205	20170105
950836	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170205	20170105
3085048	`ref`	`cc`	20170205	20170105
3361008	`ref`	`gcc`	20170205	20170105
3372540	`ref`	`gcc -funroll-loops`	20170205	20170105

Compiler output

Implementation: crypto_aead/scream12v2/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/scream12v2/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/scream12v2/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