Implementation notes: amd64, glyme, crypto_aead/scream10v3

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: scream10v3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
83704	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170205	20170105
83712	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
83864	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170205	20170105
83868	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170205	20170105
83896	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170205	20170105
87860	`sse`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
90848	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
90876	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170205	20170105
91032	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170205	20170105
91316	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170205	20170105
91388	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170205	20170105
94496	`sse`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
96344	`sse`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
97540	`sse`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
99292	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170205	20170105
99296	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170205	20170105
99432	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
99436	`sse`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
99772	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170205	20170105
99776	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170205	20170105
134916	`sse`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170205	20170105
135120	`sse`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170205	20170105
135456	`sse`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170205	20170105
135528	`sse`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
135576	`sse`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105
135764	`sse`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170205	20170105
548540	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
548588	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
548992	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
549032	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
552724	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
552724	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
557336	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
557640	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170205	20170105
557988	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170205	20170105
558900	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170205	20170105
559520	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170205	20170105
560504	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
560508	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
560952	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
561864	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
561864	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
562540	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
562544	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
562868	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
563224	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
563228	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
565196	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
570116	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
570116	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
573796	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170205	20170105
573796	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
573928	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170205	20170105
574856	`ref`	`gcc -O3 -fomit-frame-pointer`	20170205	20170105
574856	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
574856	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170205	20170105
614580	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
614584	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
626220	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
626220	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
626596	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
626596	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
627660	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170205	20170105
627660	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170205	20170105
628976	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
638948	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170205	20170105
638972	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
639708	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170205	20170105
641188	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170205	20170105
641416	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
641612	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
641804	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170205	20170105
645376	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170205	20170105
646184	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170205	20170105
690776	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170205	20170105
691172	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170205	20170105
691544	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170205	20170105
696184	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
697028	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170205	20170105
698820	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20170205	20170105
699756	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
700232	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170205	20170105
702976	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
702992	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
703128	`ref`	`gcc -O -fomit-frame-pointer`	20170205	20170105
704192	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
704448	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
706940	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170205	20170105
706972	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170205	20170105
706996	`ref`	`gcc -O2 -fomit-frame-pointer`	20170205	20170105
707004	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170205	20170105
707396	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
707776	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
707788	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
709256	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170205	20170105
709540	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
713756	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
717232	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
720124	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
722172	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170205	20170105
724196	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170205	20170105
725264	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
725576	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170205	20170105
728124	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170205	20170105
799528	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170205	20170105
803648	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170205	20170105
805212	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170205	20170105
806388	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170205	20170105
809920	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
811392	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
812580	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
813948	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170205	20170105
814180	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
815956	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105
819008	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
820440	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170205	20170105
821608	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
824380	`ref`	`gcc -Os -fomit-frame-pointer`	20170205	20170105
824692	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
824996	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
825068	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
826944	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
828528	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
829148	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
830048	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170205	20170105
830076	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
831944	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
836276	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
2510416	`ref`	`cc`	20170205	20170105
2749088	`ref`	`gcc`	20170205	20170105
2753440	`ref`	`gcc -funroll-loops`	20170205	20170105

Compiler output

Implementation: crypto_aead/scream10v3/sse
Compiler: cc

scream.c: scream.c:202:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:203:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:207:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:208:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:215:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:216:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:220:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:221:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:228:10: 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/scream10v3/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/scream10v3/sse
Compiler: gcc -m64 -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 -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