Implementation notes: amd64, glyme, crypto_aead/scream10v2

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: scream10v2
TimeImplementationCompilerBenchmark dateSUPERCOP version
81112ssegcc -m64 -march=corei7 -O3 -fomit-frame-pointer2017020520170105
81128ssegcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2017020520170105
81256ssegcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2017020520170105
81312ssegcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017020520170105
81320ssegcc -m64 -march=core2 -O3 -fomit-frame-pointer2017020520170105
84816ssegcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2017020520170105
87764ssegcc -m64 -march=core2 -O2 -fomit-frame-pointer2017020520170105
87788ssegcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017020520170105
87808ssegcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2017020520170105
87812ssegcc -m64 -march=corei7 -O2 -fomit-frame-pointer2017020520170105
87892ssegcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2017020520170105
91268ssegcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2017020520170105
94084sseclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2017020520170105
96452sseclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
98792ssegcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2017020520170105
98828ssegcc -m64 -march=corei7 -O -fomit-frame-pointer2017020520170105
99080ssegcc -m64 -march=core2 -O -fomit-frame-pointer2017020520170105
99080ssegcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2017020520170105
99184ssegcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2017020520170105
99200ssegcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2017020520170105
131532ssegcc -m64 -march=corei7 -Os -fomit-frame-pointer2017020520170105
131924ssegcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017020520170105
131960ssegcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2017020520170105
132032ssegcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2017020520170105
132124ssegcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2017020520170105
132332ssegcc -m64 -march=core2 -Os -fomit-frame-pointer2017020520170105
490212refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2017020520170105
490220refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2017020520170105
494648refgcc -march=nocona -O3 -fomit-frame-pointer2017020520170105
494668refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2017020520170105
499928refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2017020520170105
499936refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2017020520170105
500044refgcc -march=barcelona -O3 -fomit-frame-pointer2017020520170105
500188refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2017020520170105
500480refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2017020520170105
500516refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2017020520170105
500584refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2017020520170105
500584refgcc -march=k8 -O3 -fomit-frame-pointer2017020520170105
503240refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2017020520170105
509284refgcc -m64 -march=core2 -O3 -fomit-frame-pointer2017020520170105
509416refgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2017020520170105
509424refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2017020520170105
509428refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2017020520170105
510424refgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2017020520170105
510424refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2017020520170105
510660refgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017020520170105
511876refgcc -funroll-loops -O3 -fomit-frame-pointer2017020520170105
515624refgcc -O3 -fomit-frame-pointer2017020520170105
515624refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2017020520170105
515624refgcc -m64 -O3 -fomit-frame-pointer2017020520170105
566728refclang -O3 -fomit-frame-pointer -Qunused-arguments2017020520170105
567556refclang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
567948refclang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
568028refclang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
573700refclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
573712refclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2017020520170105
576060refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2017020520170105
576060refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2017020520170105
576664refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2017020520170105
576744refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2017020520170105
576940refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2017020520170105
579372refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2017020520170105
579376refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2017020520170105
579612refgcc -funroll-loops -O2 -fomit-frame-pointer2017020520170105
580324refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2017020520170105
588088refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2017020520170105
588448refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2017020520170105
591920refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2017020520170105
592036refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2017020520170105
594568refgcc -funroll-loops -O -fomit-frame-pointer2017020520170105
594588refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2017020520170105
595224refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2017020520170105
595336refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2017020520170105
595624refgcc -funroll-loops -m64 -O -fomit-frame-pointer2017020520170105
673204refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2017020520170105
681576refgcc -march=nocona -O2 -fomit-frame-pointer2017020520170105
683364refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2017020520170105
685116refgcc -march=barcelona -O2 -fomit-frame-pointer2017020520170105
685188refgcc -m64 -O2 -fomit-frame-pointer2017020520170105
685244refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2017020520170105
685260refgcc -O2 -fomit-frame-pointer2017020520170105
685516refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2017020520170105
686136refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2017020520170105
688020refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2017020520170105
688460refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2017020520170105
689448refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2017020520170105
691328refgcc -march=k8 -O2 -fomit-frame-pointer2017020520170105
691364refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017020520170105
691752refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2017020520170105
695296refgcc -march=nocona -O -fomit-frame-pointer2017020520170105
695344refgcc -m64 -march=nocona -O -fomit-frame-pointer2017020520170105
696180refgcc -m64 -march=k8 -O -fomit-frame-pointer2017020520170105
696268refgcc -m64 -O -fomit-frame-pointer2017020520170105
697320refgcc -fno-schedule-insns -O -fomit-frame-pointer2017020520170105
698968refgcc -m64 -march=barcelona -O -fomit-frame-pointer2017020520170105
698976refgcc -march=barcelona -O -fomit-frame-pointer2017020520170105
699032refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2017020520170105
699040refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2017020520170105
699420refgcc -m64 -march=core2 -O -fomit-frame-pointer2017020520170105
699620refgcc -march=k8 -O -fomit-frame-pointer2017020520170105
700404refgcc -O -fomit-frame-pointer2017020520170105
700416refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2017020520170105
701692refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2017020520170105
702972refgcc -m64 -march=corei7 -O -fomit-frame-pointer2017020520170105
802008refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2017020520170105
804056refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2017020520170105
804784refgcc -funroll-loops -Os -fomit-frame-pointer2017020520170105
806744refgcc -march=nocona -Os -fomit-frame-pointer2017020520170105
807924refgcc -m64 -march=nocona -Os -fomit-frame-pointer2017020520170105
809732refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2017020520170105
810220refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2017020520170105
810620refgcc -march=k8 -Os -fomit-frame-pointer2017020520170105
810632refgcc -m64 -Os -fomit-frame-pointer2017020520170105
810668refgcc -fno-schedule-insns -Os -fomit-frame-pointer2017020520170105
813240refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2017020520170105
814524refgcc -Os -fomit-frame-pointer2017020520170105
816620refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017020520170105
818796refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2017020520170105
818804refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2017020520170105
819164refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2017020520170105
819392refgcc -m64 -march=k8 -Os -fomit-frame-pointer2017020520170105
821980refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2017020520170105
822892refgcc -m64 -march=core2 -Os -fomit-frame-pointer2017020520170105
824720refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2017020520170105
825224refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2017020520170105
826148refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2017020520170105
826968refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2017020520170105
827652refgcc -march=barcelona -Os -fomit-frame-pointer2017020520170105
2652440refcc2017020520170105
2869592refgcc2017020520170105
2871200refgcc -funroll-loops2017020520170105

Compiler output

Implementation: crypto_aead/scream10v2/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:
CompilerImplementations
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/scream10v2/sse
Compiler: gcc
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: 70, namely:
CompilerImplementations
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/scream10v2/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:
CompilerImplementations
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