Implementation notes: amd64, glyme, crypto_aead/scream10v1

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: scream10v1
TimeImplementationCompilerBenchmark dateSUPERCOP version
81584ssegcc -m64 -march=corei7 -O3 -fomit-frame-pointer2017020520170105
81644ssegcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2017020520170105
81712ssegcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2017020520170105
81724ssegcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017020520170105
81796ssegcc -m64 -march=core2 -O3 -fomit-frame-pointer2017020520170105
85672ssegcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2017020520170105
88480ssegcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2017020520170105
88508ssegcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017020520170105
88508ssegcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2017020520170105
88788ssegcc -m64 -march=core2 -O2 -fomit-frame-pointer2017020520170105
89052ssegcc -m64 -march=corei7 -O2 -fomit-frame-pointer2017020520170105
92152ssegcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2017020520170105
95824sseclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
95864sseclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2017020520170105
98892ssegcc -m64 -march=corei7 -O -fomit-frame-pointer2017020520170105
98932ssegcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2017020520170105
99028ssegcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2017020520170105
99180ssegcc -m64 -march=core2 -O -fomit-frame-pointer2017020520170105
99280ssegcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2017020520170105
100428ssegcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2017020520170105
132900ssegcc -m64 -march=corei7 -Os -fomit-frame-pointer2017020520170105
133260ssegcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017020520170105
133264ssegcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2017020520170105
133784ssegcc -m64 -march=core2 -Os -fomit-frame-pointer2017020520170105
134072ssegcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2017020520170105
134328ssegcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2017020520170105
489692refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2017020520170105
489692refgcc -march=nocona -O3 -fomit-frame-pointer2017020520170105
489844refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2017020520170105
489852refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2017020520170105
499840refgcc -march=barcelona -O3 -fomit-frame-pointer2017020520170105
500188refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2017020520170105
500188refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2017020520170105
500544refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2017020520170105
500752refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2017020520170105
500752refgcc -march=k8 -O3 -fomit-frame-pointer2017020520170105
501316refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2017020520170105
502360refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2017020520170105
503116refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2017020520170105
508944refgcc -m64 -march=core2 -O3 -fomit-frame-pointer2017020520170105
509300refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2017020520170105
509300refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2017020520170105
509424refgcc -funroll-loops -O3 -fomit-frame-pointer2017020520170105
509636refgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2017020520170105
509784refgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2017020520170105
509784refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2017020520170105
511436refgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017020520170105
515392refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2017020520170105
515392refgcc -m64 -O3 -fomit-frame-pointer2017020520170105
515396refgcc -O3 -fomit-frame-pointer2017020520170105
567308refclang -O3 -fomit-frame-pointer -Qunused-arguments2017020520170105
567592refclang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
567980refclang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
569156refclang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
573192refclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2017020520170105
573192refclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020520170105
575080refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2017020520170105
576828refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2017020520170105
577032refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2017020520170105
577296refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2017020520170105
577584refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2017020520170105
577796refgcc -funroll-loops -O2 -fomit-frame-pointer2017020520170105
578468refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2017020520170105
578608refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2017020520170105
579448refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2017020520170105
588328refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2017020520170105
588636refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2017020520170105
590804refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2017020520170105
590896refgcc -funroll-loops -O -fomit-frame-pointer2017020520170105
591648refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2017020520170105
591924refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2017020520170105
591968refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2017020520170105
592412refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2017020520170105
594004refgcc -funroll-loops -m64 -O -fomit-frame-pointer2017020520170105
676324refgcc -march=nocona -O2 -fomit-frame-pointer2017020520170105
681688refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2017020520170105
681692refgcc -march=k8 -O2 -fomit-frame-pointer2017020520170105
684880refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2017020520170105
685896refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2017020520170105
685956refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017020520170105
686148refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2017020520170105
686164refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2017020520170105
686764refgcc -m64 -O2 -fomit-frame-pointer2017020520170105
689756refgcc -march=barcelona -O2 -fomit-frame-pointer2017020520170105
690384refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2017020520170105
690492refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2017020520170105
690704refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2017020520170105
690756refgcc -O2 -fomit-frame-pointer2017020520170105
692004refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2017020520170105
695944refgcc -fno-schedule-insns -O -fomit-frame-pointer2017020520170105
696196refgcc -march=nocona -O -fomit-frame-pointer2017020520170105
696356refgcc -m64 -O -fomit-frame-pointer2017020520170105
698484refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2017020520170105
698568refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2017020520170105
698768refgcc -march=k8 -O -fomit-frame-pointer2017020520170105
699276refgcc -m64 -march=corei7 -O -fomit-frame-pointer2017020520170105
699300refgcc -m64 -march=core2 -O -fomit-frame-pointer2017020520170105
699448refgcc -O -fomit-frame-pointer2017020520170105
699492refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2017020520170105
700268refgcc -m64 -march=nocona -O -fomit-frame-pointer2017020520170105
701976refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2017020520170105
703300refgcc -m64 -march=k8 -O -fomit-frame-pointer2017020520170105
703336refgcc -m64 -march=barcelona -O -fomit-frame-pointer2017020520170105
708556refgcc -march=barcelona -O -fomit-frame-pointer2017020520170105
800528refgcc -m64 -march=nocona -Os -fomit-frame-pointer2017020520170105
802664refgcc -march=nocona -Os -fomit-frame-pointer2017020520170105
803108refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2017020520170105
804232refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2017020520170105
804236refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017020520170105
804472refgcc -fno-schedule-insns -Os -fomit-frame-pointer2017020520170105
804484refgcc -m64 -Os -fomit-frame-pointer2017020520170105
805108refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2017020520170105
805552refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2017020520170105
808756refgcc -m64 -march=core2 -Os -fomit-frame-pointer2017020520170105
810276refgcc -march=barcelona -Os -fomit-frame-pointer2017020520170105
810952refgcc -m64 -march=k8 -Os -fomit-frame-pointer2017020520170105
811792refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2017020520170105
814868refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2017020520170105
815984refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2017020520170105
818596refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2017020520170105
818728refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2017020520170105
818980refgcc -Os -fomit-frame-pointer2017020520170105
819328refgcc -march=k8 -Os -fomit-frame-pointer2017020520170105
820376refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2017020520170105
823512refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2017020520170105
826312refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2017020520170105
826312refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2017020520170105
829356refgcc -funroll-loops -Os -fomit-frame-pointer2017020520170105
2649108refcc2017020520170105
2874824refgcc -funroll-loops2017020520170105
2875188refgcc2017020520170105

Compiler output

Implementation: crypto_aead/scream10v1/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/scream10v1/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/scream10v1/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