Implementation notes: amd64, hydra1, crypto_aead/scream10v2

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: scream10v2
TimeImplementationCompilerBenchmark dateSUPERCOP version
412193refgcc -funroll-loops -O2 -fomit-frame-pointer2016102320161009
412195refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2016102320161009
412294refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2016102320161009
412368refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2016102320161009
412370refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2016102320161009
412620refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
413114refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2016102320161009
434605refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016102320161009
435436refgcc -march=k8 -O3 -fomit-frame-pointer2016102320161009
435512refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2016102320161009
436243refgcc -march=barcelona -O3 -fomit-frame-pointer2016102320161009
436376refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
436629refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2016102320161009
437680refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2016102320161009
438875refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2016102320161009
439237refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2016102320161009
439333refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2016102320161009
440395refgcc -m64 -O3 -fomit-frame-pointer2016102320161009
440661refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2016102320161009
440698refgcc -O3 -fomit-frame-pointer2016102320161009
443651refgcc -funroll-loops -O3 -fomit-frame-pointer2016102320161009
443784refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2016102320161009
443925refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2016102320161009
443936refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2016102320161009
444542refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2016102320161009
453759refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2016102320161009
455327refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2016102320161009
455562refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2016102320161009
455678refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2016102320161009
460021refgcc -funroll-loops -m64 -O -fomit-frame-pointer2016102320161009
460143refgcc -funroll-loops -O -fomit-frame-pointer2016102320161009
460565refgcc -march=nocona -O3 -fomit-frame-pointer2016102320161009
460685refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2016102320161009
460987refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2016102320161009
461487refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2016102320161009
461767refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2016102320161009
461994refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2016102320161009
462327refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2016102320161009
721156refclang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016102320161009
725501refclang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016102320161009
725533refclang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016102320161009
739552refclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2016102320161009
740085refclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016102320161009
740152refclang -O3 -fomit-frame-pointer -Qunused-arguments2016102320161009
964144refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2016102320161009
964149refgcc -march=nocona -O2 -fomit-frame-pointer2016102320161009
969448refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2016102320161009
972389refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2016102320161009
974573refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2016102320161009
974640refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2016102320161009
974925refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016102320161009
977358refgcc -march=nocona -O -fomit-frame-pointer2016102320161009
977427refgcc -m64 -march=nocona -O -fomit-frame-pointer2016102320161009
979547refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2016102320161009
981056refgcc -march=nocona -Os -fomit-frame-pointer2016102320161009
983021refgcc -m64 -march=k8 -O -fomit-frame-pointer2016102320161009
983184refgcc -march=k8 -O -fomit-frame-pointer2016102320161009
985349refgcc -m64 -march=nocona -Os -fomit-frame-pointer2016102320161009
985438refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2016102320161009
985464refgcc -O2 -fomit-frame-pointer2016102320161009
985597refgcc -m64 -O2 -fomit-frame-pointer2016102320161009
986678refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2016102320161009
986763refgcc -march=k8 -O2 -fomit-frame-pointer2016102320161009
995215refgcc -O -fomit-frame-pointer2016102320161009
995398refgcc -m64 -march=corei7 -O -fomit-frame-pointer2016102320161009
995416refgcc -fno-schedule-insns -O -fomit-frame-pointer2016102320161009
996546refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2016102320161009
997162refgcc -march=barcelona -O2 -fomit-frame-pointer2016102320161009
998773refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2016102320161009
1000272refgcc -m64 -march=core2 -O -fomit-frame-pointer2016102320161009
1000477refgcc -march=barcelona -O -fomit-frame-pointer2016102320161009
1000506refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2016102320161009
1000530refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016102320161009
1000784refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2016102320161009
1001104refgcc -m64 -O -fomit-frame-pointer2016102320161009
1001725refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2016102320161009
1002157refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1002328refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2016102320161009
1002390refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2016102320161009
1002424refgcc -funroll-loops -Os -fomit-frame-pointer2016102320161009
1002429refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2016102320161009
1003673refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2016102320161009
1003886refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016102320161009
1006608refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2016102320161009
1014461refgcc -m64 -march=barcelona -O -fomit-frame-pointer2016102320161009
1032087refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2016102320161009
1032619refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2016102320161009
1033805refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016102320161009
1035658refgcc -m64 -march=core2 -Os -fomit-frame-pointer2016102320161009
1036075refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016102320161009
1044843refgcc -Os -fomit-frame-pointer2016102320161009
1046451refgcc -march=k8 -Os -fomit-frame-pointer2016102320161009
1046530refgcc -m64 -march=k8 -Os -fomit-frame-pointer2016102320161009
1047078refgcc -march=barcelona -Os -fomit-frame-pointer2016102320161009
1047193refgcc -m64 -Os -fomit-frame-pointer2016102320161009
1047752refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2016102320161009
1048826refgcc -fno-schedule-insns -Os -fomit-frame-pointer2016102320161009
1049699refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2016102320161009
4664069refgcc2016102320161009
4672737refcc2016102320161009
4673647refgcc -funroll-loops2016102320161009

Test failure

Implementation: crypto_aead/scream10v2/sse
Compiler: gcc -m64 -march=core2 -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 14, namely:
CompilerImplementations
gcc -m64 -march=core2 -O2 -fomit-frame-pointer sse
gcc -m64 -march=core2 -O3 -fomit-frame-pointer ref sse
gcc -m64 -march=core2 -O -fomit-frame-pointer sse
gcc -m64 -march=core2 -Os -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer sse
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer sse
gcc -m64 -march=corei7 -O -fomit-frame-pointer sse
gcc -m64 -march=corei7 -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream10v2/sse
Compiler: cc
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: 79, namely:
CompilerImplementations
cc sse
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=native -mtune=native -O2 -fomit-frame-pointer sse
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer sse
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer sse
gcc -m64 -march=native -mtune=native -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=native -mtune=native -O2 -fomit-frame-pointer -fwrapv sse
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv sse
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv sse
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv 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: clang -O3 -fomit-frame-pointer -Qunused-arguments
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: 6, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments sse
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments sse
clang -march=native -O3 -fomit-frame-pointer -fwrapv -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 -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