Implementation notes: amd64, h3neo, crypto_aead/scream12v3

Computer: h3neo
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream12v3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
508322? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2016111020161009
508497? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016111020161009
508591? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2016111020161009
508793? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2016111020161009
509362? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2016111020161009
509558? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2016111020161009
510881? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016111020161009
510887? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2016111020161009
513718? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2016111020161009
513944? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2016111020161009
514675? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2016111020161009
516606? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2016111020161009
516916? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2016111020161009
517143? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2016111020161009
526182? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016111020161009
544554? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2016111020161009
545513? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2016111020161009
546409? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2016111020161009
546757? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2016111020161009
547321? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2016111020161009
554555? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016111020161009
554621? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016111020161009
554689? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2016111020161009
562112? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2016111020161009
562124? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2016111020161009
563931? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2016111020161009
564478? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2016111020161009
564529? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2016111020161009
564880? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2016111020161009
582017? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2016111020161009
582119? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2016111020161009
608220? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2016111020161009
608299? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2016111020161009
608327? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2016111020161009
608807? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2016111020161009
608824? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2016111020161009
609008? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2016111020161009
609054? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2016111020161009
811228? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016111020161009
811471? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016111020161009
814535? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016111020161009
816778? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2016111020161009
816893? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016111020161009
817118? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016111020161009
1058585? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2016111020161009
1058837? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2016111020161009
1066305? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016111020161009
1067053? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016111020161009
1072107? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016111020161009
1072379? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016111020161009
1074058? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2016111020161009
1075142? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2016111020161009
1075660? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016111020161009
1076355? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2016111020161009
1076405? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016111020161009
1077691? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016111020161009
1082608? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2016111020161009
1083267? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2016111020161009
1083398? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2016111020161009
1086757? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2016111020161009
1086800? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2016111020161009
1087495? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2016111020161009
1088619? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2016111020161009
1089965? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016111020161009
1090665? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016111020161009
1092986? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2016111020161009
1096058? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016111020161009
1097472? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2016111020161009
1097591? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2016111020161009
1097634? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016111020161009
1097671? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2016111020161009
1097799? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016111020161009
1121099? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2016111020161009
1126737? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2016111020161009
1126788? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2016111020161009
1127097? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2016111020161009
1140811? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2016111020161009
1141268? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2016111020161009
1142118? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2016111020161009
1161164? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2016111020161009
1161250? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2016111020161009
1161289? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2016111020161009
1161306? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2016111020161009
1161348? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2016111020161009
1170656? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016111020161009
1172332? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2016111020161009
1172527? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016111020161009
1173729? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016111020161009
1174245? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2016111020161009
1174591? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2016111020161009
1174853? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2016111020161009
1175042? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2016111020161009
1175093? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2016111020161009
1175207? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2016111020161009
1175213? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2016111020161009
1175628? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2016111020161009
1184830? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016111020161009
1185056? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2016111020161009
5064474? ? ?? ? ?refgcc_-funroll-loops2016111020161009
5162033? ? ?? ? ?refcc2016111020161009
5171035? ? ?? ? ?refgcc2016111020161009

Test failure

Implementation: crypto_aead/scream12v3/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/scream12v3/sse
Compiler: cc
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: 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/scream12v3/sse
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
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: 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/scream12v3/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:
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