Implementation notes: amd64, mace, crypto_aead/scream12v1

Computer: mace
Architecture: amd64
CPU ID: AuthenticAMD-00040fb2-178bfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream12v1
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
500035? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2016111420161009
500050? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2016111420161009
500160? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2016111420161009
509564? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2016111420161009
509745? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016111420161009
509755? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2016111420161009
509900? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2016111420161009
519219? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016111420161009
519983? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2016111420161009
520258? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016111420161009
520425? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016111420161009
520449? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2016111420161009
520465? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2016111420161009
520504? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2016111420161009
520571? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2016111420161009
520940? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2016111420161009
521155? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016111420161009
522112? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2016111420161009
522160? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2016111420161009
522234? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2016111420161009
536018? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2016111420161009
536067? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2016111420161009
541634? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2016111420161009
541914? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2016111420161009
542357? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2016111420161009
543167? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2016111420161009
543350? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2016111420161009
543364? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2016111420161009
543570? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2016111420161009
550580? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2016111420161009
550643? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2016111420161009
550897? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2016111420161009
552762? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2016111420161009
552999? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2016111420161009
553098? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2016111420161009
554518? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2016111420161009
564541? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2016111420161009
564929? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2016111420161009
839375? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016111420161009
845194? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2016111420161009
847177? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016111420161009
847178? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016111420161009
853613? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016111420161009
855274? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016111420161009
1228719? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016111420161009
1229215? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016111420161009
1229479? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016111420161009
1232191? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2016111420161009
1234372? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2016111420161009
1234508? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2016111420161009
1235603? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2016111420161009
1236692? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016111420161009
1237209? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016111420161009
1237307? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2016111420161009
1237378? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2016111420161009
1239541? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016111420161009
1239546? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2016111420161009
1239849? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2016111420161009
1244766? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016111420161009
1272212? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2016111420161009
1272292? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2016111420161009
1274794? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2016111420161009
1275091? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2016111420161009
1279244? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2016111420161009
1279410? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016111420161009
1280640? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2016111420161009
1288397? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016111420161009
1290713? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2016111420161009
1291174? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2016111420161009
1292493? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2016111420161009
1292662? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2016111420161009
1292722? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016111420161009
1293822? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2016111420161009
1293992? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016111420161009
1294076? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016111420161009
1310680? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2016111420161009
1315546? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2016111420161009
1315554? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2016111420161009
1316037? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2016111420161009
1316047? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2016111420161009
1316054? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2016111420161009
1317745? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2016111420161009
1319186? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2016111420161009
1319191? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2016111420161009
1322804? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016111420161009
1345667? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016111420161009
1346240? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2016111420161009
1347949? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2016111420161009
1348177? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2016111420161009
1349938? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2016111420161009
1350851? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016111420161009
1351032? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2016111420161009
1351506? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2016111420161009
1351515? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2016111420161009
1352117? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2016111420161009
1356068? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2016111420161009
1357714? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016111420161009
1359839? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2016111420161009
5957211? ? ?? ? ?refgcc2016111420161009
5969754? ? ?? ? ?refgcc_-funroll-loops2016111420161009
5983958? ? ?? ? ?refcc2016111420161009

Test failure

Implementation: crypto_aead/scream12v1/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/scream12v1/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/scream12v1/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/scream12v1/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