Implementation notes: amd64, hydra3, crypto_aead/scream10v3

Computer: hydra3
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream10v3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
388616? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2017092320170725
389488? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2017092320170725
389587? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017092320170725
389592? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2017092320170725
389786? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2017092320170725
390346? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2017092320170725
390392? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017092320170725
390732? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2017092320170725
392518? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2017092320170725
392710? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2017092320170725
392745? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2017092320170725
392802? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2017092320170725
392963? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2017092320170725
393282? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2017092320170725
402980? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017092320170725
414804? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2017092320170725
415206? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2017092320170725
415298? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2017092320170725
416833? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2017092320170725
416858? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2017092320170725
422357? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2017092320170725
422727? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017092320170725
423211? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017092320170725
424529? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2017092320170725
425347? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2017092320170725
427903? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2017092320170725
428807? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2017092320170725
436864? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2017092320170725
436881? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2017092320170725
444371? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2017092320170725
444386? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2017092320170725
461504? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2017092320170725
462741? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2017092320170725
463400? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2017092320170725
463409? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2017092320170725
463474? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2017092320170725
463723? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2017092320170725
464937? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2017092320170725
606426? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2017092320170725
610246? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017092320170725
612298? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017092320170725
612475? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017092320170725
614039? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017092320170725
614901? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2017092320170725
787743? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2017092320170725
790797? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2017092320170725
804517? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2017092320170725
805860? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2017092320170725
808192? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2017092320170725
810396? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017092320170725
810731? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2017092320170725
811742? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2017092320170725
812777? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017092320170725
812815? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2017092320170725
813466? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2017092320170725
815927? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2017092320170725
816667? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017092320170725
817695? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017092320170725
819293? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2017092320170725
822966? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017092320170725
823035? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2017092320170725
823424? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017092320170725
826201? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2017092320170725
827966? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2017092320170725
828308? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017092320170725
828410? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2017092320170725
829752? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017092320170725
830074? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017092320170725
837919? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017092320170725
842127? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017092320170725
843909? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2017092320170725
844084? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017092320170725
851618? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2017092320170725
852956? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2017092320170725
853786? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2017092320170725
856944? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2017092320170725
862386? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2017092320170725
865826? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2017092320170725
883756? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2017092320170725
884070? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2017092320170725
885222? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017092320170725
885347? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2017092320170725
885987? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017092320170725
886151? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2017092320170725
886377? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017092320170725
887132? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2017092320170725
887492? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017092320170725
887706? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017092320170725
887878? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2017092320170725
888921? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017092320170725
891972? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2017092320170725
892777? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017092320170725
893199? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2017092320170725
893941? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2017092320170725
893980? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2017092320170725
894044? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2017092320170725
897652? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2017092320170725
901072? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017092320170725
3755407? ? ?? ? ?refcc2017092320170725
3827216? ? ?? ? ?refgcc_-funroll-loops2017092320170725
3839330? ? ?? ? ?refgcc2017092320170725

Test failure

Implementation: crypto_aead/scream10v3/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/scream10v3/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/scream10v3/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/scream10v3/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