Implementation notes: amd64, hydra9, crypto_aead/scream10v2

Computer: hydra9
Architecture: amd64
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream10v2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
78750? ? ?? ? ?ssegcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017091420170725
78778? ? ?? ? ?ssegcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017091420170725
82822? ? ?? ? ?ssegcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017091420170725
82935? ? ?? ? ?ssegcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017091420170725
83047? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017091420170725
83090? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017091420170725
85526? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091420170725
85799? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091420170725
86234? ? ?? ? ?ssegcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017091420170725
86558? ? ?? ? ?ssegcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017091420170725
88639? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017091420170725
88664? ? ?? ? ?ssegcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017091420170725
88678? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091420170725
88800? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017091420170725
90208? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091420170725
90588? ? ?? ? ?ssegcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017091420170725
93201? ? ?? ? ?ssegcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017091420170725
93260? ? ?? ? ?ssegcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017091420170725
95353? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091420170725
95515? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091420170725
98574? ? ?? ? ?ssegcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017091420170725
98766? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017091420170725
98816? ? ?? ? ?ssegcc_-m64_-march=core2_-O_-fomit-frame-pointer2017091420170725
99420? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017091420170725
404776? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017091420170725
405120? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017091420170725
405567? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017091420170725
406127? ? ?? ? ?refgcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017091420170725
407474? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2017091420170725
408038? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2017091420170725
408046? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2017091420170725
412276? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2017091420170725
412805? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2017091420170725
412833? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017091420170725
413116? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091420170725
413656? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017091420170725
413673? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091420170725
415238? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2017091420170725
415466? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2017091420170725
415691? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2017091420170725
415999? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2017091420170725
416194? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2017091420170725
417601? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2017091420170725
417828? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2017091420170725
417925? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2017091420170725
418330? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2017091420170725
418336? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2017091420170725
420909? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2017091420170725
420911? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017091420170725
421209? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2017091420170725
421218? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2017091420170725
421339? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017091420170725
421644? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2017091420170725
425689? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2017091420170725
425805? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017091420170725
429775? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2017091420170725
429903? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2017091420170725
429947? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2017091420170725
430358? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2017091420170725
430862? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2017091420170725
433085? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2017091420170725
433145? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2017091420170725
434078? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2017091420170725
434863? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2017091420170725
441970? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2017091420170725
442047? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2017091420170725
445363? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2017091420170725
445937? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2017091420170725
714399? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017091420170725
716071? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017091420170725
717798? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017091420170725
718286? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017091420170725
718296? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017091420170725
720791? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017091420170725
723296? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091420170725
723695? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2017091420170725
727768? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091420170725
727841? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2017091420170725
729108? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2017091420170725
729903? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2017091420170725
730148? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2017091420170725
730285? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2017091420170725
732321? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2017091420170725
732512? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2017091420170725
732527? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2017091420170725
732633? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2017091420170725
732881? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017091420170725
733198? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017091420170725
733863? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091420170725
734010? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017091420170725
734208? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2017091420170725
734412? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2017091420170725
734628? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017091420170725
735341? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017091420170725
735374? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2017091420170725
735409? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2017091420170725
736638? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2017091420170725
739021? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2017091420170725
739390? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2017091420170725
743406? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091420170725
762270? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2017091420170725
762303? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017091420170725
979958? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2017091420170725
980957? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2017091420170725
994156? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2017091420170725
995109? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2017091420170725
996684? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2017091420170725
996989? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2017091420170725
997797? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2017091420170725
998417? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017091420170725
998641? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2017091420170725
1239359? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2017091420170725
1240641? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017091420170725
1240834? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2017091420170725
1241368? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2017091420170725
1242494? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2017091420170725
1244416? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017091420170725
1245392? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017091420170725
1245921? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017091420170725
1259278? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091420170725
1271717? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017091420170725
1273149? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2017091420170725
1278971? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2017091420170725
1283196? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2017091420170725
1285198? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2017091420170725
1285242? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091420170725
1285361? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2017091420170725
1286878? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2017091420170725
2313850? ? ?? ? ?refcc2017091420170725
2325369? ? ?? ? ?refgcc_-funroll-loops2017091420170725
2329239? ? ?? ? ?refgcc2017091420170725

Test failure

Implementation: crypto_aead/scream10v2/sse
Compiler: gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 14, namely:
CompilerImplementations
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer sse
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer ref sse
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer ref sse
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer ref sse
gcc -m64 -march=core2 -Os -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer sse
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer sse
gcc -m64 -march=corei7 -Os -fomit-frame-pointer sse
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer sse
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv sse

Compiler output

Implementation: crypto_aead/scream10v2/sse
Compiler: cc
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi' 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' 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' 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' 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' 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' 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' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:204:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 71, 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=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/scream10v2/sse
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi' 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' 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' 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' 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' 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' 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' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:204:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: ...
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi' 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' 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' 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' 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' 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' 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' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:204:7: error: conversion of scalar 'int' to vector 'v16qi' involves truncation
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
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