Implementation notes: x86, katana, crypto_aead/scream12v2

Computer: katana
Architecture: x86
CPU ID: GenuineIntel-000006f6-bfebfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream12v2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
635240? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016102820161009
636688? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016102820161009
637368? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016102820161009
637392? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016102820161009
652144? ? ?? ? ?refgcc_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016102820161009
653392? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016102820161009
653512? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016102820161009
654608? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016102820161009
656376? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016102820161009
656776? ? ?? ? ?refgcc_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016102820161009
657984? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016102820161009
658368? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016102820161009
683328? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O3_-fomit-frame-pointer2016102820161009
683384? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016102820161009
685688? ? ?? ? ?refgcc_-m32_-march=athlon_-O3_-fomit-frame-pointer2016102820161009
685800? ? ?? ? ?refgcc_-m32_-march=k8_-O3_-fomit-frame-pointer2016102820161009
685912? ? ?? ? ?refgcc_-m32_-O3_-fomit-frame-pointer2016102820161009
690064? ? ?? ? ?refgcc_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
690200? ? ?? ? ?refgcc_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016102820161009
691504? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
693088? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
693880? ? ?? ? ?refgcc_-m32_-march=core2_-O3_-fomit-frame-pointer2016102820161009
696688? ? ?? ? ?refgcc_-funroll-loops_-m32_-O3_-fomit-frame-pointer2016102820161009
698984? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O3_-fomit-frame-pointer2016102820161009
701048? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O3_-fomit-frame-pointer2016102820161009
701720? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
705288? ? ?? ? ?refgcc_-m32_-march=prescott_-O3_-fomit-frame-pointer2016102820161009
705496? ? ?? ? ?refgcc_-m32_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
713024? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O_-fomit-frame-pointer2016102820161009
713296? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O_-fomit-frame-pointer2016102820161009
714000? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016102820161009
715312? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016102820161009
738752? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016102820161009
739712? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O3_-fomit-frame-pointer2016102820161009
739976? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016102820161009
746856? ? ?? ? ?refgcc_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016102820161009
747672? ? ?? ? ?refgcc_-m32_-march=k6_-O3_-fomit-frame-pointer2016102820161009
748024? ? ?? ? ?refgcc_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016102820161009
770152? ? ?? ? ?refgcc_-funroll-loops_-m32_-O2_-fomit-frame-pointer2016102820161009
770888? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
771464? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O2_-fomit-frame-pointer2016102820161009
781136? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O2_-fomit-frame-pointer2016102820161009
781464? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O2_-fomit-frame-pointer2016102820161009
783608? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
790152? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016102820161009
793136? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O_-fomit-frame-pointer2016102820161009
793328? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O_-fomit-frame-pointer2016102820161009
801936? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O3_-fomit-frame-pointer2016102820161009
802368? ? ?? ? ?refgcc_-m32_-march=i486_-O3_-fomit-frame-pointer2016102820161009
812000? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O3_-fomit-frame-pointer2016102820161009
812120? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016102820161009
816656? ? ?? ? ?refgcc_-m32_-march=pentium_-O3_-fomit-frame-pointer2016102820161009
817288? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016102820161009
818072? ? ?? ? ?refgcc_-m32_-march=athlon_-O2_-fomit-frame-pointer2016102820161009
818392? ? ?? ? ?refgcc_-m32_-march=k8_-O2_-fomit-frame-pointer2016102820161009
820568? ? ?? ? ?refgcc_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016102820161009
820840? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
821280? ? ?? ? ?refgcc_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
822152? ? ?? ? ?refgcc_-m32_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
822224? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
823872? ? ?? ? ?refgcc_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016102820161009
827864? ? ?? ? ?refgcc_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016102820161009
830448? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016102820161009
830496? ? ?? ? ?refgcc_-m32_-march=i386_-O3_-fomit-frame-pointer2016102820161009
830912? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O3_-fomit-frame-pointer2016102820161009
832384? ? ?? ? ?refgcc_-m32_-O2_-fomit-frame-pointer2016102820161009
833464? ? ?? ? ?refgcc_-m32_-march=pentium3_-O_-fomit-frame-pointer2016102820161009
834712? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016102820161009
835656? ? ?? ? ?refgcc_-m32_-march=prescott_-O2_-fomit-frame-pointer2016102820161009
836528? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016102820161009
837784? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
838528? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O_-fomit-frame-pointer2016102820161009
838664? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O_-fomit-frame-pointer2016102820161009
839152? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O_-fomit-frame-pointer2016102820161009
840256? ? ?? ? ?refgcc_-m32_-march=pentium2_-O_-fomit-frame-pointer2016102820161009
841656? ? ?? ? ?refgcc_-m32_-march=nocona_-O_-fomit-frame-pointer2016102820161009
843360? ? ?? ? ?refgcc_-m32_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
844128? ? ?? ? ?refgcc_-m32_-march=core2_-O2_-fomit-frame-pointer2016102820161009
847752? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016102820161009
848224? ? ?? ? ?refgcc_-m32_-march=prescott_-O_-fomit-frame-pointer2016102820161009
848760? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
851808? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
852056? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
852224? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
854008? ? ?? ? ?refgcc_-m32_-O_-fomit-frame-pointer2016102820161009
856504? ? ?? ? ?refgcc_-funroll-loops_-m32_-O_-fomit-frame-pointer2016102820161009
860048? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O2_-fomit-frame-pointer2016102820161009
861872? ? ?? ? ?refgcc_-m32_-march=core2_-O_-fomit-frame-pointer2016102820161009
862816? ? ?? ? ?refgcc_-m32_-march=athlon_-O_-fomit-frame-pointer2016102820161009
864648? ? ?? ? ?refgcc_-m32_-march=corei7_-O_-fomit-frame-pointer2016102820161009
872872? ? ?? ? ?refgcc_-m32_-march=pentium4_-O_-fomit-frame-pointer2016102820161009
873728? ? ?? ? ?refgcc_-m32_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
876560? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016102820161009
876752? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O2_-fomit-frame-pointer2016102820161009
879656? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016102820161009
879752? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O_-fomit-frame-pointer2016102820161009
880688? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O2_-fomit-frame-pointer2016102820161009
881352? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016102820161009
886752? ? ?? ? ?refgcc_-m32_-march=k8_-O_-fomit-frame-pointer2016102820161009
891696? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O2_-fomit-frame-pointer2016102820161009
912072? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O_-fomit-frame-pointer2016102820161009
912648? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O_-fomit-frame-pointer2016102820161009
913968? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O_-fomit-frame-pointer2016102820161009
944512? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O_-fomit-frame-pointer2016102820161009
945056? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016102820161009
958280? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O_-fomit-frame-pointer2016102820161009
961448? ? ?? ? ?refgcc_-m32_-march=i386_-O_-fomit-frame-pointer2016102820161009
965760? ? ?? ? ?refgcc_-m32_-march=i386_-Os_-fomit-frame-pointer2016102820161009
967320? ? ?? ? ?refgcc_-m32_-march=i486_-Os_-fomit-frame-pointer2016102820161009
968360? ? ?? ? ?refgcc_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016102820161009
970096? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016102820161009
973920? ? ?? ? ?refgcc_-m32_-march=prescott_-Os_-fomit-frame-pointer2016102820161009
975296? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-Os_-fomit-frame-pointer2016102820161009
976112? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016102820161009
977608? ? ?? ? ?refgcc_-m32_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
977808? ? ?? ? ?refgcc_-m32_-march=k6-2_-O_-fomit-frame-pointer2016102820161009
978280? ? ?? ? ?refgcc_-m32_-Os_-fomit-frame-pointer2016102820161009
980592? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-Os_-fomit-frame-pointer2016102820161009
983520? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016102820161009
984232? ? ?? ? ?refgcc_-m32_-march=k6-3_-O_-fomit-frame-pointer2016102820161009
984720? ? ?? ? ?refgcc_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
984896? ? ?? ? ?refgcc_-m32_-march=i386_-O2_-fomit-frame-pointer2016102820161009
985824? ? ?? ? ?refgcc_-m32_-march=k8_-Os_-fomit-frame-pointer2016102820161009
986000? ? ?? ? ?refgcc_-m32_-march=athlon_-Os_-fomit-frame-pointer2016102820161009
986400? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016102820161009
986416? ? ?? ? ?refgcc_-m32_-march=pentium_-Os_-fomit-frame-pointer2016102820161009
987552? ? ?? ? ?refgcc_-m32_-march=k6_-O_-fomit-frame-pointer2016102820161009
987904? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-Os_-fomit-frame-pointer2016102820161009
989400? ? ?? ? ?refgcc_-m32_-march=corei7_-Os_-fomit-frame-pointer2016102820161009
989728? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016102820161009
990664? ? ?? ? ?refgcc_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016102820161009
991328? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
991720? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
995248? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-Os_-fomit-frame-pointer2016102820161009
995688? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-Os_-fomit-frame-pointer2016102820161009
996576? ? ?? ? ?refgcc_-funroll-loops_-m32_-Os_-fomit-frame-pointer2016102820161009
998664? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-Os_-fomit-frame-pointer2016102820161009
1001480? ? ?? ? ?refgcc_-m32_-march=core2_-Os_-fomit-frame-pointer2016102820161009
1001760? ? ?? ? ?refgcc_-m32_-march=k6_-O2_-fomit-frame-pointer2016102820161009
1003432? ? ?? ? ?refgcc_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016102820161009
1003560? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016102820161009
1003568? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-Os_-fomit-frame-pointer2016102820161009
1004008? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016102820161009
1018568? ? ?? ? ?refgcc_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016102820161009
1023288? ? ?? ? ?refgcc_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016102820161009
1036240? ? ?? ? ?refgcc_-m32_-march=k6_-Os_-fomit-frame-pointer2016102820161009
1068376? ? ?? ? ?refgcc_-m32_-march=i486_-O2_-fomit-frame-pointer2016102820161009
1071416? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016102820161009
1073888? ? ?? ? ?refgcc_-m32_-march=pentium_-O2_-fomit-frame-pointer2016102820161009
1078104? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-Os_-fomit-frame-pointer2016102820161009
1092304? ? ?? ? ?refgcc_-m32_-march=i486_-O_-fomit-frame-pointer2016102820161009
1105360? ? ?? ? ?refgcc_-m32_-march=pentium_-O_-fomit-frame-pointer2016102820161009
1105528? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016102820161009
1482720? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016102820161009
1484680? ? ?? ? ?refgcc_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016102820161009
1484728? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016102820161009
1485256? ? ?? ? ?refgcc_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016102820161009
1488632? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016102820161009
1489144? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016102820161009
1489176? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016102820161009
1490064? ? ?? ? ?refgcc_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016102820161009

Test failure

Implementation: crypto_aead/scream12v2/ref
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 35, namely:
CompilerImplementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer ref sse
gcc -m32 -march=core2 -O2 -fomit-frame-pointer sse
gcc -m32 -march=core2 -O3 -fomit-frame-pointer sse
gcc -m32 -march=core2 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -Os -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer sse
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer ref sse
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer ref sse
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer ref sse
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer sse
gcc -m32 -march=corei7 -O -fomit-frame-pointer sse
gcc -m32 -march=corei7 -Os -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream12v2/sse
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:16:32: warning: implicit declaration of function '__builtin_ia32_psrldi128' [-Wimplicit-function-declaration]
scream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
scream.c: ^
scream.c: scream.c:182:10: note: in expansion of macro 'shift_right'
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:182:5: error: can't convert between vector values of different size
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:183:5: error: can't convert between vector values of different size
scream.c: t1 = shift_right(in[2]) & V(0xf);
scream.c: ^
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: ...

Number of similar (compiler,implementation) pairs: 96, namely:
CompilerImplementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer sse
gcc -m32 -O2 -fomit-frame-pointer sse
gcc -m32 -O3 -fomit-frame-pointer sse
gcc -m32 -O -fomit-frame-pointer sse
gcc -m32 -Os -fomit-frame-pointer sse
gcc -m32 -march=athlon -O2 -fomit-frame-pointer sse
gcc -m32 -march=athlon -O3 -fomit-frame-pointer sse
gcc -m32 -march=athlon -O -fomit-frame-pointer sse
gcc -m32 -march=athlon -Os -fomit-frame-pointer sse
gcc -m32 -march=i386 -O2 -fomit-frame-pointer sse
gcc -m32 -march=i386 -O3 -fomit-frame-pointer sse
gcc -m32 -march=i386 -O -fomit-frame-pointer sse
gcc -m32 -march=i386 -Os -fomit-frame-pointer sse
gcc -m32 -march=i486 -O2 -fomit-frame-pointer sse
gcc -m32 -march=i486 -O3 -fomit-frame-pointer sse
gcc -m32 -march=i486 -O -fomit-frame-pointer sse
gcc -m32 -march=i486 -Os -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -O -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -O -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer sse
gcc -m32 -march=k6 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k6 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k6 -O -fomit-frame-pointer sse
gcc -m32 -march=k6 -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -O -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -O -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium -O -fomit-frame-pointer sse
gcc -m32 -march=pentium -Os -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream12v2/sse
Compiler: gcc -funroll-loops -m32 -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: ...

Number of similar (compiler,implementation) pairs: 44, namely:
CompilerImplementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer sse
gcc -m32 -march=k8 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k8 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k8 -O -fomit-frame-pointer sse
gcc -m32 -march=k8 -Os -fomit-frame-pointer sse
gcc -m32 -march=nocona -O2 -fomit-frame-pointer sse
gcc -m32 -march=nocona -O3 -fomit-frame-pointer sse
gcc -m32 -march=nocona -O -fomit-frame-pointer sse
gcc -m32 -march=nocona -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -O -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -O -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer sse
gcc -m32 -march=prescott -O2 -fomit-frame-pointer sse
gcc -m32 -march=prescott -O3 -fomit-frame-pointer sse
gcc -m32 -march=prescott -O -fomit-frame-pointer sse
gcc -m32 -march=prescott -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream12v2/sse
Compiler: gcc -m32 -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 -m32 -march=barcelona -O2 -fomit-frame-pointer sse
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer sse
gcc -m32 -march=barcelona -O -fomit-frame-pointer sse
gcc -m32 -march=barcelona -Os -fomit-frame-pointer sse