Implementation notes: x86, katana, crypto_aead/scream12v1

Computer: katana
Architecture: x86
CPU ID: GenuineIntel-000006f6-bfebfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream12v1
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
634320? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016102820161009
635832? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016102820161009
636336? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016102820161009
642952? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016102820161009
650816? ? ?? ? ?refgcc_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016102820161009
651536? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016102820161009
653184? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016102820161009
653280? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016102820161009
653968? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016102820161009
658808? ? ?? ? ?refgcc_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016102820161009
660560? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016102820161009
662224? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016102820161009
684480? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016102820161009
684904? ? ?? ? ?refgcc_-m32_-O3_-fomit-frame-pointer2016102820161009
685344? ? ?? ? ?refgcc_-m32_-march=athlon_-O3_-fomit-frame-pointer2016102820161009
688248? ? ?? ? ?refgcc_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016102820161009
689704? ? ?? ? ?refgcc_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
690880? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
690984? ? ?? ? ?refgcc_-m32_-march=k8_-O3_-fomit-frame-pointer2016102820161009
691688? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
692208? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O3_-fomit-frame-pointer2016102820161009
692216? ? ?? ? ?refgcc_-m32_-march=core2_-O3_-fomit-frame-pointer2016102820161009
693536? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O3_-fomit-frame-pointer2016102820161009
695984? ? ?? ? ?refgcc_-funroll-loops_-m32_-O3_-fomit-frame-pointer2016102820161009
701464? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
701584? ? ?? ? ?refgcc_-m32_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
701640? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O3_-fomit-frame-pointer2016102820161009
703760? ? ?? ? ?refgcc_-m32_-march=prescott_-O3_-fomit-frame-pointer2016102820161009
711648? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O_-fomit-frame-pointer2016102820161009
712000? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016102820161009
714032? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016102820161009
714496? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O_-fomit-frame-pointer2016102820161009
739528? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O3_-fomit-frame-pointer2016102820161009
739936? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016102820161009
742624? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016102820161009
744552? ? ?? ? ?refgcc_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016102820161009
746224? ? ?? ? ?refgcc_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016102820161009
747120? ? ?? ? ?refgcc_-m32_-march=k6_-O3_-fomit-frame-pointer2016102820161009
768888? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
769056? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O2_-fomit-frame-pointer2016102820161009
773968? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O2_-fomit-frame-pointer2016102820161009
774264? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O2_-fomit-frame-pointer2016102820161009
775576? ? ?? ? ?refgcc_-funroll-loops_-m32_-O2_-fomit-frame-pointer2016102820161009
776496? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
785664? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016102820161009
794592? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O_-fomit-frame-pointer2016102820161009
795968? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O_-fomit-frame-pointer2016102820161009
801720? ? ?? ? ?refgcc_-m32_-march=i486_-O3_-fomit-frame-pointer2016102820161009
801856? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O3_-fomit-frame-pointer2016102820161009
807000? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016102820161009
807656? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O3_-fomit-frame-pointer2016102820161009
815392? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016102820161009
815632? ? ?? ? ?refgcc_-m32_-march=pentium_-O3_-fomit-frame-pointer2016102820161009
816752? ? ?? ? ?refgcc_-m32_-march=athlon_-O2_-fomit-frame-pointer2016102820161009
819976? ? ?? ? ?refgcc_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
820936? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
822936? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
823288? ? ?? ? ?refgcc_-m32_-march=core2_-O2_-fomit-frame-pointer2016102820161009
823720? ? ?? ? ?refgcc_-m32_-O2_-fomit-frame-pointer2016102820161009
826112? ? ?? ? ?refgcc_-m32_-march=k8_-O2_-fomit-frame-pointer2016102820161009
827624? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016102820161009
828408? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O3_-fomit-frame-pointer2016102820161009
828920? ? ?? ? ?refgcc_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016102820161009
832496? ? ?? ? ?refgcc_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016102820161009
832528? ? ?? ? ?refgcc_-m32_-march=prescott_-O2_-fomit-frame-pointer2016102820161009
834352? ? ?? ? ?refgcc_-m32_-march=pentium3_-O_-fomit-frame-pointer2016102820161009
837072? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O_-fomit-frame-pointer2016102820161009
838240? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O_-fomit-frame-pointer2016102820161009
838400? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016102820161009
838784? ? ?? ? ?refgcc_-m32_-march=pentium2_-O_-fomit-frame-pointer2016102820161009
838952? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
839144? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O_-fomit-frame-pointer2016102820161009
840080? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016102820161009
840616? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
841760? ? ?? ? ?refgcc_-m32_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
841856? ? ?? ? ?refgcc_-m32_-march=i386_-O3_-fomit-frame-pointer2016102820161009
844088? ? ?? ? ?refgcc_-m32_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
844328? ? ?? ? ?refgcc_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016102820161009
844904? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016102820161009
848192? ? ?? ? ?refgcc_-m32_-march=nocona_-O_-fomit-frame-pointer2016102820161009
850952? ? ?? ? ?refgcc_-m32_-march=prescott_-O_-fomit-frame-pointer2016102820161009
852480? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O2_-fomit-frame-pointer2016102820161009
854024? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
854248? ? ?? ? ?refgcc_-m32_-march=core2_-O_-fomit-frame-pointer2016102820161009
855216? ? ?? ? ?refgcc_-funroll-loops_-m32_-O_-fomit-frame-pointer2016102820161009
855976? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
857256? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
859344? ? ?? ? ?refgcc_-m32_-O_-fomit-frame-pointer2016102820161009
864552? ? ?? ? ?refgcc_-m32_-march=corei7_-O_-fomit-frame-pointer2016102820161009
874200? ? ?? ? ?refgcc_-m32_-march=athlon_-O_-fomit-frame-pointer2016102820161009
874832? ? ?? ? ?refgcc_-m32_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
875456? ? ?? ? ?refgcc_-m32_-march=k8_-O_-fomit-frame-pointer2016102820161009
876456? ? ?? ? ?refgcc_-m32_-march=pentium4_-O_-fomit-frame-pointer2016102820161009
878040? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016102820161009
878136? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O_-fomit-frame-pointer2016102820161009
880552? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016102820161009
880792? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016102820161009
881112? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O2_-fomit-frame-pointer2016102820161009
885704? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O2_-fomit-frame-pointer2016102820161009
891296? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O2_-fomit-frame-pointer2016102820161009
913096? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O_-fomit-frame-pointer2016102820161009
914072? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O_-fomit-frame-pointer2016102820161009
914560? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O_-fomit-frame-pointer2016102820161009
946664? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016102820161009
946856? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O_-fomit-frame-pointer2016102820161009
960560? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O_-fomit-frame-pointer2016102820161009
961296? ? ?? ? ?refgcc_-m32_-march=i386_-O_-fomit-frame-pointer2016102820161009
963480? ? ?? ? ?refgcc_-m32_-march=i386_-O2_-fomit-frame-pointer2016102820161009
967872? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-Os_-fomit-frame-pointer2016102820161009
967904? ? ?? ? ?refgcc_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016102820161009
973376? ? ?? ? ?refgcc_-m32_-march=pentium_-Os_-fomit-frame-pointer2016102820161009
975912? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
976624? ? ?? ? ?refgcc_-m32_-march=i386_-Os_-fomit-frame-pointer2016102820161009
977072? ? ?? ? ?refgcc_-m32_-march=prescott_-Os_-fomit-frame-pointer2016102820161009
977304? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016102820161009
977336? ? ?? ? ?refgcc_-m32_-march=athlon_-Os_-fomit-frame-pointer2016102820161009
977600? ? ?? ? ?refgcc_-m32_-march=i486_-Os_-fomit-frame-pointer2016102820161009
977640? ? ?? ? ?refgcc_-m32_-march=k6_-O_-fomit-frame-pointer2016102820161009
978384? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016102820161009
978416? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-Os_-fomit-frame-pointer2016102820161009
983016? ? ?? ? ?refgcc_-m32_-march=k8_-Os_-fomit-frame-pointer2016102820161009
984160? ? ?? ? ?refgcc_-m32_-march=corei7_-Os_-fomit-frame-pointer2016102820161009
984960? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016102820161009
985680? ? ?? ? ?refgcc_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
986216? ? ?? ? ?refgcc_-m32_-Os_-fomit-frame-pointer2016102820161009
986648? ? ?? ? ?refgcc_-m32_-march=k6-3_-O_-fomit-frame-pointer2016102820161009
986944? ? ?? ? ?refgcc_-funroll-loops_-m32_-Os_-fomit-frame-pointer2016102820161009
987152? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-Os_-fomit-frame-pointer2016102820161009
988280? ? ?? ? ?refgcc_-m32_-march=k6-2_-O_-fomit-frame-pointer2016102820161009
988776? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-Os_-fomit-frame-pointer2016102820161009
995040? ? ?? ? ?refgcc_-m32_-march=core2_-Os_-fomit-frame-pointer2016102820161009
996072? ? ?? ? ?refgcc_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016102820161009
998088? ? ?? ? ?refgcc_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016102820161009
999424? ? ?? ? ?refgcc_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016102820161009
999712? ? ?? ? ?refgcc_-m32_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
1001520? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
1002648? ? ?? ? ?refgcc_-m32_-march=k6_-O2_-fomit-frame-pointer2016102820161009
1003168? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016102820161009
1006080? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016102820161009
1006448? ? ?? ? ?refgcc_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016102820161009
1010424? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016102820161009
1011440? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-Os_-fomit-frame-pointer2016102820161009
1011544? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-Os_-fomit-frame-pointer2016102820161009
1014512? ? ?? ? ?refgcc_-m32_-march=k6_-Os_-fomit-frame-pointer2016102820161009
1046144? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-Os_-fomit-frame-pointer2016102820161009
1049872? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016102820161009
1050400? ? ?? ? ?refgcc_-m32_-march=pentium_-O2_-fomit-frame-pointer2016102820161009
1053512? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016102820161009
1058416? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-Os_-fomit-frame-pointer2016102820161009
1089496? ? ?? ? ?refgcc_-m32_-march=i486_-O2_-fomit-frame-pointer2016102820161009
1098432? ? ?? ? ?refgcc_-m32_-march=pentium_-O_-fomit-frame-pointer2016102820161009
1104712? ? ?? ? ?refgcc_-m32_-march=i486_-O_-fomit-frame-pointer2016102820161009
1110648? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016102820161009
1482520? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016102820161009
1483288? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016102820161009
1483328? ? ?? ? ?refgcc_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016102820161009
1485320? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016102820161009
1491936? ? ?? ? ?refgcc_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016102820161009
1492912? ? ?? ? ?refgcc_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016102820161009
1493160? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016102820161009
1508528? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016102820161009

Test failure

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