Implementation notes: x86, katana, crypto_aead/scream10v1

Computer: katana
Architecture: x86
CPU ID: GenuineIntel-000006f6-bfebfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream10v1
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
545544? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016102820161009
546256? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016102820161009
549744? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016102820161009
550400? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016102820161009
557144? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016102820161009
557776? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016102820161009
557920? ? ?? ? ?refgcc_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016102820161009
559800? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016102820161009
561120? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016102820161009
562024? ? ?? ? ?refgcc_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016102820161009
564288? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016102820161009
568920? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016102820161009
585696? ? ?? ? ?refgcc_-m32_-march=athlon_-O3_-fomit-frame-pointer2016102820161009
587112? ? ?? ? ?refgcc_-m32_-march=core2_-O3_-fomit-frame-pointer2016102820161009
588224? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
588584? ? ?? ? ?refgcc_-m32_-march=k8_-O3_-fomit-frame-pointer2016102820161009
588608? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O3_-fomit-frame-pointer2016102820161009
589240? ? ?? ? ?refgcc_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
590288? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
590816? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O3_-fomit-frame-pointer2016102820161009
591768? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
595104? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O3_-fomit-frame-pointer2016102820161009
597872? ? ?? ? ?refgcc_-funroll-loops_-m32_-O3_-fomit-frame-pointer2016102820161009
597936? ? ?? ? ?refgcc_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016102820161009
599224? ? ?? ? ?refgcc_-m32_-march=prescott_-O3_-fomit-frame-pointer2016102820161009
599960? ? ?? ? ?refgcc_-m32_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
599984? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016102820161009
603856? ? ?? ? ?refgcc_-m32_-O3_-fomit-frame-pointer2016102820161009
604096? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016102820161009
604344? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O_-fomit-frame-pointer2016102820161009
605176? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016102820161009
605824? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O_-fomit-frame-pointer2016102820161009
629160? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O3_-fomit-frame-pointer2016102820161009
633168? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016102820161009
634688? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016102820161009
638904? ? ?? ? ?refgcc_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016102820161009
639048? ? ?? ? ?refgcc_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016102820161009
640072? ? ?? ? ?refgcc_-m32_-march=k6_-O3_-fomit-frame-pointer2016102820161009
655256? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016102820161009
658528? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O2_-fomit-frame-pointer2016102820161009
659632? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
661720? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O2_-fomit-frame-pointer2016102820161009
662080? ? ?? ? ?refgcc_-funroll-loops_-m32_-O2_-fomit-frame-pointer2016102820161009
662752? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
663760? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O2_-fomit-frame-pointer2016102820161009
666928? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O_-fomit-frame-pointer2016102820161009
667544? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O_-fomit-frame-pointer2016102820161009
683600? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O3_-fomit-frame-pointer2016102820161009
687016? ? ?? ? ?refgcc_-m32_-march=i486_-O3_-fomit-frame-pointer2016102820161009
690352? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O_-fomit-frame-pointer2016102820161009
690488? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O_-fomit-frame-pointer2016102820161009
692384? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
695408? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O3_-fomit-frame-pointer2016102820161009
695800? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016102820161009
706240? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O3_-fomit-frame-pointer2016102820161009
707304? ? ?? ? ?refgcc_-m32_-march=core2_-O2_-fomit-frame-pointer2016102820161009
707480? ? ?? ? ?refgcc_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
708360? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016102820161009
708416? ? ?? ? ?refgcc_-m32_-O2_-fomit-frame-pointer2016102820161009
708584? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
708776? ? ?? ? ?refgcc_-m32_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
709080? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
709192? ? ?? ? ?refgcc_-m32_-march=pentium_-O3_-fomit-frame-pointer2016102820161009
709624? ? ?? ? ?refgcc_-m32_-march=athlon_-O2_-fomit-frame-pointer2016102820161009
710024? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
710880? ? ?? ? ?refgcc_-m32_-march=i386_-O3_-fomit-frame-pointer2016102820161009
712232? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016102820161009
712760? ? ?? ? ?refgcc_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016102820161009
712952? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016102820161009
713248? ? ?? ? ?refgcc_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016102820161009
713424? ? ?? ? ?refgcc_-m32_-march=k8_-O2_-fomit-frame-pointer2016102820161009
714616? ? ?? ? ?refgcc_-m32_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
714928? ? ?? ? ?refgcc_-m32_-march=pentium2_-O_-fomit-frame-pointer2016102820161009
715056? ? ?? ? ?refgcc_-m32_-march=prescott_-O2_-fomit-frame-pointer2016102820161009
715864? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016102820161009
716864? ? ?? ? ?refgcc_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016102820161009
717336? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O_-fomit-frame-pointer2016102820161009
718960? ? ?? ? ?refgcc_-m32_-march=pentium3_-O_-fomit-frame-pointer2016102820161009
723960? ? ?? ? ?refgcc_-funroll-loops_-m32_-O_-fomit-frame-pointer2016102820161009
725536? ? ?? ? ?refgcc_-m32_-march=prescott_-O_-fomit-frame-pointer2016102820161009
731360? ? ?? ? ?refgcc_-m32_-march=nocona_-O_-fomit-frame-pointer2016102820161009
734088? ? ?? ? ?refgcc_-m32_-march=corei7_-O_-fomit-frame-pointer2016102820161009
735728? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
735776? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
736056? ? ?? ? ?refgcc_-m32_-march=core2_-O_-fomit-frame-pointer2016102820161009
738160? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
738648? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O_-fomit-frame-pointer2016102820161009
740200? ? ?? ? ?refgcc_-m32_-O_-fomit-frame-pointer2016102820161009
748328? ? ?? ? ?refgcc_-m32_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
749744? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O2_-fomit-frame-pointer2016102820161009
749800? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016102820161009
749824? ? ?? ? ?refgcc_-m32_-march=athlon_-O_-fomit-frame-pointer2016102820161009
751320? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016102820161009
751512? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O_-fomit-frame-pointer2016102820161009
751672? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O_-fomit-frame-pointer2016102820161009
752576? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O_-fomit-frame-pointer2016102820161009
752856? ? ?? ? ?refgcc_-m32_-march=pentium4_-O_-fomit-frame-pointer2016102820161009
753528? ? ?? ? ?refgcc_-m32_-march=k8_-O_-fomit-frame-pointer2016102820161009
753888? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O2_-fomit-frame-pointer2016102820161009
761688? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016102820161009
761984? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O2_-fomit-frame-pointer2016102820161009
771336? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016102820161009
774440? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O2_-fomit-frame-pointer2016102820161009
806736? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O_-fomit-frame-pointer2016102820161009
817216? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O_-fomit-frame-pointer2016102820161009
818536? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016102820161009
824544? ? ?? ? ?refgcc_-m32_-march=i386_-O2_-fomit-frame-pointer2016102820161009
826096? ? ?? ? ?refgcc_-m32_-march=i386_-O_-fomit-frame-pointer2016102820161009
831848? ? ?? ? ?refgcc_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016102820161009
832712? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-Os_-fomit-frame-pointer2016102820161009
837584? ? ?? ? ?refgcc_-m32_-march=k6-2_-O_-fomit-frame-pointer2016102820161009
837640? ? ?? ? ?refgcc_-m32_-march=k6_-O_-fomit-frame-pointer2016102820161009
839104? ? ?? ? ?refgcc_-m32_-march=k6-3_-O_-fomit-frame-pointer2016102820161009
839888? ? ?? ? ?refgcc_-m32_-march=i386_-Os_-fomit-frame-pointer2016102820161009
839912? ? ?? ? ?refgcc_-m32_-march=i486_-Os_-fomit-frame-pointer2016102820161009
840976? ? ?? ? ?refgcc_-m32_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
842328? ? ?? ? ?refgcc_-m32_-march=pentium_-Os_-fomit-frame-pointer2016102820161009
842440? ? ?? ? ?refgcc_-m32_-march=prescott_-Os_-fomit-frame-pointer2016102820161009
843328? ? ?? ? ?refgcc_-m32_-march=core2_-Os_-fomit-frame-pointer2016102820161009
845008? ? ?? ? ?refgcc_-m32_-march=athlon_-Os_-fomit-frame-pointer2016102820161009
845424? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016102820161009
845592? ? ?? ? ?refgcc_-m32_-march=corei7_-Os_-fomit-frame-pointer2016102820161009
846440? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016102820161009
847504? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
847792? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-Os_-fomit-frame-pointer2016102820161009
847920? ? ?? ? ?refgcc_-m32_-Os_-fomit-frame-pointer2016102820161009
849976? ? ?? ? ?refgcc_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
850248? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016102820161009
852096? ? ?? ? ?refgcc_-m32_-march=k8_-Os_-fomit-frame-pointer2016102820161009
852496? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-Os_-fomit-frame-pointer2016102820161009
852744? ? ?? ? ?refgcc_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016102820161009
852752? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016102820161009
853984? ? ?? ? ?refgcc_-funroll-loops_-m32_-Os_-fomit-frame-pointer2016102820161009
854784? ? ?? ? ?refgcc_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016102820161009
856384? ? ?? ? ?refgcc_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016102820161009
859072? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-Os_-fomit-frame-pointer2016102820161009
859568? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-Os_-fomit-frame-pointer2016102820161009
859648? ? ?? ? ?refgcc_-m32_-march=k6_-O2_-fomit-frame-pointer2016102820161009
860464? ? ?? ? ?refgcc_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016102820161009
862160? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016102820161009
864824? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016102820161009
865352? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
866408? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-Os_-fomit-frame-pointer2016102820161009
871312? ? ?? ? ?refgcc_-m32_-march=k6_-Os_-fomit-frame-pointer2016102820161009
890616? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-Os_-fomit-frame-pointer2016102820161009
899376? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016102820161009
901840? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-Os_-fomit-frame-pointer2016102820161009
903720? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016102820161009
908200? ? ?? ? ?refgcc_-m32_-march=pentium_-O2_-fomit-frame-pointer2016102820161009
916624? ? ?? ? ?refgcc_-m32_-march=i486_-O2_-fomit-frame-pointer2016102820161009
939864? ? ?? ? ?refgcc_-m32_-march=pentium_-O_-fomit-frame-pointer2016102820161009
941424? ? ?? ? ?refgcc_-m32_-march=i486_-O_-fomit-frame-pointer2016102820161009
941888? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016102820161009
1264920? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016102820161009
1265072? ? ?? ? ?refgcc_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016102820161009
1266368? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016102820161009
1271112? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016102820161009
1274696? ? ?? ? ?refgcc_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016102820161009
1274872? ? ?? ? ?refgcc_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016102820161009
1275048? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016102820161009
1275224? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016102820161009

Test failure

Implementation: crypto_aead/scream10v1/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/scream10v1/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/scream10v1/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/scream10v1/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