Implementation notes: x86, katana, crypto_aead/scream12v3

Computer: katana
Architecture: x86
CPU ID: GenuineIntel-000006f6-bfebfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream12v3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
671224? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016102820161009
673848? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016102820161009
675864? ? ?? ? ?refgcc_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016102820161009
676200? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016102820161009
677200? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016102820161009
679656? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O3_-fomit-frame-pointer2016102820161009
686808? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016102820161009
688536? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016102820161009
694912? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016102820161009
695088? ? ?? ? ?refgcc_-m32_-march=pentium2_-O3_-fomit-frame-pointer2016102820161009
695784? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2016102820161009
704592? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2016102820161009
739792? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-O_-fomit-frame-pointer2016102820161009
740120? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016102820161009
741160? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-O_-fomit-frame-pointer2016102820161009
741232? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016102820161009
782816? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
783208? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O3_-fomit-frame-pointer2016102820161009
804640? ? ?? ? ?refgcc_-m32_-march=k8_-O3_-fomit-frame-pointer2016102820161009
810416? ? ?? ? ?refgcc_-m32_-O3_-fomit-frame-pointer2016102820161009
814936? ? ?? ? ?refgcc_-funroll-loops_-m32_-O3_-fomit-frame-pointer2016102820161009
815120? ? ?? ? ?refgcc_-m32_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
822280? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O3_-fomit-frame-pointer2016102820161009
822392? ? ?? ? ?refgcc_-m32_-march=core2_-O3_-fomit-frame-pointer2016102820161009
829392? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
829680? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
831216? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O3_-fomit-frame-pointer2016102820161009
835128? ? ?? ? ?refgcc_-m32_-march=athlon_-O3_-fomit-frame-pointer2016102820161009
835664? ? ?? ? ?refgcc_-m32_-march=prescott_-O3_-fomit-frame-pointer2016102820161009
837040? ? ?? ? ?refgcc_-m32_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
846720? ? ?? ? ?refgcc_-m32_-march=pentium2_-O2_-fomit-frame-pointer2016102820161009
850320? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016102820161009
850856? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2016102820161009
858448? ? ?? ? ?refgcc_-m32_-march=pentium-m_-O_-fomit-frame-pointer2016102820161009
861576? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2016102820161009
862008? ? ?? ? ?refgcc_-m32_-march=pentium3_-O2_-fomit-frame-pointer2016102820161009
862872? ? ?? ? ?refgcc_-m32_-march=pentium3_-O_-fomit-frame-pointer2016102820161009
863440? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O2_-fomit-frame-pointer2016102820161009
868200? ? ?? ? ?refgcc_-m32_-march=pentium4_-O3_-fomit-frame-pointer2016102820161009
874920? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O2_-fomit-frame-pointer2016102820161009
877544? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
888224? ? ?? ? ?refgcc_-funroll-loops_-m32_-O2_-fomit-frame-pointer2016102820161009
893472? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016102820161009
906384? ? ?? ? ?refgcc_-m32_-march=pentium2_-O_-fomit-frame-pointer2016102820161009
909936? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2016102820161009
910664? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
911384? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O2_-fomit-frame-pointer2016102820161009
913560? ? ?? ? ?refgcc_-m32_-march=athlon_-O_-fomit-frame-pointer2016102820161009
917216? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-O_-fomit-frame-pointer2016102820161009
917888? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-O_-fomit-frame-pointer2016102820161009
918424? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-O_-fomit-frame-pointer2016102820161009
918472? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-O_-fomit-frame-pointer2016102820161009
920856? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
929128? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O2_-fomit-frame-pointer2016102820161009
931632? ? ?? ? ?refgcc_-funroll-loops_-m32_-O_-fomit-frame-pointer2016102820161009
936096? ? ?? ? ?refgcc_-m32_-march=k8_-O_-fomit-frame-pointer2016102820161009
938904? ? ?? ? ?refgcc_-m32_-march=k8_-O2_-fomit-frame-pointer2016102820161009
938936? ? ?? ? ?refgcc_-m32_-march=athlon_-O2_-fomit-frame-pointer2016102820161009
941856? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-O_-fomit-frame-pointer2016102820161009
942544? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016102820161009
942720? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016102820161009
943376? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O3_-fomit-frame-pointer2016102820161009
947664? ? ?? ? ?refgcc_-m32_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
952008? ? ?? ? ?refgcc_-m32_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
953264? ? ?? ? ?refgcc_-m32_-march=pentium4_-O_-fomit-frame-pointer2016102820161009
956432? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O3_-fomit-frame-pointer2016102820161009
956904? ? ?? ? ?refgcc_-m32_-march=k6-2_-O3_-fomit-frame-pointer2016102820161009
957992? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
958064? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
958104? ? ?? ? ?refgcc_-m32_-march=core2_-O_-fomit-frame-pointer2016102820161009
958288? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
958464? ? ?? ? ?refgcc_-m32_-march=k6-3_-O3_-fomit-frame-pointer2016102820161009
959360? ? ?? ? ?refgcc_-m32_-O_-fomit-frame-pointer2016102820161009
962600? ? ?? ? ?refgcc_-m32_-march=i386_-O3_-fomit-frame-pointer2016102820161009
963224? ? ?? ? ?refgcc_-m32_-march=corei7_-O_-fomit-frame-pointer2016102820161009
964104? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016102820161009
964208? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O3_-fomit-frame-pointer2016102820161009
965400? ? ?? ? ?refgcc_-m32_-march=k6_-O3_-fomit-frame-pointer2016102820161009
967784? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O3_-fomit-frame-pointer2016102820161009
970216? ? ?? ? ?refgcc_-m32_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
971952? ? ?? ? ?refgcc_-m32_-O2_-fomit-frame-pointer2016102820161009
973472? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
974624? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
974776? ? ?? ? ?refgcc_-m32_-march=core2_-O2_-fomit-frame-pointer2016102820161009
975608? ? ?? ? ?refgcc_-m32_-march=nocona_-O_-fomit-frame-pointer2016102820161009
975640? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
982480? ? ?? ? ?refgcc_-m32_-march=prescott_-O_-fomit-frame-pointer2016102820161009
989440? ? ?? ? ?refgcc_-m32_-march=prescott_-O2_-fomit-frame-pointer2016102820161009
991832? ? ?? ? ?refgcc_-m32_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
995488? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2016102820161009
996360? ? ?? ? ?refgcc_-m32_-march=pentium_-O3_-fomit-frame-pointer2016102820161009
1027040? ? ?? ? ?refgcc_-m32_-march=i486_-O3_-fomit-frame-pointer2016102820161009
1046368? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O_-fomit-frame-pointer2016102820161009
1047552? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O_-fomit-frame-pointer2016102820161009
1047784? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O_-fomit-frame-pointer2016102820161009
1048616? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O_-fomit-frame-pointer2016102820161009
1050144? ? ?? ? ?refgcc_-m32_-march=i386_-O_-fomit-frame-pointer2016102820161009
1058456? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016102820161009
1058552? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O2_-fomit-frame-pointer2016102820161009
1068048? ? ?? ? ?refgcc_-m32_-march=k8_-Os_-fomit-frame-pointer2016102820161009
1069176? ? ?? ? ?refgcc_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
1074064? ? ?? ? ?refgcc_-m32_-march=corei7_-Os_-fomit-frame-pointer2016102820161009
1075152? ? ?? ? ?refgcc_-m32_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016102820161009
1077800? ? ?? ? ?refgcc_-m32_-march=pentium4_-O2_-fomit-frame-pointer2016102820161009
1078688? ? ?? ? ?refgcc_-m32_-march=i386_-O2_-fomit-frame-pointer2016102820161009
1080672? ? ?? ? ?refgcc_-m32_-march=prescott_-Os_-fomit-frame-pointer2016102820161009
1083560? ? ?? ? ?refgcc_-m32_-march=athlon_-Os_-fomit-frame-pointer2016102820161009
1085536? ? ?? ? ?refgcc_-m32_-Os_-fomit-frame-pointer2016102820161009
1085992? ? ?? ? ?refgcc_-m32_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
1087320? ? ?? ? ?refgcc_-funroll-loops_-m32_-Os_-fomit-frame-pointer2016102820161009
1087616? ? ?? ? ?refgcc_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016102820161009
1090336? ? ?? ? ?refgcc_-m32_-march=core2_-msse4_-Os_-fomit-frame-pointer2016102820161009
1091784? ? ?? ? ?refgcc_-m32_-march=i386_-Os_-fomit-frame-pointer2016102820161009
1092568? ? ?? ? ?refgcc_-m32_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016102820161009
1092800? ? ?? ? ?refgcc_-m32_-march=core2_-Os_-fomit-frame-pointer2016102820161009
1093584? ? ?? ? ?refgcc_-m32_-march=i486_-Os_-fomit-frame-pointer2016102820161009
1096120? ? ?? ? ?refgcc_-m32_-march=k6-2_-O_-fomit-frame-pointer2016102820161009
1096328? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=athlon_-Os_-fomit-frame-pointer2016102820161009
1099832? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium4_-Os_-fomit-frame-pointer2016102820161009
1100128? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=prescott_-Os_-fomit-frame-pointer2016102820161009
1100912? ? ?? ? ?refgcc_-m32_-march=pentium_-Os_-fomit-frame-pointer2016102820161009
1100928? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
1101736? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016102820161009
1102024? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-O2_-fomit-frame-pointer2016102820161009
1102264? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016102820161009
1102920? ? ?? ? ?refgcc_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016102820161009
1103352? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-O2_-fomit-frame-pointer2016102820161009
1103480? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k8_-Os_-fomit-frame-pointer2016102820161009
1104088? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
1104680? ? ?? ? ?refgcc_-m32_-march=k6_-O_-fomit-frame-pointer2016102820161009
1105008? ? ?? ? ?refgcc_-m32_-march=k6-3_-O_-fomit-frame-pointer2016102820161009
1105096? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-Os_-fomit-frame-pointer2016102820161009
1107624? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016102820161009
1117096? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i386_-O_-fomit-frame-pointer2016102820161009
1117312? ? ?? ? ?refgcc_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016102820161009
1118168? ? ?? ? ?refgcc_-m32_-march=k6_-Os_-fomit-frame-pointer2016102820161009
1120784? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-Os_-fomit-frame-pointer2016102820161009
1121424? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2016102820161009
1122208? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium_-O_-fomit-frame-pointer2016102820161009
1126096? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=i486_-Os_-fomit-frame-pointer2016102820161009
1126688? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016102820161009
1140336? ? ?? ? ?refgcc_-m32_-march=k6-3_-O2_-fomit-frame-pointer2016102820161009
1146936? ? ?? ? ?refgcc_-m32_-march=k6-2_-O2_-fomit-frame-pointer2016102820161009
1147360? ? ?? ? ?refgcc_-m32_-march=pentium_-O_-fomit-frame-pointer2016102820161009
1152320? ? ?? ? ?refgcc_-m32_-march=i486_-O2_-fomit-frame-pointer2016102820161009
1161224? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2016102820161009
1164744? ? ?? ? ?refgcc_-m32_-march=i486_-O_-fomit-frame-pointer2016102820161009
1164896? ? ?? ? ?refgcc_-m32_-march=k6_-O2_-fomit-frame-pointer2016102820161009
1173136? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6_-Os_-fomit-frame-pointer2016102820161009
1173440? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-2_-Os_-fomit-frame-pointer2016102820161009
1177912? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=k6-3_-Os_-fomit-frame-pointer2016102820161009
1182784? ? ?? ? ?refgcc_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2016102820161009
1184864? ? ?? ? ?refgcc_-m32_-march=pentium_-O2_-fomit-frame-pointer2016102820161009
1500152? ? ?? ? ?refgcc_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016102820161009
1500200? ? ?? ? ?refgcc_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016102820161009
1501568? ? ?? ? ?refgcc_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016102820161009
1507256? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016102820161009
1509264? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium3_-Os_-fomit-frame-pointer2016102820161009
1510384? ? ?? ? ?refgcc_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2016102820161009
1516632? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentium2_-Os_-fomit-frame-pointer2016102820161009
1516856? ? ?? ? ?refgcc_-funroll-loops_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2016102820161009

Test failure

Implementation: crypto_aead/scream12v3/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/scream12v3/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:199:10: note: in expansion of macro 'shift_right'
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:199:5: 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:200:5: 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:202:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:202:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:203:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:207:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: ...

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/scream12v3/sse
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:202:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:202:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:203:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:207:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:208:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:215:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:216:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:220:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...

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/scream12v3/sse
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:202:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:202:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:203:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:207:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:208:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:215:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:216:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:220:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:202:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:202:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:203:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:207:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:208:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:215:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:216:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:220:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -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