Implementation notes: amd64, katana, crypto_aead/scream12v2

Computer: katana
Architecture: amd64
CPU ID: GenuineIntel-000006f6-bfebfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream12v2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
144736? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
144936? ? ?? ? ?ssegcc_-m64_-march=core2_-O3_-fomit-frame-pointer2016102820161009
146696? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016102820161009
150464? ? ?? ? ?sseclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016102820161009
150824? ? ?? ? ?sseclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
153960? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
154240? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
154344? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
154920? ? ?? ? ?ssegcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016102820161009
155856? ? ?? ? ?ssegcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
157056? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016102820161009
164488? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016102820161009
164592? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
164600? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
164624? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
164736? ? ?? ? ?ssegcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016102820161009
165128? ? ?? ? ?ssegcc_-m64_-march=core2_-O_-fomit-frame-pointer2016102820161009
618424? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2016102820161009
619152? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
620120? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
620152? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2016102820161009
624784? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
625128? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
628928? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
629568? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
629928? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
630392? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2016102820161009
632968? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016102820161009
633360? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2016102820161009
633920? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
637272? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
640760? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2016102820161009
644408? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102820161009
649800? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2016102820161009
652544? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2016102820161009
654944? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2016102820161009
655688? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102820161009
656584? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2016102820161009
667480? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
676616? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2016102820161009
676920? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102820161009
678944? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2016102820161009
679752? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2016102820161009
679816? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
680528? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
688264? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
693656? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2016102820161009
718088? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2016102820161009
719744? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2016102820161009
728864? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2016102820161009
729048? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2016102820161009
729952? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2016102820161009
730912? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2016102820161009
731032? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2016102820161009
731336? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
732032? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
766472? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
766504? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
766776? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016102820161009
766784? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
767016? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
767472? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2016102820161009
780736? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
780808? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
781608? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
781728? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016102820161009
781872? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
782840? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016102820161009
784792? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
786488? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
787256? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2016102820161009
791472? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2016102820161009
793264? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2016102820161009
799896? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2016102820161009
800408? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2016102820161009
800672? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
801264? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
801304? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102820161009
801824? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2016102820161009
801872? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2016102820161009
802200? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2016102820161009
803224? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2016102820161009
803376? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2016102820161009
810688? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
810872? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
811936? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016102820161009
811992? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016102820161009
812112? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
812936? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2016102820161009
816704? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2016102820161009
819696? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
820656? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
882376? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
889088? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2016102820161009
889920? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
890016? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
893064? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
896608? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2016102820161009
896704? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102820161009
904912? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
905264? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016102820161009
905728? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016102820161009
906704? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2016102820161009
906856? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
907408? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2016102820161009
909856? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2016102820161009
910824? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2016102820161009
913056? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2016102820161009
919520? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2016102820161009
928592? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2016102820161009
929696? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
933632? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2016102820161009
965208? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
982112? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2016102820161009
984560? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102820161009
997376? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2016102820161009
2608648? ? ?? ? ?refcc2016102820161009
2624840? ? ?? ? ?refgcc2016102820161009
2625280? ? ?? ? ?refgcc_-funroll-loops2016102820161009

Test failure

Implementation: crypto_aead/scream12v2/sse
Compiler: gcc -m64 -march=core2 -Os -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 6, namely:
CompilerImplementations
gcc -m64 -march=core2 -Os -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer sse
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer sse
gcc -m64 -march=corei7 -Os -fomit-frame-pointer sse
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer sse
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv sse

Compiler output

Implementation: crypto_aead/scream12v2/sse
Compiler: cc
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: 71, namely:
CompilerImplementations
cc sse
gcc sse
gcc -O2 -fomit-frame-pointer sse
gcc -O3 -fomit-frame-pointer sse
gcc -O -fomit-frame-pointer sse
gcc -Os -fomit-frame-pointer sse
gcc -fno-schedule-insns -O2 -fomit-frame-pointer sse
gcc -fno-schedule-insns -O3 -fomit-frame-pointer sse
gcc -fno-schedule-insns -O -fomit-frame-pointer sse
gcc -fno-schedule-insns -Os -fomit-frame-pointer sse
gcc -funroll-loops sse
gcc -funroll-loops -O2 -fomit-frame-pointer sse
gcc -funroll-loops -O3 -fomit-frame-pointer sse
gcc -funroll-loops -O -fomit-frame-pointer sse
gcc -funroll-loops -Os -fomit-frame-pointer sse
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer sse
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer sse
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer sse
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer sse
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m64 -O -fomit-frame-pointer sse
gcc -funroll-loops -m64 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer sse
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer sse
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer sse
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer sse
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer sse
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer sse
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer sse
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer sse
gcc -m64 -O2 -fomit-frame-pointer sse
gcc -m64 -O3 -fomit-frame-pointer sse
gcc -m64 -O -fomit-frame-pointer sse
gcc -m64 -Os -fomit-frame-pointer sse
gcc -m64 -march=k8 -O2 -fomit-frame-pointer sse
gcc -m64 -march=k8 -O3 -fomit-frame-pointer sse
gcc -m64 -march=k8 -O -fomit-frame-pointer sse
gcc -m64 -march=k8 -Os -fomit-frame-pointer sse
gcc -m64 -march=nocona -O2 -fomit-frame-pointer sse
gcc -m64 -march=nocona -O3 -fomit-frame-pointer sse
gcc -m64 -march=nocona -O -fomit-frame-pointer sse
gcc -m64 -march=nocona -Os -fomit-frame-pointer sse
gcc -march=barcelona -O2 -fomit-frame-pointer sse
gcc -march=barcelona -O3 -fomit-frame-pointer sse
gcc -march=barcelona -O -fomit-frame-pointer sse
gcc -march=barcelona -Os -fomit-frame-pointer sse
gcc -march=k8 -O2 -fomit-frame-pointer sse
gcc -march=k8 -O3 -fomit-frame-pointer sse
gcc -march=k8 -O -fomit-frame-pointer sse
gcc -march=k8 -Os -fomit-frame-pointer sse
gcc -march=nocona -O2 -fomit-frame-pointer sse
gcc -march=nocona -O3 -fomit-frame-pointer sse
gcc -march=nocona -O -fomit-frame-pointer sse
gcc -march=nocona -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream12v2/sse
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
scream.c: scream.c:185:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:204:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:211:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments sse
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse

Compiler output

Implementation: crypto_aead/scream12v2/sse
Compiler: gcc -m64 -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 -m64 -march=barcelona -O2 -fomit-frame-pointer sse
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer sse
gcc -m64 -march=barcelona -O -fomit-frame-pointer sse
gcc -m64 -march=barcelona -Os -fomit-frame-pointer sse