Implementation notes: amd64, katana, crypto_aead/scream10v1

Computer: katana
Architecture: amd64
CPU ID: GenuineIntel-000006f6-bfebfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream10v1
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
123304? ? ?? ? ?ssegcc_-m64_-march=core2_-O3_-fomit-frame-pointer2016102820161009
123568? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
125104? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016102820161009
129656? ? ?? ? ?sseclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016102820161009
129824? ? ?? ? ?sseclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
131080? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
131336? ? ?? ? ?ssegcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016102820161009
131464? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
131768? ? ?? ? ?ssegcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
131912? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
134944? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016102820161009
140768? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
140784? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
140824? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
141040? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016102820161009
141200? ? ?? ? ?ssegcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016102820161009
142824? ? ?? ? ?ssegcc_-m64_-march=core2_-O_-fomit-frame-pointer2016102820161009
529376? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
530744? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
532872? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2016102820161009
535736? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2016102820161009
536744? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2016102820161009
537424? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
539904? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
539968? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2016102820161009
540624? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
541840? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
542320? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
542808? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016102820161009
543576? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
546496? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2016102820161009
546544? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
548544? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2016102820161009
548720? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102820161009
549208? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2016102820161009
549224? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2016102820161009
549424? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2016102820161009
550200? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102820161009
569240? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
571256? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
577648? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2016102820161009
577704? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2016102820161009
577960? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102820161009
578136? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2016102820161009
578152? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2016102820161009
579712? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
580984? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
607672? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2016102820161009
608672? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2016102820161009
618400? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2016102820161009
619440? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2016102820161009
619472? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2016102820161009
619512? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2016102820161009
619712? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
619984? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
621520? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2016102820161009
646160? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2016102820161009
647112? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
647656? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
647840? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016102820161009
647896? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
648760? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
672200? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
673432? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016102820161009
673704? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
674704? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
674984? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
675464? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016102820161009
677912? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2016102820161009
677976? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102820161009
678216? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2016102820161009
680552? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2016102820161009
681096? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2016102820161009
682592? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
683904? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2016102820161009
683928? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
685624? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
685688? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
686696? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
686848? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2016102820161009
690648? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
692984? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2016102820161009
693056? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2016102820161009
693336? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2016102820161009
694208? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
694296? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2016102820161009
694816? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016102820161009
694944? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016102820161009
695112? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
695200? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
696400? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2016102820161009
696632? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2016102820161009
761400? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
767752? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
772912? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
773336? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
778056? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2016102820161009
778096? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2016102820161009
778152? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2016102820161009
782280? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
783008? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
786032? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2016102820161009
786536? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
788968? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2016102820161009
789312? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
790616? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102820161009
790760? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2016102820161009
822016? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102820161009
826816? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2016102820161009
830920? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016102820161009
836136? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2016102820161009
839856? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2016102820161009
840672? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2016102820161009
846256? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2016102820161009
856616? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016102820161009
858168? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2016102820161009
2206792? ? ?? ? ?refgcc_-funroll-loops2016102820161009
2211912? ? ?? ? ?refgcc2016102820161009
2216384? ? ?? ? ?refcc2016102820161009

Test failure

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