Implementation notes: amd64, katana, crypto_aead/scream10v2

Computer: katana
Architecture: amd64
CPU ID: GenuineIntel-000006f6-bfebfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: scream10v2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
122264? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
122880? ? ?? ? ?ssegcc_-m64_-march=core2_-O3_-fomit-frame-pointer2016102820161009
124280? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016102820161009
127408? ? ?? ? ?sseclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016102820161009
129912? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
130680? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
130720? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
130720? ? ?? ? ?ssegcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
130728? ? ?? ? ?ssegcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016102820161009
133784? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016102820161009
139712? ? ?? ? ?ssegcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016102820161009
139880? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
140048? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
140232? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016102820161009
140256? ? ?? ? ?ssegcc_-m64_-march=core2_-O_-fomit-frame-pointer2016102820161009
140888? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
154880? ? ?? ? ?sseclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
530408? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
531400? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
532608? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2016102820161009
532776? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2016102820161009
536328? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
536400? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
536960? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
537592? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2016102820161009
537824? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2016102820161009
539584? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2016102820161009
540816? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
543296? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102820161009
543552? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102820161009
543728? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016102820161009
545008? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2016102820161009
549000? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2016102820161009
549448? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2016102820161009
549712? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102820161009
550096? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2016102820161009
550584? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2016102820161009
555656? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102820161009
570536? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
570968? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
577808? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2016102820161009
577952? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2016102820161009
578080? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2016102820161009
578352? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102820161009
580816? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2016102820161009
581896? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
582480? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
607592? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2016102820161009
608456? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2016102820161009
618104? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2016102820161009
619536? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2016102820161009
619576? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2016102820161009
619832? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
620144? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2016102820161009
620240? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2016102820161009
620784? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
646320? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
646688? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016102820161009
647320? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
647576? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
647872? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102820161009
648360? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2016102820161009
674016? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016102820161009
674776? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102820161009
675288? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102820161009
675904? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016102820161009
676616? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102820161009
677944? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2016102820161009
678120? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
678264? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102820161009
678376? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016102820161009
678480? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2016102820161009
678608? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102820161009
682744? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2016102820161009
683488? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2016102820161009
683968? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2016102820161009
684304? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2016102820161009
684696? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
685640? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102820161009
686272? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2016102820161009
688376? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
688672? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102820161009
690952? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2016102820161009
691056? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2016102820161009
691488? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2016102820161009
691792? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2016102820161009
695808? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2016102820161009
696544? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102820161009
696584? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102820161009
697064? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016102820161009
697536? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016102820161009
697776? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016102820161009
761304? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
763376? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
767496? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
771768? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
771912? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
773808? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2016102820161009
773848? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016102820161009
774632? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2016102820161009
775592? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102820161009
776368? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2016102820161009
777696? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2016102820161009
779208? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2016102820161009
781856? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016102820161009
782792? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2016102820161009
783792? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2016102820161009
784696? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102820161009
786792? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2016102820161009
790160? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2016102820161009
790224? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2016102820161009
791144? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102820161009
792016? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
840928? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2016102820161009
841920? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2016102820161009
842464? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2016102820161009
2212984? ? ?? ? ?refgcc2016102820161009
2234400? ? ?? ? ?refgcc_-funroll-loops2016102820161009
2234744? ? ?? ? ?refcc2016102820161009

Test failure

Implementation: crypto_aead/scream10v2/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/scream10v2/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/scream10v2/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/scream10v2/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