Implementation notes: amd64, h8bobcat, crypto_aead/scream10v3

Computer: h8bobcat
Architecture: amd64
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream10v3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
325646? ? ?? ? ?ssegcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017081820170718
325817? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017081820170718
331920? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017081820170718
346223? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017081820170718
347790? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017081820170718
347904? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017081820170718
347928? ? ?? ? ?ssegcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017081820170718
350175? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017081820170718
352398? ? ?? ? ?ssegcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017081820170718
354488? ? ?? ? ?ssegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017081820170718
356621? ? ?? ? ?ssegcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017081820170718
356687? ? ?? ? ?sseclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2017081820170718
357362? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017081820170718
357476? ? ?? ? ?ssegcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017081820170718
357575? ? ?? ? ?ssegcc_-m64_-march=core2_-O_-fomit-frame-pointer2017081820170718
358914? ? ?? ? ?ssegcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017081820170718
360672? ? ?? ? ?sseclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017081820170718
579804? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2017081820170718
579889? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2017081820170718
584060? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2017081820170718
584117? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2017081820170718
584131? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2017081820170718
585546? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017081820170718
585576? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2017081820170718
594500? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2017081820170718
595551? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2017081820170718
595864? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2017081820170718
598500? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2017081820170718
598510? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2017081820170718
599697? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2017081820170718
601075? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2017081820170718
601350? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017081820170718
607492? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017081820170718
612532? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2017081820170718
622891? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2017081820170718
623015? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2017081820170718
627456? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2017081820170718
628776? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2017081820170718
630367? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017081820170718
631147? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2017081820170718
631199? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2017081820170718
631556? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2017081820170718
632173? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2017081820170718
632306? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2017081820170718
632415? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2017081820170718
632691? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017081820170718
633902? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017081820170718
646746? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2017081820170718
649025? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2017081820170718
650256? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2017081820170718
651363? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2017081820170718
653538? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2017081820170718
653552? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2017081820170718
653799? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2017081820170718
655723? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2017081820170718
656521? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2017081820170718
897218? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017081820170718
897645? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2017081820170718
897650? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017081820170718
898044? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017081820170718
898767? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2017081820170718
901037? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2017081820170718
903336? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2017081820170718
904757? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2017081820170718
905930? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2017081820170718
906419? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017081820170718
907758? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017081820170718
908333? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017081820170718
908414? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2017081820170718
911630? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017081820170718
912300? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2017081820170718
937133? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2017081820170718
937850? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2017081820170718
938334? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017081820170718
939882? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2017081820170718
944324? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017081820170718
950005? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2017081820170718
950584? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2017081820170718
959281? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2017081820170718
959804? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017081820170718
960165? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017081820170718
960868? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017081820170718
965323? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017081820170718
965490? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2017081820170718
965756? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017081820170718
965799? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2017081820170718
966060? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017081820170718
966478? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017081820170718
971132? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2017081820170718
973759? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2017081820170718
975612? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2017081820170718
977503? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2017081820170718
982676? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2017081820170718
983221? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2017081820170718
984599? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2017081820170718
984822? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017081820170718
987819? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2017081820170718
989245? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2017081820170718
989596? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2017081820170718
989961? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2017081820170718
991363? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2017081820170718
994541? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2017081820170718
1000673? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2017081820170718
1017312? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017081820170718
1017716? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2017081820170718
1020471? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017081820170718
1020632? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017081820170718
1021293? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017081820170718
1029918? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017081820170718
1030612? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017081820170718
1036726? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017081820170718
1038587? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2017081820170718
1040107? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2017081820170718
1040217? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2017081820170718
1043257? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2017081820170718
1044587? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2017081820170718
3607734? ? ?? ? ?refgcc2017081820170718
3617838? ? ?? ? ?refgcc_-funroll-loops2017081820170718
3636306? ? ?? ? ?refcc2017081820170718

Test failure

Implementation: crypto_aead/scream10v3/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/scream10v3/sse
Compiler: cc
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: 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/scream10v3/sse
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
scream.c: scream.c:202:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:203:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:207:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:208:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:215:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:216:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:220:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:221:10: error: '__builtin_ia32_pshufb128' needs target feature ssse3
scream.c: D ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:228:10: 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/scream10v3/sse
Compiler: gcc -m64 -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 -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