Implementation notes: amd64, gpu, crypto_aead/scream10v1

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_aead
Primitive: scream10v1
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
6046524129 0 043501 784 928ssegcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2019083020190816
6383624129 0 043501 784 928ssegcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2019083020190816
6557624449 0 043725 784 928ssegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019083020190816
6849224129 0 043501 784 928ssegcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019083020190816
6866113493 0 030477 784 928ssegcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2019083020190816
6867613493 0 030477 784 928ssegcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019083020190816
7014333331 0 054709 760 1160sseclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
7051233331 0 053925 760 1160sseclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019083020190816
7314013493 0 030477 784 928ssegcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2019083020190816
7407326781 0 045941 784 928ssegcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2019083020190816
7629233331 0 054709 760 1160sseclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2019083020190816
7686426349 0 045613 784 928ssegcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019083020190816
7695213565 0 030549 784 928ssegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019083020190816
7748433331 0 053925 760 1160sseclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019083020190816
7888214257 0 031005 784 928ssegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019083020190816
7893614241 0 030989 784 928ssegcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2019083020190816
7935014241 0 030989 784 928ssegcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019083020190816
8047626349 0 045661 784 928ssegcc_-m64_-march=core2_-O3_-fomit-frame-pointer2019083020190816
8202614561 0 031549 784 928ssegcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2019083020190816
8284814193 0 031205 784 928ssegcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2019083020190816
8288114193 0 031205 784 928ssegcc_-m64_-march=core2_-O2_-fomit-frame-pointer2019083020190816
8394026349 0 045677 784 928ssegcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2019083020190816
8512814193 0 031205 784 928ssegcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019083020190816
8554414241 0 030989 784 928ssegcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2019083020190816
9207614556 0 031293 784 928ssegcc_-m64_-march=core2_-O_-fomit-frame-pointer2019083020190816
9236714556 0 031293 784 928ssegcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2019083020190816
9432415325 0 032061 784 928ssegcc_-m64_-march=corei7_-O_-fomit-frame-pointer2019083020190816
16794414556 0 031293 784 928ssegcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019083020190816
36108310624 0 030829 784 928refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019083020190816
36128710624 0 030829 784 928refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019083020190816
3617019464 0 028693 784 928refgcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2019083020190816
3624669408 0 028461 784 928refgcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2019083020190816
3635049464 0 028629 784 928refgcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019083020190816
3644919112 0 031349 784 928refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2019083020190816
3647829417 0 028677 784 928refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019083020190816
3653198878 0 028053 784 928refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019083020190816
36597610767 0 031037 784 928refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2019083020190816
36699610709 0 030701 784 928refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2019083020190816
3670028439 0 029725 760 1160refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
3671468439 0 029725 760 1160refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2019083020190816
3696248822 0 028485 784 928refgcc_-march=barcelona_-O3_-fomit-frame-pointer2019083020190816
37079610624 0 030829 784 928refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2019083020190816
37292710446 0 030341 784 928refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2019083020190816
3732209417 0 028677 784 928refgcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2019083020190816
37351810619 0 030213 784 928refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2019083020190816
3736249496 0 028709 784 928refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2019083020190816
3738329417 0 028677 784 928refgcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2019083020190816
3746289112 0 031349 784 928refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2019083020190816
3758848830 0 028165 784 928refgcc_-march=k8_-O3_-fomit-frame-pointer2019083020190816
3760169136 0 031125 784 928refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2019083020190816
37655610767 0 031037 784 928refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2019083020190816
3767528231 0 028733 760 1160refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019083020190816
37681610709 0 030701 784 928refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2019083020190816
3786408231 0 028733 760 1160refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019083020190816
38099110316 0 030453 784 928refgcc_-funroll-loops_-O_-fomit-frame-pointer2019083020190816
38115910316 0 030453 784 928refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2019083020190816
3814289742 0 030701 784 928refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2019083020190816
3818078390 0 031933 760 872refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
38189710316 0 030453 784 928refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019083020190816
38248810274 0 030197 784 928refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2019083020190816
3830139668 0 028861 784 928refgcc_-m64_-O3_-fomit-frame-pointer2019083020190816
3830438318 0 030541 760 872refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019083020190816
38307610446 0 030341 784 928refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2019083020190816
38334010274 0 030197 784 928refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2019083020190816
38342410321 0 030301 784 928refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2019083020190816
38368810619 0 030213 784 928refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2019083020190816
3839379956 0 031469 784 928refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2019083020190816
3839889956 0 031469 784 928refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019083020190816
3845049433 0 028093 784 928refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2019083020190816
3894368830 0 028165 784 928refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2019083020190816
38952817644 0 028485 784 928refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2019083020190816
3922528390 0 031933 760 872refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
3922729668 0 028861 784 928refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019083020190816
3923688390 0 031933 760 872refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
3924329742 0 030701 784 928refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2019083020190816
3935809668 0 028861 784 928refgcc_-O3_-fomit-frame-pointer2019083020190816
3938769956 0 031469 784 928refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019083020190816
3946489433 0 028093 784 928refgcc_-march=nocona_-O3_-fomit-frame-pointer2019083020190816
3978089136 0 031125 784 928refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2019083020190816
41734810321 0 030301 784 928refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2019083020190816
55975212986 0 023717 784 928refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2019083020190816
5634726397 0 022781 784 928refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2019083020190816
5677656484 0 023037 784 928refgcc_-march=nocona_-O_-fomit-frame-pointer2019083020190816
5682846485 0 023317 784 928refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2019083020190816
5686656535 0 023477 784 928refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2019083020190816
5773446369 0 022949 784 928refgcc_-march=k8_-O_-fomit-frame-pointer2019083020190816
5777886389 0 023069 784 928refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019083020190816
5780376369 0 022949 784 928refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2019083020190816
5787646512 0 023437 784 928refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019083020190816
5792736318 0 022973 784 928refgcc_-march=barcelona_-O_-fomit-frame-pointer2019083020190816
5843606485 0 023317 784 928refgcc_-march=k8_-O2_-fomit-frame-pointer2019083020190816
5847806535 0 023477 784 928refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2019083020190816
5849446463 0 023389 784 928refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2019083020190816
5850046463 0 023389 784 928refgcc_-O2_-fomit-frame-pointer2019083020190816
5852046535 0 023477 784 928refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019083020190816
5859966463 0 023389 784 928refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019083020190816
5892246388 0 023069 784 928refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2019083020190816
5928606389 0 023069 784 928refgcc_-O_-fomit-frame-pointer2019083020190816
5932766493 0 023717 784 928refgcc_-march=barcelona_-O2_-fomit-frame-pointer2019083020190816
5943846388 0 023069 784 928refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2019083020190816
5944086388 0 023069 784 928refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019083020190816
5947326388 0 023069 784 928refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019083020190816
5947406512 0 023437 784 928refgcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2019083020190816
5952766397 0 022781 784 928refgcc_-march=nocona_-O2_-fomit-frame-pointer2019083020190816
5975806543 0 023469 784 928refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019083020190816
6002206484 0 023037 784 928refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2019083020190816
6022166463 0 023389 784 928refgcc_-m64_-O2_-fomit-frame-pointer2019083020190816
6089326389 0 023069 784 928refgcc_-m64_-O_-fomit-frame-pointer2019083020190816
6102926388 0 023069 784 928refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2019083020190816
6109646388 0 023069 784 928refgcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2019083020190816
6118286391 0 023069 784 928refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019083020190816
6119406512 0 023437 784 928refgcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2019083020190816
61196412636 0 022973 784 928refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2019083020190816
6281886388 0 023069 784 928refgcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2019083020190816
8646185819 0 021168 760 896refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2019083020190816
8647445819 0 021168 760 896refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2019083020190816
8652575819 0 021160 760 896refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2019083020190816
8652905744 0 021072 760 896refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019083020190816
8656745744 0 021072 760 896refgcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2019083020190816
8658545744 0 021072 760 896refgcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2019083020190816
86610011638 0 021168 760 896refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2019083020190816
8663675819 0 021168 760 896refgcc_-march=barcelona_-Os_-fomit-frame-pointer2019083020190816
8669165763 0 021088 760 896refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019083020190816
8724275717 0 021032 760 896refgcc_-m64_-Os_-fomit-frame-pointer2019083020190816
8872965819 0 021160 760 896refgcc_-march=k8_-Os_-fomit-frame-pointer2019083020190816
8919005819 0 021168 760 896refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2019083020190816
8951005717 0 021032 760 896refgcc_-Os_-fomit-frame-pointer2019083020190816
8980605717 0 021040 760 896refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2019083020190816
9155245817 0 021144 760 896refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2019083020190816
9195285717 0 021032 760 896refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019083020190816
9375045817 0 021144 760 896refgcc_-march=nocona_-Os_-fomit-frame-pointer2019083020190816
9939455865 0 021248 760 896refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2019083020190816
9956165865 0 021256 760 896refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2019083020190816
9956315861 0 021232 760 896refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2019083020190816
9996455763 0 021120 760 896refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019083020190816
10002125865 0 021248 760 896refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2019083020190816
10003685763 0 021120 760 896refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019083020190816
10026695763 0 021120 760 896refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2019083020190816
10273165865 0 021256 760 896refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2019083020190816
10516725861 0 021232 760 896refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2019083020190816
19904858605 0 026999 768 888refgcc_-funroll-loops2019083020190816
20004218605 0 026999 768 888refcc2019083020190816
20521968605 0 026999 768 888refgcc2019083020190816

Test failure

Implementation: ref
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 14, namely:
CompilerImplementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer ref
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer sse
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer sse
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer sse
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer sse
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-avx -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: sse
Security model: unknown
Compiler: cc
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128'; did you mean '__builtin_ia32_psubb128'? [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^~~~~~~~~~~~~~~~~~~~~~~~
scream.c: __builtin_ia32_psubb128
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: ...

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: sse
Security model: unknown
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: sse
Security model: unknown
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'; did you mean '__builtin_ia32_psubb128'? [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^~~~~~~~~~~~~~~~~~~~~~~~
scream.c: __builtin_ia32_psubb128
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: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128'; did you mean '__builtin_ia32_psubb128'? [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^~~~~~~~~~~~~~~~~~~~~~~~
scream.c: __builtin_ia32_psubb128
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: ...

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