Implementation notes: amd64, gpu, crypto_aead/scream12v2

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_aead
Primitive: scream12v2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
7052423513 0 042917 784 928ssegcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2019083020190816
7150523513 0 042917 784 928ssegcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2019083020190816
7449323785 0 043093 784 928ssegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019083020190816
7710023513 0 042917 784 928ssegcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019083020190816
7993212997 0 030013 784 928ssegcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019083020190816
8426032915 0 054325 760 1160sseclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
8437612997 0 030013 784 928ssegcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2019083020190816
8679212997 0 030013 784 928ssegcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2019083020190816
8940925749 0 045109 784 928ssegcc_-m64_-march=core2_-O3_-fomit-frame-pointer2019083020190816
8959613069 0 030085 784 928ssegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019083020190816
9011225749 0 045125 784 928ssegcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2019083020190816
9050032915 0 054325 760 1160sseclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2019083020190816
9071232915 0 053541 760 1160sseclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019083020190816
9098113434 0 030221 784 928ssegcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2019083020190816
9113713450 0 030237 784 928ssegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019083020190816
9142213434 0 030221 784 928ssegcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019083020190816
9364813434 0 030221 784 928ssegcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2019083020190816
9475232915 0 053541 760 1160sseclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019083020190816
9495613617 0 030677 784 928ssegcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2019083020190816
9515413617 0 030677 784 928ssegcc_-m64_-march=core2_-O2_-fomit-frame-pointer2019083020190816
9633914081 0 031101 784 928ssegcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2019083020190816
10027225749 0 045061 784 928ssegcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019083020190816
10068813617 0 030677 784 928ssegcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019083020190816
10746914517 0 031293 784 928ssegcc_-m64_-march=corei7_-O_-fomit-frame-pointer2019083020190816
10772713744 0 030525 784 928ssegcc_-m64_-march=core2_-O_-fomit-frame-pointer2019083020190816
10785013744 0 030525 784 928ssegcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019083020190816
10787413744 0 030525 784 928ssegcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2019083020190816
18734426213 0 045405 784 928ssegcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2019083020190816
4278519295 0 028597 784 928refgcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2019083020190816
4279149333 0 028597 784 928refgcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2019083020190816
4283289277 0 028365 784 928refgcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2019083020190816
4291029295 0 028597 784 928refgcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2019083020190816
4291538977 0 031253 784 928refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2019083020190816
4300748967 0 030997 784 928refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2019083020190816
4300748742 0 027957 784 928refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019083020190816
4307678745 0 028421 784 928refgcc_-march=barcelona_-O3_-fomit-frame-pointer2019083020190816
43364417490 0 028421 784 928refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2019083020190816
4341577517 0 028061 760 1160refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019083020190816
4343257517 0 028061 760 1160refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019083020190816
43535610496 0 030733 784 928refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019083020190816
4354449555 0 030541 784 928refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2019083020190816
43563610496 0 030733 784 928refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019083020190816
43570810496 0 030733 784 928refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2019083020190816
43602910324 0 030277 784 928refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2019083020190816
4391329365 0 028613 784 928refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2019083020190816
43934110516 0 030133 784 928refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2019083020190816
4394409333 0 028533 784 928refgcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019083020190816
44013210688 0 031005 784 928refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2019083020190816
44019210596 0 030637 784 928refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2019083020190816
4413688967 0 030997 784 928refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2019083020190816
4415288977 0 031253 784 928refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2019083020190816
44171610688 0 031005 784 928refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2019083020190816
4445488713 0 028085 784 928refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2019083020190816
4446408713 0 028085 784 928refgcc_-march=k8_-O3_-fomit-frame-pointer2019083020190816
4451407517 0 028845 760 1160refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
4453449775 0 031325 784 928refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019083020190816
4459029503 0 028733 784 928refgcc_-O3_-fomit-frame-pointer2019083020190816
4460829503 0 028733 784 928refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019083020190816
4465479775 0 031325 784 928refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2019083020190816
4471167517 0 028845 760 1160refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2019083020190816
44716410516 0 030133 784 928refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2019083020190816
44782810172 0 030189 784 928refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2019083020190816
44794410324 0 030277 784 928refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2019083020190816
4481049555 0 030541 784 928refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2019083020190816
44862310224 0 030405 784 928refgcc_-funroll-loops_-O_-fomit-frame-pointer2019083020190816
45133510172 0 030189 784 928refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2019083020190816
4513769281 0 027997 784 928refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2019083020190816
45281610596 0 030637 784 928refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2019083020190816
4531507695 0 031277 760 872refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
4531987695 0 031277 760 872refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
45781210123 0 030085 784 928refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2019083020190816
4579329775 0 031325 784 928refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019083020190816
4583049503 0 028733 784 928refgcc_-m64_-O3_-fomit-frame-pointer2019083020190816
45888010123 0 030085 784 928refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2019083020190816
46071210224 0 030405 784 928refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019083020190816
46163210224 0 030405 784 928refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2019083020190816
4636169281 0 027997 784 928refgcc_-march=nocona_-O3_-fomit-frame-pointer2019083020190816
4659289295 0 028597 784 928refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019083020190816
4664167695 0 031277 760 872refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019083020190816
4667047686 0 029949 760 872refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019083020190816
6608976485 0 023437 784 928refgcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2019083020190816
6793126485 0 023437 784 928refgcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2019083020190816
6810166524 0 023525 784 928refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019083020190816
6815136270 0 022989 784 928refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2019083020190816
6817086524 0 023525 784 928refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2019083020190816
68179812404 0 022893 784 928refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2019083020190816
6825606270 0 022989 784 928refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019083020190816
6827976270 0 022989 784 928refgcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2019083020190816
6828246271 0 022989 784 928refgcc_-O_-fomit-frame-pointer2019083020190816
6833446452 0 023317 784 928refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2019083020190816
6866166366 0 022941 784 928refgcc_-march=nocona_-O_-fomit-frame-pointer2019083020190816
6873766468 0 023421 784 928refgcc_-m64_-O2_-fomit-frame-pointer2019083020190816
6880966468 0 023421 784 928refgcc_-O2_-fomit-frame-pointer2019083020190816
69713612968 0 023765 784 928refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2019083020190816
6974566484 0 023765 784 928refgcc_-march=barcelona_-O2_-fomit-frame-pointer2019083020190816
6983406364 0 022797 784 928refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2019083020190816
6988926485 0 023437 784 928refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019083020190816
6994206364 0 022797 784 928refgcc_-march=nocona_-O2_-fomit-frame-pointer2019083020190816
7007606270 0 022989 784 928refgcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2019083020190816
7008166524 0 023525 784 928refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2019083020190816
7015486485 0 023437 784 928refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019083020190816
7017486270 0 022989 784 928refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2019083020190816
7026566271 0 022989 784 928refgcc_-m64_-O_-fomit-frame-pointer2019083020190816
7045686271 0 022989 784 928refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019083020190816
7045726250 0 022853 784 928refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2019083020190816
7049366452 0 023317 784 928refgcc_-march=k8_-O2_-fomit-frame-pointer2019083020190816
7053046366 0 022941 784 928refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2019083020190816
7068606468 0 023421 784 928refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019083020190816
7077646468 0 023421 784 928refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2019083020190816
7192206250 0 022853 784 928refgcc_-march=k8_-O_-fomit-frame-pointer2019083020190816
7203286273 0 022989 784 928refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019083020190816
7209886270 0 022989 784 928refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019083020190816
7211886270 0 022989 784 928refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2019083020190816
7221966202 0 022893 784 928refgcc_-march=barcelona_-O_-fomit-frame-pointer2019083020190816
10267325743 0 021088 760 896refgcc_-march=barcelona_-Os_-fomit-frame-pointer2019083020190816
10275095665 0 020992 760 896refgcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2019083020190816
10284875741 0 021080 760 896refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2019083020190816
10287365665 0 020992 760 896refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019083020190816
10293725638 0 020952 760 896refgcc_-Os_-fomit-frame-pointer2019083020190816
10298375638 0 020960 760 896refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2019083020190816
10339715743 0 021088 760 896refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2019083020190816
10343585743 0 021088 760 896refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2019083020190816
10347905638 0 020952 760 896refgcc_-m64_-Os_-fomit-frame-pointer2019083020190816
103479011486 0 021088 760 896refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2019083020190816
10352885743 0 021080 760 896refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2019083020190816
10401215684 0 021024 760 896refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019083020190816
10545525743 0 021088 760 896refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2019083020190816
10577405665 0 020992 760 896refgcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2019083020190816
10887525638 0 020952 760 896refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019083020190816
10897845741 0 021080 760 896refgcc_-march=nocona_-Os_-fomit-frame-pointer2019083020190816
10904165743 0 021080 760 896refgcc_-march=k8_-Os_-fomit-frame-pointer2019083020190816
11745065795 0 021176 760 896refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2019083020190816
11755055795 0 021176 760 896refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2019083020190816
11774885791 0 021168 760 896refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2019083020190816
11789855791 0 021168 760 896refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2019083020190816
11807285690 0 021040 760 896refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019083020190816
11818055690 0 021040 760 896refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2019083020190816
11876315690 0 021040 760 896refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019083020190816
12063765795 0 021168 760 896refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2019083020190816
12067525795 0 021168 760 896refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2019083020190816
23855288493 0 026887 768 888refgcc_-funroll-loops2019083020190816
23978768493 0 026887 768 888refcc2019083020190816
25074448493 0 026887 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