Implementation notes: x86, hydra1, crypto_aead/morus640128v2

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: morus640128v2
TimeImplementationCompilerBenchmark dateSUPERCOP version
14229sse2gcc -m32 -march=prescott -O3 -fomit-frame-pointer2016122720161220
14230sse2gcc -m32 -march=nocona -O3 -fomit-frame-pointer2016122720161220
14287sse2gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016122720161220
14333sse2gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016122720161220
14333sse2gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016122720161220
14418sse2gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016122720161220
15645sse2gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016122720161220
15678sse2gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016122720161220
15848sse2gcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016122720161220
15848sse2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016122720161220
15880sse2gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016122720161220
15890sse2gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016122720161220
16360sse2gcc -m32 -march=k8 -O3 -fomit-frame-pointer2016122720161220
17184sse2gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016122720161220
17202sse2gcc -m32 -march=pentium-m -O -fomit-frame-pointer2016122720161220
17314sse2gcc -m32 -march=nocona -O -fomit-frame-pointer2016122720161220
17317sse2gcc -m32 -march=prescott -O -fomit-frame-pointer2016122720161220
17325sse2gcc -m32 -march=k8 -O -fomit-frame-pointer2016122720161220
17486sse2gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016122720161220
17549sse2gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016122720161220
17589sse2gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016122720161220
17589sse2gcc -m32 -march=core2 -O -fomit-frame-pointer2016122720161220
17602sse2gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016122720161220
17680sse2gcc -m32 -march=pentium4 -O -fomit-frame-pointer2016122720161220
17794sse2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016122720161220
17831sse2gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016122720161220
17890sse2gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016122720161220
17901sse2gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016122720161220
17904sse2gcc -m32 -march=nocona -O2 -fomit-frame-pointer2016122720161220
17949sse2gcc -m32 -march=prescott -O2 -fomit-frame-pointer2016122720161220
17965sse2gcc -m32 -march=barcelona -O -fomit-frame-pointer2016122720161220
18038sse2gcc -m32 -march=corei7 -O -fomit-frame-pointer2016122720161220
18111sse2gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016122720161220
18128sse2gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016122720161220
18382sse2gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016122720161220
18464sse2gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016122720161220
18728sse2gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016122720161220
18741sse2gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016122720161220
18851sse2gcc -m32 -march=k8 -O2 -fomit-frame-pointer2016122720161220
19278sse2gcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016122720161220
19413sse2gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016122720161220
19585sse2gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016122720161220
19585sse2gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016122720161220
19605sse2gcc -m32 -march=core2 -O2 -fomit-frame-pointer2016122720161220
20006sse2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016122720161220
20022sse2gcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016122720161220
20368sse2gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016122720161220
34208refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2016122720161220
34419refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2016122720161220
34446refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2016122720161220
34499refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2016122720161220
34508refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2016122720161220
34533refgcc -m32 -O2 -fomit-frame-pointer2016122720161220
34559refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2016122720161220
34592refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2016122720161220
34597refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2016122720161220
34616refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2016122720161220
34624refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2016122720161220
34632refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2016122720161220
34643refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2016122720161220
34648refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2016122720161220
34648refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2016122720161220
34666refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2016122720161220
34667refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2016122720161220
34704refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2016122720161220
34710refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2016122720161220
34718refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2016122720161220
34718refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2016122720161220
34720refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2016122720161220
34768refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2016122720161220
34779refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2016122720161220
34782refgcc -m32 -march=i486 -O -fomit-frame-pointer2016122720161220
34798refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2016122720161220
34799refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2016122720161220
34824refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2016122720161220
34837refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2016122720161220
34850refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2016122720161220
34850refgcc -m32 -march=k8 -O -fomit-frame-pointer2016122720161220
34853refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2016122720161220
34863refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2016122720161220
34864refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2016122720161220
34899refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2016122720161220
34907refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2016122720161220
34910refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2016122720161220
34917refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2016122720161220
34950refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2016122720161220
34973refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2016122720161220
35046refgcc -funroll-loops -m32 -O -fomit-frame-pointer2016122720161220
35063refgcc -m32 -march=i386 -O -fomit-frame-pointer2016122720161220
35090refgcc -m32 -march=athlon -O -fomit-frame-pointer2016122720161220
35099refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2016122720161220
35120refgcc -m32 -march=pentium -O -fomit-frame-pointer2016122720161220
35122refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2016122720161220
35142refgcc -m32 -march=k6 -O -fomit-frame-pointer2016122720161220
35149refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2016122720161220
35200refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2016122720161220
35228refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2016122720161220
35229refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2016122720161220
35264refgcc -m32 -march=nocona -O -fomit-frame-pointer2016122720161220
35266refgcc -m32 -march=barcelona -O -fomit-frame-pointer2016122720161220
35302refgcc -m32 -march=corei7 -O -fomit-frame-pointer2016122720161220
35334refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2016122720161220
35379refgcc -m32 -march=prescott -O -fomit-frame-pointer2016122720161220
35389refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2016122720161220
35389refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2016122720161220
35438refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2016122720161220
35453refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2016122720161220
35536refgcc -m32 -O -fomit-frame-pointer2016122720161220
35549refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2016122720161220
35568refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2016122720161220
35691refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2016122720161220
35696refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2016122720161220
35763refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2016122720161220
35794refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2016122720161220
35821refgcc -m32 -march=core2 -O -fomit-frame-pointer2016122720161220
35824refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2016122720161220
35827refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2016122720161220
36147refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2016122720161220
36160refgcc -m32 -march=prescott -Os -fomit-frame-pointer2016122720161220
36170refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2016122720161220
36212refgcc -m32 -march=nocona -Os -fomit-frame-pointer2016122720161220
36235refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2016122720161220
36533refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2016122720161220
36549refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2016122720161220
36604refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2016122720161220
36608refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016122720161220
36613refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2016122720161220
36618refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2016122720161220
36691refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2016122720161220
36696refgcc -m32 -march=i386 -Os -fomit-frame-pointer2016122720161220
36707refgcc -m32 -march=i486 -Os -fomit-frame-pointer2016122720161220
36730refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2016122720161220
36768refgcc -m32 -march=pentium -Os -fomit-frame-pointer2016122720161220
36784refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2016122720161220
36811refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2016122720161220
36820refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2016122720161220
36842refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2016122720161220
36862refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2016122720161220
36874refgcc -m32 -march=k8 -Os -fomit-frame-pointer2016122720161220
36899refgcc -m32 -march=core2 -Os -fomit-frame-pointer2016122720161220
36909refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2016122720161220
36912refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2016122720161220
36926refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2016122720161220
36927refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2016122720161220
36947refgcc -m32 -march=athlon -Os -fomit-frame-pointer2016122720161220
36955refgcc -m32 -Os -fomit-frame-pointer2016122720161220
36968refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2016122720161220
36977refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2016122720161220
36987refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2016122720161220
36999refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2016122720161220
37000refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2016122720161220
37019refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2016122720161220
37026refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2016122720161220
37054refgcc -m32 -march=k6 -Os -fomit-frame-pointer2016122720161220
37090refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2016122720161220
37101refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2016122720161220
37133refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2016122720161220
37151refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2016122720161220
37946refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2016122720161220
37992refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016122720161220
38008refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2016122720161220
38037refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2016122720161220
38610refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2016122720161220
38640refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016122720161220
38779refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2016122720161220
38798refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2016122720161220
38882refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2016122720161220
38936refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2016122720161220
39341refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2016122720161220
39355refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2016122720161220
43275refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2016122720161220
43349refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2016122720161220
43379refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2016122720161220
43402refgcc -m32 -O3 -fomit-frame-pointer2016122720161220
43408refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2016122720161220
43549refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2016122720161220
43551refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2016122720161220
43619refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2016122720161220
43694refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2016122720161220
43861refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2016122720161220
43892refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2016122720161220
43917refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2016122720161220
43978refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2016122720161220
43995refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016122720161220
44014refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2016122720161220
44037refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2016122720161220
44099refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2016122720161220
44170refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2016122720161220
44227refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2016122720161220
44268refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2016122720161220
44432refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2016122720161220
44447refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2016122720161220
44508refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016122720161220
44706refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2016122720161220
44728refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2016122720161220
45083refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2016122720161220
45272refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2016122720161220
45325refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2016122720161220
45414refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2016122720161220
45430refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2016122720161220
45501refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2016122720161220
45634refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2016122720161220
45658refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2016122720161220
45744refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2016122720161220
45957refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2016122720161220
45959refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2016122720161220
46041refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2016122720161220

Test failure

Implementation: crypto_aead/morus640128v2/sse2
Compiler: gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 36, namely:
CompilerImplementations
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer sse2
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer ref sse2
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer ref sse2
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer ref sse2
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer ref sse2
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer ref sse2
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer ref sse2
gcc -m32 -march=core2 -O3 -fomit-frame-pointer ref sse2
gcc -m32 -march=core2 -Os -fomit-frame-pointer sse2
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer sse2
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer sse2
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer ref sse2
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer ref sse2
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer ref sse2
gcc -m32 -march=corei7 -Os -fomit-frame-pointer sse2
gcc -m32 -march=k8 -Os -fomit-frame-pointer sse2
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer sse2
gcc -m32 -march=nocona -Os -fomit-frame-pointer sse2
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer sse2
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer sse2
gcc -m32 -march=prescott -Os -fomit-frame-pointer sse2

Test failure

Implementation: crypto_aead/morus640128v2/sse2
Compiler: gcc -m32 -march=barcelona -Os -fomit-frame-pointer
error 111
error 111

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
gcc -m32 -march=barcelona -Os -fomit-frame-pointer sse2

Compiler output

Implementation: crypto_aead/morus640128v2/sse2
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer
encrypt.c: encrypt.c: In function 'morus_stateupdate':
encrypt.c: encrypt.c:39:11: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
encrypt.c: state[0] = XOR(state[0], state[3]);
encrypt.c: ^
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
encrypt.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
encrypt.c: from encrypt.c:2:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1415:1: error: inlining failed in call to always_inline '_mm_shuffle_epi32': target specific option mismatch
encrypt.c: _mm_shuffle_epi32 (__m128i __A, const int __mask)
encrypt.c: ^
encrypt.c: encrypt.c:28:24: error: called from here
encrypt.c: #define ROTL32(x) _mm_shuffle_epi32((x),_MM_SHUFFLE(2,1,0,3)) /*Rotate x by 32-bit positions to the left*/
encrypt.c: ^
encrypt.c: encrypt.c:66:13: note: in expansion of macro 'ROTL32'
encrypt.c: state[2] = ROTL32(state[2]);
encrypt.c: ^
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
encrypt.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
encrypt.c: from encrypt.c:2:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
encrypt.c: _mm_xor_si128 (__m128i __A, __m128i __B)
encrypt.c: ^
encrypt.c: encrypt.c:18:24: error: called from here
encrypt.c: #define XOR(x,y) _mm_xor_si128((x),(y)) /*XOR(x,y) = x ^ y, where x and y are two 128-bit word*/
encrypt.c: ^
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 88, namely:
CompilerImplementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer sse2
gcc -m32 -O2 -fomit-frame-pointer sse2
gcc -m32 -O3 -fomit-frame-pointer sse2
gcc -m32 -O -fomit-frame-pointer sse2
gcc -m32 -Os -fomit-frame-pointer sse2
gcc -m32 -march=athlon -O2 -fomit-frame-pointer sse2
gcc -m32 -march=athlon -O3 -fomit-frame-pointer sse2
gcc -m32 -march=athlon -O -fomit-frame-pointer sse2
gcc -m32 -march=athlon -Os -fomit-frame-pointer sse2
gcc -m32 -march=i386 -O2 -fomit-frame-pointer sse2
gcc -m32 -march=i386 -O3 -fomit-frame-pointer sse2
gcc -m32 -march=i386 -O -fomit-frame-pointer sse2
gcc -m32 -march=i386 -Os -fomit-frame-pointer sse2
gcc -m32 -march=i486 -O2 -fomit-frame-pointer sse2
gcc -m32 -march=i486 -O3 -fomit-frame-pointer sse2
gcc -m32 -march=i486 -O -fomit-frame-pointer sse2
gcc -m32 -march=i486 -Os -fomit-frame-pointer sse2
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer sse2
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer sse2
gcc -m32 -march=k6-2 -O -fomit-frame-pointer sse2
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer sse2
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer sse2
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer sse2
gcc -m32 -march=k6-3 -O -fomit-frame-pointer sse2
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer sse2
gcc -m32 -march=k6 -O2 -fomit-frame-pointer sse2
gcc -m32 -march=k6 -O3 -fomit-frame-pointer sse2
gcc -m32 -march=k6 -O -fomit-frame-pointer sse2
gcc -m32 -march=k6 -Os -fomit-frame-pointer sse2
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer sse2
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer sse2
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer sse2
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer sse2
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer sse2
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer sse2
gcc -m32 -march=pentium2 -O -fomit-frame-pointer sse2
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer sse2
gcc -m32 -march=pentium -O2 -fomit-frame-pointer sse2
gcc -m32 -march=pentium -O3 -fomit-frame-pointer sse2
gcc -m32 -march=pentium -O -fomit-frame-pointer sse2
gcc -m32 -march=pentium -Os -fomit-frame-pointer sse2
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer sse2
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer sse2
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer sse2
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer sse2

Compiler output

Implementation: crypto_aead/morus640128v2/sse2
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
encrypt.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
encrypt.c: from encrypt.c:2:
encrypt.c: encrypt.c: In function 'morus_stateupdate':
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1415:1: error: inlining failed in call to always_inline '_mm_shuffle_epi32': target specific option mismatch
encrypt.c: _mm_shuffle_epi32 (__m128i __A, const int __mask)
encrypt.c: ^
encrypt.c: encrypt.c:28:24: error: called from here
encrypt.c: #define ROTL32(x) _mm_shuffle_epi32((x),_MM_SHUFFLE(2,1,0,3)) /*Rotate x by 32-bit positions to the left*/
encrypt.c: ^
encrypt.c: encrypt.c:66:13: note: in expansion of macro 'ROTL32'
encrypt.c: state[2] = ROTL32(state[2]);
encrypt.c: ^
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
encrypt.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:29,
encrypt.c: from encrypt.c:2:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
encrypt.c: _mm_xor_si128 (__m128i __A, __m128i __B)
encrypt.c: ^
encrypt.c: encrypt.c:18:24: error: called from here
encrypt.c: #define XOR(x,y) _mm_xor_si128((x),(y)) /*XOR(x,y) = x ^ y, where x and y are two 128-bit word*/
encrypt.c: ^
encrypt.c: encrypt.c:25:24: note: in expansion of macro 'XOR'
encrypt.c: #define ROTL(x,n) XOR(_mm_slli_epi32((x), (n)), _mm_srli_epi32((x),(32-n))) /*Rotate 4 32-bit unsigned integers in x to the left by n-bit positions*/
encrypt.c: ^
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:
CompilerImplementations
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer sse2
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer sse2
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer sse2
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer sse2
gcc -m32 -march=pentium3 -O -fomit-frame-pointer sse2
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer sse2