Implementation notes: x86, kizomba, crypto_sign/sphincsf128shake256

Computer: kizomba
Architecture: x86
CPU ID: GenuineIntel-000906e9-bfebfbff
SUPERCOP version: 20181216
Operation: crypto_sign
Primitive: sphincsf128shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
405358012avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018083120180818
432723643avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018083120180818
612921716avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018083120180818
626293069avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018083120180818
629312645avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018083120180818
648567418avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018083120180818
1014933724avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018083120180818
1294957062refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2018083120180818
1295961107refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2018083120180818
1297087084refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018083120180818
1310208466refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2018083120180818
1323212040refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018083120180818
1324809204refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2018083120180818
1352731595refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018083120180818
1353718103refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2018083120180818
1452670266refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2018083120180818
1468563115refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2018083120180818
1475931863refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018083120180818
1479695362refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2018083120180818
1481196091refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2018083120180818
1502456010refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2018083120180818
1504006827refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2018083120180818
1504046040refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2018083120180818
1504274818avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018083120180818
1504278440refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2018083120180818
1504628399refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2018083120180818
1506968673refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2018083120180818
1512020114refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2018083120180818
1514914135refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018083120180818
1520372590refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2018083120180818
1520632363refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2018083120180818
1520768156refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018083120180818
1526901800refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2018083120180818
1527150510refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2018083120180818
1529166588refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2018083120180818
1530077443refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2018083120180818
1530168822refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018083120180818
1584780420refgcc -m32 -march=nocona -Os -fomit-frame-pointer2018083120180818
1584878645refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2018083120180818
1585030657refgcc -m32 -march=prescott -Os -fomit-frame-pointer2018083120180818
1586761929refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2018083120180818
1593282635refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2018083120180818
1593298256refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2018083120180818
1593507284refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2018083120180818
1614026785refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2018083120180818
1614503796refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2018083120180818
1618775678refgcc -m32 -march=core2 -Os -fomit-frame-pointer2018083120180818
1619694928refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2018083120180818
1619748482refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2018083120180818
1619908111refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2018083120180818
1625189720refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2018083120180818
1625387071refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2018083120180818
1625756575refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2018083120180818
1631079940refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2018083120180818
1632446004refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2018083120180818
1635304125refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2018083120180818
1649899852refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018083120180818
1680102149refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018083120180818
1681667065refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2018083120180818
1790346348refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2018083120180818
1790408629refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2018083120180818
1793152839refgcc -m32 -march=prescott -O -fomit-frame-pointer2018083120180818
1793292635refgcc -m32 -march=nocona -O -fomit-frame-pointer2018083120180818
1799032780refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2018083120180818
1800539531refgcc -m32 -march=barcelona -O -fomit-frame-pointer2018083120180818
1801149512refgcc -m32 -march=k8 -O -fomit-frame-pointer2018083120180818
1808494963refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2018083120180818
1816837915refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2018083120180818
1825868412refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2018083120180818
1825905996refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2018083120180818
1827022117refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2018083120180818
1832141004refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2018083120180818
1840026783refgcc -m32 -O3 -fomit-frame-pointer2018083120180818
1850164904refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2018083120180818
1850271609refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2018083120180818
1853747049refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2018083120180818
1858724373refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2018083120180818
1872723716refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2018083120180818
1875748347refgcc -m32 -march=corei7 -O -fomit-frame-pointer2018083120180818
1875826597refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2018083120180818
1876069963refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2018083120180818
1894030821refgcc -m32 -march=core2 -O -fomit-frame-pointer2018083120180818
1894288530refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2018083120180818
1894620950refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2018083120180818
1922568855refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2018083120180818
1922751726refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2018083120180818
1928755401refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2018083120180818
1928797867refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018083120180818
1935038353refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2018083120180818
1939199797refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2018083120180818
1967062090refgcc -funroll-loops -m32 -O -fomit-frame-pointer2018083120180818
1970713950refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2018083120180818
1972325756refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2018083120180818
1973127268refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2018083120180818
1973297240refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2018083120180818
1973333414refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2018083120180818
1981322984refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2018083120180818
1981442875refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2018083120180818
1981589549refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2018083120180818
1981733943refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2018083120180818
1982640740refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2018083120180818
2006985947refgcc -m32 -march=k6 -Os -fomit-frame-pointer2018083120180818
2007039575refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2018083120180818
2007086334refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2018083120180818
2010118470refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2018083120180818
2015499833refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018083120180818
2015919482refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2018083120180818
2019563160refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2018083120180818
2019632478refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2018083120180818
2020586238refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2018083120180818
2039998070refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2018083120180818
2045519359refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2018083120180818
2045521258refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018083120180818
2045537235refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2018083120180818
2045970804refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2018083120180818
2046248812refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2018083120180818
2046866649refgcc -m32 -march=i386 -Os -fomit-frame-pointer2018083120180818
2049581589refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2018083120180818
2050488397refgcc -m32 -march=i486 -Os -fomit-frame-pointer2018083120180818
2055463484refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2018083120180818
2055827204refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2018083120180818
2058684897refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2018083120180818
2059474941refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2018083120180818
2059868397refgcc -m32 -march=athlon -Os -fomit-frame-pointer2018083120180818
2060025532refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2018083120180818
2060374948refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2018083120180818
2061132688refgcc -m32 -Os -fomit-frame-pointer2018083120180818
2081533948refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018083120180818
2082520822refgcc -m32 -march=pentium -Os -fomit-frame-pointer2018083120180818
2089833260refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2018083120180818
2089833597refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2018083120180818
2090021933refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2018083120180818
2090107256refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018083120180818
2090231911refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018083120180818
2091395258refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2018083120180818
2092029040refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2018083120180818
2110279492refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2018083120180818
2110338798refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018083120180818
2150426912refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2018083120180818
2151080524refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2018083120180818
2151381869refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2018083120180818
2171358605refgcc -m32 -O -fomit-frame-pointer2018083120180818
2171487314refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018083120180818
2171711002refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2018083120180818
2175553296refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2018083120180818
2175812109refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2018083120180818
2175926913refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2018083120180818
2190202484refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2018083120180818
2190587131refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2018083120180818
2190626819refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2018083120180818
2200312760refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2018083120180818
2219312133refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2018083120180818
2219423673refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2018083120180818
2219791101refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2018083120180818
2224708732refgcc -m32 -march=k6 -O -fomit-frame-pointer2018083120180818
2225246423refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2018083120180818
2225685073refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2018083120180818
2232690434refgcc -m32 -march=athlon -O -fomit-frame-pointer2018083120180818
2237460325refgcc -m32 -O2 -fomit-frame-pointer2018083120180818
2269404294refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2018083120180818
2279172942refgcc -m32 -march=i386 -O -fomit-frame-pointer2018083120180818
2289718598refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2018083120180818
2311772543refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018083120180818
2314189455refgcc -m32 -march=pentium -O -fomit-frame-pointer2018083120180818
2315035191refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2018083120180818
2315082803refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2018083120180818
2315188994refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2018083120180818
2334316623refgcc -m32 -march=i486 -O -fomit-frame-pointer2018083120180818
2351017391refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2018083120180818
2351123990refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018083120180818
4220655399refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2018083120180818
4262027653refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2018083120180818
4547698053refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2018083120180818
4548168070refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2018083120180818
4720496006refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018083120180818
4745926117refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2018083120180818
4763063204refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2018083120180818
4847128141refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2018083120180818
4884585877refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018083120180818
4901262042refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2018083120180818
4979482173refgcc -m32 -march=k8 -Os -fomit-frame-pointer2018083120180818
4989095841refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2018083120180818
5131974635refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2018083120180818
5200847045refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2018083120180818

Compiler output

Implementation: crypto_sign/sphincsf128shake256/avx2
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 156, namely:
CompilerImplementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer avx2
gcc -m32 -O2 -fomit-frame-pointer avx2
gcc -m32 -O3 -fomit-frame-pointer avx2
gcc -m32 -O -fomit-frame-pointer avx2
gcc -m32 -Os -fomit-frame-pointer avx2
gcc -m32 -march=athlon -O2 -fomit-frame-pointer avx2
gcc -m32 -march=athlon -O3 -fomit-frame-pointer avx2
gcc -m32 -march=athlon -O -fomit-frame-pointer avx2
gcc -m32 -march=athlon -Os -fomit-frame-pointer avx2
gcc -m32 -march=core2 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -O -fomit-frame-pointer avx2
gcc -m32 -march=core2 -Os -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer avx2
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=corei7 -O -fomit-frame-pointer avx2
gcc -m32 -march=corei7 -Os -fomit-frame-pointer avx2
gcc -m32 -march=i386 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=i386 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=i386 -O -fomit-frame-pointer avx2
gcc -m32 -march=i386 -Os -fomit-frame-pointer avx2
gcc -m32 -march=i486 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=i486 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=i486 -O -fomit-frame-pointer avx2
gcc -m32 -march=i486 -Os -fomit-frame-pointer avx2
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=k6-2 -O -fomit-frame-pointer avx2
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer avx2
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=k6-3 -O -fomit-frame-pointer avx2
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer avx2
gcc -m32 -march=k6 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=k6 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=k6 -O -fomit-frame-pointer avx2
gcc -m32 -march=k6 -Os -fomit-frame-pointer avx2
gcc -m32 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=k8 -O -fomit-frame-pointer avx2
gcc -m32 -march=k8 -Os -fomit-frame-pointer avx2
gcc -m32 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -m32 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -m32 -march=nocona -O -fomit-frame-pointer avx2
gcc -m32 -march=nocona -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium-m -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium2 -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium3 -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium4 -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer avx2
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer avx2
gcc -m32 -march=prescott -O2 -fomit-frame-pointer avx2
gcc -m32 -march=prescott -O3 -fomit-frame-pointer avx2
gcc -m32 -march=prescott -O -fomit-frame-pointer avx2
gcc -m32 -march=prescott -Os -fomit-frame-pointer avx2

Compiler output

Implementation: crypto_sign/sphincsf128shake256/avx2
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -m32 -march=barcelona -O -fomit-frame-pointer avx2
gcc -m32 -march=barcelona -Os -fomit-frame-pointer avx2

Compiler output

Implementation: crypto_sign/sphincsf128shake256/avx2
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:142:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+2], lanes2 ),\
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:
CompilerImplementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer avx2
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer avx2
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer avx2
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer avx2
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer avx2
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer avx2
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer avx2
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer avx2