Implementation notes: x86, samba, crypto_sign/sphincsf128shake256robust

Computer: samba
Architecture: x86
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_sign
Primitive: sphincsf128shake256robust
TimeImplementationCompilerBenchmark dateSUPERCOP version
400919123avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
401174651avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
609009692avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
609030045avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
612467223avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
612511879avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
654179445avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
654317900avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
1283545348refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2019080820190803
1285400589refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2019080820190803
1285605887refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2019080820190803
1292199510refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2019080820190803
1306943200refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
1307373193refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
1307561742refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
1339198167refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
1419127835refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
1449692155refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
1455323614refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2019080820190803
1455478840refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2019080820190803
1484711456refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1484813216refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1486997034refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1487124645refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1490573628refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
1509002778refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
1509028355refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
1514387335refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
1524715494refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
1525533869refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
1526111633refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
1533841582refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
1533888095refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
1544108117refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
1544207992refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
1556026474refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
1561580623refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2019080820190803
1561920625refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2019080820190803
1568714546refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2019080820190803
1568817788refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2019080820190803
1568977998refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
1569058215refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
1602246947refgcc -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
1602386365refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
1602464304refgcc -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
1619424363refgcc -m32 -march=core2 -Os -fomit-frame-pointer2019080820190803
1619448051refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2019080820190803
1619481157refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2019080820190803
1619610401refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2019080820190803
1634211821refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2019080820190803
1634289883refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2019080820190803
1635068780refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2019080820190803
1641896694refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
1641938869refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
1641986070refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
1673327379refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
1684022426refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
1709959381refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
1759796824refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2019080820190803
1763208629refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
1763252322refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
1811268917refgcc -m32 -O3 -fomit-frame-pointer2019080820190803
1814141022refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
1817353681refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
1820489313refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
1820584982refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
1822483417refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
1824820699refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2019080820190803
1833893804refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
1839996490refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
1844353528refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
1844567801refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
1847611705refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
1860864303refgcc -funroll-loops -m32 -O -fomit-frame-pointer2019080820190803
1862290635refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
1862888066refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2019080820190803
1864874589refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
1864884248refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
1864951645refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
1867322996refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
1867368736refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
1867498496refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
1874494688refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
1874527734refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
1875299241refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
1888801395refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
1888972560refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
1907103341refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
1912167382refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
1913535337refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
1918130710refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
1927061068refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
1937324381refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
1939201262refgcc -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
1940370415refgcc -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
1940412155refgcc -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
1945335246refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
1945341855refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
1949924478refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
1951186884refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
1959219163refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
1960336944refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
1960344971refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
1960731278refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
1960790030refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
1965482844refgcc -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
1976352411refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
1982009494refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2019080820190803
1982113903refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
1982214258refgcc -m32 -march=corei7 -O -fomit-frame-pointer2019080820190803
1982272065refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2019080820190803
1984497157refgcc -m32 -march=core2 -O -fomit-frame-pointer2019080820190803
1984529706refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2019080820190803
1984547474refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2019080820190803
2001319851refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
2008132770refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
2008146065refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
2008372718refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
2034192008refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
2034210879refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
2034774280refgcc -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
2034906129refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
2034993447refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
2043610840refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
2043631800refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
2045104828refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
2045217586refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
2045425875refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
2049851722refgcc -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
2050473264refgcc -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
2053884315refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
2054167276refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
2060097226refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
2068982976refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
2069066014refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
2070127851refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
2070701020refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
2082567329refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
2082612797refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
2082705946refgcc -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
2083110669refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
2090939750refgcc -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
2091583002refgcc -m32 -Os -fomit-frame-pointer2019080820190803
2100290649refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
2100335147refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
2100694716refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
2124161512refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2019080820190803
2126148490refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
2229183746refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
2229276115refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
2229462407refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
2231516754refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
2232041548refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
2232245905refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
2243456564refgcc -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
2243724629refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
2245230734refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
2258985576refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
2266353695refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
2267404930refgcc -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
2306826918refgcc -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
2309761816refgcc -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
2311852317refgcc -m32 -O -fomit-frame-pointer2019080820190803
2324556389refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
2333126849refgcc -m32 -O2 -fomit-frame-pointer2019080820190803
2343269371refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
2343527968refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
2343954859refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
2364052548refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
2364274744refgcc -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
2432377238refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
2432402318refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
4198557732refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
4250500673refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
4542002948refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
4548638718refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
4751099750refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2019080820190803
4769655536refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803
4864988565refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
4901017643refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
5094355387refgcc -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
5120732131refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
5170902889refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2019080820190803
5241976998refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803

Compiler output

Implementation: crypto_sign/sphincsf128shake256robust/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/sphincsf128shake256robust/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/sphincsf128shake256robust/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