Implementation notes: x86, kizomba, crypto_sign/sphincsf192shake256

Computer: kizomba
Architecture: x86
CPU ID: GenuineIntel-000906e9-bfebfbff
SUPERCOP version: 20181216
Operation: crypto_sign
Primitive: sphincsf192shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
561005357avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018083120180818
599488620avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018083120180818
837556581avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018083120180818
859831601avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018083120180818
863456808avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018083120180818
880979841avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018083120180818
1416902679avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018083120180818
1698737956refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018083120180818
1700265413refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2018083120180818
1700296365refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2018083120180818
1717326510refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2018083120180818
1733507789refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2018083120180818
1733801820refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018083120180818
1771059636refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018083120180818
1773581548refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2018083120180818
1914982238refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2018083120180818
1929865841refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2018083120180818
1936900871refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2018083120180818
1939247893refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2018083120180818
1947478012refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018083120180818
1950835603refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2018083120180818
1952709766refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2018083120180818
1963078064refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2018083120180818
1969172387refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2018083120180818
1969206510refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2018083120180818
1969941300refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2018083120180818
1970047063refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2018083120180818
1998148986refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018083120180818
2004068478refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018083120180818
2004247944refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2018083120180818
2004401018refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2018083120180818
2021305702refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2018083120180818
2021612386refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2018083120180818
2039444512refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018083120180818
2039457580refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2018083120180818
2039655732refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2018083120180818
2083709385refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2018083120180818
2083880303refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2018083120180818
2084138815refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2018083120180818
2084696934avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018083120180818
2088914776refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2018083120180818
2089481214refgcc -m32 -march=prescott -Os -fomit-frame-pointer2018083120180818
2089498536refgcc -m32 -march=nocona -Os -fomit-frame-pointer2018083120180818
2117561246refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2018083120180818
2118718563refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2018083120180818
2118931664refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2018083120180818
2119021514refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2018083120180818
2124043587refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2018083120180818
2125413373refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2018083120180818
2133994375refgcc -m32 -march=core2 -Os -fomit-frame-pointer2018083120180818
2135308135refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2018083120180818
2135638818refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2018083120180818
2141641420refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2018083120180818
2142826815refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2018083120180818
2144441873refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2018083120180818
2153094479refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018083120180818
2159600133refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2018083120180818
2176689912refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2018083120180818
2193716103refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018083120180818
2343837783refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2018083120180818
2343976339refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2018083120180818
2377552024refgcc -m32 -march=k8 -O -fomit-frame-pointer2018083120180818
2379848946refgcc -m32 -march=prescott -O -fomit-frame-pointer2018083120180818
2380179943refgcc -m32 -march=nocona -O -fomit-frame-pointer2018083120180818
2386487145refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2018083120180818
2386538608refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2018083120180818
2387641541refgcc -m32 -march=barcelona -O -fomit-frame-pointer2018083120180818
2390408730refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2018083120180818
2390746641refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2018083120180818
2392015163refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2018083120180818
2399079145refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2018083120180818
2412557282refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2018083120180818
2413139992refgcc -m32 -O3 -fomit-frame-pointer2018083120180818
2423851371refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2018083120180818
2425934347refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2018083120180818
2426144097refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2018083120180818
2426337675refgcc -m32 -march=corei7 -O -fomit-frame-pointer2018083120180818
2428094053refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2018083120180818
2431685121refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2018083120180818
2432333025refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2018083120180818
2443243812refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2018083120180818
2446716226refgcc -m32 -march=core2 -O -fomit-frame-pointer2018083120180818
2446838236refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2018083120180818
2447667943refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2018083120180818
2521804085refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2018083120180818
2527280178refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2018083120180818
2529226459refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2018083120180818
2529619701refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018083120180818
2537816702refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2018083120180818
2562763593refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2018083120180818
2568979506refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2018083120180818
2581491682refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2018083120180818
2582021768refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2018083120180818
2582405104refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2018083120180818
2582671775refgcc -funroll-loops -m32 -O -fomit-frame-pointer2018083120180818
2591881707refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2018083120180818
2601152475refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2018083120180818
2602050720refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2018083120180818
2602134298refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2018083120180818
2603051524refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2018083120180818
2611205224refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2018083120180818
2611481554refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2018083120180818
2611594302refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2018083120180818
2641588161refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2018083120180818
2647962911refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2018083120180818
2648311072refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2018083120180818
2648656601refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018083120180818
2669876234refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2018083120180818
2670217775refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2018083120180818
2677738730refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2018083120180818
2677914891refgcc -m32 -march=k6 -Os -fomit-frame-pointer2018083120180818
2678001022refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2018083120180818
2679221694refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018083120180818
2679752607refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2018083120180818
2680728704refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2018083120180818
2686478887refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2018083120180818
2686714207refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018083120180818
2693354841refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2018083120180818
2693485968refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2018083120180818
2696230450refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2018083120180818
2699344758refgcc -m32 -march=i486 -Os -fomit-frame-pointer2018083120180818
2699369841refgcc -m32 -march=i386 -Os -fomit-frame-pointer2018083120180818
2701049903refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2018083120180818
2704639399refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2018083120180818
2705537625refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2018083120180818
2705823715refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2018083120180818
2707586480refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2018083120180818
2733659516refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018083120180818
2734368440refgcc -m32 -march=pentium -Os -fomit-frame-pointer2018083120180818
2745427018refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018083120180818
2745840147refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2018083120180818
2745864240refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2018083120180818
2749736919refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2018083120180818
2752064536refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2018083120180818
2774180986refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018083120180818
2774274556refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2018083120180818
2798318474refgcc -m32 -march=athlon -Os -fomit-frame-pointer2018083120180818
2800076998refgcc -m32 -Os -fomit-frame-pointer2018083120180818
2818781488refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2018083120180818
2818809135refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2018083120180818
2819911413refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2018083120180818
2842530813refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2018083120180818
2842667226refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2018083120180818
2843020030refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2018083120180818
2845149691refgcc -m32 -O -fomit-frame-pointer2018083120180818
2850031093refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2018083120180818
2850149020refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2018083120180818
2850684772refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2018083120180818
2865666173refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2018083120180818
2865934591refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018083120180818
2884664538refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2018083120180818
2884897688refgcc -m32 -march=k6 -O -fomit-frame-pointer2018083120180818
2885080670refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2018083120180818
2916258379refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2018083120180818
2916364750refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2018083120180818
2917573174refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2018083120180818
2921277109refgcc -m32 -O2 -fomit-frame-pointer2018083120180818
2935203863refgcc -m32 -march=athlon -O -fomit-frame-pointer2018083120180818
2936257897refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2018083120180818
2990312027refgcc -m32 -march=i486 -O -fomit-frame-pointer2018083120180818
3006420921refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2018083120180818
3010617657refgcc -m32 -march=i386 -O -fomit-frame-pointer2018083120180818
3015447129refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2018083120180818
3024176496refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2018083120180818
3024539054refgcc -m32 -march=pentium -O -fomit-frame-pointer2018083120180818
3057624643refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2018083120180818
3057744994refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2018083120180818
3057959539refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018083120180818
3106308548refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018083120180818
3106346169refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2018083120180818
5531148581refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2018083120180818
5584361302refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2018083120180818
5956196663refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2018083120180818
5957981822refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2018083120180818
6192997417refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018083120180818
6239847964refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2018083120180818
6255720290refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2018083120180818
6346490925refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2018083120180818
6405340514refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018083120180818
6426774655refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2018083120180818
6526172371refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2018083120180818
6554379143refgcc -m32 -march=k8 -Os -fomit-frame-pointer2018083120180818
6739286319refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2018083120180818
6816783471refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2018083120180818

Compiler output

Implementation: crypto_sign/sphincsf192shake256/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/sphincsf192shake256/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/sphincsf192shake256/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