Implementation notes: x86, rumba5, crypto_sign/sphincsf192shake256

Computer: rumba5
Architecture: x86
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20181216
Operation: crypto_sign
Primitive: sphincsf192shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
872151808avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018090320180818
896799968avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018090320180818
1252217504avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018090320180818
1252300640avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018090320180818
1256356576avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018090320180818
1262816928avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018090320180818
1264685344avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018090320180818
1298196512avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018090320180818
2937721952refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018090320180818
2959040736refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018090320180818
3126217632refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2018090320180818
3130792416refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2018090320180818
3131374560refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018090320180818
3133750816refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2018090320180818
3136561248refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2018090320180818
3144391296refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2018090320180818
3149265056refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2018090320180818
3173206720refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2018090320180818
3173674176refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2018090320180818
3180825088refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2018090320180818
3183177792refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2018090320180818
3186175328refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2018090320180818
3187566784refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2018090320180818
3194699712refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2018090320180818
3204810592refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2018090320180818
3205254144refgcc -m32 -O3 -fomit-frame-pointer2018090320180818
3207787328refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2018090320180818
3250422688refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2018090320180818
3250867200refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2018090320180818
3251488576refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2018090320180818
3253734816refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2018090320180818
3261929376refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2018090320180818
3279684864refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2018090320180818
3279832864refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2018090320180818
3287743136refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2018090320180818
3296444704refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2018090320180818
3319007168refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2018090320180818
3333003904refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2018090320180818
3334617216refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2018090320180818
3340854496refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018090320180818
3344542592refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2018090320180818
3381528384refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2018090320180818
3385005248refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2018090320180818
3386142848refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2018090320180818
3388141760refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2018090320180818
3398274880refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2018090320180818
3400460736refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2018090320180818
3400972160refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2018090320180818
3401833760refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018090320180818
3405493088refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2018090320180818
3414614496refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2018090320180818
3415277376refgcc -funroll-loops -m32 -O -fomit-frame-pointer2018090320180818
3418925440refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2018090320180818
3430310528refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2018090320180818
3430974016refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2018090320180818
3436223744refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018090320180818
3445486400refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2018090320180818
3446886304refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2018090320180818
3449735360refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2018090320180818
3451758880refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2018090320180818
3456349984refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018090320180818
3456361760refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018090320180818
3456657536refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2018090320180818
3456934688refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2018090320180818
3457036704refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2018090320180818
3465823904refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2018090320180818
3477158496refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2018090320180818
3477478080refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2018090320180818
3478147392refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2018090320180818
3480681440refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2018090320180818
3482193376refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2018090320180818
3488362528refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018090320180818
3498896064refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2018090320180818
3499414048refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2018090320180818
3504589376refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2018090320180818
3507488512refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2018090320180818
3516864896refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018090320180818
3521265056refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018090320180818
3523268896refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018090320180818
3524757088refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2018090320180818
3530335328refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2018090320180818
3530960160refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2018090320180818
3531452864refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2018090320180818
3558826240refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018090320180818
3565792736refgcc -m32 -march=pentium -Os -fomit-frame-pointer2018090320180818
3567418976refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2018090320180818
3575922304refgcc -m32 -march=k6 -Os -fomit-frame-pointer2018090320180818
3578874720refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2018090320180818
3582453632refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018090320180818
3583919680refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2018090320180818
3587164128refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2018090320180818
3588777504refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2018090320180818
3597183200refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2018090320180818
3601234880refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2018090320180818
3601631360refgcc -m32 -march=nocona -Os -fomit-frame-pointer2018090320180818
3601644320refgcc -m32 -march=prescott -Os -fomit-frame-pointer2018090320180818
3602326400refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2018090320180818
3602776736refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2018090320180818
3603348192refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2018090320180818
3604554368refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2018090320180818
3625853888refgcc -m32 -march=i486 -Os -fomit-frame-pointer2018090320180818
3630282304refgcc -m32 -march=i386 -Os -fomit-frame-pointer2018090320180818
3644743584refgcc -m32 -march=athlon -O -fomit-frame-pointer2018090320180818
3649544480refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018090320180818
3662605952refgcc -m32 -march=k8 -O -fomit-frame-pointer2018090320180818
3662752640refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2018090320180818
3666493280refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2018090320180818
3666509728refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2018090320180818
3679835136refgcc -m32 -march=corei7 -O -fomit-frame-pointer2018090320180818
3681705120refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2018090320180818
3681920224refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2018090320180818
3682365248refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2018090320180818
3685005280refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2018090320180818
3687930560refgcc -m32 -O -fomit-frame-pointer2018090320180818
3688387104refgcc -m32 -march=k6 -O -fomit-frame-pointer2018090320180818
3692116736refgcc -m32 -march=barcelona -O -fomit-frame-pointer2018090320180818
3693080096refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2018090320180818
3695188736refgcc -m32 -march=prescott -O -fomit-frame-pointer2018090320180818
3702358208refgcc -m32 -march=nocona -O -fomit-frame-pointer2018090320180818
3703054784refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2018090320180818
3704911936refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2018090320180818
3705305472refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2018090320180818
3709859616refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2018090320180818
3726647584refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2018090320180818
3728491552refgcc -m32 -march=i386 -O -fomit-frame-pointer2018090320180818
3732223712refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2018090320180818
3732728864refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2018090320180818
3739553056refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2018090320180818
3743135328refgcc -m32 -march=core2 -O -fomit-frame-pointer2018090320180818
3748050976refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2018090320180818
3748355360refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2018090320180818
3748489248refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2018090320180818
3748585792refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2018090320180818
3748873376refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2018090320180818
3749036064refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2018090320180818
3752731808refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2018090320180818
3753731104refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2018090320180818
3756839360refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2018090320180818
3759130592refgcc -m32 -march=i486 -O -fomit-frame-pointer2018090320180818
3759523488refgcc -m32 -march=pentium -O -fomit-frame-pointer2018090320180818
3760679008refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2018090320180818
3764921696refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018090320180818
3767814688refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2018090320180818
3770840160refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2018090320180818
3771747520refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2018090320180818
3774079360refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2018090320180818
3776612096refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2018090320180818
3782979808refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2018090320180818
3786871456refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2018090320180818
3787645856refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018090320180818
3789907296refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2018090320180818
3790526272refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2018090320180818
3791229888refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2018090320180818
3792451872refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018090320180818
3792477984refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2018090320180818
3796143200refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2018090320180818
3802666592refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2018090320180818
3802719648refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2018090320180818
3802956864refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2018090320180818
3806598848refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018090320180818
3835028416refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018090320180818
3850749312refgcc -m32 -march=core2 -Os -fomit-frame-pointer2018090320180818
3865093792refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2018090320180818
3875426880refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2018090320180818
3955120384refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2018090320180818
3963956576refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2018090320180818
3972659072refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2018090320180818
3974169536refgcc -m32 -march=k8 -Os -fomit-frame-pointer2018090320180818
3974391648refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2018090320180818
3975985856refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2018090320180818
4012069920refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2018090320180818
4019004832refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2018090320180818
4027182784refgcc -m32 -O2 -fomit-frame-pointer2018090320180818
4036685120refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2018090320180818
4057440224refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2018090320180818
4057702656refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2018090320180818
4064019328refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2018090320180818
4064241760refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2018090320180818
4071007616refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018090320180818
4076166240refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2018090320180818
4085794944refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2018090320180818
4105136096refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2018090320180818
4410166560refgcc -m32 -Os -fomit-frame-pointer2018090320180818
4669434464refgcc -m32 -march=athlon -Os -fomit-frame-pointer2018090320180818

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/5/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/5/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: error: 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/5/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/5/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/5/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/5/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: error: 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/5/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/5/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/5/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/5/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: error: 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/5/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/5/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/5/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/5/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: error: 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/5/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/5/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: error: 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