Implementation notes: x86, titan0, crypto_sign/sphincsf256shake256simple

Computer: titan0
Architecture: x86
CPU ID: GenuineIntel-000306c3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_sign
Primitive: sphincsf256shake256simple
TimeImplementationCompilerBenchmark dateSUPERCOP version
588893356avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080920190803
597187012avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080920190803
968361816avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080920190803
970834820avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080920190803
1008585580avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080920190803
1008701816avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080920190803
1032500804avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080920190803
1033046100avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080920190803
1980362768refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2019080920190803
1986065432refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2019080920190803
1995530172refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2019080920190803
2018049368refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2019080920190803
2044661180refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080920190803
2085661116refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080920190803
2097477412refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080920190803
2097725764refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080920190803
2205683756refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080920190803
2277808696refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2019080920190803
2282876568refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2019080920190803
2294998804refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2019080920190803
2298192808refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2019080920190803
2308208032refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080920190803
2336255540refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2019080920190803
2337225912refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2019080920190803
2342493716refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2019080920190803
2342755040refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080920190803
2347812448refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2019080920190803
2396317648refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2019080920190803
2397516540refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2019080920190803
2397811460refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2019080920190803
2399247720refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2019080920190803
2405156924refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2019080920190803
2406144952refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2019080920190803
2486441696refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080920190803
2490859168refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080920190803
2498881148refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080920190803
2516839736refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2019080920190803
2537393480refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080920190803
2539124152refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080920190803
2542751756refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2019080920190803
2636294076refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2019080920190803
2637133648refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2019080920190803
2664775548refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080920190803
2683609204refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2019080920190803
2683752184refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2019080920190803
2683979952refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2019080920190803
2817107328refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080920190803
2819191768refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080920190803
2839584180refgcc -m32 -O3 -fomit-frame-pointer2019080920190803
2863910756refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2019080920190803
2868438960refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2019080920190803
2875130948refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2019080920190803
2877658816refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080920190803
2879843356refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080920190803
2880961204refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2019080920190803
2886205016refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2019080920190803
2888388848refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2019080920190803
2913005536refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080920190803
2919079792refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080920190803
2938257812refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080920190803
2942983968refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2019080920190803
2945607040refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2019080920190803
2946096136refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2019080920190803
2956080496refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080920190803
2957282124refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2019080920190803
2957792040refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2019080920190803
2958297312refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2019080920190803
2959541760refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2019080920190803
2962339952refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2019080920190803
2962857936refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2019080920190803
2962893704refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080920190803
2964315852refgcc -funroll-loops -m32 -O -fomit-frame-pointer2019080920190803
2965860104refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2019080920190803
2966373796refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2019080920190803
2973481164refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2019080920190803
2974240388refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2019080920190803
3010761092refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2019080920190803
3011378840refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2019080920190803
3014004712refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080920190803
3014700196refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2019080920190803
3017964908refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080920190803
3024015948refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080920190803
3032313180refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2019080920190803
3039659276refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2019080920190803
3042137516refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080920190803
3047189880refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2019080920190803
3048556104refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080920190803
3057161620refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080920190803
3062223068refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2019080920190803
3068821712refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2019080920190803
3094710492refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2019080920190803
3094912084refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2019080920190803
3097575420refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080920190803
3104212100refgcc -m32 -march=nocona -O -fomit-frame-pointer2019080920190803
3107647100refgcc -m32 -march=prescott -O -fomit-frame-pointer2019080920190803
3111541244refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2019080920190803
3112716564refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2019080920190803
3113024964refgcc -m32 -march=corei7 -O -fomit-frame-pointer2019080920190803
3122015484refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2019080920190803
3122919636refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2019080920190803
3129355032refgcc -m32 -march=core2 -O -fomit-frame-pointer2019080920190803
3141354508refgcc -m32 -march=nocona -Os -fomit-frame-pointer2019080920190803
3144646728refgcc -m32 -march=prescott -Os -fomit-frame-pointer2019080920190803
3145548572refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2019080920190803
3151515420refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080920190803
3152674152refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080920190803
3159722108refgcc -m32 -march=core2 -Os -fomit-frame-pointer2019080920190803
3162889148refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080920190803
3173526520refgcc -m32 -march=barcelona -O -fomit-frame-pointer2019080920190803
3179015368refgcc -m32 -march=k8 -O -fomit-frame-pointer2019080920190803
3188421976refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2019080920190803
3191556444refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080920190803
3194145216refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2019080920190803
3204879528refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080920190803
3208094596refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2019080920190803
3214263284refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2019080920190803
3215497100refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2019080920190803
3216344452refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2019080920190803
3229736096refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2019080920190803
3230596200refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2019080920190803
3231239912refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2019080920190803
3246463096refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080920190803
3252966924refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2019080920190803
3268984612refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2019080920190803
3343365444refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2019080920190803
3344122572refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2019080920190803
3344407532refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2019080920190803
3350161636refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2019080920190803
3356683052refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2019080920190803
3360705756refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2019080920190803
3361716768refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2019080920190803
3363069588refgcc -m32 -march=k6 -Os -fomit-frame-pointer2019080920190803
3369310408refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080920190803
3370254204refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2019080920190803
3389232768refgcc -m32 -march=pentium -Os -fomit-frame-pointer2019080920190803
3389336176refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080920190803
3401705904refgcc -m32 -march=i386 -Os -fomit-frame-pointer2019080920190803
3417406632refgcc -m32 -march=i486 -Os -fomit-frame-pointer2019080920190803
3423126568refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2019080920190803
3423546844refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2019080920190803
3424646588refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080920190803
3449030988refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2019080920190803
3449414068refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2019080920190803
3450801384refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2019080920190803
3453351304refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080920190803
3455238800refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2019080920190803
3464603424refgcc -m32 -march=athlon -Os -fomit-frame-pointer2019080920190803
3489168580refgcc -m32 -Os -fomit-frame-pointer2019080920190803
3555751328refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2019080920190803
3573024732refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2019080920190803
3581351016refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2019080920190803
3583152992refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2019080920190803
3590793856refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2019080920190803
3591267116refgcc -m32 -march=k6 -O -fomit-frame-pointer2019080920190803
3611627600refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080920190803
3639221456refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2019080920190803
3650583044refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2019080920190803
3661458720refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2019080920190803
3668860860refgcc -m32 -march=athlon -O -fomit-frame-pointer2019080920190803
3674168964refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080920190803
3687429128refgcc -m32 -O2 -fomit-frame-pointer2019080920190803
3698189628refgcc -m32 -O -fomit-frame-pointer2019080920190803
3751155140refgcc -m32 -march=pentium -O -fomit-frame-pointer2019080920190803
3754775188refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080920190803
3758769696refgcc -m32 -march=i486 -O -fomit-frame-pointer2019080920190803
3766211784refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2019080920190803
3812679748refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080920190803
3817261816refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080920190803
3818802272refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080920190803
3852703492refgcc -m32 -march=i386 -O -fomit-frame-pointer2019080920190803
3854787368refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2019080920190803
3866447396refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080920190803
6351826268refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2019080920190803
6429942928refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2019080920190803
6802131972refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2019080920190803
6807348936refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2019080920190803
7090679876refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2019080920190803
7179974632refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2019080920190803
7430995128refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2019080920190803
7442965504refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2019080920190803
7605049160refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2019080920190803
7682980324refgcc -m32 -march=k8 -Os -fomit-frame-pointer2019080920190803
7728211324refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2019080920190803
7840433188refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2019080920190803

Compiler output

Implementation: crypto_sign/sphincsf256shake256simple/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/sphincsf256shake256simple/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/sphincsf256shake256simple/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