Implementation notes: x86, titan0, crypto_sign/sphincsf192shake256robust

Computer: titan0
Architecture: x86
CPU ID: GenuineIntel-000306c3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_sign
Primitive: sphincsf192shake256robust
TimeImplementationCompilerBenchmark dateSUPERCOP version
583482076avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
583532356avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
897215760avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
899439576avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
901122092avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
901240312avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
920988600avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
921574160avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
1725736148refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2019080820190803
1726854532refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2019080820190803
1742549052refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2019080820190803
1770644452refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
1785393000refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
1792081920refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2019080820190803
1828558380refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
1830632484refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
1879638084refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
1973868944refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1974093864refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1978203688refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1978806748refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1982499524refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
2001016832refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
2004890088refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
2016087096refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
2039552660refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2019080820190803
2039608644refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2019080820190803
2051791880refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
2059393560refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
2060221324refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
2061920876refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
2062452396refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
2064108856refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
2127823964refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
2187347764refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
2188779652refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
2200046464refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
2209752504refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
2222298232refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2019080820190803
2255805356refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2019080820190803
2317081376refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2019080820190803
2319045580refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2019080820190803
2360979084refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
2368638576refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2019080820190803
2370289488refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2019080820190803
2370582188refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2019080820190803
2434524996refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
2434788856refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
2449435264refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2019080820190803
2475195032refgcc -m32 -O3 -fomit-frame-pointer2019080820190803
2479348096refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
2480636284refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2019080820190803
2489590424refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
2494194196refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
2494238672refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
2498717608refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
2503487148refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
2504566704refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
2514121124refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
2517299948refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
2533300820refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
2533873912refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
2537888484refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
2539256792refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2019080820190803
2540740316refgcc -funroll-loops -m32 -O -fomit-frame-pointer2019080820190803
2560623460refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
2564472280refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
2564574616refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
2565554496refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
2566001384refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
2571775524refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
2572285032refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
2572399304refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
2576979388refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
2597254504refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
2602470112refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
2605694528refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
2605878432refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
2606112204refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
2612395480refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
2613438500refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
2624957492refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
2626425256refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
2629579560refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
2638270196refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
2638754952refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
2647434756refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
2650300568refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
2651849872refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
2652511688refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
2663337220refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
2682164444refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
2685739324refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
2689037584refgcc -m32 -march=core2 -Os -fomit-frame-pointer2019080820190803
2691654648refgcc -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
2692547012refgcc -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
2715493036refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
2715625096refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
2715942260refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
2726135448refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
2726255676refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
2726327412refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
2726447492refgcc -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
2726466352refgcc -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
2731625288refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
2740346276refgcc -m32 -march=corei7 -O -fomit-frame-pointer2019080820190803
2740384516refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2019080820190803
2740654464refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2019080820190803
2749129720refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2019080820190803
2749786684refgcc -m32 -march=core2 -O -fomit-frame-pointer2019080820190803
2750302860refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2019080820190803
2751898128refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
2753601868refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
2758739112refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
2761710908refgcc -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
2770933508refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2019080820190803
2770961056refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
2771045208refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2019080820190803
2771354656refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2019080820190803
2772535504refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
2785704948refgcc -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
2797870880refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
2811640332refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
2822868764refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
2873352696refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
2874270460refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
2874580856refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
2904890520refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
2905095076refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
2905096212refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
2957648960refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
2957702504refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
2958013952refgcc -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
2959897608refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
2960501488refgcc -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
2961158036refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
2963601392refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
2976317376refgcc -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
2977801748refgcc -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
2979908184refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
2980096628refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
2980126496refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
3003511128refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
3011455864refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
3036434112refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2019080820190803
3036715612refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
3038661804refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
3047396320refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
3050078120refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
3055693228refgcc -m32 -Os -fomit-frame-pointer2019080820190803
3055995468refgcc -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
3058192364refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
3058330216refgcc -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
3058609904refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
3112809136refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
3118478208refgcc -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
3127946056refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
3135415344refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
3135601856refgcc -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
3182237820refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
3196089972refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
3196249468refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
3196386636refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
3203596772refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
3236650036refgcc -m32 -O -fomit-frame-pointer2019080820190803
3240283372refgcc -m32 -O2 -fomit-frame-pointer2019080820190803
3242779708refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
3245209304refgcc -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
3274672968refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
3279706212refgcc -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
3320175896refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
3320733432refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
5565596712refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
5650055696refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
5959212864refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
5982104832refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
6203762980refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2019080820190803
6273903452refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803
6451920512refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
6512156168refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
6633574096refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
6725621468refgcc -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
6788277548refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803
6873977980refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2019080820190803

Compiler output

Implementation: crypto_sign/sphincsf192shake256robust/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/sphincsf192shake256robust/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/sphincsf192shake256robust/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