In this benchmark, you get an average of 4 Mkeys/s per core, possibly because this version uses a fully random approach, which impacts the speed.
The biggest performance gain comes from generating eight random numbers simultaneously using AVX-512.
__m512i randVec = _mm512_set_epi64x(rng1, rng2, rng3, rng4, rng5, rng6, rng7, rng8);
Of course, I won't publicly disclose the exact details of how this works.

You know what? My system said, 'Let’s try it!'

… And guess what? It’s running absolutely fine. But me? I’m the one getting hanged multiple times while playing around with Cyclone.

Forked this repo 4 times, applied my
4 favorite logics, and everything is working perfectly!
In these processes, I faced tons of bugs, challenges, endless AI conversations, and way too many forum posts—seriously, that stuff sucked the life out of me!

One of my forks includes stride logic—I saw you mention somewhere that stride doesn’t work properly above 32-bit or something like that… Well, My stride version is unlimited and working flawlessly with zero issues.
Anyway… no more stress—I’m just gonna chill now. And as you said, I’m off for some fishing too!

Oh, and just a heads-up—soon, all 4 forks will be available on GitHub, so get ready because you guys are gonna love this!

And before some random keyboard warrior jumps in with their detective skills, let me make one thing crystal clear—there’s no source code available for any of them. So, if you have a problem with that… well, you know what? F*ck off!

If you wanna use it, great! If not, here’s a complimentary finger from my side.
/"\
|\./|
| |
| |
| |
| |
/'\| |/'\
/'\| | | |
| | | | |\
| | | | | \
| * * * * |> > ALL YOURS! 
| /
| /
| /
\ |
| |
I ain’t your babysitter, and I definitely don’t have time to argue with those saying, 'OMG, you put viruses in your .exe!' or 'You're trying to steal our few satoshis from our wallet!' 🤦♂️ Bruh… take it or leave it—I’m just here having fun!
Best Wishes to Every One 