TalkChess.com

syzygy wrote: ↑

Tue Sep 08, 2020 11:53 pm

Gian-Carlo Pascutto wrote: ↑

Tue Sep 08, 2020 6:15 pm

Has anyone benchmarked Stockfish NNUE's performance on an AVX-512 system with an AVX-512 build? How does it compare to a Zen2 AVX2 build?

This seems to get close:
https://github.com/official-stockfish/S ... -678426702

Thanks. So no point in getting AVX512 hardware.

Has anyone benchmarked Stockfish NNUE's performance on an AVX-512 system with an AVX-512 build? How does it compare to a Zen2 AVX2 build?

This makes sense but I don't think this is the optimal way to go about this. Of course in quiet positions 50% less nps is not as critical as in the endgame, but I believe even in the endgame the NN evaluation can have a better evaluation in many positions. They could yes, but clearly overall it's b...

Notably, my understanding is nodchip also has as input for each square whether a capture occured there. Ha, interesting, there's a lot of tricks one can do here. You can also cheat with piece types. It's not clear to me whether NNUE can distinguish between castling state right now? But you can fix ...

... If one engine can use 100M of data files, then so should the others. Doesn't matter what is contained in them. ?? Some tournaments disallow "books" but allow "neural networks", even if this distinction does not exist in reality, because you can train a neural network to remember openings.

There's still so much room for experimentation. And I suspect that trying and training new approaches is quite a bit faster on a 20M NNUE net compared to a Leela one...

Dream situation for computer chess.

On CPU, LC0 relies on Blas. Afaik Blas backends can be used interchangeably and share the same basic interface. There's an Eigen backend as well, but it is just used for basic matrix/matrix multiplies, i.e. as an alternative BLAS library. Giraffe relies on Eigen. I am not really familiar with Eigen...

People should start learning how NN works? If you give a NN a ton of opening positions to learn, it will definitely learn to remember them. But for NNUE it is more complicated. The output does not contain move recommendations, just the evaluation of the position. I don't think the current learning ...

So far I have payed zero attention to the LeelaChess Zero project, as I have no good GPU. But now I want to do some testing at ultra-low node count, and I suppose a CPU-only version would be good enough for that. What would I have to do to run a game with LC0-CPU as UCI engine? I downloaded an arch...

Gerd Isenberg wrote: ↑

Sat May 30, 2020 4:21 pm

I agree it is a shame, that Zen is so slow with pext. AMD has to spent some transistors for a fast hardware pext in one cycle!

Note that Intel has several patents on the efficient implementation of those instructions.