TalkChess.com

Did anyone notice that the newest droidfish with NNUE is much slower than SF11 even when NNUE is turned off?

Which is more beneficial for chess? BMI2 or AVX512?

is BMI2 support activated in the bitboard tests?

Stockfish uses the NNUE evaluation when the position is balanced, then move on classical evaluation when the position is unbalanced. Why does this happen? Can we train a particularly effective evaluation net for unbalanced positions? A net with intrinsic contempt! I assume that what you mean by unb...

Isn't it that in the classical evaluation function, the positions evaluated at the leaf are just quiet positions because all captures and threats are already exhausted during quiescence search? With that in mind, I wonder if the position statistics stored in the NNUE Net are also just quiet position...

How much processing power does SF11 need to add in order to gain 120 ELO at the level of NNUE? Like 2X?

Is Hyperthreading preferable in NNUE?

The plan: 1. a "master net" to classify a position and choose which evaluation net to use 2. a large number of evaluation nets to do the actual evaluation, each specialising in a different type of position Although I wasn't thinking about NNs at the time, I had the same basic idea of a large number...

Most of the net should be in CPU cache so that the CPU will evaluate millions of positions /sec, which is the case actually, with the last Intel or AMD processors. With 160 MB Leela nets will be fast when processors will have at least 100 MB cache. You mean the 20MB is already for high end PC? How ...

RogerC wrote: ↑

Fri Aug 14, 2020 7:25 pm

And size difference of nets are worse : 20MB NNUE nets vs 160MB SV-384x30-t60-3010 LEELA net.

How is the 20MB NNUE decided? Is 20MB an optimal size or can it be set bigger like 100MB when faster CPU's come?