TalkChess.com

A very long conversation on Lc0 discord yesterday suggested they wouldn't be that great The reason? Not as great as possible 150% improvement or much much lower than that? I didn’t stay for the whole thing but the gist of it was: 1) Lc0 uses tensor cores 2) new tensor performance has 2 values 3) Lc...

A very long conversation on Lc0 discord yesterday suggested they wouldn't be that great The reason? Not as great as possible 150% improvement or much much lower than that? I didn’t stay for the whole thing but the gist of it was: 1) Lc0 uses tensor cores 2) new tensor performance has 2 values 3) Lc...

A very long conversation on Lc0 discord yesterday suggested they wouldn't be that great

mwyoung wrote: ↑

Sat Sep 05, 2020 3:49 am

Lc0 is clearly improving faster then Stockfish at this point in time. Even at 3m+2s time controls vs past matches at the same time controls.

Is this definitely true? The T60 graph has been flat for ages. I know there are other improvements outside of the nets, but this is quite a big thing

Because the Neural Net in Lc0 is bigger than the one in SF NNUE, do we have any examples of where Lc0 evaluates a position better?
I'm thinking of positions where a deep AB search won't help much, such as blocked positions.

I remember Houdart saying it was fine. I also typically use an even number of cores doubling from 2, but that's more out of habit than something rational.

I wonder how a head to head would go between the 3090 and 2x2080Ti for Lc0. I guess running off one card would be quite a big advantage

Although it's not stated, surely that means FP16 on CUDA alone will be 71 TFLOPS, no? That's well over 2x performance increase for Lc0..

OK this looks BIG

https://www.anandtech.com/show/16057/nv ... 0-rtx-3090

Actually black moves first is being seen as an anti-racist idea, based on the assumption chess promotes white privilege (white moves first).

Nutty if you ask me...