TalkChess.com

Rough maths suggests he has at least 1000 cores to do that. If we call several = 5 5 billion fens a day = 50000 fens per second, which if he samples at 25% implies 12500 games per second. One game every 0.08 ms. For massively fast bullet that needs 1000 cores at least, I think. 1000 cores would all...

OK, now that I am actually running the nnue version, I am getting 60% of Stockfish speed. :oops: Still pretty good, but it was too good to be true. :D I did basically the same thing the other day. I was wondering which was the fastest EXE version for threadripper, so I started testing them all agai...

This is a bit confusing using normal terminology. "age" refers to the search that an entry is stored. IE it advances once for each real move played on the board. The idea is to let you recognize entries that come from the previous search (which might be great for the current search or completely us...

I tested 2214 against the relatively early net 1134 both with PO-AVX2 @ 20+0.2 5000 games with a 4-move book as a sanity check for progress. The results were: 1. SFSF-NNUE-2214 2645.0/5000 922-632-3446 2. SFSF-NNUE-1134 2355.0/5000 632-922-3446 About a 20 ELO difference with 7 ELO error bars if my g...

Following up on this, I ended up adding code to Abbess to pull the selection of pgn files I wanted - pgn games truncated to where a certain number of pieces are left. However, I actually only want games that are still in progress, i.e. no games ending in checkmate or draw. pgn-extract has --checkma...

[...] I think splitting it by number of plies played is a mistake. You can be in an endgame in 40 plies. Better to do it on the number of pieces and pawns left on the board. Every capture decrements the piece count by one so it's easy to keep track of. The other advantage is the depth of search can...

Haven't read all of this thread so excuse me if it was already mentioned: tttak's fork has a lot of different architectures to try out. I'm interested in the "Gameply40x4" one which effectively holds 4 NNs in one file which get used sequentially switching every 40 plies until the 4th is loaded. Thi...

Can confirm 0109 as best for me up to now, but only 1000 games. Haven't checked all of them, it seems the latest 0912 is not stronger. I am running 0109 right now, increased the number of games to 5000. After 500 games a 64% score, that's +98 elo :D We will see. I tested 1218 with PO-AVX2 @ 20+0.2 ...

Has NNUE refuted a few lines yet? Yes, there's a little opening revolution as we speak, people that haven't updated their lines have lost +70 elo points. I'm currently outperforming people in much faster hardware than mine and I'm not even using NNUE , just holding up with drawish openings that don...

On threadripper I got a HUGE regression in speed when using either the POPC or AVX2 version listed here vice using stockfish.avx2. no-nnue.nnue-gen-sfen-from-original-eval .2020-07-19.exe. I'm getting 900K to 1.2Mnps vice 2Mnps on a single core. Regards, Zenmastur Because you are comparing regular ...