SlowChess Blitz Classic 2.0

[Modern Times]

Udpate On FRC play :

I ran some more testing and in FRC 2.5 was weaker than 2.4 even with AVX. (Although standard it was still 40+ elo stronger, really shows how specific neural nets can be.)

Thanks, I'll stick to 2.4 for FRC.

[pohl4711]

SlowChess Blitz 2.5 is now available at
https://www.3dkingdoms.com/chess/slow.htm

7000 games testrun of Slow Chess 2.5 finished. Impressive progress!

https://www.sp-cc.de

(Perhaps you have to clear your browsercache or reload the website)

[Gabor Szots]

Hi Jonathan,

Where are the updated endgame nets? The last one I have was from v2.4 and dates 30th October.

[jonkr]

Where are the updated endgame nets? The last one I have was from v2.4 and dates 30th October.

I renamed the net binary file to NeuralNets.snn since it includes the main general net too now so isn't just endgame.
There are some changes so the nets/binary file isn't directly compatible between different versions.

[Carlos777]

Thanks for this new version.

The nopopcnt version does not work on my old PC (AMD Phenom II x4), 2.4 version works fine.
When 2.5 starts thinking (out of the book), it crashes.

SlowChess Blitz 2.5 is now available at
https://www.3dkingdoms.com/chess/slow.htm

You should use slow64-avx if your computer supports AVX2.
The alternative is slow64-noPop. It is plain SSE2. Hardware popcount doesn't really matter since not used in neural net eval, so I didn't compile any more versions.

Slow 2.5 now uses neural nets for every stage of the game. I decided it was time to drop Classic from the name. The endgame nets are the same as 2.4, except with more training and the addition of a Q v R(s) network. The main addition is a network to replace the general evaluations. It's the same structure as the endgame nets, but with a more neurons on first later ( 320x32x32x1 ) Inputs are the same too, just piece/sq, with horizontal symmetry based on white king.

Playing style is similar to 2.4 but more different than any of the hard-coded evals were to each other. Replacing a hard-coded eval with a neural net is a big change, even one based partially on the same training positions and partially on search with same eval. Older hce versions with just certain terms added and factors tweaked showed an extra high draw % playing against previous version, and this one doesn't show that. I think eval definitely main factor in how an engine plays.

On the plus side

• I estimate it's about 40 elo stronger in standard chess than 2.4
• Can beat Stockfish 8 in 2-moves book matches by a few elo on my computer.
• The play based on win percentages does feel more human-like to me.

On the minus side

• requires AVX2 for strongest play
• struggles in Chess960 variant (can't recommend it over 2.4)
• can take longer to close out games. Probably from valuing sure wins so high. (Some day I may see if I can train it try to close out as aggressively as possible.)

I think it's of some interest to have a neural net program that is not standard NNUE and not based on it in any way. (Although it's clearly much weaker than any stockfish NNUEs, and I'm not sure how much is based on my lack of computer resources for training, and how much is from not being the best possible architecture or training process.)

At this point the idea of working more to make it stronger sounds too tedious so I'm releasing it, but if the past is a guide I expect eventually I will start experimenting again then make enough progress to make another version.

[Tibono]

Thanks for this new version.

The nopopcnt version does not work on my old PC (AMD Phenom II x4), 2.4 version works fine.
When 2.5 starts thinking (out of the book), it crashes.

+1 (Intel Pentium Penryn, Instructions sets: MMX, SSE, SSE2, SSE3, SSSE3, EM64T)
Cheers,
Tibono

[jonkr]

Tibono and Carlos777

Thanks for the report, I found what is likely to be the issue, I accidently used "_mm_packus_epi32" instruction in an optimization for the SSE neural net calculation, instead of "_mm_packs_epi32". The packus version is listed as SSE4, I think everything else I use is SSE2.

I had already done some other refactoring and fixed an unrelated issue, so right now I'm testing the potential fix version in games to try to make sure the play/strength is unchanged. I'll update this post with quoted reply when I update the webpage.

[Tibono]

Thanks Jonathan, much appreciated! I am keen on running it
Cheers,
Eric

[jonkr]

Thanks for this new version.

The nopopcnt version does not work on my old PC (AMD Phenom II x4), 2.4 version works fine.
When 2.5 starts thinking (out of the book), it crashes.

+1 (Intel Pentium Penryn, Instructions sets: MMX, SSE, SSE2, SSE3, SSSE3, EM64T)
Cheers,
Tibono

I updated the download for 2.5 here.
https://www.3dkingdoms.com/chess/slow.htm

The exes should be almost exactly the same, and strength was the same in my overnight test. (Actually was a bit better, but nps bit slower, assume both were random noise.)

I don't have any older computers to test on, but if 2.4 worked for you, then hopefully the "slow64-sse" should now work fine.

(I also fixed an unrelated check evade move ordering bug where it sometimes accessed a static array slightly out of bounds, which was confusing to track down because the initial issue I noticed was sometimes commenting out completely unused code would change node count.)

[Frank Quisinsky]

Hi Jonathan,

I added your v2.5 in my still running FCP Tourney-2021 and changed to v2.5 from today after round 4 out of 50.

Now after 160 games place 3 / 41 with 116 / 160 points, 1.5 points more as Ethereal.
Seems to be the same strength as Ethereal, but I haven't enough games.

Thank you!

Best
Frank