Chess Forum

Author: AndrovT
Date: Wed Jun 14 18:36:39 2023 +0200
Timestamp: 1686760599

Permute master net weights to increase sparsity

Activation data collection using https://github.com/AndrovT/Stockfish/co ... 7729c10a77 run as

bench 16 1 13 varied_1000.epd depth NNUE log.bin

on FENs from https://gist.github.com/AndrovT/7eae691 ... fe7938953c.

Permutation found using https://gist.github.com/AndrovT/359c831 ... 01eb96949e.
Uses a greedy algorithm that goes sequentially through the output positions and
chooses a neuron for that position such that the number of nonzero quartets is the smallest.

Net weights permuted using https://gist.github.com/AndrovT/9e3fbae ... 7e02094cb3.

Benchmark:

Result of 100 runs of 'bench 16 1 13 default depth NNUE'
========================================================
base (...kfish-master) = 885869 +/- 7395
test (./stockfish ) = 895885 +/- 7368
diff = +10016 +/- 2984

speedup = +0.0113
P(speedup > 0) = 1.0000

Passed STC:
https://tests.stockfishchess.org/tests/ ... 385c804728
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 126784 W: 34003 L: 33586 D: 59195 Elo +1.14
Ptnml(0-2): 283, 13001, 36437, 13358, 313

closes https://github.com/official-stockfish/S ... /pull/4620

No functional change.

Author: cj5716
Date: Fri Jun 16 19:14:58 2023 +0200
Timestamp: 1686935698

Small cleanup

This non-functional change keeps formatting consistent.

closes https://github.com/official-stockfish/S ... /pull/4623

Bench 2370027

Author: maxim
Date: Mon Jun 19 21:37:23 2023 +0200
Timestamp: 1687203443

Compressed network parameters

Implemented LEB128 (de)compression for the feature transformer.
Reduces embedded network size from 70 MiB to 39 Mib.

The new nn-78bacfcee510.nnue corresponds to the master net compressed.

closes https://github.com/official-stockfish/S ... /pull/4617

No functional change

Author: disservin
Date: Tue Jun 20 08:55:54 2023 +0200
Timestamp: 1687244154

create prereleases upon push to master

using github actions, create a prerelease for the latest commit to master.
As such a development version will be available on github, in addition to the latest release.

closes https://github.com/official-stockfish/S ... /pull/4622

No functional change

Author: Joerg Oster
Date: Tue Jun 20 10:47:07 2023 +0200
Timestamp: 1687250827

Fix indentation in qsearch.

https://github.com/official-stockfish/S ... /pull/4630

No functional change.

Author: disservin
Date: Tue Jun 20 18:50:12 2023 +0200
Timestamp: 1687279812

Fix failing CI of pull requests

adds a guard to prevent pull requests from trying to delete the previous pre-release

closing https://github.com/official-stockfish/S ... /pull/4631

No functional change.
see source

Author: Linmiao Xu
Date: Thu Jun 22 10:33:19 2023 +0200
Timestamp: 1687422799

Update default net to nn-5af11540bbfe.nnue

Net available here >> https://tests.stockfishchess.org/nns
Created by retraining the sparsified master net (nn-cd2ff4716c34.nnue) on
a 100% minified dataset including Leela transformers data from T80 may2023.

Weights permuted with the exact methods and code in:
https://github.com/official-stockfish/S ... /pull/4620

LEB128 compression done with the new serialize.py param in:
https://github.com/glinscott/nnue-pytorch/pull/251

Initially trained with max epoch 800. Around epoch 780, training was paused
and max epoch raised to 960.

python3 easy_train.py \
--experiment-name L1-1536-sparse-master-retrain \
--training-dataset /data/leela96-dfrc99-v2-T60novdecT77decT78jantosepT79aprmayT80juntonovjan-v6dd-T80febtomay2023.min.binpack \
--early-fen-skipping 27 \
--start-from-engine-test-net True \
--max_epoch 960 \
--lr 4.375e-4 \
--gamma 0.995 \
--start-lambda 1.0 \
--end-lambda 0.7 \
--tui False \
--seed $RANDOM \
--gpus 0

For preparing the training dataset (interleaved size 328G):

python3 interleave_binpacks.py \
leela96-filt-v2.min.binpack \
dfrc99-16tb7p-eval-filt-v2.min.binpack \
filt-v6-dd-min/test60-novdec2021-12tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test77-dec2021-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test78-jantomay2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test78-juntosep2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test79-apr2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test79-may2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test80-jun2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test80-jul2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test80-aug2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test80-sep2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test80-oct2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test80-nov2022-16tb7p-filter-v6-dd.min.binpack \
filt-v6-dd-min/test80-jan2023-16tb7p-filter-v6-dd.min.binpack \
test80-2023/test80-feb2023-16tb7p-no-db.min.binpack \
test80-2023/test80-mar2023-2tb7p-no-db.min.binpack \
test80-2023/test80-apr2023-2tb7p-no-db.min.binpack \
test80-2023/test80-may2023-2tb7p-no-db.min.binpack \
/data/leela96-dfrc99-v2-T60novdecT77decT78jantosepT79aprmayT80juntonovjan-v6dd-T80febtomay2023.min.binpack

Minified binpacks and Leela T80 training data from 2023 available at:
https://robotmoon.com/nnue-training-data/

Local elo at 25k nodes per move:
nn-epoch879.nnue : 3.9 +/- 5.7

Passed STC:
https://tests.stockfishchess.org/tests/ ... ce609c7690
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 72000 W: 19242 L: 18889 D: 33869 Elo +1.70
Ptnml(0-2): 182, 7787, 19716, 8126, 189

Passed LTC:
https://tests.stockfishchess.org/tests/ ... ce609c82e3
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 54552 W: 14978 L: 14647 D: 24927 Elo +2.11
Ptnml(0-2): 23, 5123, 16650, 5460, 20

closes https://github.com/official-stockfish/S ... /pull/4635

bench 2593605
see source

Stockfish 16

https://stockfishchess.org/download/

Author: Joost VandeVondele
Date: Thu Jun 29 08:00:10 2023 +0200
Timestamp: 1688018410

Stockfish 16

Official release version of Stockfish 16

Bench: 2593605

---

Stockfish 16

A new major release of Stockfish is now available at

https://stockfishchess.org/download/

*Quality of chess play*

Stockfish continues to demonstrate its ability to discover superior moves
with remarkable speed. In self-play against Stockfish 15, this new
release gains up to 50 Elo[1] and wins up to 12 times more game pairs[2]
than it loses. In major chess engine tournaments, Stockfish reliably tops
the rankings[3] winning the TCEC season 24 Superfinal, Swiss, Fischer
Random, and Double Random Chess tournaments and the CCC 19 Bullet,
20 Blitz, and 20 Rapid competitions. Leela Chess Zero[4] was the
challenger in most finals, putting top-engine chess now firmly in the
hands of teams embracing free and open-source software.

*Progress made*

This updated version of Stockfish introduces several enhancements,
including an upgraded neural net architecture (SFNNv6)[5], improved
implementation, and refined parameterization. The ongoing utilization
of Leela’s data combined with a novel inference approach exploiting
sparsity[6], and network compression[7] ensure a speedy evaluation and
modest binary sizes while allowing for more weights and higher accuracy.
The search has undergone more optimization, leading to improved
performance, particularly in longer analyses[8]. Additionally,
the Fishtest framework has been improved and is now able to run the
tests needed to validate new ideas with 10000s of CPU cores.

*Usability improvements*

Stockfish now comes with documentation, found in the wiki folder when
downloading it or on GitHub[9]. Additionally, Stockfish now includes
a clear and consistent forced tablebase win score, displaying a value
of 200 minus the number of plies required to reach a tablebase win[10].
Furthermore, the UCI_Elo option, to reduce its strength, has been
calibrated[11]. It is worth noting that the evaluation system remains
consistent with Stockfish 15.1[12], maintaining the choice that 100cp
means a 50% chance of winning the game against an equal opponent[13].
Finally, binaries of our latest development version are now provided
continuously as pre-releases on GitHub making it easier for
enthusiasts to download the latest and strongest version of
the program[14], we thank Roman Korba for having provided a similar
service for a long time.

*Thank you*

The success of the Stockfish project relies on the vibrant community
of passionate enthusiasts (we appreciate each and every one of you!)
who generously contribute their knowledge, time, and resources.
Together, this dedicated community works towards the common goal of
developing a powerful, freely accessible, and open-source chess engine.
We invite all chess enthusiasts to join the Fishtest testing framework
and contribute to the project[15].

The Stockfish team

[1] https://tests.stockfishchess.org/tests/ ... ce609c99cc
[2] https://tests.stockfishchess.org/tests/ ... ce609c99c6
[3] https://en.wikipedia.org/wiki/Stockfish ... on_results
[4] https://lczero.org/
[5] https://github.com/official-stockfish/S ... it/c1fff71
[6] https://github.com/official-stockfish/S ... it/38e6166
[7] https://github.com/official-stockfish/S ... it/a46087e
[8] https://github.com/official-stockfish/S ... it/472e726
[9] https://github.com/official-stockfish/Stockfish/wiki/
[10] https://github.com/official-stockfish/S ... it/def2966
[11] https://github.com/official-stockfish/S ... it/a08b8d4
[12] https://github.com/official-stockfish/S ... it/52e84e4
[13] https://github.com/official-stockfish/S ... evaluation
[14] https://github.com/official-stockfish/S ... ase%3Atrue
[15] https://stockfishchess.org/get-involved/
see source

janus wrote: ↑Fri Jun 30, 2023 10:27 pm

Stockfish 16

https://stockfishchess.org/download/

Author: Joost VandeVondele
Date: Thu Jun 29 08:00:10 2023 +0200
Timestamp: 1688018410

Stockfish 16

Official release version of Stockfish 16

Bench: 2593605

---

Stockfish 16

A new major release of Stockfish is now available at

https://stockfishchess.org/download/

*Quality of chess play*

Stockfish continues to demonstrate its ability to discover superior moves
with remarkable speed. In self-play against Stockfish 15, this new
release gains up to 50 Elo[1] and wins up to 12 times more game pairs[2]
than it loses. In major chess engine tournaments, Stockfish reliably tops
the rankings[3] winning the TCEC season 24 Superfinal, Swiss, Fischer
Random, and Double Random Chess tournaments and the CCC 19 Bullet,
20 Blitz, and 20 Rapid competitions. Leela Chess Zero[4] was the
challenger in most finals, putting top-engine chess now firmly in the
hands of teams embracing free and open-source software.

*Progress made*

This updated version of Stockfish introduces several enhancements,
including an upgraded neural net architecture (SFNNv6)[5], improved
implementation, and refined parameterization. The ongoing utilization
of Leela’s data combined with a novel inference approach exploiting
sparsity[6], and network compression[7] ensure a speedy evaluation and
modest binary sizes while allowing for more weights and higher accuracy.
The search has undergone more optimization, leading to improved
performance, particularly in longer analyses[8]. Additionally,
the Fishtest framework has been improved and is now able to run the
tests needed to validate new ideas with 10000s of CPU cores.

*Usability improvements*

Stockfish now comes with documentation, found in the wiki folder when
downloading it or on GitHub[9]. Additionally, Stockfish now includes
a clear and consistent forced tablebase win score, displaying a value
of 200 minus the number of plies required to reach a tablebase win[10].
Furthermore, the UCI_Elo option, to reduce its strength, has been
calibrated[11]. It is worth noting that the evaluation system remains
consistent with Stockfish 15.1[12], maintaining the choice that 100cp
means a 50% chance of winning the game against an equal opponent[13].
Finally, binaries of our latest development version are now provided
continuously as pre-releases on GitHub making it easier for
enthusiasts to download the latest and strongest version of
the program[14], we thank Roman Korba for having provided a similar
service for a long time.

*Thank you*

The success of the Stockfish project relies on the vibrant community
of passionate enthusiasts (we appreciate each and every one of you!)
who generously contribute their knowledge, time, and resources.
Together, this dedicated community works towards the common goal of
developing a powerful, freely accessible, and open-source chess engine.
We invite all chess enthusiasts to join the Fishtest testing framework
and contribute to the project[15].

The Stockfish team

[1] https://tests.stockfishchess.org/tests/ ... ce609c99cc
[2] https://tests.stockfishchess.org/tests/ ... ce609c99c6
[3] https://en.wikipedia.org/wiki/Stockfish ... on_results
[4] https://lczero.org/
[5] https://github.com/official-stockfish/S ... it/c1fff71
[6] https://github.com/official-stockfish/S ... it/38e6166
[7] https://github.com/official-stockfish/S ... it/a46087e
[8] https://github.com/official-stockfish/S ... it/472e726
[9] https://github.com/official-stockfish/Stockfish/wiki/
[10] https://github.com/official-stockfish/S ... it/def2966
[11] https://github.com/official-stockfish/S ... it/a08b8d4
[12] https://github.com/official-stockfish/S ... it/52e84e4
[13] https://github.com/official-stockfish/S ... evaluation
[14] https://github.com/official-stockfish/S ... ase%3Atrue
[15] https://stockfishchess.org/get-involved/
see source

https://github.com/official-stockfish/S ... 9063b3eb52

Was about to have my tea with lemon .. these appeared ..
Latest is the first on the list.


Author: Linmiao Xu
Date: Sat Jul 1 13:34:30 2023 +0200
Timestamp: 1688211270

Update NNUE architecture to SFNNv7 with larger L1 size of 2048

Author: cj5716
Date: Sat Jul 1 13:06:49 2023 +0200
Timestamp: 1688209609

Negative extension on cutNodes based on depth

Author: Stéphane Nicolet
Date: Sat Jul 1 13:01:28 2023 +0200
Timestamp: 1688209288

Document the LEB128 patch

Author: Daniel Monroe
Date: Sat Jul 1 12:59:28 2023 +0200
Timestamp: 1688209168

Update default net to nn-a3d1bfca1672.nnue

Author: Joost VandeVondele
Date: Sat Jul 1 12:52:31 2023 +0200
Timestamp: 1688208751

Restore development