2018-12-29 03:49:10 -07:00
|
|
|
## Overview
|
2015-10-23 23:27:24 -06:00
|
|
|
|
2021-06-18 04:03:03 -06:00
|
|
|
[![Build Status](https://github.com/official-stockfish/Stockfish/actions/workflows/stockfish.yml/badge.svg)](https://github.com/official-stockfish/Stockfish/actions)
|
2019-05-02 11:36:25 -06:00
|
|
|
[![Build Status](https://ci.appveyor.com/api/projects/status/github/official-stockfish/Stockfish?branch=master&svg=true)](https://ci.appveyor.com/project/mcostalba/stockfish/branch/master)
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
[Stockfish](https://stockfishchess.org) is a free, powerful UCI chess engine
|
2020-07-11 08:59:33 -06:00
|
|
|
derived from Glaurung 2.1. Stockfish is not a complete chess program and requires a
|
|
|
|
UCI-compatible graphical user interface (GUI) (e.g. XBoard with PolyGlot, Scid,
|
|
|
|
Cute Chess, eboard, Arena, Sigma Chess, Shredder, Chess Partner or Fritz) in order
|
|
|
|
to be used comfortably. Read the documentation for your GUI of choice for information
|
|
|
|
about how to use Stockfish with it.
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
|
2020-07-11 08:59:33 -06:00
|
|
|
The Stockfish engine features two evaluation functions for chess, the classical
|
|
|
|
evaluation based on handcrafted terms, and the NNUE evaluation based on efficiently
|
2020-11-29 01:07:31 -07:00
|
|
|
updatable neural networks. The classical evaluation runs efficiently on almost all
|
Embed default net, and simplify using non-default nets
covers the most important cases from the user perspective:
It embeds the default net in the binary, so a download of that binary will result
in a working engine with the default net. The engine will be functional in the default mode
without any additional user action.
It allows non-default nets to be used, which will be looked for in up to
three directories (working directory, location of the binary, and optionally a specific default directory).
This mechanism is also kept for those developers that use MSVC,
the one compiler that doesn't have an easy mechanism for embedding data.
It is possible to disable embedding, and instead specify a specific directory, e.g. linux distros might want to use
CXXFLAGS="-DNNUE_EMBEDDING_OFF -DDEFAULT_NNUE_DIRECTORY=/usr/share/games/stockfish/" make -j ARCH=x86-64 profile-build
passed STC non-regression:
https://tests.stockfishchess.org/tests/view/5f4a581c150f0aef5f8ae03a
LLR: 2.95 (-2.94,2.94) {-1.25,-0.25}
Total: 66928 W: 7202 L: 7147 D: 52579
Ptnml(0-2): 291, 5309, 22211, 5360, 293
closes https://github.com/official-stockfish/Stockfish/pull/3070
fixes https://github.com/official-stockfish/Stockfish/issues/3030
No functional change.
2020-08-23 05:43:38 -06:00
|
|
|
CPU architectures, while the NNUE evaluation benefits from the vector
|
|
|
|
intrinsics available on most CPUs (sse2, avx2, neon, or similar).
|
2012-07-18 17:46:51 -06:00
|
|
|
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
## Files
|
2009-11-05 11:29:26 -07:00
|
|
|
|
|
|
|
This distribution of Stockfish consists of the following files:
|
|
|
|
|
2021-05-18 12:52:59 -06:00
|
|
|
* [Readme.md](https://github.com/official-stockfish/Stockfish/blob/master/README.md), the file you are currently reading.
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2021-05-18 12:52:59 -06:00
|
|
|
* [Copying.txt](https://github.com/official-stockfish/Stockfish/blob/master/Copying.txt), a text file containing the GNU General Public License version 3.
|
2021-05-07 04:24:12 -06:00
|
|
|
|
2021-05-18 12:52:59 -06:00
|
|
|
* [AUTHORS](https://github.com/official-stockfish/Stockfish/blob/master/AUTHORS), a text file with the list of authors for the project
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2021-05-18 12:52:59 -06:00
|
|
|
* [src](https://github.com/official-stockfish/Stockfish/tree/master/src), a subdirectory containing the full source code, including a Makefile
|
2014-06-04 07:56:34 -06:00
|
|
|
that can be used to compile Stockfish on Unix-like systems.
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2021-05-07 04:24:12 -06:00
|
|
|
* a file with the .nnue extension, storing the neural network for the NNUE
|
Embed default net, and simplify using non-default nets
covers the most important cases from the user perspective:
It embeds the default net in the binary, so a download of that binary will result
in a working engine with the default net. The engine will be functional in the default mode
without any additional user action.
It allows non-default nets to be used, which will be looked for in up to
three directories (working directory, location of the binary, and optionally a specific default directory).
This mechanism is also kept for those developers that use MSVC,
the one compiler that doesn't have an easy mechanism for embedding data.
It is possible to disable embedding, and instead specify a specific directory, e.g. linux distros might want to use
CXXFLAGS="-DNNUE_EMBEDDING_OFF -DDEFAULT_NNUE_DIRECTORY=/usr/share/games/stockfish/" make -j ARCH=x86-64 profile-build
passed STC non-regression:
https://tests.stockfishchess.org/tests/view/5f4a581c150f0aef5f8ae03a
LLR: 2.95 (-2.94,2.94) {-1.25,-0.25}
Total: 66928 W: 7202 L: 7147 D: 52579
Ptnml(0-2): 291, 5309, 22211, 5360, 293
closes https://github.com/official-stockfish/Stockfish/pull/3070
fixes https://github.com/official-stockfish/Stockfish/issues/3030
No functional change.
2020-08-23 05:43:38 -06:00
|
|
|
evaluation. Binary distributions will have this file embedded.
|
2020-07-11 08:59:33 -06:00
|
|
|
|
2021-04-29 00:18:37 -06:00
|
|
|
## The UCI protocol and available options
|
2018-12-29 03:49:10 -07:00
|
|
|
|
2021-06-13 01:59:34 -06:00
|
|
|
The Universal Chess Interface (UCI) is a standard protocol used to communicate with
|
|
|
|
a chess engine, and is the recommended way to do so for typical graphical user interfaces
|
|
|
|
(GUI) or chess tools. Stockfish implements the majority of it options as described
|
|
|
|
in [the UCI protocol](https://www.shredderchess.com/download/div/uci.zip).
|
|
|
|
|
|
|
|
Developers can see the default values for UCI options available in Stockfish by typing
|
|
|
|
`./stockfish uci` in a terminal, but the majority of users will typically see them and
|
|
|
|
change them via a chess GUI. This is a list of available UCI options in Stockfish:
|
2018-12-29 03:49:10 -07:00
|
|
|
|
|
|
|
* #### Threads
|
2019-05-02 11:36:25 -06:00
|
|
|
The number of CPU threads used for searching a position. For best performance, set
|
2018-12-29 03:49:10 -07:00
|
|
|
this equal to the number of CPU cores available.
|
|
|
|
|
|
|
|
* #### Hash
|
2020-05-04 11:49:27 -06:00
|
|
|
The size of the hash table in MB. It is recommended to set Hash after setting Threads.
|
2018-12-29 03:49:10 -07:00
|
|
|
|
2021-02-16 08:19:37 -07:00
|
|
|
* #### Clear Hash
|
|
|
|
Clear the hash table.
|
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
* #### Ponder
|
|
|
|
Let Stockfish ponder its next move while the opponent is thinking.
|
|
|
|
|
|
|
|
* #### MultiPV
|
|
|
|
Output the N best lines (principal variations, PVs) when searching.
|
|
|
|
Leave at 1 for best performance.
|
|
|
|
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
* #### Use NNUE
|
|
|
|
Toggle between the NNUE and classical evaluation functions. If set to "true",
|
Embed default net, and simplify using non-default nets
covers the most important cases from the user perspective:
It embeds the default net in the binary, so a download of that binary will result
in a working engine with the default net. The engine will be functional in the default mode
without any additional user action.
It allows non-default nets to be used, which will be looked for in up to
three directories (working directory, location of the binary, and optionally a specific default directory).
This mechanism is also kept for those developers that use MSVC,
the one compiler that doesn't have an easy mechanism for embedding data.
It is possible to disable embedding, and instead specify a specific directory, e.g. linux distros might want to use
CXXFLAGS="-DNNUE_EMBEDDING_OFF -DDEFAULT_NNUE_DIRECTORY=/usr/share/games/stockfish/" make -j ARCH=x86-64 profile-build
passed STC non-regression:
https://tests.stockfishchess.org/tests/view/5f4a581c150f0aef5f8ae03a
LLR: 2.95 (-2.94,2.94) {-1.25,-0.25}
Total: 66928 W: 7202 L: 7147 D: 52579
Ptnml(0-2): 291, 5309, 22211, 5360, 293
closes https://github.com/official-stockfish/Stockfish/pull/3070
fixes https://github.com/official-stockfish/Stockfish/issues/3030
No functional change.
2020-08-23 05:43:38 -06:00
|
|
|
the network parameters must be available to load from file (see also EvalFile),
|
|
|
|
if they are not embedded in the binary.
|
UCI_Elo implementation (#2225)
This exploits the recent fractional Skill Level, and is a result from some discussion in #2221 and the older #758.
Basically, if UCI_LimitStrength is set, it will internally convert UCI_Elo to a matching fractional Skill Level.
The Elo estimate is based on games at TC 60+0.6, Hash 64Mb, 8moves_v3.pgn, rated with Ordo, anchored to goldfish1.13 (CCRL 40/4 ~2000).
Note that this is mostly about internal consistency, the anchoring to CCRL is a bit weak, e.g. within this tournament,
goldfish and sungorus only have a 200Elo difference, their rating difference on CCRL is 300Elo.
I propose that we continue to expose 'Skill Level' as an UCI option, for backwards compatibility.
The result of a tournament under those conditions are given by the following table, where the player name reflects the UCI_Elo.
# PLAYER : RATING ERROR POINTS PLAYED (%) CFS(%)
1 Elo2837 : 2792.2 50.8 536.5 711 75 100
2 Elo2745 : 2739.0 49.0 487.5 711 69 100
3 Elo2654 : 2666.4 49.2 418.0 711 59 100
4 Elo2562 : 2604.5 38.5 894.5 1383 65 100
5 Elo2471 : 2515.2 38.1 651.5 924 71 100
6 Elo2380 : 2365.9 35.4 478.5 924 52 100
7 Elo2289 : 2290.0 28.0 864.0 1596 54 100
8 sungorus1.4 : 2204.9 27.8 680.5 1596 43 60
9 Elo2197 : 2201.1 30.1 523.5 924 57 100
10 Elo2106 : 2103.8 24.5 730.5 1428 51 100
11 Elo2014 : 2030.5 30.3 377.5 756 50 98
12 goldfish1.13 : 2000.0 ---- 511.0 1428 36 100
13 Elo1923 : 1928.5 30.9 641.5 1260 51 100
14 Elo1831 : 1829.0 42.1 370.5 756 49 100
15 Elo1740 : 1738.3 42.9 277.5 756 37 100
16 Elo1649 : 1625.0 42.1 525.5 1260 42 100
17 Elo1558 : 1521.5 49.9 298.0 756 39 100
18 Elo1467 : 1471.3 51.3 246.5 756 33 100
19 Elo1375 : 1407.1 51.9 183.0 756 24 ---
It can be observed that all set Elos correspond within the error bars with the observed Ordo rating.
No functional change
2019-07-14 06:47:50 -06:00
|
|
|
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
* #### EvalFile
|
|
|
|
The name of the file of the NNUE evaluation parameters. Depending on the GUI the
|
Embed default net, and simplify using non-default nets
covers the most important cases from the user perspective:
It embeds the default net in the binary, so a download of that binary will result
in a working engine with the default net. The engine will be functional in the default mode
without any additional user action.
It allows non-default nets to be used, which will be looked for in up to
three directories (working directory, location of the binary, and optionally a specific default directory).
This mechanism is also kept for those developers that use MSVC,
the one compiler that doesn't have an easy mechanism for embedding data.
It is possible to disable embedding, and instead specify a specific directory, e.g. linux distros might want to use
CXXFLAGS="-DNNUE_EMBEDDING_OFF -DDEFAULT_NNUE_DIRECTORY=/usr/share/games/stockfish/" make -j ARCH=x86-64 profile-build
passed STC non-regression:
https://tests.stockfishchess.org/tests/view/5f4a581c150f0aef5f8ae03a
LLR: 2.95 (-2.94,2.94) {-1.25,-0.25}
Total: 66928 W: 7202 L: 7147 D: 52579
Ptnml(0-2): 291, 5309, 22211, 5360, 293
closes https://github.com/official-stockfish/Stockfish/pull/3070
fixes https://github.com/official-stockfish/Stockfish/issues/3030
No functional change.
2020-08-23 05:43:38 -06:00
|
|
|
filename might have to include the full path to the folder/directory that contains the file.
|
|
|
|
Other locations, such as the directory that contains the binary and the working directory,
|
|
|
|
are also searched.
|
UCI_Elo implementation (#2225)
This exploits the recent fractional Skill Level, and is a result from some discussion in #2221 and the older #758.
Basically, if UCI_LimitStrength is set, it will internally convert UCI_Elo to a matching fractional Skill Level.
The Elo estimate is based on games at TC 60+0.6, Hash 64Mb, 8moves_v3.pgn, rated with Ordo, anchored to goldfish1.13 (CCRL 40/4 ~2000).
Note that this is mostly about internal consistency, the anchoring to CCRL is a bit weak, e.g. within this tournament,
goldfish and sungorus only have a 200Elo difference, their rating difference on CCRL is 300Elo.
I propose that we continue to expose 'Skill Level' as an UCI option, for backwards compatibility.
The result of a tournament under those conditions are given by the following table, where the player name reflects the UCI_Elo.
# PLAYER : RATING ERROR POINTS PLAYED (%) CFS(%)
1 Elo2837 : 2792.2 50.8 536.5 711 75 100
2 Elo2745 : 2739.0 49.0 487.5 711 69 100
3 Elo2654 : 2666.4 49.2 418.0 711 59 100
4 Elo2562 : 2604.5 38.5 894.5 1383 65 100
5 Elo2471 : 2515.2 38.1 651.5 924 71 100
6 Elo2380 : 2365.9 35.4 478.5 924 52 100
7 Elo2289 : 2290.0 28.0 864.0 1596 54 100
8 sungorus1.4 : 2204.9 27.8 680.5 1596 43 60
9 Elo2197 : 2201.1 30.1 523.5 924 57 100
10 Elo2106 : 2103.8 24.5 730.5 1428 51 100
11 Elo2014 : 2030.5 30.3 377.5 756 50 98
12 goldfish1.13 : 2000.0 ---- 511.0 1428 36 100
13 Elo1923 : 1928.5 30.9 641.5 1260 51 100
14 Elo1831 : 1829.0 42.1 370.5 756 49 100
15 Elo1740 : 1738.3 42.9 277.5 756 37 100
16 Elo1649 : 1625.0 42.1 525.5 1260 42 100
17 Elo1558 : 1521.5 49.9 298.0 756 39 100
18 Elo1467 : 1471.3 51.3 246.5 756 33 100
19 Elo1375 : 1407.1 51.9 183.0 756 24 ---
It can be observed that all set Elos correspond within the error bars with the observed Ordo rating.
No functional change
2019-07-14 06:47:50 -06:00
|
|
|
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
* #### UCI_AnalyseMode
|
|
|
|
An option handled by your GUI.
|
|
|
|
|
|
|
|
* #### UCI_Chess960
|
|
|
|
An option handled by your GUI. If true, Stockfish will play Chess960.
|
2014-11-25 16:45:28 -07:00
|
|
|
|
Provide WDL statistics
A number of engines, GUIs and tournaments start to report WDL estimates
along or instead of scores. This patch enables reporting of those stats
in a more or less standard way (http://www.talkchess.com/forum3/viewtopic.php?t=72140)
The model this reporting uses is based on data derived from a few million fishtest LTC games,
given a score and a game ply, a win rate is provided that matches rather closely,
especially in the intermediate range [0.05, 0.95] that data. Some data is shown at
https://github.com/glinscott/fishtest/wiki/UsefulData#win-loss-draw-statistics-of-ltc-games-on-fishtest
Making the conversion game ply dependent is important for a good fit, and is in line
with experience that a +1 score in the early midgame is more likely a win than in the late endgame.
Even when enabled, the printing of the info causes no significant overhead.
Passed STC:
LLR: 2.94 (-2.94,2.94) {-1.50,0.50}
Total: 197112 W: 37226 L: 37347 D: 122539
Ptnml(0-2): 2591, 21025, 51464, 20866, 2610
https://tests.stockfishchess.org/tests/view/5ef79ef4f993893290cc146b
closes https://github.com/official-stockfish/Stockfish/pull/2778
No functional change
2020-06-27 13:29:29 -06:00
|
|
|
* #### UCI_ShowWDL
|
|
|
|
If enabled, show approximate WDL statistics as part of the engine output.
|
|
|
|
These WDL numbers model expected game outcomes for a given evaluation and
|
|
|
|
game ply for engine self-play at fishtest LTC conditions (60+0.6s per game).
|
|
|
|
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
* #### UCI_LimitStrength
|
|
|
|
Enable weaker play aiming for an Elo rating as set by UCI_Elo. This option overrides Skill Level.
|
2014-11-25 16:45:28 -07:00
|
|
|
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
* #### UCI_Elo
|
|
|
|
If enabled by UCI_LimitStrength, aim for an engine strength of the given Elo.
|
|
|
|
This Elo rating has been calibrated at a time control of 60s+0.6s and anchored to CCRL 40/4.
|
2014-11-25 16:45:28 -07:00
|
|
|
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
* #### Skill Level
|
|
|
|
Lower the Skill Level in order to make Stockfish play weaker (see also UCI_LimitStrength).
|
|
|
|
Internally, MultiPV is enabled, and with a certain probability depending on the Skill Level a
|
|
|
|
weaker move will be played.
|
2014-11-25 16:45:28 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
* #### SyzygyPath
|
2019-05-02 11:36:25 -06:00
|
|
|
Path to the folders/directories storing the Syzygy tablebase files. Multiple
|
|
|
|
directories are to be separated by ";" on Windows and by ":" on Unix-based
|
2018-12-29 03:49:10 -07:00
|
|
|
operating systems. Do not use spaces around the ";" or ":".
|
2019-05-02 11:36:25 -06:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
Example: `C:\tablebases\wdl345;C:\tablebases\wdl6;D:\tablebases\dtz345;D:\tablebases\dtz6`
|
2019-05-02 11:36:25 -06:00
|
|
|
|
|
|
|
It is recommended to store .rtbw files on an SSD. There is no loss in storing
|
2019-01-03 15:56:11 -07:00
|
|
|
the .rtbz files on a regular HD. It is recommended to verify all md5 checksums
|
|
|
|
of the downloaded tablebase files (`md5sum -c checksum.md5`) as corruption will
|
|
|
|
lead to engine crashes.
|
2014-11-25 16:45:28 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
* #### SyzygyProbeDepth
|
|
|
|
Minimum remaining search depth for which a position is probed. Set this option
|
2020-11-29 01:07:31 -07:00
|
|
|
to a higher value to probe less aggressively if you experience too much slowdown
|
2021-02-16 08:19:37 -07:00
|
|
|
(in terms of nps) due to tablebase probing.
|
2018-12-29 03:49:10 -07:00
|
|
|
|
|
|
|
* #### Syzygy50MoveRule
|
|
|
|
Disable to let fifty-move rule draws detected by Syzygy tablebase probes count
|
|
|
|
as wins or losses. This is useful for ICCF correspondence games.
|
|
|
|
|
|
|
|
* #### SyzygyProbeLimit
|
|
|
|
Limit Syzygy tablebase probing to positions with at most this many pieces left
|
|
|
|
(including kings and pawns).
|
|
|
|
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
* #### Move Overhead
|
|
|
|
Assume a time delay of x ms due to network and GUI overheads. This is useful to
|
|
|
|
avoid losses on time in those cases.
|
|
|
|
|
|
|
|
* #### Slow Mover
|
|
|
|
Lower values will make Stockfish take less time in games, higher values will
|
|
|
|
make it think longer.
|
|
|
|
|
|
|
|
* #### nodestime
|
|
|
|
Tells the engine to use nodes searched instead of wall time to account for
|
|
|
|
elapsed time. Useful for engine testing.
|
|
|
|
|
|
|
|
* #### Debug Log File
|
|
|
|
Write all communication to and from the engine into a text file.
|
|
|
|
|
2021-04-29 00:18:37 -06:00
|
|
|
For developers the following non-standard commands might be of interest, mainly useful for debugging:
|
|
|
|
|
2021-06-02 00:37:00 -06:00
|
|
|
* #### bench *ttSize threads limit fenFile limitType evalType*
|
|
|
|
Performs a standard benchmark using various options. The signature of a version (standard node
|
|
|
|
count) is obtained using all defaults. `bench` is currently `bench 16 1 13 default depth mixed`.
|
2021-04-29 00:18:37 -06:00
|
|
|
|
2021-05-02 10:50:09 -06:00
|
|
|
* #### compiler
|
|
|
|
Give information about the compiler and environment used for building a binary.
|
|
|
|
|
2021-04-29 00:18:37 -06:00
|
|
|
* #### d
|
|
|
|
Display the current position, with ascii art and fen.
|
|
|
|
|
|
|
|
* #### eval
|
|
|
|
Return the evaluation of the current position.
|
|
|
|
|
2021-05-07 04:24:12 -06:00
|
|
|
* #### export_net [filename]
|
|
|
|
Exports the currently loaded network to a file.
|
|
|
|
If the currently loaded network is the embedded network and the filename
|
|
|
|
is not specified then the network is saved to the file matching the name
|
|
|
|
of the embedded network, as defined in evaluate.h.
|
|
|
|
If the currently loaded network is not the embedded network (some net set
|
|
|
|
through the UCI setoption) then the filename parameter is required and the
|
|
|
|
network is saved into that file.
|
2021-05-02 10:50:09 -06:00
|
|
|
|
|
|
|
* #### flip
|
|
|
|
Flips the side to move.
|
|
|
|
|
|
|
|
|
2021-02-16 08:19:37 -07:00
|
|
|
## A note on classical evaluation versus NNUE evaluation
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
|
|
|
|
Both approaches assign a value to a position that is used in alpha-beta (PVS) search
|
|
|
|
to find the best move. The classical evaluation computes this value as a function
|
|
|
|
of various chess concepts, handcrafted by experts, tested and tuned using fishtest.
|
|
|
|
The NNUE evaluation computes this value with a neural network based on basic
|
|
|
|
inputs (e.g. piece positions only). The network is optimized and trained
|
Add large page support for NNUE weights and simplify TT mem management
Use TT memory functions to allocate memory for the NNUE weights. This
should provide a small speed-up on systems where large pages are not
automatically used, including Windows and some Linux distributions.
Further, since we now have a wrapper for std::aligned_alloc(), we can
simplify the TT memory management a bit:
- We no longer need to store separate pointers to the hash table and
its underlying memory allocation.
- We also get to merge the Linux-specific and default implementations
of aligned_ttmem_alloc().
Finally, we'll enable the VirtualAlloc code path with large page
support also for Win32.
STC: https://tests.stockfishchess.org/tests/view/5f66595823a84a47b9036fba
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 14896 W: 1854 L: 1686 D: 11356
Ptnml(0-2): 65, 1224, 4742, 1312, 105
closes https://github.com/official-stockfish/Stockfish/pull/3081
No functional change.
2020-08-30 10:41:30 -06:00
|
|
|
on the evaluations of millions of positions at moderate search depth.
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
|
|
|
|
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
|
|
|
|
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
|
|
|
|
of the neural network need to be updated after a typical chess move.
|
|
|
|
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
|
2021-02-16 08:19:37 -07:00
|
|
|
tools to train and develop the NNUE networks. On CPUs supporting modern vector instructions
|
|
|
|
(avx2 and similar), the NNUE evaluation results in much stronger playing strength, even
|
|
|
|
if the nodes per second computed by the engine is somewhat lower (roughly 80% of nps
|
|
|
|
is typical).
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
|
2021-02-16 08:19:37 -07:00
|
|
|
Notes:
|
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823
https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825
https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
2020-08-05 09:11:15 -06:00
|
|
|
|
2021-02-16 08:19:37 -07:00
|
|
|
1) the NNUE evaluation depends on the Stockfish binary and the network parameter
|
|
|
|
file (see the EvalFile UCI option). Not every parameter file is compatible with a given
|
|
|
|
Stockfish binary, but the default value of the EvalFile UCI option is the name of a network
|
|
|
|
that is guaranteed to be compatible with that binary.
|
|
|
|
|
|
|
|
2) to use the NNUE evaluation, the additional data file with neural network parameters
|
2021-05-07 04:24:12 -06:00
|
|
|
needs to be available. Normally, this file is already embedded in the binary or it
|
2021-02-16 08:19:37 -07:00
|
|
|
can be downloaded. The filename for the default (recommended) net can be found as the default
|
|
|
|
value of the `EvalFile` UCI option, with the format `nn-[SHA256 first 12 digits].nnue`
|
|
|
|
(for instance, `nn-c157e0a5755b.nnue`). This file can be downloaded from
|
|
|
|
```
|
|
|
|
https://tests.stockfishchess.org/api/nn/[filename]
|
|
|
|
```
|
|
|
|
replacing `[filename]` as needed.
|
2018-12-29 03:49:10 -07:00
|
|
|
|
2021-02-16 08:19:37 -07:00
|
|
|
## What to expect from the Syzygy tablebases?
|
2014-11-25 16:45:28 -07:00
|
|
|
|
|
|
|
If the engine is searching a position that is not in the tablebases (e.g.
|
2018-08-28 18:00:14 -06:00
|
|
|
a position with 8 pieces), it will access the tablebases during the search.
|
2021-05-07 04:24:12 -06:00
|
|
|
If the engine reports a very large score (typically 153.xx), this means
|
2020-11-29 01:07:31 -07:00
|
|
|
it has found a winning line into a tablebase position.
|
2014-11-25 16:45:28 -07:00
|
|
|
|
|
|
|
If the engine is given a position to search that is in the tablebases, it
|
|
|
|
will use the tablebases at the beginning of the search to preselect all
|
|
|
|
good moves, i.e. all moves that preserve the win or preserve the draw while
|
|
|
|
taking into account the 50-move rule.
|
|
|
|
It will then perform a search only on those moves. **The engine will not move
|
|
|
|
immediately**, unless there is only a single good move. **The engine likely
|
2020-11-29 01:07:31 -07:00
|
|
|
will not report a mate score, even if the position is known to be won.**
|
2014-11-25 16:45:28 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
It is therefore clear that this behaviour is not identical to what one might
|
2014-11-25 16:45:28 -07:00
|
|
|
be used to with Nalimov tablebases. There are technical reasons for this
|
|
|
|
difference, the main technical reason being that Nalimov tablebases use the
|
2021-02-16 08:19:37 -07:00
|
|
|
DTM metric (distance-to-mate), while the Syzygy tablebases use a variation of the
|
2014-11-25 16:45:28 -07:00
|
|
|
DTZ metric (distance-to-zero, zero meaning any move that resets the 50-move
|
2021-02-16 08:19:37 -07:00
|
|
|
counter). This special metric is one of the reasons that the Syzygy tablebases are
|
2014-11-25 16:45:28 -07:00
|
|
|
more compact than Nalimov tablebases, while still storing all information
|
|
|
|
needed for optimal play and in addition being able to take into account
|
|
|
|
the 50-move rule.
|
|
|
|
|
2020-05-04 11:49:27 -06:00
|
|
|
## Large Pages
|
|
|
|
|
|
|
|
Stockfish supports large pages on Linux and Windows. Large pages make
|
|
|
|
the hash access more efficient, improving the engine speed, especially
|
2020-09-24 03:38:35 -06:00
|
|
|
on large hash sizes. Typical increases are 5..10% in terms of nodes per
|
|
|
|
second, but speed increases up to 30% have been measured. The support is
|
2020-05-04 11:49:27 -06:00
|
|
|
automatic. Stockfish attempts to use large pages when available and
|
|
|
|
will fall back to regular memory allocation when this is not the case.
|
|
|
|
|
|
|
|
### Support on Linux
|
|
|
|
|
|
|
|
Large page support on Linux is obtained by the Linux kernel
|
|
|
|
transparent huge pages functionality. Typically, transparent huge pages
|
2020-11-29 01:07:31 -07:00
|
|
|
are already enabled, and no configuration is needed.
|
2020-05-04 11:49:27 -06:00
|
|
|
|
|
|
|
### Support on Windows
|
|
|
|
|
|
|
|
The use of large pages requires "Lock Pages in Memory" privilege. See
|
|
|
|
[Enable the Lock Pages in Memory Option (Windows)](https://docs.microsoft.com/en-us/sql/database-engine/configure-windows/enable-the-lock-pages-in-memory-option-windows)
|
2020-09-24 03:38:35 -06:00
|
|
|
on how to enable this privilege, then run [RAMMap](https://docs.microsoft.com/en-us/sysinternals/downloads/rammap)
|
|
|
|
to double-check that large pages are used. We suggest that you reboot
|
|
|
|
your computer after you have enabled large pages, because long Windows
|
2020-11-29 01:07:31 -07:00
|
|
|
sessions suffer from memory fragmentation, which may prevent Stockfish
|
2020-09-24 03:38:35 -06:00
|
|
|
from getting large pages: a fresh session is better in this regard.
|
2014-11-25 16:45:28 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
## Compiling Stockfish yourself from the sources
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2020-06-07 16:49:27 -06:00
|
|
|
Stockfish has support for 32 or 64-bit CPUs, certain hardware
|
|
|
|
instructions, big-endian machines such as Power PC, and other platforms.
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2020-06-07 16:49:27 -06:00
|
|
|
On Unix-like systems, it should be easy to compile Stockfish
|
|
|
|
directly from the source code with the included Makefile in the folder
|
|
|
|
`src`. In general it is recommended to run `make help` to see a list of make
|
|
|
|
targets with corresponding descriptions.
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2020-06-07 16:49:27 -06:00
|
|
|
```
|
|
|
|
cd src
|
|
|
|
make help
|
2020-07-11 08:59:33 -06:00
|
|
|
make net
|
2020-09-24 03:38:35 -06:00
|
|
|
make build ARCH=x86-64-modern
|
2020-06-07 16:49:27 -06:00
|
|
|
```
|
|
|
|
|
2020-11-29 01:07:31 -07:00
|
|
|
When not using the Makefile to compile (for instance, with Microsoft MSVC) you
|
2020-06-07 16:49:27 -06:00
|
|
|
need to manually set/unset some switches in the compiler command line; see
|
|
|
|
file *types.h* for a quick reference.
|
2011-01-03 15:55:12 -07:00
|
|
|
|
2021-03-24 14:55:49 -06:00
|
|
|
When reporting an issue or a bug, please tell us which Stockfish version
|
|
|
|
and which compiler you used to create your executable. This information
|
|
|
|
can be found by typing the following command in a console:
|
2020-01-15 14:21:15 -07:00
|
|
|
|
|
|
|
```
|
2020-07-11 08:59:33 -06:00
|
|
|
./stockfish compiler
|
2020-01-15 14:21:15 -07:00
|
|
|
```
|
2017-12-10 05:46:43 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
## Understanding the code base and participating in the project
|
|
|
|
|
2021-03-24 14:55:49 -06:00
|
|
|
Stockfish's improvement over the last decade has been a great community
|
|
|
|
effort. There are a few ways to help contribute to its growth.
|
2018-12-29 03:49:10 -07:00
|
|
|
|
|
|
|
### Donating hardware
|
|
|
|
|
|
|
|
Improving Stockfish requires a massive amount of testing. You can donate
|
2020-01-03 18:48:32 -07:00
|
|
|
your hardware resources by installing the [Fishtest Worker](https://github.com/glinscott/fishtest/wiki/Running-the-worker:-overview)
|
|
|
|
and view the current tests on [Fishtest](https://tests.stockfishchess.org/tests).
|
2018-12-29 03:49:10 -07:00
|
|
|
|
|
|
|
### Improving the code
|
|
|
|
|
2020-01-03 18:48:32 -07:00
|
|
|
If you want to help improve the code, there are several valuable resources:
|
2018-12-29 03:49:10 -07:00
|
|
|
|
|
|
|
* [In this wiki,](https://www.chessprogramming.org) many techniques used in
|
|
|
|
Stockfish are explained with a lot of background information.
|
|
|
|
|
|
|
|
* [The section on Stockfish](https://www.chessprogramming.org/Stockfish)
|
|
|
|
describes many features and techniques used by Stockfish. However, it is
|
|
|
|
generic rather than being focused on Stockfish's precise implementation.
|
|
|
|
Nevertheless, a helpful resource.
|
2017-12-10 05:46:43 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
* The latest source can always be found on [GitHub](https://github.com/official-stockfish/Stockfish).
|
2021-02-16 08:19:37 -07:00
|
|
|
Discussions about Stockfish take place these days mainly in the [FishCooking](https://groups.google.com/forum/#!forum/fishcooking)
|
|
|
|
group and on the [Stockfish Discord channel](https://discord.gg/nv8gDtt).
|
|
|
|
The engine testing is done on [Fishtest](https://tests.stockfishchess.org/tests).
|
2018-12-29 03:49:10 -07:00
|
|
|
If you want to help improve Stockfish, please read this [guideline](https://github.com/glinscott/fishtest/wiki/Creating-my-first-test)
|
|
|
|
first, where the basics of Stockfish development are explained.
|
2017-12-10 05:46:43 -07:00
|
|
|
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
## Terms of use
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
Stockfish is free, and distributed under the **GNU General Public License version 3**
|
2020-11-29 01:07:31 -07:00
|
|
|
(GPL v3). Essentially, this means you are free to do almost exactly
|
2009-11-05 11:29:26 -07:00
|
|
|
what you want with the program, including distributing it among your
|
2020-11-29 01:07:31 -07:00
|
|
|
friends, making it available for download from your website, selling
|
2009-11-05 11:29:26 -07:00
|
|
|
it (either by itself or as part of some bigger software package), or
|
|
|
|
using it as the starting point for a software project of your own.
|
|
|
|
|
|
|
|
The only real limitation is that whenever you distribute Stockfish in
|
2021-02-16 08:19:37 -07:00
|
|
|
some way, you MUST always include the full source code, or a pointer
|
|
|
|
to where the source code can be found, to generate the exact binary
|
|
|
|
you are distributing. If you make any changes to the source code,
|
|
|
|
these changes must also be made available under the GPL.
|
2009-11-05 11:29:26 -07:00
|
|
|
|
2018-12-29 03:49:10 -07:00
|
|
|
For full details, read the copy of the GPL v3 found in the file named
|
2021-05-18 12:52:59 -06:00
|
|
|
[*Copying.txt*](https://github.com/official-stockfish/Stockfish/blob/master/Copying.txt).
|