2021-08-13 14:20:11 -06:00
|
|
|
# List of authors for Stockfish
|
2014-06-20 19:35:09 -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
|
|
|
# Founders of the Stockfish project and fishtest infrastructure
|
2018-02-17 17:51:35 -07:00
|
|
|
Tord Romstad (romstad)
|
2016-11-04 07:39:24 -06:00
|
|
|
Marco Costalba (mcostalba)
|
|
|
|
Joona Kiiski (zamar)
|
|
|
|
Gary Linscott (glinscott)
|
2018-02-17 17:51:35 -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
|
|
|
# Authors and inventors of NNUE, training, NNUE port
|
|
|
|
Yu Nasu (ynasu87)
|
|
|
|
Motohiro Isozaki (yaneurao)
|
|
|
|
Hisayori Noda (nodchip)
|
|
|
|
|
|
|
|
# all other authors of the code in alphabetical order
|
2018-11-29 07:15:43 -07:00
|
|
|
Aditya (absimaldata)
|
2018-12-29 03:49:10 -07:00
|
|
|
Adrian Petrescu (apetresc)
|
2018-02-17 17:51:35 -07:00
|
|
|
Ajith Chandy Jose (ajithcj)
|
|
|
|
Alain Savard (Rocky640)
|
Adjust aspiration window with eval
This patch changes the base aspiration window size depending on the absolute
value of the previous iteration score, increasing it away from zero. This
stems from the observation that the further away from zero, the more likely
the evaluation is to change significantly with more depth. Conversely, a
tighter aspiration window is more efficient when close to zero.
A beneficial side-effect is that analysis of won positions without a quick
mate is less prone to waste nodes in repeated fail-high that change the eval
by tiny steps.
STC:
LLR: 2.96 (-2.94,2.94) [0.50,4.50]
Total: 60102 W: 13327 L: 12868 D: 33907
http://tests.stockfishchess.org/tests/view/5d9a70d40ebc5902b6cf39ba
LTC:
LLR: 2.95 (-2.94,2.94) [0.00,3.50]
Total: 155553 W: 25745 L: 25141 D: 104667
http://tests.stockfishchess.org/tests/view/5d9a7ca30ebc5902b6cf4028
Future work : the values used in this patch were only a reasonable guess.
Further testing should unveil more optimal values. However, the aspiration
window is rather tight with a minimum of 21 internal units, so discrete
integers put a practical limitation to such tweaking.
More exotic experiments around the aspiration window parameters could also
be tried, but efficient conditions to adjust the base aspiration window size
or allow it to not be centered on the current evaluation are not obvious.
The aspiration window increases after a fail-high or a fail-low is another
avenue to explore for potential enhancements.
Bench: 4043748
2019-10-07 11:02:33 -06:00
|
|
|
Alayan Feh (Alayan-stk-2)
|
2014-06-20 19:35:09 -06:00
|
|
|
Alexander Kure
|
2019-08-14 14:15:41 -06:00
|
|
|
Alexander Pagel (Lolligerhans)
|
Increase reduction based on the number of best move changes.
Thanks to Vizvezdenec for the PvNode idea and also to vondele the !PvNode idea.
Passed STC:
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 19120 W: 1998 L: 1839 D: 15283
Ptnml(0-2): 76, 1445, 6375, 1572, 92
https://tests.stockfishchess.org/tests/view/5fa8af3e67cbf42301d6a6c9
Passed LTC:
LLR: 2.94 (-2.94,2.94) {0.25,1.25}
Total: 75584 W: 3454 L: 3205 D: 68925
Ptnml(0-2): 54, 2832, 31771, 3081, 54
closes https://github.com/official-stockfish/Stockfish/pull/3224
Bench: 3595418
2020-11-08 19:43:32 -07:00
|
|
|
Alfredo Menezes (lonfom169)
|
2018-02-17 17:51:35 -07:00
|
|
|
Ali AlZhrani (Cooffe)
|
2021-05-27 09:04:47 -06:00
|
|
|
Andrei Vetrov (proukornew)
|
2018-02-17 17:51:35 -07:00
|
|
|
Andrew Grant (AndyGrant)
|
|
|
|
Andrey Neporada (nepal)
|
2014-06-20 19:35:09 -06:00
|
|
|
Andy Duplain
|
2021-01-30 01:50:04 -07:00
|
|
|
Antoine Champion (antoinechampion)
|
2018-02-17 17:51:35 -07:00
|
|
|
Aram Tumanian (atumanian)
|
|
|
|
Arjun Temurnikar
|
2021-04-12 04:42:35 -06:00
|
|
|
Artem Solopiy (EntityFX)
|
2014-06-20 19:35:09 -06:00
|
|
|
Auguste Pop
|
|
|
|
Balint Pfliegel
|
2018-02-17 17:51:35 -07:00
|
|
|
Ben Koshy (BKSpurgeon)
|
|
|
|
Bill Henry (VoyagerOne)
|
2020-01-07 13:35:47 -07:00
|
|
|
Bojun Guo (noobpwnftw, Nooby)
|
2018-02-17 17:51:35 -07:00
|
|
|
braich
|
2020-01-07 13:35:47 -07:00
|
|
|
Brian Sheppard (SapphireBrand, briansheppard-toast)
|
2021-01-09 23:30:40 -07:00
|
|
|
Bruno de Melo Costa (BM123499)
|
2018-02-17 17:51:35 -07:00
|
|
|
Bryan Cross (crossbr)
|
2020-01-07 13:35:47 -07:00
|
|
|
candirufish
|
|
|
|
Chess13234
|
2018-02-17 17:51:35 -07:00
|
|
|
Chris Cain (ceebo)
|
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
|
|
|
Dale Weiler (graphitemaster)
|
2020-01-07 13:35:47 -07:00
|
|
|
Dan Schmidt (dfannius)
|
|
|
|
Daniel Axtens (daxtens)
|
2018-02-17 17:51:35 -07:00
|
|
|
Daniel Dugovic (ddugovic)
|
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
|
|
|
Dariusz Orzechowski (dorzechowski)
|
2018-02-17 17:51:35 -07:00
|
|
|
David Zar
|
|
|
|
Daylen Yang (daylen)
|
2020-11-12 06:05:28 -07:00
|
|
|
Deshawn Mohan-Smith (GoldenRare)
|
2021-01-09 08:46:06 -07:00
|
|
|
Dieter Dobbelaere (ddobbelaere)
|
2016-01-02 02:43:25 -07:00
|
|
|
DiscanX
|
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
|
|
|
Dominik Schlösser (domschl)
|
2020-01-07 13:35:47 -07:00
|
|
|
double-beep
|
2021-05-17 01:13:34 -06:00
|
|
|
Douglas Matos Gomes (dsmsgms)
|
2020-01-07 13:35:47 -07:00
|
|
|
Eduardo Cáceres (eduherminio)
|
|
|
|
Eelco de Groot (KingDefender)
|
2018-12-29 03:49:10 -07:00
|
|
|
Elvin Liu (solarlight2)
|
2018-02-17 17:51:35 -07:00
|
|
|
erbsenzaehler
|
2016-01-02 02:43:25 -07:00
|
|
|
Ernesto Gatti
|
Tuned safe checks and minor piece king protectors
A combination of terms related to king safety one tuned safe check weights,
the other tuned knight and bishop king protector weights separately with
some compensation in the high outpost bonuses given to the minor pieces.
passed STC
LLR: 2.95 (-2.94,2.94) {-0.50,1.50}
Total: 39892 W: 7594 L: 7350 D: 24948
Ptnml(0-2): 643, 4559, 9314, 4771, 659
https://tests.stockfishchess.org/tests/view/5ea49635b908f6dd28f34b82
passed LTC
LLR: 2.94 (-2.94,2.94) {0.25,1.75}
Total: 104934 W: 13300 L: 12834 D: 78800
Ptnml(0-2): 697, 9571, 31514, 9939, 746
https://tests.stockfishchess.org/tests/view/5ea4abf6b908f6dd28f34bcb
closes https://github.com/official-stockfish/Stockfish/pull/2649
Bench 4800754
2020-04-25 13:55:35 -06:00
|
|
|
Linmiao Xu (linrock)
|
2018-02-17 17:51:35 -07:00
|
|
|
Fabian Beuke (madnight)
|
|
|
|
Fabian Fichter (ianfab)
|
2020-08-09 08:20:45 -06:00
|
|
|
Fanael Linithien (Fanael)
|
2018-02-17 17:51:35 -07:00
|
|
|
fanon
|
|
|
|
Fauzi Akram Dabat (FauziAkram)
|
|
|
|
Felix Wittmann
|
|
|
|
gamander
|
2020-03-05 10:37:08 -07:00
|
|
|
Gary Heckman (gheckman)
|
2020-08-21 04:28:53 -06:00
|
|
|
George Sobala (gsobala)
|
2018-02-17 17:51:35 -07:00
|
|
|
gguliash
|
Apply good/bad history reduction also when inCheck
Main idea is that, in some cases, 'in check' situations are not so different from 'not in check' ones.
Trying to use piece count in order to select only a few 'in check' situations have failed LTC testing.
It could be interesting to apply one of those ideas in other parts of the search function.
passed STC:
https://tests.stockfishchess.org/tests/view/60f1b68dd1189bed71812d40
LLR: 2.93 (-2.94,2.94) <-2.50,0.50>
Total: 53472 W: 4078 L: 4008 D: 45386
Ptnml(0-2): 127, 3297, 19795, 3413, 104
passed LTC:
https://tests.stockfishchess.org/tests/view/60f291e6d1189bed71812de3
LLR: 2.92 (-2.94,2.94) <-2.50,0.50>
Total: 89712 W: 2651 L: 2632 D: 84429
Ptnml(0-2): 60, 2261, 40188, 2294, 53
closes https://github.com/official-stockfish/Stockfish/pull/3619
Bench: 5185789
2021-07-18 12:14:11 -06:00
|
|
|
Giacomo Lorenzetti (G-Lorenz)
|
2018-02-17 17:51:35 -07:00
|
|
|
Gian-Carlo Pascutto (gcp)
|
|
|
|
Gontran Lemaire (gonlem)
|
|
|
|
Goodkov Vasiliy Aleksandrovich (goodkov)
|
2014-06-20 19:35:09 -06:00
|
|
|
Gregor Cramer
|
2018-08-12 10:40:03 -06:00
|
|
|
GuardianRM
|
2018-02-17 17:51:35 -07:00
|
|
|
Günther Demetz (pb00067, pb00068)
|
|
|
|
Guy Vreuls (gvreuls)
|
|
|
|
Henri Wiechers
|
2016-11-04 07:39:24 -06:00
|
|
|
Hiraoka Takuya (HiraokaTakuya)
|
2018-02-17 17:51:35 -07:00
|
|
|
homoSapiensSapiens
|
2014-06-20 19:35:09 -06:00
|
|
|
Hongzhi Cheng
|
2018-02-17 17:51:35 -07:00
|
|
|
Ivan Ivec (IIvec)
|
|
|
|
Jacques B. (Timshel)
|
|
|
|
Jan Ondruš (hxim)
|
2018-11-29 07:15:43 -07:00
|
|
|
Jared Kish (Kurtbusch)
|
2018-02-17 17:51:35 -07:00
|
|
|
Jarrod Torriero (DU-jdto)
|
2020-01-07 13:35:47 -07:00
|
|
|
Jean Gauthier (OuaisBla)
|
2018-09-03 04:46:05 -06:00
|
|
|
Jean-Francois Romang (jromang)
|
2020-01-07 13:35:47 -07:00
|
|
|
Jekaa
|
2018-02-17 17:51:35 -07:00
|
|
|
Jerry Donald Watson (jerrydonaldwatson)
|
2020-08-08 04:07:07 -06:00
|
|
|
jjoshua2
|
2018-02-17 17:51:35 -07:00
|
|
|
Jonathan Calovski (Mysseno)
|
Increase reduction at root
when the best move does not change frequently
STC:
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 51320 W: 5159 L: 4956 D: 41205
Ptnml(0-2): 215, 3897, 17242, 4082, 224
https://tests.stockfishchess.org/tests/view/5faa072367cbf42301d6a767
LTC:
LLR: 2.98 (-2.94,2.94) {0.25,1.25}
Total: 15952 W: 762 L: 642 D: 14548
Ptnml(0-2): 8, 561, 6725, 667, 15
https://tests.stockfishchess.org/tests/view/5faa4c3567cbf42301d6a794
closes https://github.com/official-stockfish/Stockfish/pull/3225
Bench: 3954692
2020-11-10 10:28:43 -07:00
|
|
|
Jonathan Buladas Dumale (SFisGOD)
|
2018-02-17 17:51:35 -07:00
|
|
|
Joost VandeVondele (vondele)
|
|
|
|
Jörg Oster (joergoster)
|
Using a S-curve for the optimism measure
Add a logarithmic term in the optimism computation, increase
the maximal optimism and lower the contempt offset.
This increases the dynamics of the optimism aspects, giving
a boost for balanced positions without skewing too much on
unbalanced positions (but this version will enter panic mode
faster than previous master when behind, trying to draw faster
when slightly behind). This helps, since optimism is in general
a good thing, for instance at LTC, but too high optimism
rapidly contaminates play.
passed STC:
LLR: 2.96 (-2.94,2.94) [0.00,5.00]
Total: 159343 W: 34489 L: 33588 D: 91266
http://tests.stockfishchess.org/tests/view/5a8db9340ebc590297cc85b6
passed LTC:
LLR: 2.97 (-2.94,2.94) [0.00,5.00]
Total: 47491 W: 7825 L: 7517 D: 32149
http://tests.stockfishchess.org/tests/view/5a9456a80ebc590297cc8a89
It must be mentioned that a version of the PR with contempt 0
did not pass STC [0,5]. The version in the patch, which uses
default contempt 12, was found to be as strong as current master
on different matches against SF7 and SF8, both at STC and LTC.
One drawback maybe is that it raises the draw rate in self-play
from 56% to 59%, giving a little bit less sensitivity for SF
developpers to find evaluation improvements by selfplay tests
in fishtest.
Possible further work:
• tune the values accurately, while keeping in mind the drawrate issue
• check whether it is possible to remove linear and offset term
• try to simplify the S-shape curve
Bench: 5934644
2018-03-04 08:50:19 -07:00
|
|
|
Joseph Ellis (jhellis3)
|
2018-02-17 17:51:35 -07:00
|
|
|
Joseph R. Prostko
|
Update default net to nn-8e47cf062333.nnue
This net is the result of training on data used by the Leela project. More precisely,
we shuffled T60 and T74 data kindly provided by borg (for different Tnn, the data is
a result of Leela selfplay with differently sized Leela nets).
The data is available at vondele's google drive:
https://drive.google.com/drive/folders/1mftuzYdl9o6tBaceR3d_VBQIrgKJsFpl.
The Leela data comes in small chunks of .binpack files. To shuffle them, we simply
used a small python script to randomly rename the files, and then concatenated them
using `cat`. As validation data we picked a file of T60 data. We will further investigate
T74 data.
The training for the NNUE architecture used 200 epochs with the Python trainer from
the Stockfish project. Unlike the previous run we tried with this data, this run does
not have adjusted scaling — not because we didn't want to, but because we forgot.
However, this training randomly skips 40% more positions than previous run. The loss
was very spiky and decreased slower than it does usually.
Training loss: https://github.com/official-stockfish/images/blob/main/training-loss-8e47cf062333.png
Validation loss: https://github.com/official-stockfish/images/blob/main/validation-loss-8e47cf062333.png
This is the exact training command:
python train.py --smart-fen-skipping --random-fen-skipping 14 --batch-size 16384 --threads 4 --num-workers 4 --gpus 1 trainingdata\training_data.binpack validationdata\val.binpack
---
10k STC result:
ELO: 3.61 +-3.3 (95%) LOS: 98.4%
Total: 10000 W: 1241 L: 1137 D: 7622
Ptnml(0-2): 68, 841, 3086, 929, 76
https://tests.stockfishchess.org/tests/view/60c67e50457376eb8bcaae70
10k LTC result:
ELO: 2.71 +-2.4 (95%) LOS: 98.8%
Total: 10000 W: 659 L: 581 D: 8760
Ptnml(0-2): 22, 485, 3900, 579, 14
https://tests.stockfishchess.org/tests/view/60c69deb457376eb8bcaae98
Passed LTC:
LLR: 2.93 (-2.94,2.94) <0.50,3.50>
Total: 9648 W: 685 L: 545 D: 8418
Ptnml(0-2): 22, 448, 3740, 596, 18
https://tests.stockfishchess.org/tests/view/60c6d41c457376eb8bcaaecf
---
closes https://github.com/official-stockfish/Stockfish/pull/3550
Bench: 4877339
2021-06-13 15:48:32 -06:00
|
|
|
Julian Willemer (NightlyKing)
|
2018-02-17 17:51:35 -07:00
|
|
|
jundery
|
2020-01-07 13:35:47 -07:00
|
|
|
Justin Blanchard (UncombedCoconut)
|
2014-06-20 19:35:09 -06:00
|
|
|
Kelly Wilson
|
2018-02-17 17:51:35 -07:00
|
|
|
Ken Takusagawa
|
|
|
|
kinderchocolate
|
|
|
|
Kiran Panditrao (Krgp)
|
2014-06-20 19:35:09 -06:00
|
|
|
Kojirion
|
2020-12-31 09:00:39 -07:00
|
|
|
Krystian Kuzniarek (kuzkry)
|
2018-11-29 07:15:43 -07:00
|
|
|
Leonardo Ljubičić (ICCF World Champion)
|
2018-02-17 17:51:35 -07:00
|
|
|
Leonid Pechenik (lp--)
|
2021-07-21 01:33:13 -06:00
|
|
|
Liam Keegan (lkeegan)
|
2020-01-07 13:35:47 -07:00
|
|
|
Linus Arver (listx)
|
2018-02-17 17:51:35 -07:00
|
|
|
loco-loco
|
2018-12-01 02:28:10 -07:00
|
|
|
Lub van den Berg (ElbertoOne)
|
2018-02-17 17:51:35 -07:00
|
|
|
Luca Brivio (lucabrivio)
|
|
|
|
Lucas Braesch (lucasart)
|
|
|
|
Lyudmil Antonov (lantonov)
|
2019-08-14 14:15:41 -06:00
|
|
|
Maciej Żenczykowski (zenczykowski)
|
Smarter time management near stop limit
This patch makes Stockfish search same depth again if > 60% of optimum time is
already used, instead of trying the next iteration. The idea is that the next
iteration will generally take about the same amount of time as has already been
used in total. When we are likely to begin the last iteration, as judged by total
time taken so far > 0.6 * optimum time, searching the last depth again instead of
increasing the depth still helps the other threads in lazy SMP and prepares better
move ordering for the next moves.
STC :
LLR: 2.95 (-2.94,2.94) {-1.00,3.00}
Total: 13436 W: 2695 L: 2558 D: 8183
Ptnml(0-2): 222, 1538, 3087, 1611, 253
https://tests.stockfishchess.org/tests/view/5e1618a761fe5f83a67dd964
LTC :
LLR: 2.94 (-2.94,2.94) {0.00,2.00}
Total: 32160 W: 4261 L: 4047 D: 23852
Ptnml(0-2): 211, 2988, 9448, 3135, 247
https://tests.stockfishchess.org/tests/view/5e162ca061fe5f83a67dd96d
The code was revised as suggested by @vondele for multithreading:
STC (8 threads):
LLR: 2.95 (-2.94,2.94) {0.00,2.00}
Total: 16640 W: 2049 L: 1885 D: 12706
Ptnml(0-2): 119, 1369, 5158, 1557, 108
https://tests.stockfishchess.org/tests/view/5e19826a2cc590e03c3c2f52
LTC (8 threads):
LLR: 2.95 (-2.94,2.94) {-1.00,3.00}
Total: 16536 W: 2758 L: 2629 D: 11149
Ptnml(0-2): 182, 1758, 4296, 1802, 224
https://tests.stockfishchess.org/tests/view/5e18b91a27dab692fcf9a140
Thanks to those discussing Stockfish lazy SMP on fishcooking which made me
try this, and to @vondele for suggestions and doing related tests.
See full discussion in the pull request thread:
https://github.com/official-stockfish/Stockfish/pull/2482
Bench: 4586187
2020-01-11 15:10:22 -07:00
|
|
|
Malcolm Campbell (xoto10)
|
Introduce Overload
This patch applies a S(10, 5) bonus for every square that is:
- Occupied by an enemy piece which is not a pawn
- Attacked exactly once by our pieces
- Defended exactly once by enemy pieces
The idea is that these pieces must be defended. Their defenders have
dramatically limited mobility, and they are vulnerable to our future
attack.
As with connectivity, there are probably many more tests to be run in
this area. In particular:
- I believe @snicolet's queen overload tests have demonstrated a potential
need for a queen overload bonus above and beyond this one; however, the
conditions for "overload" in this patch are different (excluding pieces
we attack twice). My next test after this is (hopefully) merged will be
to intersect the Bitboard I define here with the enemy's queen attacks and
attempt to give additional bonus.
- Perhaps we should exclude pieces attacked by pawns--can pawns really be
overloaded? Should they have the same weight, or less? This didn't work
with a previous version, but it could work with this one.
- More generally, different pieces may need more or less bonus. We could
change bonuses based on what type of enemy piece is being overloaded, what
type of friendly piece is attacking, and/or what type of piece is being
defended by the overloaded piece and attacked by us, or any intersection
of these three. For example, here attacked/defended pawns are excluded,
but they're not totally worthless targets, and could be added again with
a smaller bonus.
- This list is by no means exhaustive.
STC:
LLR: 2.96 (-2.94,2.94) [0.00,5.00]
Total: 17439 W: 3599 L: 3390 D: 10450
http://tests.stockfishchess.org/tests/view/5ac78a2e0ebc59435923735e
LTC:
LLR: 2.95 (-2.94,2.94) [0.00,5.00]
Total: 43304 W: 6533 L: 6256 D: 30515
http://tests.stockfishchess.org/tests/view/5ac7a1d80ebc59435923736f
Closes https://github.com/official-stockfish/Stockfish/pull/1533
Bench: 5248871
----------------
This is my first time opening a PR, so I apologize if there are errors.
There are too many people to thank since I submitted my first test just
over a month ago. Thank you all for the warm welcome and here is to more
green patches!
In particular, I would like to thank:
- @crossbr, whose comment in a FishCooking thread first inspired me to
consider the overloading of pieces other than queens,
- @snicolet, whose queen overload tests inspired this one and served as
the base of my first overload attempts,
- @protonspring, whose connectivity tests inspired this one and who provided
much of the feedback needed to take this from red to green,
- @vondele, who kindly corrected me when I submitted a bad LTC test,
- @Rocky640, who has helped me over and over again in the past month.
Thank you all!
2018-04-06 17:20:48 -06:00
|
|
|
Mark Tenzer (31m059)
|
2020-01-07 13:35:47 -07:00
|
|
|
marotear
|
2021-02-11 14:29:28 -07:00
|
|
|
Matt Ginsberg (mattginsberg)
|
2020-01-07 13:35:47 -07:00
|
|
|
Matthew Lai (matthewlai)
|
|
|
|
Matthew Sullivan (Matt14916)
|
2020-11-13 17:55:29 -07:00
|
|
|
Maxim Molchanov (Maxim)
|
2020-01-07 13:35:47 -07:00
|
|
|
Michael An (man)
|
2018-02-17 17:51:35 -07:00
|
|
|
Michael Byrne (MichaelB7)
|
2018-09-03 04:46:05 -06:00
|
|
|
Michael Chaly (Vizvezdenec)
|
2020-01-07 13:35:47 -07:00
|
|
|
Michael Stembera (mstembera)
|
|
|
|
Michael Whiteley (protonspring)
|
2018-02-17 17:51:35 -07:00
|
|
|
Michel Van den Bergh (vdbergh)
|
Use single value for KingProtector.
After some recent big tuning session, the values for King Protector were
simplified to only be used on minor pieces. This patch tries to further
simplify by just using a single value, since current S(6,5) and S(5,6)
are close to each other. The value S(6,6) ended up passing, although
S(5,5) was also tried and failed STC.
STC
LLR: 2.95 (-2.94,2.94) [-3.00,1.00]
Total: 14261 W: 3288 L: 3151 D: 7822
http://tests.stockfishchess.org/tests/view/5b4ccdf50ebc5902bdb77f65
LTC
LLR: 2.96 (-2.94,2.94) [-3.00,1.00]
Total: 19606 W: 3396 L: 3273 D: 12937
http://tests.stockfishchess.org/tests/view/5b4ce4280ebc5902bdb7803b
Bench: 5448998
2018-07-16 10:51:43 -06:00
|
|
|
Miguel Lahoz (miguel-l)
|
2018-03-13 01:10:59 -06:00
|
|
|
Mikael Bäckman (mbootsector)
|
2020-01-07 13:35:47 -07:00
|
|
|
Mira
|
2018-02-17 17:51:35 -07:00
|
|
|
Miroslav Fontán (Hexik)
|
2018-04-30 23:12:17 -06:00
|
|
|
Moez Jellouli (MJZ1977)
|
2018-02-17 17:51:35 -07:00
|
|
|
Mohammed Li (tthsqe12)
|
|
|
|
Nathan Rugg (nmrugg)
|
2019-09-21 01:59:32 -06:00
|
|
|
Nick Pelling (nickpelling)
|
2018-02-17 17:51:35 -07:00
|
|
|
Nicklas Persson (NicklasPersson)
|
|
|
|
Niklas Fiekas (niklasf)
|
2020-01-07 13:35:47 -07:00
|
|
|
Nikolay Kostov (NikolayIT)
|
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
|
|
|
Nguyen Pham (nguyenpham)
|
|
|
|
Norman Schmidt (FireFather)
|
2020-08-16 09:59:13 -06:00
|
|
|
notruck
|
Range reductions
adding reductions for when the delta between the static eval and the child's eval is consistently low.
passed STC
https://tests.stockfishchess.org/html/live_elo.html?614d7b3c7bdc23e77ceb8a5d
LLR: 2.95 (-2.94,2.94) <-0.50,2.50>
Total: 88872 W: 22672 L: 22366 D: 43834
Ptnml(0-2): 343, 10150, 23117, 10510, 316
passed LTC
https://tests.stockfishchess.org/html/live_elo.html?614daf3e7bdc23e77ceb8a82
LLR: 2.93 (-2.94,2.94) <0.50,3.50>
Total: 24368 W: 6153 L: 5928 D: 12287
Ptnml(0-2): 13, 2503, 6937, 2708, 23
closes https://github.com/official-stockfish/Stockfish/pull/3717
Bench: 5443950
2021-09-23 14:16:17 -06:00
|
|
|
Ofek Shochat (OfekShochat, ghostway)
|
2018-09-03 04:46:05 -06:00
|
|
|
Ondrej Mosnáček (WOnder93)
|
2016-01-02 02:43:25 -07:00
|
|
|
Oskar Werkelin Ahlin
|
2014-06-20 19:35:09 -06:00
|
|
|
Pablo Vazquez
|
2020-01-07 13:35:47 -07:00
|
|
|
Panthee
|
2016-01-02 02:43:25 -07:00
|
|
|
Pascal Romaret
|
2018-02-17 17:51:35 -07:00
|
|
|
Pasquale Pigazzini (ppigazzini)
|
|
|
|
Patrick Jansen (mibere)
|
|
|
|
pellanda
|
2018-09-04 05:36:42 -06:00
|
|
|
Peter Zsifkovits (CoffeeOne)
|
Movecount pruning reduction logic
This patch refines search reduction logic in case the position is not a former PV node and is pruned based on move count.
passed STC
https://tests.stockfishchess.org/tests/view/5e8092bde42a5c3b3ca2ed35
LLR: 2.94 (-2.94,2.94) {-0.50,1.50}
Total: 78848 W: 15480 L: 15170 D: 48198
Ptnml(0-2): 1406, 9310, 17773, 9438, 1497
passed LTC
https://tests.stockfishchess.org/tests/view/5e80bb13e42a5c3b3ca2ed4b
LLR: 2.94 (-2.94,2.94) {0.25,1.75}
Total: 86596 W: 11451 L: 11033 D: 64112
Ptnml(0-2): 624, 7993, 25687, 8329, 665
closes https://github.com/official-stockfish/Stockfish/pull/2605
Bench: 5138771
2020-03-29 22:52:42 -06:00
|
|
|
Praveen Kumar Tummala (praveentml)
|
Remove set statScore to zero
Simplification. Removes setting statScore to zero if negative.
STC:
LLR: 2.95 (-2.94,2.94) {-1.50,0.50}
Total: 84820 W: 16100 L: 16033 D: 52687
Ptnml(0-2): 1442, 9865, 19723, 9944, 1436
https://tests.stockfishchess.org/tests/view/5e654fdae42a5c3b3ca2e2f8
LTC:
LLR: 2.94 (-2.94,2.94) {-1.50,0.50}
Total: 57658 W: 7435 L: 7391 D: 42832
Ptnml(0-2): 441, 5397, 17104, 5451, 436
https://tests.stockfishchess.org/tests/view/5e657ce9e42a5c3b3ca2e307
closes https://github.com/official-stockfish/Stockfish/pull/2578
Bench: 5168890
2020-03-08 13:52:05 -06:00
|
|
|
Rahul Dsilva (silversolver1)
|
2018-02-17 17:51:35 -07:00
|
|
|
Ralph Stößer (Ralph Stoesser)
|
2014-06-20 19:35:09 -06:00
|
|
|
Raminder Singh
|
2018-02-17 17:51:35 -07:00
|
|
|
renouve
|
|
|
|
Reuven Peleg
|
2014-06-20 19:35:09 -06:00
|
|
|
Richard Lloyd
|
2018-02-17 17:51:35 -07:00
|
|
|
Rodrigo Exterckötter Tjäder
|
2018-09-03 04:46:05 -06:00
|
|
|
Ron Britvich (Britvich)
|
2020-01-07 13:35:47 -07:00
|
|
|
Ronald de Man (syzygy1, syzygy)
|
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
|
|
|
rqs
|
2018-02-17 17:51:35 -07:00
|
|
|
Ryan Schmitt
|
2014-06-20 19:35:09 -06:00
|
|
|
Ryan Takker
|
2020-01-07 13:35:47 -07:00
|
|
|
Sami Kiminki (skiminki)
|
2018-11-29 07:15:43 -07:00
|
|
|
Sebastian Buchwald (UniQP)
|
2018-02-17 17:51:35 -07:00
|
|
|
Sergei Antonov (saproj)
|
2020-01-07 13:35:47 -07:00
|
|
|
Sergei Ivanov (svivanov72)
|
Update default net to nn-9931db908a9b.nnue
Net created at 20200806-1802
passed STC:
https://tests.stockfishchess.org/tests/view/5f2d00b461e3b6af64881f21
LLR: 2.94 (-2.94,2.94) {-0.50,1.50}
Total: 6672 W: 1052 L: 898 D: 4722
Ptnml(0-2): 63, 600, 1868, 730, 75
passed LTC:
https://tests.stockfishchess.org/tests/view/5f2d052a61e3b6af64881f29
LLR: 2.96 (-2.94,2.94) {0.25,1.75}
Total: 7576 W: 573 L: 463 D: 6540
Ptnml(0-2): 8, 392, 2889, 480, 19
closes https://github.com/official-stockfish/Stockfish/pull/2923
Bench: 4390086
2020-08-07 01:15:04 -06:00
|
|
|
Sergio Vieri (sergiovieri)
|
2016-01-02 02:43:25 -07:00
|
|
|
sf-x
|
2020-01-07 13:35:47 -07:00
|
|
|
Shane Booth (shane31)
|
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
|
|
|
Shawn Varghese (xXH4CKST3RXx)
|
Change advanced pawn push threshold
A pawn push is now considered to be "advanced" if the relative destination
rank is > 6 (previously it was > 5). This affects the search heuristic.
Also remove an assert concerning en passant moves in qsearch().
STC:
LLR: 2.97 (-2.94,2.94) {-0.25,1.25}
Total: 46744 W: 4224 L: 4040 D: 38480
Ptnml(0-2): 165, 3206, 16451, 3380, 170
https://tests.stockfishchess.org/tests/view/604746082433018de7a3872e
LTC:
LLR: 2.94 (-2.94,2.94) {0.25,1.25}
Total: 107840 W: 4198 L: 3892 D: 99750
Ptnml(0-2): 58, 3472, 46557, 3772, 61
https://tests.stockfishchess.org/tests/view/60475eae2433018de7a38737
Closes https://github.com/official-stockfish/Stockfish/pull/3389
Bench: 4796780
2021-03-08 11:46:41 -07:00
|
|
|
Siad Daboul (Topologist)
|
2018-02-17 17:51:35 -07:00
|
|
|
Stefan Geschwentner (locutus2)
|
|
|
|
Stefano Cardanobile (Stefano80)
|
2020-01-07 13:35:47 -07:00
|
|
|
Steinar Gunderson (sesse)
|
2018-02-17 17:51:35 -07:00
|
|
|
Stéphane Nicolet (snicolet)
|
2021-05-12 12:15:21 -06:00
|
|
|
Prokop Randáček (ProkopRandacek)
|
2018-02-17 17:51:35 -07:00
|
|
|
Thanar2
|
2014-06-20 19:35:09 -06:00
|
|
|
thaspel
|
2020-01-07 13:35:47 -07:00
|
|
|
theo77186
|
|
|
|
Tom Truscott
|
2018-02-17 17:51:35 -07:00
|
|
|
Tom Vijlbrief (tomtor)
|
2020-05-12 13:41:55 -06:00
|
|
|
Tomasz Sobczyk (Sopel97)
|
2020-01-07 13:35:47 -07:00
|
|
|
Torsten Franz (torfranz, tfranzer)
|
Update default net to nn-ac5605a608d6.nnue
This net was created with the nnue-pytorch trainer, it used the previous master net as a starting point.
The training data includes all T60 data (https://drive.google.com/drive/folders/1rzZkgIgw7G5vQMLr2hZNiUXOp7z80613), all T74 data (https://drive.google.com/drive/folders/1aFUv3Ih3-A8Vxw9064Kw_FU4sNhMHZU-) and the wrongNNUE_02_d9.binpack (https://drive.google.com/file/d/1seGNOqcVdvK_vPNq98j-zV3XPE5zWAeq). The Leela data were randomly named and then concatenated. All data was merged into one binpack using interleave_binpacks.py.
python3 train.py \
../data/t60_t74_wrong.binpack \
../data/t60_t74_wrong.binpack \
--resume-from-model ../data/nn-e8321e467bf6.pt \
--gpus 1 \
--threads 4 \
--num-workers 1 \
--batch-size 16384 \
--progress_bar_refresh_rate 300 \
--random-fen-skipping 3 \
--features=HalfKAv2_hm^ \
--lambda=1.0 \
--max_epochs=600 \
--seed $RANDOM \
--default_root_dir ../output/exp_24
STC:
LLR: 2.95 (-2.94,2.94) <-0.50,2.50>
Total: 15320 W: 1415 L: 1257 D: 12648
Ptnml(0-2): 50, 1002, 5402, 1152, 54
https://tests.stockfishchess.org/tests/view/611c404a4977aa1525c9c97f
LTC:
LLR: 2.94 (-2.94,2.94) <0.50,3.50>
Total: 9440 W: 345 L: 248 D: 8847
Ptnml(0-2): 3, 222, 4175, 315, 5
https://tests.stockfishchess.org/tests/view/611c6c7d4977aa1525c9c996
LTC with UHO_XXL_+0.90_+1.19.epd:
LLR: 2.94 (-2.94,2.94) <0.50,3.50>
Total: 6232 W: 1638 L: 1459 D: 3135
Ptnml(0-2): 5, 592, 1744, 769, 6
https://tests.stockfishchess.org/tests/view/611c9b214977aa1525c9c9cb
closes https://github.com/official-stockfish/Stockfish/pull/3664
Bench: 5375286
2021-08-18 01:12:14 -06:00
|
|
|
Torsten Hellwig (Torom)
|
2020-01-07 13:35:47 -07:00
|
|
|
Tracey Emery (basepr1me)
|
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
|
|
|
tttak
|
2020-06-23 09:56:38 -06:00
|
|
|
Unai Corzo (unaiic)
|
2018-02-17 17:51:35 -07:00
|
|
|
Uri Blass (uriblass)
|
2020-01-07 13:35:47 -07:00
|
|
|
Vince Negri (cuddlestmonkey)
|
2021-10-10 06:03:51 -06:00
|
|
|
xefoci7612
|
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
|
|
|
zz4032
|
2019-09-22 08:56:36 -06:00
|
|
|
|
Smarter time management near stop limit
This patch makes Stockfish search same depth again if > 60% of optimum time is
already used, instead of trying the next iteration. The idea is that the next
iteration will generally take about the same amount of time as has already been
used in total. When we are likely to begin the last iteration, as judged by total
time taken so far > 0.6 * optimum time, searching the last depth again instead of
increasing the depth still helps the other threads in lazy SMP and prepares better
move ordering for the next moves.
STC :
LLR: 2.95 (-2.94,2.94) {-1.00,3.00}
Total: 13436 W: 2695 L: 2558 D: 8183
Ptnml(0-2): 222, 1538, 3087, 1611, 253
https://tests.stockfishchess.org/tests/view/5e1618a761fe5f83a67dd964
LTC :
LLR: 2.94 (-2.94,2.94) {0.00,2.00}
Total: 32160 W: 4261 L: 4047 D: 23852
Ptnml(0-2): 211, 2988, 9448, 3135, 247
https://tests.stockfishchess.org/tests/view/5e162ca061fe5f83a67dd96d
The code was revised as suggested by @vondele for multithreading:
STC (8 threads):
LLR: 2.95 (-2.94,2.94) {0.00,2.00}
Total: 16640 W: 2049 L: 1885 D: 12706
Ptnml(0-2): 119, 1369, 5158, 1557, 108
https://tests.stockfishchess.org/tests/view/5e19826a2cc590e03c3c2f52
LTC (8 threads):
LLR: 2.95 (-2.94,2.94) {-1.00,3.00}
Total: 16536 W: 2758 L: 2629 D: 11149
Ptnml(0-2): 182, 1758, 4296, 1802, 224
https://tests.stockfishchess.org/tests/view/5e18b91a27dab692fcf9a140
Thanks to those discussing Stockfish lazy SMP on fishcooking which made me
try this, and to @vondele for suggestions and doing related tests.
See full discussion in the pull request thread:
https://github.com/official-stockfish/Stockfish/pull/2482
Bench: 4586187
2020-01-11 15:10:22 -07:00
|
|
|
|
Tweak futility pruning constants
Based on recent improvement of futility pruning by @locutus2 : we lower
the futility margin to apply it for more nodes but as a compensation
we also lower the history threshold to apply it to less nodes. Further
work in tweaking constants can always be done - numbers are guessed
"by hand" and are not results of some tuning, maybe there is some more
Elo to squeeze from this part of code.
Passed STC
LLR: 2.98 (-2.94,2.94) {-1.00,3.00}
Total: 15300 W: 3081 L: 2936 D: 9283
Ptnml(0-2): 260, 1816, 3382, 1900, 290
http://tests.stockfishchess.org/tests/view/5e18da3b27dab692fcf9a158
Passed LTC
LLR: 2.94 (-2.94,2.94) {0.00,2.00}
Total: 108670 W: 14509 L: 14070 D: 80091
Ptnml(0-2): 813, 10259, 31736, 10665, 831
http://tests.stockfishchess.org/tests/view/5e18fc9627dab692fcf9a180
Bench: 4643972
2020-01-12 16:59:06 -07:00
|
|
|
# Additionally, we acknowledge the authors and maintainers of fishtest,
|
Smarter time management near stop limit
This patch makes Stockfish search same depth again if > 60% of optimum time is
already used, instead of trying the next iteration. The idea is that the next
iteration will generally take about the same amount of time as has already been
used in total. When we are likely to begin the last iteration, as judged by total
time taken so far > 0.6 * optimum time, searching the last depth again instead of
increasing the depth still helps the other threads in lazy SMP and prepares better
move ordering for the next moves.
STC :
LLR: 2.95 (-2.94,2.94) {-1.00,3.00}
Total: 13436 W: 2695 L: 2558 D: 8183
Ptnml(0-2): 222, 1538, 3087, 1611, 253
https://tests.stockfishchess.org/tests/view/5e1618a761fe5f83a67dd964
LTC :
LLR: 2.94 (-2.94,2.94) {0.00,2.00}
Total: 32160 W: 4261 L: 4047 D: 23852
Ptnml(0-2): 211, 2988, 9448, 3135, 247
https://tests.stockfishchess.org/tests/view/5e162ca061fe5f83a67dd96d
The code was revised as suggested by @vondele for multithreading:
STC (8 threads):
LLR: 2.95 (-2.94,2.94) {0.00,2.00}
Total: 16640 W: 2049 L: 1885 D: 12706
Ptnml(0-2): 119, 1369, 5158, 1557, 108
https://tests.stockfishchess.org/tests/view/5e19826a2cc590e03c3c2f52
LTC (8 threads):
LLR: 2.95 (-2.94,2.94) {-1.00,3.00}
Total: 16536 W: 2758 L: 2629 D: 11149
Ptnml(0-2): 182, 1758, 4296, 1802, 224
https://tests.stockfishchess.org/tests/view/5e18b91a27dab692fcf9a140
Thanks to those discussing Stockfish lazy SMP on fishcooking which made me
try this, and to @vondele for suggestions and doing related tests.
See full discussion in the pull request thread:
https://github.com/official-stockfish/Stockfish/pull/2482
Bench: 4586187
2020-01-11 15:10:22 -07:00
|
|
|
# an amazing and essential framework for the development of Stockfish!
|
|
|
|
#
|
2019-09-22 08:56:36 -06:00
|
|
|
# https://github.com/glinscott/fishtest/blob/master/AUTHORS
|