Nnue1 #318
Open
Nnue1 #318
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
LTO with static linking is still only working with the latest versions of gcc, causing problems for some devs. on a modern mingw toolchain LTO optimizations can still be enabled as: ``` CXXFLAGS='-flto' make -j ARCH=x86-64-modern COMP=mingw profile-build ``` fixes official-stockfish/Stockfish#2769 closes official-stockfish/Stockfish#2774 No functional change.
This fixes an old issue where we want to make a position unique but only change a small number of bits in the key instead of all 64 of them randomly. This is fragile and can lead to non uniqueness issues in the TT. Key make_key(uint64_t seed) takes any integer and produces a unique random 64 bit key. It is computationally efficient and is based on a congruential pseudo random number generator using well tested constants by Donald Knuth (see https://en.wikipedia.org/wiki/Linear_congruential_generator) STC https://tests.stockfishchess.org/tests/view/5ef6c78f761b685b4c724bb6 LLR: 2.95 (-2.94,2.94) {-1.50,0.50} Total: 154320 W: 29343 L: 29376 D: 95601 Ptnml(0-2): 2543, 18170, 35891, 17889, 2667 LTC https://tests.stockfishchess.org/tests/view/5ef7d1a9020eec13834a940e LLR: 2.95 (-2.94,2.94) {-1.50,0.50} Total: 53488 W: 6629 L: 6584 D: 40275 Ptnml(0-2): 372, 4878, 16183, 4955, 356 closes official-stockfish/Stockfish#2773 bench: 4626776
Removes an 8 year old micro optimization aimed at 32-bit architectures because back then doing an xor of a Key could not be done in one instruction. See original commit here 821e1c7 STC https://tests.stockfishchess.org/tests/view/5ef5833dde213bf647527d0c LLR: 2.94 (-2.94,2.94) {-1.50,0.50} Total: 162648 W: 31053 L: 31097 D: 100498 Ptnml(0-2): 2841, 18966, 37715, 19000, 2802 LTC https://tests.stockfishchess.org/tests/view/5ef7b1bbf993893290cc1489 LLR: 2.93 (-2.94,2.94) {-1.50,0.50} Total: 62360 W: 7617 L: 7586 D: 47157 Ptnml(0-2): 423, 5662, 18994, 5663, 438 closes official-stockfish/Stockfish#2775 bench: 4591425
This patch increases the endgame value of pawns on the fifth rank.
The increase is very small (+1 evaluation point, about 0.005 pawn)
for the pawns on external columns (a-b-c-f-g-h) and a bit bigger
(+7 evaluation points, about 0.033 pawn) for the pawns on d5/e5.
STC:
LLR: 2.93 (-2.94,2.94) {-0.50,1.50}
Total: 79864 W: 15331 L: 15027 D: 49506
Ptnml(0-2): 1336, 9284, 18433, 9498, 1381
https://tests.stockfishchess.org/tests/view/5ef73e2ef993893290cc0c47
LTC:
LLR: 2.94 (-2.94,2.94) {0.25,1.75}
Total: 47240 W: 5927 L: 5630 D: 35683
Ptnml(0-2): 320, 4133, 14440, 4384, 343
https://tests.stockfishchess.org/tests/view/5ef7c0c4f993893290cc14b7
closes official-stockfish/Stockfish#2776
Bench: 4794633
STC:
LLR: 2.96 (-2.94,2.94) {-0.50,1.50}
Total: 82136 W: 15694 L: 15407 D: 51035
Ptnml(0-2): 1076, 8960, 20767, 9131, 1134
https://tests.stockfishchess.org/tests/view/5ef86cf8020eec13834a94dd
LTC:
LLR: 2.93 (-2.94,2.94) {0.25,1.75}
Total: 70200 W: 8787 L: 8440 D: 52973
Ptnml(0-2): 325, 5983, 22170, 6264, 358
https://tests.stockfishchess.org/tests/view/5ef88225020eec13834a950a
closes official-stockfish/Stockfish#2780
Bench: 4478869
We lower the endgame value of the evaluation when we detect that there
is only one queen left on the board (more precisely, we use a scale
factor of 37/64, or about 0.58, for the endgame part of the evaluation).
Hopefully this helps a little bit for the assessment of positions with
queen imbalance, which are one of the well-known Stockfish weaknesses.
STC:
LLR: 2.94 (-2.94,2.94) {-0.50,1.50}
Total: 21600 W: 4176 L: 3955 D: 13469
Ptnml(0-2): 351, 2457, 5003, 2598, 391
https://tests.stockfishchess.org/tests/view/5ef871b6020eec13834a94e8
LTC:
LLR: 2.97 (-2.94,2.94) {0.25,1.75}
Total: 248328 W: 30596 L: 29720 D: 188012
Ptnml(0-2): 1544, 22345, 75665, 22911, 1699
https://tests.stockfishchess.org/tests/view/5ef87aec020eec13834a94fe
Closes official-stockfish/Stockfish#2781
Bench: 4441323
Increase scaling factor for each minor of the opponent side of the queen.
STC:
LLR: 2.94 (-2.94,2.94) {-0.50,1.50}
Total: 14528 W: 2860 L: 2653 D: 9015
Ptnml(0-2): 217, 1632, 3408, 1741, 266
https://tests.stockfishchess.org/tests/view/5ef98384020eec13834a96a0
LTC:
LLR: 2.95 (-2.94,2.94) {0.25,1.75}
Total: 34584 W: 4371 L: 4111 D: 26102
Ptnml(0-2): 205, 3080, 10501, 3262, 244
https://tests.stockfishchess.org/tests/view/5ef99972020eec13834a96c9
closes official-stockfish/Stockfish#2782
Bench: 4523573
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 official-stockfish/Stockfish#2778 No functional change
for safe checks, outposts and king protectors in evaluate.cpp Tested for non regression on the safe checks https://tests.stockfishchess.org/tests/view/5ef8b75c020eec13834a9596 LLR: 2.95 (-2.94,2.94) {-1.50,0.50} Total: 22256 W: 4283 L: 4143 D: 13830 Ptnml(0-2): 291, 2439, 5588, 2459, 351 Tested for non regression on the safe checks, outposts and king protectors https://tests.stockfishchess.org/tests/view/5ef8e543020eec13834a95e7 LLR: 2.95 (-2.94,2.94) {-1.50,0.50} Total: 28400 W: 5382 L: 5253 D: 17765 Ptnml(0-2): 394, 3078, 7119, 3223, 386 closes official-stockfish/Stockfish#2785 No functional change
UCI_ShowWDL might not be shown by GUIs that don't know the option, but crash on the WDL output, effectively making it hard for users to turn it off and run the engine. This sets it by default to false. fixes official-stockfish/Stockfish#2787 closes official-stockfish/Stockfish#2788 No functional change.
This will help scale down relatively high eval in drawish rook endgames with passed pawn like in TCEC S18 Superfinal Game 90.
Passed STC
LLR: 2.94 (-2.94,2.94) {-1.50,0.50}
Total: 50456 W: 9644 L: 9540 D: 31272
Ptnml(0-2): 760, 5637, 12332, 5737, 762
https://tests.stockfishchess.org/tests/view/5efcb76e59f6f035328940ed
Passed LTC
LLR: 2.94 (-2.94,2.94) {-1.50,0.50}
Total: 77264 W: 9518 L: 9518 D: 58228
Ptnml(0-2): 402, 6766, 24321, 6716, 427
https://tests.stockfishchess.org/tests/view/5efd2ad759f6f03532894143
closes official-stockfish/Stockfish#2792
Bench: 4431626
a non-functional code style change that denormalizes the KRKP endgame, making it somewhat easier to read. closes official-stockfish/Stockfish#2786 No functional change
Fix for overevaluated blocked pawns on the 5th and 6th rank.
This is a rewrite of the original idea that uses only two parameters.
Thanks to rocky640 for pointing this out.
STC:
LLR: 2.94 (-2.94,2.94) {-0.50,1.50}
Total: 50800 W: 9707 L: 9446 D: 31647
Ptnml(0-2): 831, 5851, 11822, 6018, 878
https://tests.stockfishchess.org/tests/view/5f00b4f359f6f03532894304
LTC:
LLR: 2.93 (-2.94,2.94) {0.25,1.75}
Total: 52064 W: 6477 L: 6167 D: 39420
Ptnml(0-2): 331, 4628, 15834, 4878, 361
https://tests.stockfishchess.org/tests/view/5f0115fe59f6f03532894345
closes official-stockfish/Stockfish#2794
Bench: 4882833
the goal of this PR is to better document how we process the ep square (if any) given position fen command, and to output more meaningful (and consistent) debug fen on the "d" command. The implementation follows https://en.wikipedia.org/wiki/X-FEN#Encoding_en-passant following x-fen, it is "valid" to record ep even if ep would put king en prise. fixes #2784 closes official-stockfish/Stockfish#2797 No functional change
There is no need to score blocked pawns at many places. The idea originated from: Rocky Tuning and testing by: Fauzi Passed STC: https://tests.stockfishchess.org/tests/view/5f04f8fd59f6f035328945d4 LLR: 2.94 (-2.94,2.94) {-1.50,0.50} Total: 6352 W: 1299 L: 1118 D: 3935 Ptnml(0-2): 89, 695, 1469, 792, 131 Passed LTC: https://tests.stockfishchess.org/tests/view/5f0527bd59f6f035328945e3 LLR: 2.94 (-2.94,2.94) {-1.50,0.50} Total: 27648 W: 3517 L: 3433 D: 20698 Ptnml(0-2): 177, 2561, 8301, 2571, 214 closes official-stockfish/Stockfish#2799 Bench: 4734746
Remove special case handling of QUIET_CHECKS in make_promotions() STC https://tests.stockfishchess.org/tests/view/5f055dbb59f6f035328945fb LLR: 2.98 (-2.94,2.94) {-1.50,0.50} Total: 42808 W: 8177 L: 8054 D: 26577 Ptnml(0-2): 665, 4890, 10201, 4953, 695 LTC https://tests.stockfishchess.org/tests/view/5f06231a59f6f03532894661 LLR: 2.96 (-2.94,2.94) {-1.50,0.50} Total: 9616 W: 1214 L: 1111 D: 7291 Ptnml(0-2): 53, 821, 2965, 908, 61 closes official-stockfish/Stockfish#2800 Bench: 4576410
closes official-stockfish/Stockfish#2772 No functional change
Probcut is a heuristic that wasn't changed a lot in past years, all attempts to change it using information / writing info to transposition table failed. This patch has a number of differences that can be summarized as follows: * For TT write/read we use depth - 3. Because probcut search is depth - 4 but we actually do the move prior to it so effectively we do depth - 3 search; * In any case of depth of eval from transposition table being >= depth - 3 we either produce cutoff or refuse to even do probcut search, this is allowing us to write info of probcut to transposition table because we know that we wouldn't be overwriting some deeper data with our depth - 3 search - this is an important aspect of this patch; * For some not really known reason this patch completely ignores tte->bound() - which was the case for previous patch that made probcut interact with TT, maybe 2) is the reason, although it's unproven. A first version of this patch passed STC and LTC passed STC https://tests.stockfishchess.org/tests/view/5f05908a59f6f03532894613 LLR: 2.95 (-2.94,2.94) {-0.50,1.50} Total: 95776 W: 18300 L: 17973 D: 59503 Ptnml(0-2): 1646, 10944, 22377, 11279, 1642 passed LTC https://tests.stockfishchess.org/tests/view/5f06b54059f6f035328946bb LLR: 2.94 (-2.94,2.94) {0.25,1.75} Total: 57128 W: 7266 L: 6938 D: 42924 Ptnml(0-2): 372, 5163, 17217, 5389, 423 However, an additional bugfix was needed to avoid checking a condition on ttMove if was not available. This passed non-regression bounds on top of the first version: at STC https://tests.stockfishchess.org/tests/view/5f080e5059f6f03532894766 LLR: 2.94 (-2.94,2.94) {-1.50,0.50} Total: 14096 W: 2800 L: 2628 D: 8668 Ptnml(0-2): 225, 1620, 3238, 1688, 277 at LTC https://tests.stockfishchess.org/tests/view/5f0836a559f6f0353289479c LLR: 2.95 (-2.94,2.94) {-1.50,0.50} Total: 25352 W: 3228 L: 3139 D: 18985 Ptnml(0-2): 175, 2350, 7549, 2415, 187 closes official-stockfish/Stockfish#2804 Bench 4540940
In some French games, Stockfish likes to bring the Knight to a bad outpost spot. This is evident in TCEC S18 Superfinal Game 63, where there is a Knight outpost on the queenside but is actually useless. Stockfish is effectively playing a piece down while holding ground against Leela's break on the kingside. This patch turns the +56 mg bonus for a Knight outpost into a -7 mg penalty if it satisfies the following conditions: * The outpost square is not on the CenterFiles (i.e. not on files C,D,E and F) * The knight is not attacking non pawn enemies. * The side where the outpost is located contains only few enemies, with a particular conditional_more_than_two() implementation Thank you to [email protected] for bringing this to our attention and for providing insights. See https://groups.google.com/forum/?fromgroups=#!topic/fishcooking/dEXNzSIBgZU Reference game: https://tcec-chess.com/#div=sf&game=63&season=18 Passed STC: LLR: 2.93 (-2.94,2.94) {-0.50,1.50} Total: 6960 W: 1454 L: 1247 D: 4259 Ptnml(0-2): 115, 739, 1610, 856, 160 https://tests.stockfishchess.org/tests/view/5f08221059f6f0353289477e Passed LTC: LLR: 2.98 (-2.94,2.94) {0.25,1.75} Total: 21440 W: 2767 L: 2543 D: 16130 Ptnml(0-2): 122, 1904, 6462, 2092, 140 https://tests.stockfishchess.org/tests/view/5f0838ed59f6f035328947a2 various related tests show strong test results, but so far no generalizations or simplifications of conditional_more_than_two() are found. See PR for details. closes official-stockfish/Stockfish#2803 Bench: 4366686
This corrects a functional change in official-stockfish/Stockfish@ddcbacd changing evaluation of KPPvK. Bench remains unchanged at low depth With this patch, 8/8/5k1p/8/7p/7K/8/8 b - - 1 11 is again correctly evaluated as a draw. closes official-stockfish/Stockfish#2807 Bench: 4366686
An extension of the lazy eval idea: when the score is sufficiently large we now skip more granular parts of the eval. Inspired by an original patch by Moez Jellouli https://tests.stockfishchess.org/tests/view/5f03b2a159f6f03532894529 Credit to him! STC https://tests.stockfishchess.org/tests/view/5f0a862c59f6f03532894924 LLR: 2.95 (-2.94,2.94) {-0.50,1.50} Total: 13504 W: 2684 L: 2472 D: 8348 Ptnml(0-2): 229, 1496, 3111, 1666, 250 LTC https://tests.stockfishchess.org/tests/view/5f0ac0e159f6f0353289495b LLR: 2.94 (-2.94,2.94) {0.25,1.75} Total: 31312 W: 3926 L: 3677 D: 23709 Ptnml(0-2): 185, 2773, 9509, 2986, 203 closes official-stockfish/Stockfish#2814 bench: 4541608
This patch allows an engine to write probcut data only in case the probcut search depth is greater than transposition table depth. passed STC https://tests.stockfishchess.org/tests/view/5f0b52e959f6f035328949a6 LLR: 2.97 (-2.94,2.94) {-0.50,1.50} Total: 52544 W: 10145 L: 9880 D: 32519 Ptnml(0-2): 853, 6097, 12121, 6334, 867 passed LTC https://tests.stockfishchess.org/tests/view/5f0bd94c59f6f035328949f3 LLR: 2.93 (-2.94,2.94) {0.25,1.75} Total: 49576 W: 6164 L: 5863 D: 37549 Ptnml(0-2): 297, 4371, 15218, 4538, 364 closes official-stockfish/Stockfish#2815 bench 4578298
This is a functional simplification that removes the conditional_more_than_two() function, which was quite strange and kooky. Note the very minor change to the bench value. See this thread for relevant comments on the passing branch: protonspring/Stockfish@d89730d...ff35b50 STC LLR: 2.95 (-2.94,2.94) {-1.50,0.50} Total: 59760 W: 11411 L: 11311 D: 37038 Ptnml(0-2): 992, 6863, 14044, 7015, 966 https://tests.stockfishchess.org/tests/view/5f179988c09435d870cb9b9a LTC LLR: 2.93 (-2.94,2.94) {-1.50,0.50} Total: 45208 W: 5553 L: 5497 D: 34158 Ptnml(0-2): 315, 4081, 13761, 4127, 320 https://tests.stockfishchess.org/tests/view/5f184847c09435d870cb9bee closes official-stockfish/Stockfish#2826 Bench: 4578290
We simplify away the late irreversible move extension, which
does not seem to be necessary in the current master.
STC
LLR: 2.93 (-2.94,2.94) {-1.50,0.50}
Total: 38584 W: 7464 L: 7342 D: 23778
Ptnml(0-2): 581, 4328, 9365, 4424, 594
https://tests.stockfishchess.org/tests/view/5f1c9669c09435d870cb9de9
LTC
LLR: 2.94 (-2.94,2.94) {-1.50,0.50}
Total: 27840 W: 3417 L: 3353 D: 21070
Ptnml(0-2): 120, 2315, 8994, 2363, 128
https://tests.stockfishchess.org/tests/view/5f1d2e22c09435d870cb9e21
closes official-stockfish/Stockfish#2836
bench: 4829420
We double the bonus for potential threats by minors and rooks against
our queen, in case of "queen vs pieces imbalance". Hopefully this will
improve a little bit the evaluation for this well-known Stockfish weakness.
passed STC:
LLR: 2.93 (-2.94,2.94) {-0.50,1.50}
Total: 72976 W: 14003 L: 13710 D: 45263
Ptnml(0-2): 1218, 8370, 17094, 8513, 1293
https://tests.stockfishchess.org/tests/view/5efa50eb020eec13834a977d
passed LTC:
LLR: 2.93 (-2.94,2.94) {0.25,1.75}
Total: 22232 W: 2779 L: 2560 D: 16893
Ptnml(0-2): 129, 1885, 6896, 2050, 156
https://tests.stockfishchess.org/tests/view/5f1fdd2dc09435d870cb9f13
closes official-stockfish/Stockfish#2864
Bench: 4367349
Less reduction for second move at non-check CUT node with depth <= 10.
STC:
LLR: 2.94 (-2.94,2.94) {-0.50,1.50}
Total: 38680 W: 7490 L: 7245 D: 23945
Ptnml(0-2): 643, 4441, 8967, 4606, 683
https://tests.stockfishchess.org/tests/view/5f21e1782f7e63962b99f451
LTC:
LLR: 2.95 (-2.94,2.94) {0.25,1.75}
Total: 71976 W: 9003 L: 8636 D: 54337
Ptnml(0-2): 440, 6414, 21972, 6663, 499
https://tests.stockfishchess.org/tests/view/5f2245762f7e63962b99f4bd
closes official-stockfish/Stockfish#2868
Bench: 4746616
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: official-stockfish/Stockfish#2823 official-stockfish/Stockfish#2728 The integration branch will be closed after the merge: official-stockfish/Stockfish#2825 https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip closes official-stockfish/Stockfish#2912 This will be an exciting time for computer chess, looking forward to seeing the evolution of this approach. Bench: 4746616
The idea is to use NNUE only on quite balanced material positions. This bring a big speedup on research since NNUE eval is slower than classical eval for most of the hardwares and specially on unbalanced positions with LazyEval. STC: https://tests.stockfishchess.org/tests/view/5f2c2680b3ebe5cbfee85b61 LLR: 2.95 (-2.94,2.94) {-0.50,1.50} Total: 3168 W: 560 L: 400 D: 2208 Ptnml(0-2): 21, 294, 819, 404, 46 LTC: https://tests.stockfishchess.org/tests/view/5f2c2ca6b3ebe5cbfee85b69 LLR: 2.98 (-2.94,2.94) {0.25,1.75} Total: 3200 W: 287 L: 183 D: 2730 Ptnml(0-2): 4, 149, 1191, 251, 5 closes official-stockfish/Stockfish#2916 Bench 4746616
STC:
LLR: 2.93 (-2.94,2.94) {-0.50,1.50}
Total: 10608 W: 1507 L: 1358 D: 7743
Ptnml(0-2): 94, 945, 3074, 1100, 91
https://tests.stockfishchess.org/tests/view/5f2c5921b3ebe5cbfee85b8b
LTC:
LLR: 2.94 (-2.94,2.94) {0.25,1.75}
Total: 7536 W: 556 L: 448 D: 6532
Ptnml(0-2): 9, 383, 2881, 481, 14
https://tests.stockfishchess.org/tests/view/5f2c6f4461e3b6af64881e95
closes official-stockfish/Stockfish#2919
Bench: 4746616
Passed STC: https://tests.stockfishchess.org/tests/view/5f2aa49fa5abc164f05e4d1b LLR: 2.95 (-2.94,2.94) {-0.50,1.50} Total: 40888 W: 7977 L: 7726 D: 25185 Ptnml(0-2): 665, 4806, 9333, 4893, 747 Passed LTC: https://tests.stockfishchess.org/tests/view/5f2b1059b3ebe5cbfee85ae7 LLR: 2.98 (-2.94,2.94) {0.25,1.75} Total: 51264 W: 6445 L: 6134 D: 38685 Ptnml(0-2): 328, 4564, 15580, 4789, 371 closes official-stockfish/Stockfish#2920 bench: 4314943
Changed name from Bad Outpost to Uncontested Outpost
Scale Uncontested Outpost with number of pawns + Decrease Bishop PSQT values and general tuning
Credits for the decrease of the Bishop PSQT values: Fauzi
Credits for scaling Uncontested Outpost with number of pawns: Lolligerhans
Credits for the tunings: Fauzi
Passed STC:
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 32040 W: 6593 L: 6281 D: 19166
Ptnml(0-2): 596, 3713, 7095, 4015, 601
https://tests.stockfishchess.org/tests/view/5ffa43026019e097de3ef0f2
Passed LTC:
LLR: 2.95 (-2.94,2.94) {0.25,1.25}
Total: 84376 W: 11395 L: 10950 D: 62031
Ptnml(0-2): 652, 7930, 24623, 8287, 696
https://tests.stockfishchess.org/tests/view/5ffa6e7b6019e097de3ef0fd
closes official-stockfish/Stockfish#3296
Bench: 4287509
This change simplifies control flow in the generate_moves function which ensures the compiler doesn't duplicate work due to possibly not resolving pureness of the function calls. Also the biggest change is the removal of the unnecessary condition checking for empty b in a convoluted way. The rationale for removal of this condition is that computing attacks_bb with occupancy is not much more costly than computing pseudo attacks and overall the condition (also being likely unpredictable) is a pessimisation. This is inspired by previous changes by @BM123499. Passed STC: LLR: 2.94 (-2.94,2.94) {-0.25,1.25} Total: 88040 W: 8172 L: 7931 D: 71937 Ptnml(0-2): 285, 6128, 30957, 6361, 289 https://tests.stockfishchess.org/tests/view/5ffc28386019e097de3ef1c7 closes official-stockfish/Stockfish#3300 No functional change.
Give an additional penalty of S(20, 10) for any doubled pawn if none of
the opponent's pawns is facing any of our
- pawns or
- pawn attacks;
that means, each of their pawns can push at least one square without
being captured.
This ignores their non-pawns pieces and attacks.
One possible justification: Their pawns' ability to push freely provides
options to react to our threats by changing their pawn structure. Our
doubled pawns however will likely lead to an exploitable weakness, even
if the pawn structure is not yet fixed.
Note that the notion of "their pawns not being fixed" is symmetric for
both players: If all of their pawns can push freely so can ours. All
pawns being freely pushable might just be an early-game-indicator.
However, it can trigger during endgame pawns races, where doubled pawns
are especially hindering, too.
LTC
LLR: 2.94 (-2.94,2.94) {0.25,1.25}
Total: 134976 W: 17964 L: 17415 D: 99597
Ptnml(0-2): 998, 12702, 39619, 13091, 1078
https://tests.stockfishchess.org/tests/view/5ffdd5316019e097de3ef281
STC
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 35640 W: 7219 L: 6904 D: 21517
Ptnml(0-2): 645, 4096, 8084, 4289, 706
https://tests.stockfishchess.org/tests/view/5ffda4a16019e097de3ef265
closes official-stockfish/Stockfish#3302
Bench: 4363873
No additional features of std::unique_lock has been previously used so it's better to use a lighter lock. closes official-stockfish/Stockfish#3284 No functional change.
add files produced during the build to a newly added .gitignore closes official-stockfish/Stockfish#3286 No functional change
This patch give a small bonus to incite the attacking side to keep more
pawns on the board.
A consequence of this bonus is that Stockfish will tend to play positions
slightly more closed on average than master, especially when it believes
that it has an advantage.
To lower the risk of blockades where Stockfish start shuffling without
progress, we also implement a progressive decrease of the evaluation
value with the 50 moves counter (along with the necessary aging of the
transposition table to reduce the impact of the Graph History Interaction
problem): since the evaluation decreases during shuffling phases, the
engine will tend to examine the consequences of pawn breaks faster during
the search.
Passed STC:
LLR: 2.96 (-2.94,2.94) {-0.25,1.25}
Total: 26184 W: 2406 L: 2252 D: 21526
Ptnml(0-2): 85, 1784, 9223, 1892, 108
https://tests.stockfishchess.org/tests/view/600cc08b735dd7f0f0352c06
Passed LCT:
LLR: 2.95 (-2.94,2.94) {0.25,1.25}
Total: 199768 W: 7695 L: 7191 D: 184882
Ptnml(0-2): 85, 6478, 86269, 6952, 100
https://tests.stockfishchess.org/tests/view/600ccd28735dd7f0f0352c10
Closes official-stockfish/Stockfish#3321
Bench: 3988915
closes official-stockfish/Stockfish#3301 No functional change
speedup of the code, enough to pass STC, failed LTC.
Passed STC:
LLR: 2.93 (-2.94,2.94) {-0.25,1.25}
Total: 68928 W: 6334 L: 6122 D: 56472
Ptnml(0-2): 233, 4701, 24369, 4943, 218
https://tests.stockfishchess.org/tests/view/6002747f6019e097de3ef8dc
Failed LTC:
LLR: -2.96 (-2.94,2.94) {0.25,1.25}
Total: 44560 W: 1702 L: 1675 D: 41183
Ptnml(0-2): 25, 1383, 19438, 1408, 26
https://tests.stockfishchess.org/tests/view/6002a4836019e097de3ef8e3
About 1% speedup:
Result of 50 runs
==================
base (...kfish.master) = 2237500 +/- 7428
test (...ckfish.patch) = 2267003 +/- 7017
diff = +29503 +/- 4774
speedup = +0.0132
P(speedup > 0) = 1.0000
closes official-stockfish/Stockfish#3304
No functional change.
There is no need to add rto or kto on the Bitboard which represents the pieces.
STC:
LLR: 2.93 (-2.94,2.94) {-1.25,0.25}
Total: 57064 W: 5096 L: 5067 D: 46901
Ptnml(0-2): 202, 3862, 20355, 3931, 182
https://tests.stockfishchess.org/tests/view/6005ea2c6019e097de3efa55
LTC:
LLR: 2.92 (-2.94,2.94) {-0.75,0.25}
Total: 30088 W: 1094 L: 1052 D: 27942
Ptnml(0-2): 10, 882, 13217, 926, 9
https://tests.stockfishchess.org/tests/view/6006115a6019e097de3efa6e
closes official-stockfish/Stockfish#3311
No functional change.
It speeds up generate<LEGAL>, and thus perft, roughly by 2-3%. closes official-stockfish/Stockfish#3312 No functional change
a little cleanup, and small speedup (about 0.3%) for Chess 960. Verified with perft on a large set of chess960 positions. Closes official-stockfish/Stockfish#3317 No functional change
We change the relative weights of the function used to order
quiet moves in our MovePicker class.
Passed STC:
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 32184 W: 2936 L: 2773 D: 26475
Ptnml(0-2): 115, 2196, 11328, 2317, 136
https://tests.stockfishchess.org/tests/view/60161ee1735dd7f0f03530f8
Passed LTC:
LLR: 2.93 (-2.94,2.94) {0.25,1.25}
Total: 33088 W: 1292 L: 1149 D: 30647
Ptnml(0-2): 14, 1030, 14318, 1163, 19
https://tests.stockfishchess.org/tests/view/60163146735dd7f0f03530ff
The new weight were chosen after the following SPSA session:
https://tests.stockfishchess.org/tests/view/60136857735dd7f0f0352f6c
Closes official-stockfish/Stockfish#3331
Bench: 4398803
simplifies the handling of en passant during search, needs a little more care in initialization.
Passed STC:
LLR: 2.95 (-2.94,2.94) {-1.25,0.25}
Total: 72608 W: 6569 L: 6559 D: 59480
Ptnml(0-2): 233, 5117, 25629, 5057, 268
https://tests.stockfishchess.org/tests/view/600f1363735dd7f0f0352ce7
Passed LTC:
LLR: 2.92 (-2.94,2.94) {-0.75,0.25}
Total: 24328 W: 913 L: 864 D: 22551
Ptnml(0-2): 10, 731, 10633, 780, 10
https://tests.stockfishchess.org/tests/view/600f2e93735dd7f0f0352cf6
closes official-stockfish/Stockfish#3330
No functional change.
A simple tuning of Pawns parameters, and some PSQT changes.
Passed STC:
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 219424 W: 43681 L: 43103 D: 132640
Ptnml(0-2): 4014, 25760, 49669, 26172, 4097
https://tests.stockfishchess.org/tests/view/601bce167f517a561bc491eb
Passed LTC:
LLR: 2.94 (-2.94,2.94) {0.25,1.25}
Total: 317312 W: 42525 L: 41579 D: 233208
Ptnml(0-2): 2447, 30157, 92636, 30835, 2581
https://tests.stockfishchess.org/tests/view/601c21557f517a561bc49227
closes official-stockfish/Stockfish#3337
Bench: 4154473
A simple tuning on search.cpp. based SPSA test: https://tests.stockfishchess.org/tests/view/601f2a787f517a561bc493cd passed STC: LLR: 2.94 (-2.94,2.94) {-0.25,1.25} Total: 117840 W: 10796 L: 10508 D: 96536 Ptnml(0-2): 422, 8381, 41041, 8639, 437 https://tests.stockfishchess.org/tests/view/602144c37f517a561bc494ae passed LTC: LLR: 2.96 (-2.94,2.94) {0.25,1.25} Total: 25024 W: 972 L: 847 D: 23205 Ptnml(0-2): 7, 767, 10847, 876, 15 https://tests.stockfishchess.org/tests/view/602156877f517a561bc494be closes official-stockfish/Stockfish#3340 Bench: 3974098
closes official-stockfish/Stockfish#3342 No functional change
Benchmarking with current Clang 12 shows that and ThinLTO is a pessimization, see issue #3341. closes official-stockfish/Stockfish#3345 No functional change.
It's about 1% speedup for Stockfish. Result of 100 runs ================== base (...fish_clang12) = 1946851 +/- 3717 test (./stockfish ) = 1967276 +/- 3408 diff = +20425 +/- 2438 speedup = +0.0105 P(speedup > 0) = 1.0000 Thanks to David Major for making me aware of this part of LLVM development. closes official-stockfish/Stockfish#3346 No functional change
This patch removes some magic numbers in TT bit management and introduce proper constants in the code, to improve documentation and ease further modifications. No function change
Do not decrease reduction at pv-nodes which are likely to fail low. The idea of this patch can be described as following: during the search, if a node on the principal variation was re-searched in non-pv search and this re-search got a value which was much lower than alpha, then we can assume that this pv-node is likely to fail low again, and we can reduce more aggressively at this node. Passed STC https://tests.stockfishchess.org/tests/view/6023a5fa7f517a561bc49638 LLR: 2.95 (-2.94,2.94) {-0.25,1.25} Total: 70288 W: 6443 L: 6223 D: 57622 Ptnml(0-2): 239, 5022, 24436, 5174, 273 Passed LTC https://tests.stockfishchess.org/tests/view/6023f2617f517a561bc49661 LLR: 2.94 (-2.94,2.94) {0.25,1.25} Total: 105656 W: 4048 L: 3748 D: 97860 Ptnml(0-2): 67, 3312, 45761, 3630, 58 Closes official-stockfish/Stockfish#3349 Bench: 3766422
No functional change
Closes official-stockfish/Stockfish#3329 No functional change
• reorder some sections of the README file • add reference to the AUTHORS file • rename Syzygybases to Syzygy tablebases • add pointer to the Discord channel • more precise info about the GPLv3 licence No functional change
Official release version of Stockfish 13 Bench: 3766422 ----- It is our pleasure to release Stockfish 13 to chess fans worldwide. As usual, downloads are freely available at https://stockfishchess.org The Stockfish project builds on a thriving community of enthusiasts who contribute their expertise, time, and resources to build a free and open-source chess engine that is robust, widely available, and very strong. We would like to thank them all! The good news first: from now on, our users can expect more frequent high-quality releases of Stockfish! Sadly, this decision has been triggered by the start of sales of the Fat Fritz 2 engine by ChessBase, which is a copy of a very recent development version of Stockfish with minor modifications. We refer to our statement on Fat Fritz 2[1] and a community blog[2] for further information. This version of Stockfish is significantly stronger than any of its predecessors. Stockfish 13 outperforms Stockfish 12 by at least 35 Elo[3]. When playing against a one-year-old Stockfish, it wins 60 times more game pairs than it loses[4]. This release features an NNUE network retrained on billions of positions, much faster network evaluation code, and significantly improved search heuristics, as well as additional evaluation tweaks. In the course of its development, this version has won the superfinals of the TCEC Season 19 and TCEC Season 20. Going forward, the Leela Chess Zero and Stockfish teams will join forces to demonstrate our commitment to open source chess engines and training tools, and open data. We are convinced that our free and open-source chess engines serve the chess community very well. Stay safe and enjoy chess! The Stockfish team [1] https://blog.stockfishchess.org/post/643239805544792064/statement-on-fat-fritz-2 [2] https://lichess.org/blog/YCvy7xMAACIA8007/fat-fritz-2-is-a-rip-off [3] https://tests.stockfishchess.org/tests/view/602bcccf7f517a561bc49b11 [4] https://tests.stockfishchess.org/tests/view/600fbb9c735dd7f0f0352d59
No functional change
The values used in this patch are taken from a SPSA parameter tuning session originated by Unai Corzo (@unaiic), but the final difference of his tune was multiplied x2 by hand. Most of the credits should go to him :-) STC: https://tests.stockfishchess.org/tests/view/602f03d07f517a561bc49d40 LLR: 2.94 (-2.94,2.94) {-0.25,1.25} Total: 67664 W: 6252 L: 6035 D: 55377 Ptnml(0-2): 256, 4799, 23527, 4972, 278 LTC: https://tests.stockfishchess.org/tests/view/602f41697f517a561bc49d5a LLR: 2.96 (-2.94,2.94) {0.25,1.25} Total: 26256 W: 1034 L: 906 D: 24316 Ptnml(0-2): 10, 804, 11377, 922, 15 Closes official-stockfish/Stockfish#3363 Bench: 3957653
The idea of this patch can be described as follows: if we are in check
and the transposition table move is a capture that returns a value
far above beta, we can assume that the opponent just blundered a piece
by giving check, and we return the transposition table value. This is
similar to the usual probCut logic for quiet moves, but with a different
threshold.
Passed STC
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 33440 W: 3056 L: 2891 D: 27493
Ptnml(0-2): 110, 2338, 11672, 2477, 123
https://tests.stockfishchess.org/tests/view/602cd1087f517a561bc49bda
Passed LTC
LLR: 2.98 (-2.94,2.94) {0.25,1.25}
Total: 10072 W: 401 L: 309 D: 9362
Ptnml(0-2): 2, 288, 4365, 378, 3
https://tests.stockfishchess.org/tests/view/602ceea57f517a561bc49bf0
The committed version has an additional fix to never return unproven wins
in the tablebase range or the mate range. This fix passed tests for non-
regression at STC and LTC:
STC:
LLR: 2.93 (-2.94,2.94) {-1.25,0.25}
Total: 26240 W: 2354 L: 2280 D: 21606
Ptnml(0-2): 85, 1763, 9372, 1793, 107
https://tests.stockfishchess.org/tests/view/602d86a87f517a561bc49c7a
LTC:
LLR: 2.95 (-2.94,2.94) {-0.75,0.25}
Total: 35304 W: 1299 L: 1256 D: 32749
Ptnml(0-2): 14, 1095, 15395, 1130, 18
https://tests.stockfishchess.org/tests/view/602d98d17f517a561bc49c83
Closes official-stockfish/Stockfish#3362
Bench: 3830215
Updated network
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.