| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: lonfom169
Date: Sun Jan 2 17:49:44 2022 +0100 Timestamp: 1641142184 Simplify away rangeReduction Remove rangeReduction, introduced in [#3717](https://github.com/official-stockfish/Stockfish/pull/3717), as it seemingly doesn't bring enough ELO anymore. It might be interesting to add new forms of reduction or tune the reduction formula in the future. STC: LLR: 2.95 (-2.94,2.94) <-2.25,0.25> Total: 45008 W: 12114 L: 11972 D: 20922 Elo +1.10 Ptnml(0-2): 174, 5031, 11952, 5173, 174 https://tests.stockfishchess.org/tests/view/61d08b7b069ca917749c9f6f LTC: LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 30792 W: 8235 L: 8086 D: 14471 Elo +1.68 Ptnml(0-2): 24, 3162, 8882, 3297, 31 https://tests.stockfishchess.org/tests/view/61d0a6ad069ca917749ca420 closes https://github.com/official-stockfish/Stockfish/pull/3878 Bench: 4048312 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: lonfom169
Date: Fri Dec 31 07:44:15 2021 +0100 Timestamp: 1640933055 Smooth out doDeeperSearch Adjust threshold based on the difference between newDepth and LMR depth. With more reduction, bigger fail-high is required in order to perform the deeper search. STC: LLR: 2.96 (-2.94,2.94) <0.00,2.50> Total: 93576 W: 24133 L: 23758 D: 45685 Elo +1.39 Ptnml(0-2): 260, 10493, 24935, 10812, 288 https://tests.stockfishchess.org/tests/view/61cbb5cee68b2a714b6eaf09 LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 109280 W: 28198 L: 27754 D: 53328 Elo +1.41 Ptnml(0-2): 60, 11225, 31637, 11647, 71 https://tests.stockfishchess.org/tests/view/61cc03fee68b2a714b6ec091 closes https://github.com/official-stockfish/Stockfish/pull/3877 Bench: 4464723 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Stéphane Nicolet
Date: Thu Dec 30 11:59:23 2021 +0100 Timestamp: 1640861963 Tweak optimism with complexity This patch increases the optimism bonus for "complex positions", where the complexity is measured as the absolute value of the difference between material and the sophisticated NNUE evaluation (idea by Joost VandeVondele). Also rename some variables in evaluate() while there. passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 88392 W: 23150 L: 22781 D: 42461 Elo +1.45 Ptnml(0-2): 318, 9961, 23257, 10354, 306 https://tests.stockfishchess.org/tests/view/61cbbedee68b2a714b6eb110 passed LTC: LLR: 2.93 (-2.94,2.94) <0.50,3.00> Total: 37848 W: 10043 L: 9766 D: 18039 Elo +2.54 Ptnml(0-2): 26, 3815, 10961, 4100, 22 https://tests.stockfishchess.org/tests/view/61cc0cc3e68b2a714b6ec28c Closes https://github.com/official-stockfish/Stockfish/pull/3875 Follow-up from https://github.com/official-stockfish/Stockfish/commit/a5a89b27c8e3225fb453d603bc4515d32bb351c3 Bench: 4125221 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: bmc4
Date: Mon Dec 27 16:43:44 2021 +0100 Timestamp: 1640619824 Don't direct prune a move if it's a retake STC: LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 36304 W: 9499 L: 9226 D: 17579 Elo +2.61 Ptnml(0-2): 96, 4102, 9508, 4325, 121 https://tests.stockfishchess.org/tests/view/61c7069ae68b2a714b6dca27 LTC: LLR: 2.95 (-2.94,2.94) <0.50,3.00> Total: 93824 W: 24478 L: 24068 D: 45278 Elo +1.52 Ptnml(0-2): 70, 9644, 27082, 10038, 78 https://tests.stockfishchess.org/tests/view/61c725fee68b2a714b6dcfa2 closes https://github.com/official-stockfish/Stockfish/pull/3871 Bench: 4106806 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Joost VandeVondele
Date: Wed Dec 22 11:02:34 2021 +0100 Timestamp: 1640167354 Update default net to nn-ac07bd334b62.nnue Trained with essentially the same data as provided and used by Farseer (mbabigian) for the previous master net. T60T70wIsRightFarseerT60T74T75T76.binpack (99GB): ['T60T70wIsRightFarseer.binpack', 'farseerT74.binpack', 'farseerT75.binpack', 'farseerT76.binpack'] using the trainer branch tweakLR1PR (https://github.com/glinscott/nnue-pytorch/pull/158) and `--gpus 1 --threads 4 --num-workers 4 --batch-size 16384 --progress_bar_refresh_rate 300 --smart-fen-skipping --random-fen-skipping 12 --features=HalfKAv2_hm^ --lambda=1.00` options passed STC: LLR: 2.95 (-2.94,2.94) <0.00,2.50> Total: 108280 W: 28042 L: 27636 D: 52602 Elo +1.30 Ptnml(0-2): 328, 12382, 28401, 12614, 415 https://tests.stockfishchess.org/tests/view/61bcd8c257a0d0f327c34fbd passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 259296 W: 66974 L: 66175 D: 126147 Elo +1.07 Ptnml(0-2): 146, 27096, 74452, 27721, 233 https://tests.stockfishchess.org/tests/view/61bda70957a0d0f327c37817 closes https://github.com/official-stockfish/Stockfish/pull/3870 Bench: 4633875 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Michael Chaly
Date: Wed Dec 22 08:18:35 2021 +0100 Timestamp: 1640157515 Fall back to NNUE if classical evaluation is much lower than threshold The idea is that if classical eval returns a value much lower than the threshold of its usage it most likely means that position isn't that simple so we need the more precise NNUE evaluation. passed STC: https://tests.stockfishchess.org/tests/view/61bf3e7557a0d0f327c3c47a LLR: 2.95 (-2.94,2.94) <0.00,2.50> Total: 108072 W: 28007 L: 27604 D: 52461 Elo +1.30 Ptnml(0-2): 352, 12147, 28650, 12520, 367 passed LTC: https://tests.stockfishchess.org/tests/view/61c0581657a0d0f327c3fa0c LLR: 2.95 (-2.94,2.94) <0.50,3.00> Total: 155096 W: 40392 L: 39841 D: 74863 Elo +1.23 Ptnml(0-2): 88, 15983, 44843, 16558, 76 closes https://github.com/official-stockfish/Stockfish/pull/3869 bench 4310422 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: bmc4
Date: Tue Dec 21 13:47:57 2021 +0100 Timestamp: 1640090877 Update Elo estimates for terms in search This updates estimates from 2yr ago #2401, and adds missing terms. All tests run at 10+0.1 (STC), 20000 games, error bars +- 1.8 Elo, book 8moves_v3.png. A table of Elo values with the links to the corresponding tests can be found at the PR closes https://github.com/official-stockfish/Stockfish/pull/3868 Non-functional Change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: bmc4
Date: Tue Dec 21 13:42:33 2021 +0100 Timestamp: 1640090553 Remove Capture history pruning Fixed number of games. (book: 8moves_v3.png): ELO: -0.69 +-1.8 (95%) LOS: 22.1% Total: 20000 W: 1592 L: 1632 D: 16776 Elo -0.69 Ptnml(0-2): 44, 1194, 7566, 1150, 46 https://tests.stockfishchess.org/tests/view/61bb8eb657a0d0f327c30ce8 STC: LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 139976 W: 36039 L: 36036 D: 67901 Elo +0.01 Ptnml(0-2): 435, 16138, 36885, 16049, 481 https://tests.stockfishchess.org/tests/view/61be731857a0d0f327c39ea2 LTC: LLR: 2.95 (-2.94,2.94) <-2.25,0.25> Total: 70656 W: 18284 L: 18189 D: 34183 Elo +0.47 Ptnml(0-2): 34, 7317, 20529, 7416, 32 https://tests.stockfishchess.org/tests/view/61bf39b657a0d0f327c3c37b closes https://github.com/official-stockfish/Stockfish/pull/3867 bench: 4281737 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: bmc4
Date: Tue Dec 21 13:40:57 2021 +0100 Timestamp: 1640090457 Remove Capture Extension This revert the patch #3692, probably can be simplified after the introduction of #3838. Fixed-game test: ELO: -1.41 +-1.8 (95%) LOS: 5.9% Total: 20000 W: 1552 L: 1633 D: 16815 Elo -1.41 Ptnml(0-2): 38, 1242, 7517, 1169, 34 https://tests.stockfishchess.org/tests/view/61bc1a2057a0d0f327c32a3c STC: LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 44528 W: 11619 L: 11478 D: 21431 Elo +1.10 Ptnml(0-2): 146, 5020, 11771, 5201, 126 https://tests.stockfishchess.org/tests/view/61bc638c57a0d0f327c338fe LTC: LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 34136 W: 8847 L: 8704 D: 16585 Elo +1.46 Ptnml(0-2): 23, 3475, 9925, 3626, 19 https://tests.stockfishchess.org/tests/view/61bcb24257a0d0f327c34813 closes https://github.com/official-stockfish/Stockfish/pull/3863 Bench: 4054695 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Stéphane Nicolet
Date: Sun Dec 19 15:44:01 2021 +0100 Timestamp: 1639925041 Simplification in evaluate_nnue.cpp Removes the test on non-pawn-material before applying the positional/materialistic bonus. Passed STC: LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 46904 W: 12197 L: 12059 D: 22648 Elo +1.02 Ptnml(0-2): 170, 5243, 12479, 5399, 161 https://tests.stockfishchess.org/tests/view/61be57cf57a0d0f327c3999d Passed LTC: LLR: 2.95 (-2.94,2.94) <-2.25,0.25> Total: 18760 W: 4958 L: 4790 D: 9012 Elo +3.11 Ptnml(0-2): 14, 1942, 5301, 2108, 15 https://tests.stockfishchess.org/tests/view/61bed1fb57a0d0f327c3afa9 closes https://github.com/official-stockfish/Stockfish/pull/3866 Bench: 4826206 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: George Sobala
Date: Sun Dec 19 11:43:18 2021 +0100 Timestamp: 1639910598 Fixes build failure on Apple M1 Silicon This pull request selectively avoids `-mdynamic-no-pic` for gcc on Apple Silicon (there was no problem with the default clang compiler). fixes https://github.com/official-stockfish/Stockfish/issues/3847 closes https://github.com/official-stockfish/Stockfish/pull/3850 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Michael Chaly
Date: Sun Dec 19 08:03:41 2021 +0100 Timestamp: 1639897421 Reintroduce futility pruning for captures This is a reintroduction of an idea that was simplified away approximately 1 year ago. There are some tweaks to it : a) exclude promotions; b) exclude Pv Nodes from it - Pv Nodes logic for captures is really different from non Pv nodes so it makes a lot of sense; c) use a big grain of capture history - idea is taken from my recent patches in futility pruning. passed STC https://tests.stockfishchess.org/tests/view/61bd90f857a0d0f327c373b7 LLR: 2.96 (-2.94,2.94) <0.00,2.50> Total: 86640 W: 22474 L: 22110 D: 42056 Elo +1.46 Ptnml(0-2): 268, 9732, 22963, 10082, 275 passed LTC https://tests.stockfishchess.org/tests/view/61be094457a0d0f327c38aa3 LLR: 2.95 (-2.94,2.94) <0.50,3.00> Total: 23240 W: 6079 L: 5838 D: 11323 Elo +3.60 Ptnml(0-2): 14, 2261, 6824, 2512, 9 https://github.com/official-stockfish/Stockfish/pull/3864 bench 4493723 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Michael Chaly
Date: Sat Dec 18 17:19:21 2021 +0100 Timestamp: 1639844361 Adjust reductions based on current node delta and root delta This patch is a follow up of previous 2 patches that introduced more reductions for PV nodes with low delta and more pruning for nodes with low delta. Instead of writing separate heuristics now it adjust reductions based on delta / rootDelta - it allows to remove 3 separate adjustements of pruning/LMR in different places and also makes reduction dependence on delta and rootDelta smoother. Also now it works for all pruning heuristics and not just 2. Passed STC https://tests.stockfishchess.org/tests/view/61ba9b6c57a0d0f327c2d48b LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 79192 W: 20513 L: 20163 D: 38516 Elo +1.54 Ptnml(0-2): 238, 8900, 21024, 9142, 292 passed LTC https://tests.stockfishchess.org/tests/view/61baf77557a0d0f327c2eb8e LLR: 2.96 (-2.94,2.94) <0.50,3.00> Total: 158400 W: 41134 L: 40572 D: 76694 Elo +1.23 Ptnml(0-2): 101, 16372, 45745, 16828, 154 closes https://github.com/official-stockfish/Stockfish/pull/3862 bench 4651538 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: George Sobala
Date: Fri Dec 17 18:52:09 2021 +0100 Timestamp: 1639763529 Fix for profile-build failure using gcc on MacOS Fixes https://github.com/official-stockfish/Stockfish/issues/3846 , where the profiling SF binary generated by GCC on MacOS would launch but failed to quit. Tested with gcc-8, gcc9, gcc10, gcc-11. The problem can be fixed by adding -fvisibility=hidden to the compiler flags, see for example the following piece of Apple documentation: https://developer.apple.com/library/archive/documentation/DeveloperTools/Conceptual/CppRuntimeEnv/Articles/SymbolVisibility.html For instance this now works: make -j8 profile-build ARCH=x86-64-avx2 COMP=gcc COMPCXX=g++-11 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: pb00067
Date: Fri Dec 17 18:37:41 2021 +0100 Timestamp: 1639762661 Remove lowPly history Seems that after pull request #3731 (Capping stat bonus at 2000) this heuristic is no longer useful. STC: https://tests.stockfishchess.org/tests/view/61b8d0e2dffbe89a35815444 LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 30672 W: 7974 L: 7812 D: 14886 Elo +1.84 Ptnml(0-2): 106, 3436, 8072, 3634, 88 LTC: https://tests.stockfishchess.org/tests/view/61b8e90cdffbe89a35815a67 LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 42448 W: 10884 L: 10751 D: 20813 Elo +1.09 Ptnml(0-2): 23, 4394, 12267, 4507, 33 closes https://github.com/official-stockfish/Stockfish/pull/3853 bench: 4474950 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: bmc4
Date: Fri Dec 17 18:22:48 2021 +0100 Timestamp: 1639761768 Simplify away singularQuietLMR While at it, we also update the Elo estimate of reduction at non-PV nodes (source: https://tests.stockfishchess.org/tests/view/61acf97156fcf33bce7d6303 ) STC: LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 243632 W: 62874 L: 63022 D: 117736 Elo -0.21 Ptnml(0-2): 810, 28024, 64249, 27970, 763 https://tests.stockfishchess.org/tests/view/61b8b1b7dffbe89a35814c0d LTC: LLR: 2.93 (-2.94,2.94) <-2.25,0.25> Total: 91392 W: 23520 L: 23453 D: 44419 Elo +0.25 Ptnml(0-2): 51, 9568, 26387, 9643, 47 https://tests.stockfishchess.org/tests/view/61b97316dffbe89a35817da7 closes https://github.com/official-stockfish/Stockfish/pull/3854 bench: 4217785 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: farseer
Date: Fri Dec 17 18:12:47 2021 +0100 Timestamp: 1639761167 Update default net to nn-4401e826ebcc.nnue Using data T60 12/1/20 to 11/2/2021, T74 4/22/21 to 7/27/21, T75 6/3/21 to 10/16/21, T76 (half of the randomly interleaved dataset due to a mistake merging) 11/10/21 to 11/21/21, wrongIsRight_nodes5000pv2.binpack, and WrongIsRight-Reloaded.binpack combined and shuffled position by position. Trained with LR=4.375e-4 and WDL filtering enabled: python train.py --smart-fen-skipping --random-fen-skipping 0 --features=HalfKAv2_hm^ --lambda=1.0 --max_epochs=800 --seed 910688689 --batch-size 16384 --progress_bar_refresh_rate 30 --threads 4 --num-workers 4 --gpus 1 --resume-from-model C:\msys64\home\Mike\nnue-pytorch\9b3d.pt E:\trainingdata\T60-T74-T75-T76-WiR-WiRR-PbyP.binpack E:\trainingdata\T60-T74-T75-T76-WiR-WiRR-PbyP.binpack Passed STC LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 41848 W: 10962 L: 10676 D: 20210 Elo +2.37 Ptnml(0-2): 142, 4699, 11016, 4865, 202 https://tests.stockfishchess.org/tests/view/61ba886857a0d0f327c2cfd6 Passed LTC LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 27776 W: 7208 L: 6953 D: 13615 Elo +3.19 Ptnml(0-2): 14, 2808, 8007, 3027, 32 https://tests.stockfishchess.org/tests/view/61baae4d57a0d0f327c2d96f closes https://github.com/official-stockfish/Stockfish/pull/3856 Bench: 4667591 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Joost VandeVondele
Date: Tue Dec 14 13:41:12 2021 +0100 Timestamp: 1639485672 Remove NNUE scaling term remove pawns scaling, probably correlated with piece scaling, and might be less useful with the recent improved nets. Might allow for another tune of the scaling params. passed STC https://tests.stockfishchess.org/tests/view/61afdb2e56fcf33bce7df31a LLR: 2.95 (-2.94,2.94) <-2.25,0.25> Total: 280864 W: 72198 L: 72399 D: 136267 Elo -0.25 Ptnml(0-2): 854, 32356, 74346, 31889, 987 passed LTC https://tests.stockfishchess.org/tests/view/61b233a606b4c2dcb1b16140 LLR: 2.95 (-2.94,2.94) <-2.25,0.25> Total: 400136 W: 102669 L: 103012 D: 194455 Elo -0.30 Ptnml(0-2): 212, 42005, 116047, 41522, 282 closes https://github.com/official-stockfish/Stockfish/pull/3851 Bench: 4735679 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Joost VandeVondele
Date: Mon Dec 13 07:17:25 2021 +0100 Timestamp: 1639376245 Update default net to nn-d93927199b3d.nnue Using the same dataset as before but slightly reduced initial LR as in https://github.com/vondele/nnue-pytorch/tree/tweakLR1 passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 51368 W: 13492 L: 13191 D: 24685 Elo +2.04 Ptnml(0-2): 168, 5767, 13526, 6042, 181 https://tests.stockfishchess.org/tests/view/61b61f43dffbe89a3580b529 passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 45128 W: 11763 L: 11469 D: 21896 Elo +2.26 Ptnml(0-2): 24, 4583, 13063, 4863, 31 https://tests.stockfishchess.org/tests/view/61b6612edffbe89a3580c447 closes https://github.com/official-stockfish/Stockfish/pull/3848 Bench: 5121336 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Stefan Geschwentner
Date: Sat Dec 11 15:56:38 2021 +0100 Timestamp: 1639234598 Simplify falling eval time factor. Remove the difference to previous best score in falling eval calculation. As compensation double the effect of the difference to previous best average score. STC: LLR: 2.95 (-2.94,2.94) <-2.25,0.25> Total: 86944 W: 22363 L: 22285 D: 42296 Elo +0.31 Ptnml(0-2): 273, 9227, 24396, 9301, 275 https://tests.stockfishchess.org/tests/view/61b111ce06b4c2dcb1b11546 LTC: LLR: 2.96 (-2.94,2.94) <-2.25,0.25> Total: 134944 W: 34606 L: 34596 D: 65742 Elo +0.03 Ptnml(0-2): 66, 12941, 41456, 12935, 74 https://tests.stockfishchess.org/tests/view/61b19ca206b4c2dcb1b13a8b closes https://github.com/official-stockfish/Stockfish/pull/3841 Bench: 4729473 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Joost VandeVondele
Date: Sat Dec 11 15:55:32 2021 +0100 Timestamp: 1639234532 Update Top CPU Contributors closes https://github.com/official-stockfish/Stockfish/pull/3842 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Michael Chaly
Date: Thu Dec 9 20:50:00 2021 +0100 Timestamp: 1639079400 Adjust singular extension depth restriction This patch is a modification of original idea by lonfom169 which had a good yellow run - do singular extension search with depth threshold 6 unless this is a PvNode with is a part of a PV line - for them set threshold to 8 instead. Passed STC https://tests.stockfishchess.org/tests/view/61b1080406b4c2dcb1b1128c LLR: 2.95 (-2.94,2.94) <0.00,2.50> Total: 84352 W: 21917 L: 21555 D: 40880 Elo +1.49 Ptnml(0-2): 288, 9524, 22185, 9896, 283 Passed LTC https://tests.stockfishchess.org/tests/view/61b1860a06b4c2dcb1b134a1 LLR: 2.95 (-2.94,2.94) <0.50,3.00> Total: 63520 W: 16575 L: 16237 D: 30708 Elo +1.85 Ptnml(0-2): 27, 6519, 18350, 6817, 47 https://github.com/official-stockfish/Stockfish/pull/3840 bench 4729473 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Stefan Geschwentner
Date: Wed Dec 8 17:16:17 2021 +0100 Timestamp: 1638980177 Improve transposition table remplacement strategy Increase chance that PV node replaces old entry in transposition table. STC: LLR: 2.93 (-2.94,2.94) <0.00,2.50> Total: 46744 W: 12108 L: 11816 D: 22820 Elo +2.17 Ptnml(0-2): 156, 5221, 12344, 5477, 174 https://tests.stockfishchess.org/tests/view/61ae068356fcf33bce7d99d0 LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 88464 W: 22912 L: 22513 D: 43039 Elo +1.57 Ptnml(0-2): 84, 9133, 25393, 9544, 78 https://tests.stockfishchess.org/tests/view/61ae973656fcf33bce7db3e1 closes https://github.com/official-stockfish/Stockfish/pull/3839 Bench: 5292488 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Michael Chaly
Date: Tue Dec 7 18:15:06 2021 +0100 Timestamp: 1638897306 Introduce post-lmr extensions This idea is somewhat similar to extentions in LMR but has a different flavour. If result of LMR was really good - thus exceeded alpha by some pretty big given margin, we can extend move after LMR in full depth search with 0 window. The idea is that this move is probably a fail high with somewhat of a big probability so extending it makes a lot of sense passed STC https://tests.stockfishchess.org/tests/view/61ad45ea56fcf33bce7d74b7 LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 59680 W: 15531 L: 15215 D: 28934 Elo +1.84 Ptnml(0-2): 193, 6711, 15734, 6991, 211 passed LTC https://tests.stockfishchess.org/tests/view/61ad9ff356fcf33bce7d8646 LLR: 2.95 (-2.94,2.94) <0.50,3.00> Total: 59104 W: 15321 L: 14992 D: 28791 Elo +1.93 Ptnml(0-2): 53, 6023, 17065, 6364, 47 closes https://github.com/official-stockfish/Stockfish/pull/3838 bench 4881329 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Tomasz Sobczyk
Date: Tue Dec 7 18:08:54 2021 +0100 Timestamp: 1638896934 Optimize FT activation and affine transform for NEON. This patch optimizes the NEON implementation in two ways. The activation layer after the feature transformer is rewritten to make it easier for the compiler to see through dependencies and unroll. This in itself is a minimal, but a positive improvement. Other architectures could benefit from this too in the future. This is not an algorithmic change. The affine transform for large matrices (first layer after FT) on NEON now utilizes the same optimized code path as >=SSSE3, which makes the memory accesses more sequential and makes better use of the available registers, which allows for code that has longer dependency chains. Benchmarks from Redshift#161, profile-build with apple clang george@Georges-MacBook-Air nets % ./stockfish-b82d93 bench 2>&1 | tail -4 (current master) =========================== Total time (ms) : 2167 Nodes searched : 4667742 Nodes/second : 2154011 george@Georges-MacBook-Air nets % ./stockfish-7377b8 bench 2>&1 | tail -4 (this patch) =========================== Total time (ms) : 1842 Nodes searched : 4667742 Nodes/second : 2534061 This is a solid 18% improvement overall, larger in a bench with NNUE-only, not mixed. Improvement is also observed on armv7-neon (Raspberry Pi, and older phones), around 5% speedup. No changes for architectures other than NEON. closes https://github.com/official-stockfish/Stockfish/pull/3837 No functional changes. see source |