| 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 Oct 8 07:41:16 2023 +0200 Timestamp: 1696743676 Remove one test in the move loop Simplification passed STC test: https://tests.stockfishchess.org/tests/view/6519fc91cff46e538ee014f6 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 191264 W: 48550 L: 48501 D: 94213 Elo +0.09 Ptnml(0-2): 576, 21529, 51392, 21540, 595 closes #4815 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: Robert Nurnberg @ elitebook
Date: Sun Oct 8 07:38:13 2023 +0200 Timestamp: 1696743493 Update links in license matches https://www.gnu.org/licenses/gpl-3.0.txt closes https://github.com/official-stockfish/Stockfish/pull/4813 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: mstembera
Date: Sun Oct 8 07:37:01 2023 +0200 Timestamp: 1696743421 Remove handcrafted MMX code too small a benefit to maintain this old target closes https://github.com/official-stockfish/Stockfish/pull/4804 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: Linmiao Xu
Date: Fri Sep 29 22:30:27 2023 +0200 Timestamp: 1696019427 Update default net to nn-0000000000a0.nnue This is a later epoch from the same experiment that led to the previous master net. In training stage 6, max-epoch was raised to 1,200 near the end of the first 1,000 epochs. For more details, see https://github.com/official-stockfish/Stockfish/pull/4795 Local elo at 25k nodes per move (vs. L1-2048 nn-1ee1aba5ed4c.nnue) ep1079 : 15.6 +/- 1.2 Passed STC: https://tests.stockfishchess.org/tests/view/651503b3b3e74811c8af1e2a LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 29408 W: 7607 L: 7304 D: 14497 Elo +3.58 Ptnml(0-2): 97, 3277, 7650, 3586, 94 Passed LTC: https://tests.stockfishchess.org/tests/view/651585ceb3e74811c8af2a5f LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 73164 W: 18828 L: 18440 D: 35896 Elo +1.84 Ptnml(0-2): 30, 7749, 20644, 8121, 38 closes https://github.com/official-stockfish/Stockfish/pull/4810 Bench: 1453057 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: cj5716
Date: Fri Sep 29 22:28:34 2023 +0200 Timestamp: 1696019314 Skip moves-loop pruning in qsearch if we have only pawns At first my idea was only to cover movecount and futility pruning, but @peregrineshahin suggested to test it on all moves-loop pruning and it worked. Passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 167968 W: 42970 L: 42480 D: 82518 Elo +1.01 Ptnml(0-2): 444, 18324, 46002, 18726, 488 https://tests.stockfishchess.org/tests/view/6511181a55b420c569d0d54c Passed LTC: LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 40794 W: 10496 L: 10182 D: 20116 Elo +2.67 Ptnml(0-2): 12, 4021, 12025, 4319, 20 https://tests.stockfishchess.org/tests/view/6512ccc4b3e74811c8aee86c closes https://github.com/official-stockfish/Stockfish/pull/4809 Bench: 1338472 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: Sebastian Buchwald
Date: Fri Sep 29 22:22:40 2023 +0200 Timestamp: 1696018960 Use C++17 variable templates for type traits The C++17 variable templates are slightly more readable and allow us to remove the typename keyword in a few cases. closes https://github.com/official-stockfish/Stockfish/pull/4806 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: mstembera
Date: Fri Sep 29 22:19:08 2023 +0200 Timestamp: 1696018748 Remove unused see_ge() code closes https://github.com/official-stockfish/Stockfish/pull/4805 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: FauziAkram
Date: Fri Sep 29 22:18:17 2023 +0200 Timestamp: 1696018697 Improve grammar of comments closes https://github.com/official-stockfish/Stockfish/pull/4801 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: FauziAkram
Date: Fri Sep 29 22:12:46 2023 +0200 Timestamp: 1696018366 Simplify pawn count in evaluation This simplifies the evaluation by removing the unnecessary pawn count term when combining nnue and optimism values. Passed STC LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 61472 W: 15748 L: 15554 D: 30170 Elo +1.10 Ptnml(0-2): 191, 7123, 15933, 7279, 210 https://tests.stockfishchess.org/tests/view/650c34cf7ca0d3f7bbf264ff Passed LTC: LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 81264 W: 20657 L: 20500 D: 40107 Elo +0.67 Ptnml(0-2): 30, 8713, 22997, 8854, 38 https://tests.stockfishchess.org/tests/view/650cc30efb151d43ae6d5987 closes https://github.com/official-stockfish/Stockfish/pull/4800 Bench: 1530568 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: Jasper Shovelton
Date: Fri Sep 29 22:07:10 2023 +0200 Timestamp: 1696018030 Increment minor section number from 3.7.1 to 3.8.1. Pext has nothing to do with git commit sha/date, so separate the two sub-sections. closes https://github.com/official-stockfish/Stockfish/pull/4785 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: Joost VandeVondele
Date: Sun Sep 24 20:04:42 2023 +0200 Timestamp: 1695578682 Explicitly invoke shell in some cases the permission on the script might be incorrect (zip downloads?). Explicitly invoke the shell closes https://github.com/official-stockfish/Stockfish/pull/4803 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: Linmiao Xu
Date: Fri Sep 22 19:26:16 2023 +0200 Timestamp: 1695403576 Update NNUE architecture to SFNNv8: L1-2560 nn-ac1dbea57aa3.nnue Creating this net involved: - a 6-stage training process from scratch. The datasets used in stages 1-5 were fully minimized. - permuting L1 weights with https://github.com/official-stockfish/nnue-pytorch/pull/254 A strong epoch after each training stage was chosen for the next. The 6 stages were: ``` 1. 400 epochs, lambda 1.0, default LR and gamma UHOx2-wIsRight-multinet-dfrc-n5000 (135G) nodes5000pv2_UHO.binpack data_pv-2_diff-100_nodes-5000.binpack wrongIsRight_nodes5000pv2.binpack multinet_pv-2_diff-100_nodes-5000.binpack dfrc_n5000.binpack 2. 800 epochs, end-lambda 0.75, LR 4.375e-4, gamma 0.995, skip 12 LeelaFarseer-T78juntoaugT79marT80dec.binpack (141G) T60T70wIsRightFarseerT60T74T75T76.binpack test78-junjulaug2022-16tb7p.no-db.min.binpack test79-mar2022-16tb7p.no-db.min.binpack test80-dec2022-16tb7p.no-db.min.binpack 3. 800 epochs, end-lambda 0.725, LR 4.375e-4, gamma 0.995, skip 20 leela93-v1-dfrc99-v2-T78juntosepT80jan-v6dd-T78janfebT79aprT80aprmay.min.binpack leela93-filt-v1.min.binpack dfrc99-16tb7p-filt-v2.min.binpack test78-juntosep2022-16tb7p-filter-v6-dd.min-mar2023.binpack test80-jan2023-3of3-16tb7p-filter-v6-dd.min-mar2023.binpack test78-janfeb2022-16tb7p.min.binpack test79-apr2022-16tb7p.min.binpack test80-apr2022-16tb7p.min.binpack test80-may2022-16tb7p.min.binpack 4. 800 epochs, end-lambda 0.7, LR 4.375e-4, gamma 0.995, skip 24 leela96-dfrc99-v2-T78juntosepT79mayT80junsepnovjan-v6dd-T80mar23-v6-T60novdecT77decT78aprmayT79aprT80may23.min.binpack leela96-filt-v2.min.binpack dfrc99-16tb7p-filt-v2.min.binpack test78-juntosep2022-16tb7p-filter-v6-dd.min-mar2023.binpack test79-may2022-16tb7p.filter-v6-dd.min.binpack test80-jun2022-16tb7p.filter-v6-dd.min.binpack test80-sep2022-16tb7p.filter-v6-dd.min.binpack test80-nov2022-16tb7p.filter-v6-dd.min.binpack test80-jan2023-3of3-16tb7p-filter-v6-dd.min-mar2023.binpack test80-mar2023-2tb7p.v6-sk16.min.binpack test60-novdec2021-16tb7p.min.binpack test77-dec2021-16tb7p.min.binpack test78-aprmay2022-16tb7p.min.binpack test79-apr2022-16tb7p.min.binpack test80-may2023-2tb7p.min.binpack 5. 960 epochs, end-lambda 0.7, LR 4.375e-4, gamma 0.995, skip 28 Increased max-epoch to 960 near the end of the first 800 epochs 5af11540bbfe dataset: https://github.com/official-stockfish/Stockfish/pull/4635 6. 1000 epochs, end-lambda 0.7, LR 4.375e-4, gamma 0.995, skip 28 Increased max-epoch to 1000 near the end of the first 800 epochs 1ee1aba5ed dataset: https://github.com/official-stockfish/Stockfish/pull/4782 ``` L1 weights permuted with: ```bash python3 serialize.py $nnue $nnue_permuted \ --features=HalfKAv2_hm \ --ft_optimize \ --ft_optimize_data=/data/fishpack32.binpack \ --ft_optimize_count=10000 ``` Speed measurements from 100 bench runs at depth 13 with profile-build x86-64-avx2: ``` sf_base = 1329051 +/- 2224 (95%) sf_test = 1163344 +/- 2992 (95%) diff = -165706 +/- 4913 (95%) speedup = -12.46807% +/- 0.370% (95%) ``` Training data can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move (vs. L1-2048 nn-1ee1aba5ed4c.nnue) ep959 : 16.2 +/- 2.3 Failed 10+0.1 STC: https://tests.stockfishchess.org/tests/view/6501beee2cd016da89abab21 LLR: -2.92 (-2.94,2.94) <0.00,2.00> Total: 13184 W: 3285 L: 3535 D: 6364 Elo -6.59 Ptnml(0-2): 85, 1662, 3334, 1440, 71 Failed 180+1.8 VLTC: https://tests.stockfishchess.org/tests/view/6505cf9a72620bc881ea908e LLR: -2.94 (-2.94,2.94) <0.00,2.00> Total: 64248 W: 16224 L: 16374 D: 31650 Elo -0.81 Ptnml(0-2): 26, 6788, 18640, 6650, 20 Passed 60+0.6 th 8 VLTC SMP (STC bounds): https://tests.stockfishchess.org/tests/view/65084a4618698b74c2e541dc LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 90630 W: 23372 L: 23033 D: 44225 Elo +1.30 Ptnml(0-2): 13, 8490, 27968, 8833, 11 Passed 60+0.6 th 8 VLTC SMP: https://tests.stockfishchess.org/tests/view/6501d45d2cd016da89abacdb LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 137804 W: 35764 L: 35276 D: 66764 Elo +1.23 Ptnml(0-2): 31, 13006, 42326, 13522, 17 closes https://github.com/official-stockfish/Stockfish/pull/4795 bench 1246812 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: Fri Sep 22 19:25:57 2023 +0200 Timestamp: 1695403557 Remove VALUE_KNOWN_WIN. After removing classic evaluation VALUE_KNOWN_WIN is not anymore returned explicit evaluation. So remove and replace it with VALUE_TB_WIN_IN_MAX_PLY. Measurement on my big bench (bench 16 1 16 pos1000.fen) verifies that at least with current net the calculated evaluation lies always in the open interval (-VALUE_KNOWN_WIN, VALUE_KNOWN_WIN). So i consider this a non-functional change. But to be safe i tested this also at LTC as requested by Stephane Nicolet. STC: https://tests.stockfishchess.org/tests/view/64f9db40eaf01be8259a6ed5 LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 455296 W: 115981 L: 116217 D: 223098 Elo -0.18 Ptnml(0-2): 1415, 50835, 123420, 50527, 1451 LTC: https://tests.stockfishchess.org/tests/view/650bfd867ca0d3f7bbf25feb LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 35826 W: 9170 L: 8973 D: 17683 Elo +1.91 Ptnml(0-2): 12, 3523, 10645, 3722, 11 closes https://github.com/official-stockfish/Stockfish/pull/4792 Bench: 1603079 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: mstembera
Date: Fri Sep 22 19:15:34 2023 +0200 Timestamp: 1695402934 Reduce SIMD register count from 32 to 16 in the case of avx512 and vnni512 archs. Up to 17% speedup, depending on the compiler, e.g. ``` AMD pro 7840u (zen4 phoenix apu 4nm) bash bench_parallel.sh ./stockfish_avx512_gcc13 ./stockfish_avx512_pr_gcc13 20 10 sf_base = 1077737 +/- 8446 (95%) sf_test = 1264268 +/- 8543 (95%) diff = 186531 +/- 4280 (95%) speedup = 17.308% +/- 0.397% (95%) ``` Prior to this patch, it appears gcc spills registers. closes https://github.com/official-stockfish/Stockfish/pull/4796 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: cj5716
Date: Fri Sep 22 19:14:29 2023 +0200 Timestamp: 1695402869 Make casting styles consistent Make casting styles consistent with the rest of the code. closes https://github.com/official-stockfish/Stockfish/pull/4793 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: Sebastian Buchwald
Date: Fri Sep 22 19:12:53 2023 +0200 Timestamp: 1695402773 Let CI check C++ includes The commit adds a CI workflow that uses the included-what-you-use (IWYU) tool to check for missing or superfluous includes in .cpp files and their corresponding .h files. This means that some .h files (especially in the nnue folder) are not checked yet. The CI setup looks like this: - We build IWYU from source to include some yet unreleased fixes. This IWYU version targets LLVM 17. Thus, we get the latest release candidate of LLVM 17 from LLVM's nightly packages. - The Makefile now has an analyze target that just build the object files (without linking) - The CI uses the analyze target with the IWYU tool as compiler to analyze the compiled .cpp file and its corresponding .h file. - If IWYU suggests a change the build fails (-Xiwyu --error). - To avoid false positives we use LLVM's libc++ as standard library - We have a custom mappings file that adds some mappings that are missing in IWYU's default mappings We also had to add one IWYU pragma to prevent a false positive in movegen.h. https://github.com/official-stockfish/Stockfish/pull/4783 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: Stéphane Nicolet
Date: Fri Sep 22 19:09:20 2023 +0200 Timestamp: 1695402560 Export makefile ARCH in binary Example of the `./stockfish compiler` command: Compiled by : g++ (GNUC) 10.3.0 on Apple Compilation architecture : x86-64-bmi2 Compilation settings : 64bit BMI2 AVX2 SSE41 SSSE3 SSE2 POPCNT Compiler __VERSION__ macro : 10.3.0 closes https://github.com/official-stockfish/Stockfish/pull/4789 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: Joost VandeVondele
Date: Fri Sep 22 19:06:37 2023 +0200 Timestamp: 1695402397 Enable a default native ARCH uses a posix compatible script to find the native arch. (based on ppigazzini's https://github.com/ppigazzini/stockfish-downloader ) use that native arch by default, no changes if ARCH is specified explicitly. SF can now be compiled in an optimal way simply using make -j profile-build closes https://github.com/official-stockfish/Stockfish/pull/4777 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: mstembera
Date: Fri Sep 22 19:03:47 2023 +0200 Timestamp: 1695402227 Sparse impl of affine_transform_non_ssse3() deal with the general case About a 8.6% speedup (for general arch) Results for 200 tests for each version: Base Test Diff Mean 141741 153998 -12257 StDev 2990 3042 3742 p-value: 0.999 speedup: 0.086 closes https://github.com/official-stockfish/Stockfish/pull/4786 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: peregrineshahin
Date: Fri Sep 22 19:02:18 2023 +0200 Timestamp: 1695402138 Reorder some lines Now that qsearch has its own repetition detection we can flip the order of lines and remove the guard of depth < 0 which is not needed after reordering (i.e. it was there to prevent checking repetition again at depth ==0). Passed STC: https://tests.stockfishchess.org/tests/view/6502ecbb2cd016da89abc3fb LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 69536 W: 17668 L: 17490 D: 34378 Elo +0.89 Ptnml(0-2): 190, 7652, 18929, 7784, 213 Passed LTC: https://tests.stockfishchess.org/tests/view/6505ce9072620bc881ea9086 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 52116 W: 13294 L: 13113 D: 25709 Elo +1.21 Ptnml(0-2): 26, 5176, 15471, 5361, 24 closes https://github.com/official-stockfish/Stockfish/pull/4791 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: Stéphane Nicolet
Date: Mon Sep 11 23:19:06 2023 +0200 Timestamp: 1694467146 Reformat some comments Also include the bench to make Continuation Integration happy on Github. Bench: 1603079 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: Sebastian Buchwald
Date: Mon Sep 11 22:46:01 2023 +0200 Timestamp: 1694465161 Cleanup code after dropping ICC support in favor of ICX The commit removes all uses of ICC's __INTEL_COMPILER macro and other references to ICC. It also adds ICX info to the compiler command and fixes two typos in Makefile's help output. closes https://github.com/official-stockfish/Stockfish/pull/4769 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: Linmiao Xu
Date: Mon Sep 11 22:37:39 2023 +0200 Timestamp: 1694464659 Update default net to nn-1ee1aba5ed4c.nnue Created by retraining the master net on a dataset composed by: - adding Leela data from T60 jul-dec 2020, T77 nov 2021, T80 jun-jul 2023 - deduplicating and unminimizing parts of the dataset before interleaving Trained initially with max epoch 800, then increased near the end of training twice. First to 960, then 1200. After training, post-processing involved: - greedy permuting L1 weights with https://github.com/official-stockfish/Stockfish/pull/4620 - greedy 2- and 3- cycle permuting with https://github.com/official-stockfish/Stockfish/pull/4640 python3 easy_train.py \ --experiment-name 2048-retrain-S6-sk28 \ --training-dataset /data/S6.binpack \ --early-fen-skipping 28 \ --start-from-engine-test-net True \ --max_epoch 1200 \ --lr 4.375e-4 \ --gamma 0.995 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --tui False \ --seed $RANDOM \ --gpus 0 In the list of datasets below, periods in the filename represent the sequence of steps applied to arrive at the particular binpack. For example: test77-dec2021-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack 1. test77 dec2021 data rescored with 16 TB of syzygy tablebases during data conversion 2. filtered with csv_filter_v6_dd.py - v6 filtering and deduplication in one step 3. minimized with the original mar2023 implementation of `minimize_binpack` in the tools branch 4. unminimized by removing all positions with score == 32002 (`VALUE_NONE`) Binpacks were: - filtered with: https://github.com/linrock/nnue-data - unminimized with: https://github.com/linrock/Stockfish/tree/tools-unminify - deduplicated with: https://github.com/linrock/Stockfish/tree/tools-dd DATASETS=( leela96-filt-v2.min.unminimized.binpack dfrc99-16tb7p-eval-filt-v2.min.unminimized.binpack # most of the 0dd1cebea57 v6-dd dataset (without test80-jul2022) # https://github.com/official-stockfish/Stockfish/pull/4606 test60-novdec2021-12tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test77-dec2021-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test78-jantomay2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test78-juntosep2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test79-apr2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test79-may2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-jun2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-aug2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-sep2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-oct2022-16tb7p.filter-v6-dd.min.binpack test80-nov2022-16tb7p.filter-v6-dd.min.binpack test80-jan2023-3of3-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-feb2023-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack # older Leela data, recently converted test60-octnovdec2020-2tb7p.min.unminimized.binpack test60-julaugsep2020-2tb7p.min.binpack test77-nov2021-2tb7p.min.dd.binpack # newer Leela data test80-mar2023-2tb7p.min.unminimized.binpack test80-apr2023-2tb7p.filter-v6-sk16.min.unminimized.binpack test80-may2023-2tb7p.min.dd.binpack test80-jun2023-2tb7p.min.binpack test80-jul2023-2tb7p.binpack ) python3 interleave_binpacks.py ${DATASETS[@]} /data/S6.binpack Training data can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move: nn-epoch1059 : 2.7 +/- 1.6 Passed STC: https://tests.stockfishchess.org/tests/view/64fc8d705dab775b5359db42 LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 168352 W: 43216 L: 42704 D: 82432 Elo +1.06 Ptnml(0-2): 599, 19672, 43134, 20160, 611 Passed LTC: https://tests.stockfishchess.org/tests/view/64fd44a75dab775b5359f065 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 154194 W: 39436 L: 38881 D: 75877 Elo +1.25 Ptnml(0-2): 78, 16577, 43238, 17120, 84 closes https://github.com/official-stockfish/Stockfish/pull/4782 Bench: 1603079 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: Mon Sep 11 22:36:26 2023 +0200 Timestamp: 1694464586 Do more futility pruning in qsearch This patch introduces a third futility pruning heuristic in qsearch. The idea is that the static exchange evaluation is much worse than the difference between futility base and alpha. Thus we can assume that the probability of the move being good enough to beat alpha is low so it can be pruned. Passed STC: https://tests.stockfishchess.org/tests/view/64fc982a5dab775b5359dc83 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 36576 W: 9484 L: 9170 D: 17922 Elo +2.98 Ptnml(0-2): 121, 4119, 9495, 4431, 122 Passed LTC: https://tests.stockfishchess.org/tests/view/64fcc7935dab775b5359e1a9 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 135408 W: 34556 L: 34041 D: 66811 Elo +1.32 Ptnml(0-2): 56, 14462, 38165, 14953, 68 closes https://github.com/official-stockfish/Stockfish/pull/4781 Bench: 1330793 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: cj5716
Date: Mon Sep 11 22:30:57 2023 +0200 Timestamp: 1694464257 Simplify cutnode depth condition With this patch, the depth condition for the cutnodes reduction is loosened from tte->depth() >= depth + 3 to just tte->depth() >= depth. Passed STC: LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 101152 W: 25830 L: 25682 D: 49640 Elo +0.51 Ptnml(0-2): 312, 11788, 26258, 11876, 342 https://tests.stockfishchess.org/tests/view/64fd15635dab775b5359eaa6 Passed LTC: LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 82542 W: 20980 L: 20824 D: 40738 Elo +0.66 Ptnml(0-2): 42, 8795, 23440, 8953, 41 https://tests.stockfishchess.org/tests/view/64fda3545dab775b5359fbf1 closes https://github.com/official-stockfish/Stockfish/pull/4780 Bench: 1479029 see source |