| 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: Andreas Matthies
Date: Tue Jun 13 08:45:25 2023 +0200 Timestamp: 1686638725 Fix for MSVC compilation. MSVC needs two more explicit casts to compile new affine_transform_sparse_input. See https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm256_castsi256_ps and https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm_castsi128_ps closes https://github.com/official-stockfish/Stockfish/pull/4616 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: Tue Jun 13 08:42:55 2023 +0200 Timestamp: 1686638575 Clean-up code indentation in qsearch closes https://github.com/official-stockfish/Stockfish/pull/4615 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: Mon Jun 12 21:17:31 2023 +0200 Timestamp: 1686597451 Improve comments Fix comments for IIR, also document non-linear scaling in extensions. Also add explicitly the bench, to fix an issue after the last commit. closes https://github.com/official-stockfish/Stockfish/pull/4614 bench 2370027 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: AndrovT
Date: Mon Jun 12 20:41:27 2023 +0200 Timestamp: 1686595287 Use block sparse input for the first layer. Use block sparse input for the first fully connected layer on architectures with at least SSSE3. Depending on the CPU architecture, this yields a speedup of up to 10%, e.g. ``` Result of 100 runs of 'bench 16 1 13 default depth NNUE' base (...ockfish-base) = 959345 +/- 7477 test (...ckfish-patch) = 1054340 +/- 9640 diff = +94995 +/- 3999 speedup = +0.0990 P(speedup > 0) = 1.0000 CPU: 8 x AMD Ryzen 7 5700U with Radeon Graphics Hyperthreading: on ``` Passed STC: https://tests.stockfishchess.org/tests/view/6485aa0965ffe077ca12409c LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 8864 W: 2479 L: 2223 D: 4162 Elo +10.04 Ptnml(0-2): 13, 829, 2504, 1061, 25 This commit includes a net with reordered weights, to increase the likelihood of block sparse inputs, but otherwise equivalent to the previous master net (nn-ea57bea57e32.nnue). Activation data collected with https://github.com/AndrovT/Stockfish/tree/log-activations, running bench 16 1 13 varied_1000.epd depth NNUE on this data. Net parameters permuted with https://gist.github.com/AndrovT/9e3fbaebb7082734dc84d27e02094cb3. closes https://github.com/official-stockfish/Stockfish/pull/4612 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: Mon Jun 12 20:35:44 2023 +0200 Timestamp: 1686594944 Add network export to CI verify the network written by export_net matches the original closes https://github.com/official-stockfish/Stockfish/pull/4613 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: Sun Jun 11 15:23:52 2023 +0200 Timestamp: 1686489832 Update default net to nn-ea57bea57e32.nnue Created by retraining an earlier epoch (ep659) of the experiment that led to the first SFNNv6 net: - First retrained on the nn-0dd1cebea573 dataset - Then retrained with skip 20 on a smaller dataset containing unfiltered Leela data - And then retrained again with skip 27 on the nn-0dd1cebea573 dataset The equivalent 7-step training sequence from scratch that led here was: 1. max-epoch 400, lambda 1.0, constant LR 9.75e-4, T79T77-filter-v6-dd.min.binpack ep379 chosen for retraining in step2 2. max-epoch 800, end-lambda 0.75, T60T70wIsRightFarseerT60T74T75T76.binpack ep679 chosen for retraining in step3 3. max-epoch 800, end-lambda 0.75, skip 28, nn-e1fb1ade4432 dataset ep799 chosen for retraining in step4 4. max-epoch 800, end-lambda 0.7, skip 28, nn-e1fb1ade4432 dataset ep759 became nn-8d69132723e2.nnue (first SFNNv6 net) ep659 chosen for retraining in step5 5. max-epoch 800, end-lambda 0.7, skip 28, nn-0dd1cebea573 dataset ep759 chosen for retraining in step6 6. max-epoch 800, end-lambda 0.7, skip 20, leela-dfrc-v2-T77decT78janfebT79aprT80apr.binpack ep639 chosen for retraining in step7 7. max-epoch 800, end-lambda 0.7, skip 27, nn-0dd1cebea573 dataset ep619 became nn-ea57bea57e32.nnue For the last retraining (step7): python3 easy_train.py --experiment-name L1-1536-Re6-masterShuffled-ep639-sk27-Re5-leela-dfrc-v2-T77toT80small-Re4-masterShuffled-ep659-Re3-sameAs-Re2-leela96-dfrc99-16t-v2-T60novdecT80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-Re1-LeelaFarseer-new-T77T79 \ --training-dataset /data/leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-1536 \ --early-fen-skipping 27 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --max_epoch 800 \ --start-from-engine-test-net False \ --start-from-model /data/L1-1536-Re5-leela-dfrc-v2-T77toT80small-epoch639.nnue \ --lr 4.375e-4 \ --gamma 0.995 \ --tui False \ --seed $RANDOM \ --gpus "0," For preparing the step6 leela-dfrc-v2-T77decT78janfebT79aprT80apr.binpack dataset: python3 interleave_binpacks.py \ leela96-filt-v2.binpack \ dfrc99-16tb7p-eval-filt-v2.binpack \ test77-dec2021-16tb7p.no-db.min-mar2023.binpack \ test78-janfeb2022-16tb7p.no-db.min-mar2023.binpack \ test79-apr2022-16tb7p-filter-v6-dd.binpack \ test80-apr2022-16tb7p.no-db.min-mar2023.binpack \ /data/leela-dfrc-v2-T77decT78janfebT79aprT80apr.binpack The unfiltered Leela data used for the step6 dataset can be found at: https://robotmoon.com/nnue-training-data Local elo at 25k nodes per move: nn-epoch619.nnue : 2.3 +/- 1.9 Passed STC: https://tests.stockfishchess.org/tests/view/6480d43c6e6ce8d9fc6d7cc8 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 40992 W: 11017 L: 10706 D: 19269 Elo +2.64 Ptnml(0-2): 113, 4400, 11170, 4689, 124 Passed LTC: https://tests.stockfishchess.org/tests/view/648119ac6e6ce8d9fc6d8208 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 129174 W: 35059 L: 34579 D: 59536 Elo +1.29 Ptnml(0-2): 66, 12548, 38868, 13050, 55 closes https://github.com/official-stockfish/Stockfish/pull/4611 bench: 2370027 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: Guenther Demetz
Date: Sun Jun 11 15:13:57 2023 +0200 Timestamp: 1686489237 Reintroduce SEE verification against discovered attacks Reintroduces https://github.com/official-stockfish/Stockfish/pull/4453 along with https://github.com/official-stockfish/Stockfish/pull/4469 Leaving out https://github.com/official-stockfish/Stockfish/pull/4533 https://github.com/official-stockfish/Stockfish/pull/4572 Passed STC: https://tests.stockfishchess.org/tests/view/647d8c37726f6b400e408a0a LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 143168 W: 38346 L: 37892 D: 66930 Elo +1.10 Ptnml(0-2): 352, 15672, 39164, 15962, 434 Passed LTC: https://tests.stockfishchess.org/tests/view/647ee8c528c4431bcb58e432 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 71538 W: 19560 L: 19190 D: 32788 Elo +1.80 Ptnml(0-2): 49, 6905, 21499, 7259, 57 closes https://github.com/official-stockfish/Stockfish/pull/4609 bench: 2595430 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: Sun Jun 11 15:05:54 2023 +0200 Timestamp: 1686488754 Simplify multiplier for improvement This simplifies a `* 99 / 1300` term into just `/ 13`. Passed non-regression STC: LLR: 2.92 (-2.94,2.94) <-1.75,0.25> Total: 58816 W: 15727 L: 15540 D: 27549 Elo +1.10 Ptnml(0-2): 149, 6370, 16203, 6517, 169 https://tests.stockfishchess.org/tests/view/647d25e4726f6b400e408165 Passed non-regression LTC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 154386 W: 41749 L: 41669 D: 70968 Elo +0.18 Ptnml(0-2): 94, 14992, 46956, 15042, 109 https://tests.stockfishchess.org/tests/view/647d9b3c726f6b400e408b2a closes https://github.com/official-stockfish/Stockfish/pull/4608 Bench: 2511327 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: Tue Jun 6 21:21:56 2023 +0200 Timestamp: 1686079316 Remove optimism multiplier in nnue eval calculation The same formula had passed SPRT against an earlier version of master. Passed non-regression STC vs. d99942f: https://tests.stockfishchess.org/tests/view/6478e76654dd118e1d98f72e LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 118720 W: 31402 L: 31277 D: 56041 Elo +0.37 Ptnml(0-2): 301, 13148, 32344, 13259, 308 Passed non-regression LTC vs. d99942f: https://tests.stockfishchess.org/tests/view/647a22c154dd118e1d991146 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 74286 W: 20019 L: 19863 D: 34404 Elo +0.73 Ptnml(0-2): 31, 7189, 22540, 7359, 24 The earlier patch had conflicted with a faster SPRT passer, so this was tested again after rebasing on latest master. Passed non-regression STC: https://tests.stockfishchess.org/tests/view/647d6e46726f6b400e408790 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 166176 W: 44309 L: 44234 D: 77633 Elo +0.16 Ptnml(0-2): 461, 18252, 45557, 18387, 431 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/647eb00ba268d1bc11255e7b LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 28170 W: 7713 L: 7513 D: 12944 Elo +2.47 Ptnml(0-2): 14, 2609, 8635, 2817, 10 closes https://github.com/official-stockfish/Stockfish/pull/4607 bench 2503095 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: Tue Jun 6 21:17:36 2023 +0200 Timestamp: 1686079056 Update default net to nn-0dd1cebea573.nnue Created by retraining an earlier epoch of the experiment leading to the first SFNNv6 net on a more-randomized version of the nn-e1fb1ade4432.nnue dataset mixed with unfiltered T80 apr2023 data. Trained using early-fen-skipping 28 and max-epoch 960. The trainer settings and epochs used in the 5-step training sequence leading here were: 1. train from scratch for 400 epochs, lambda 1.0, constant LR 9.75e-4, T79T77-filter-v6-dd.min.binpack 2. retrain ep379, max-epoch 800, end-lambda 0.75, T60T70wIsRightFarseerT60T74T75T76.binpack 3. retrain ep679, max-epoch 800, end-lambda 0.75, skip 28, nn-e1fb1ade4432 dataset 4. retrain ep799, max-epoch 800, end-lambda 0.7, skip 28, nn-e1fb1ade4432 dataset 5. retrain ep439, max-epoch 960, end-lambda 0.7, skip 28, shuffled nn-e1fb1ade4432 + T80 apr2023 This net was epoch 559 of the final (step 5) retraining: ```bash python3 easy_train.py \ --experiment-name L1-1536-Re4-leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr-shuffled-sk28 \ --training-dataset /data/leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-1536 \ --early-fen-skipping 28 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --max_epoch 960 \ --start-from-engine-test-net False \ --start-from-model /data/L1-1536-Re3-nn-epoch439.nnue \ --engine-test-branch linrock/Stockfish/L1-1536 \ --lr 4.375e-4 \ --gamma 0.995 \ --tui False \ --seed $RANDOM \ --gpus "0," ``` During data preparation, most binpacks were unminimized by removing positions with score 32002 (`VALUE_NONE`). This makes the tradeoff of increasing dataset filesize on disk to increase the randomness of positions in interleaved datasets. The code used for unminimizing is at: https://github.com/linrock/Stockfish/tree/tools-unminify For preparing the dataset used in this experiment: ```bash python3 interleave_binpacks.py \ leela96-filt-v2.binpack \ dfrc99-16tb7p-eval-filt-v2.binpack \ filt-v6-dd-min/test60-novdec2021-12tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd-min/test80-aug2022-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd-min/test80-sep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd-min/test80-jun2022-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd/test80-jul2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test80-oct2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test80-nov2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd-min/test80-jan2023-3of3-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd-min/test80-feb2023-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd/test79-apr2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test79-may2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd-min/test78-jantomay2022-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd/test78-juntosep2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test77-dec2021-16tb7p-filter-v6-dd.binpack \ test80-apr2023-2tb7p.binpack \ /data/leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr.binpack ``` T80 apr2023 data was converted using lc0-rescorer with ~2tb of tablebases and can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move vs. nn-e1fb1ade4432.nnue (L1 size 1024): nn-epoch559.nnue : 25.7 +/- 1.6 Passed STC: https://tests.stockfishchess.org/tests/view/647cd3b87cf638f0f53f9cbb LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 59200 W: 16000 L: 15660 D: 27540 Elo +2.00 Ptnml(0-2): 159, 6488, 15996, 6768, 189 Passed LTC: https://tests.stockfishchess.org/tests/view/647d58de726f6b400e4085d8 LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 58800 W: 16002 L: 15657 D: 27141 Elo +2.04 Ptnml(0-2): 44, 5607, 17748, 5962, 39 closes https://github.com/official-stockfish/Stockfish/pull/4606 bench 2141197 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: disservin
Date: Tue Jun 6 21:12:24 2023 +0200 Timestamp: 1686078744 Add binaries to releases with github actions when a release is made with a tag matching sf_* the binaries will also be uploaded to the release as assets. closes https://github.com/official-stockfish/Stockfish/pull/4596 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: Tue Jun 6 21:07:43 2023 +0200 Timestamp: 1686078463 Fix no previous moves on root. guards against no previous move existing if qSearch is called on the root node (i.e. when razoring). Passed Non-regression STC: https://tests.stockfishchess.org/tests/view/647d242d726f6b400e408143 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 53120 W: 14167 L: 13976 D: 24977 Elo +1.25 Ptnml(0-2): 109, 5597, 14981, 5740, 133 closes https://github.com/official-stockfish/Stockfish/pull/4604 Bench: 2551691 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 Jun 4 23:12:23 2023 +0200 Timestamp: 1685913143 Move internal iterative reduction before probcut This patch moves IIR before probcut which allows probcut to be produced at lower depths. Comments in IIR are also slightly updated. Passed STC: https://tests.stockfishchess.org/tests/view/6472d604d29264e4cfa749fd LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 387616 W: 103295 L: 102498 D: 181823 Elo +0.71 Ptnml(0-2): 976, 42322, 106381, 43187, 942 Passed LTC: https://tests.stockfishchess.org/tests/view/6475eb8c4a36543c4c9f42e8 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 202836 W: 54901 L: 54281 D: 93654 Elo +1.06 Ptnml(0-2): 85, 19609, 61422, 20205, 97 closes https://github.com/official-stockfish/Stockfish/pull/4597 bench 2551691 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: Sun Jun 4 23:05:28 2023 +0200 Timestamp: 1685912728 Remove static eval threshold for extensions when giving check Passed non-regression STC: https://tests.stockfishchess.org/tests/view/647685d54a36543c4c9f4f2a LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 114688 W: 30701 L: 30571 D: 53416 Elo +0.39 Ptnml(0-2): 336, 12708, 31136, 12818, 346 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/64774b02b81f005b572de770 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 107310 W: 28920 L: 28796 D: 49594 Elo +0.40 Ptnml(0-2): 33, 10427, 32621, 10531, 43 closes https://github.com/official-stockfish/Stockfish/pull/4599 bench 2597974 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: Guenther Demetz
Date: Sun Jun 4 23:01:14 2023 +0200 Timestamp: 1685912474 Simplify away SEE verification After 4 simplificatons over PR#4453 the idea does not yield significant improvement anymore. Maybe also https://tests.stockfishchess.org/tests/view/640c88092644b62c3394c1c5 was a fluke. Passed non-regression bounds: STC: https://tests.stockfishchess.org/tests/view/64705389c079b6583146d873 LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 131936 W: 35040 L: 34930 D: 61966 Elo +0.29 Ptnml(0-2): 336, 14559, 36035, 14735, 303 LTC: https://tests.stockfishchess.org/tests/view/6471a2ade549d9cf2fb213cd LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 407700 W: 109999 L: 110164 D: 187537 Elo -0.14 Ptnml(0-2): 279, 39913, 123689, 39632, 337 closes https://github.com/official-stockfish/Stockfish/pull/4595 bench: 2675974 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: Sun Jun 4 22:56:44 2023 +0200 Timestamp: 1685912204 Simplify blending nnue complexity with optimism Passed non-regression STC: https://tests.stockfishchess.org/tests/view/6478a26d54dd118e1d98f21c LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 241248 W: 64058 L: 64063 D: 113127 Elo -0.01 Ptnml(0-2): 644, 26679, 65960, 26720, 621 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/647b464854dd118e1d9928b2 LLR: 2.96 (-2.94,2.94) <-1.75,0.25> Total: 24336 W: 6658 L: 6451 D: 11227 Elo +2.96 Ptnml(0-2): 8, 2316, 7312, 2525, 7 closes https://github.com/official-stockfish/Stockfish/pull/4602 bench 2425813 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: Muzhen Gaming
Date: Sun Jun 4 22:54:13 2023 +0200 Timestamp: 1685912053 Search tuning at very long time control with new net The most significant change would be the singularBeta formula. It was first tested by cj5716 (see https://tests.stockfishchess.org/tests/view/647317c9d29264e4cfa74ec7), and I took much inspiration from that idea. LTC (fixed games): https://tests.stockfishchess.org/tests/view/6479d8da54dd118e1d990b12 Elo: 0.61 ± 1.2 (95%) LOS: 83.4% Total: 60000 W: 16278 L: 16172 D: 27550 Elo +0.61 Ptnml(0-2): 16, 5845, 18179, 5937, 23 nElo: 1.38 ± 2.8 (95%) PairsRatio: 1.02 VLTC 180+1.8: https://tests.stockfishchess.org/tests/view/6479da1454dd118e1d990b2b LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 33224 W: 9261 L: 8984 D: 14979 Elo +2.90 Ptnml(0-2): 5, 2809, 10710, 3080, 8 SMP VLTC 8-thread: https://tests.stockfishchess.org/tests/view/647b0fe354dd118e1d992425 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 61398 W: 17386 L: 17081 D: 26931 Elo +1.73 Ptnml(0-2): 7, 4571, 21232, 4888, 1 closes https://github.com/official-stockfish/Stockfish/pull/4603 Bench: 2805878 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 May 31 09:06:30 2023 +0200 Timestamp: 1685516790 Small simplification for probcut in check Remove depth condition from there as not longer needed. Passed STC: https://tests.stockfishchess.org/tests/view/647367cad29264e4cfa753e6 LLR: 2.96 (-2.94,2.94) <-1.75,0.25> Total: 254336 W: 67830 L: 67847 D: 118659 Elo -0.02 Ptnml(0-2): 580, 28181, 69697, 28096, 614 Passed LTC: https://tests.stockfishchess.org/tests/view/647576184a36543c4c9f3af7 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 80706 W: 22048 L: 21898 D: 36760 Elo +0.65 Ptnml(0-2): 28, 7721, 24712, 7857, 35 closes https://github.com/official-stockfish/Stockfish/pull/4594 bench 2381945 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: Wed May 31 08:54:38 2023 +0200 Timestamp: 1685516078 Simplify nnue eval complexity calculation Remove a multiplier when blending nnue complexity with semi-classical complexity. Passed non-regression STC: https://tests.stockfishchess.org/tests/view/6473a71dd29264e4cfa75839 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 124768 W: 33180 L: 33060 D: 58528 Elo +0.33 Ptnml(0-2): 314, 13797, 34030, 13941, 302 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/6474af3dd29264e4cfa768f4 LLR: 2.96 (-2.94,2.94) <-1.75,0.25> Total: 108180 W: 29008 L: 28884 D: 50288 Elo +0.40 Ptnml(0-2): 29, 10420, 33075, 10530, 36 closes https://github.com/official-stockfish/Stockfish/pull/4592 bench 2316827 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: Wed May 31 08:51:22 2023 +0200 Timestamp: 1685515882 Update NNUE architecture to SFNNv6 with larger L1 size of 1536 Created by training a new net from scratch with L1 size increased from 1024 to 1536. Thanks to Vizvezdenec for the idea of exploring larger net sizes after recent training data improvements. A new net was first trained with lambda 1.0 and constant LR 8.75e-4. Then a strong net from a later epoch in the training run was chosen for retraining with start-lambda 1.0 and initial LR 4.375e-4 decaying with gamma 0.995. Retraining was performed a total of 3 times, for this 4-step process: 1. 400 epochs, lambda 1.0 on filtered T77+T79 v6 deduplicated data 2. 800 epochs, end-lambda 0.75 on T60T70wIsRightFarseerT60T74T75T76.binpack 3. 800 epochs, end-lambda 0.75 and early-fen-skipping 28 on the master dataset 4. 800 epochs, end-lambda 0.7 and early-fen-skipping 28 on the master dataset In the training sequence that reached the new nn-8d69132723e2.nnue net, the epochs used for the 3x retraining runs were: 1. epoch 379 trained on T77T79-filter-v6-dd.min.binpack 2. epoch 679 trained on T60T70wIsRightFarseerT60T74T75T76.binpack 3. epoch 799 trained on the master dataset For training from scratch: python3 easy_train.py \ --experiment-name new-L1-1536-T77T79-filter-v6dd \ --training-dataset /data/T77T79-filter-v6-dd.min.binpack \ --max_epoch 400 \ --lambda 1.0 \ --start-from-engine-test-net False \ --engine-test-branch linrock/Stockfish/L1-1536 \ --nnue-pytorch-branch linrock/Stockfish/misc-fixes-L1-1536 \ --tui False \ --gpus "0," \ --seed $RANDOM Retraining commands were similar to each other. For the 3rd retraining run: python3 easy_train.py \ --experiment-name L1-1536-T77T79-v6dd-Re1-LeelaFarseer-Re2-masterDataset-Re3-sameData \ --training-dataset /data/leela96-dfrc99-v2-T60novdecT80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd.binpack \ --early-fen-skipping 28 \ --max_epoch 800 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --lr 4.375e-4 \ --gamma 0.995 \ --start-from-engine-test-net False \ --start-from-model /data/L1-1536-T77T79-v6dd-Re1-LeelaFarseer-Re2-masterDataset-nn-epoch799.nnue \ --engine-test-branch linrock/Stockfish/L1-1536 \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-1536 \ --tui False \ --gpus "0," \ --seed $RANDOM The T77+T79 data used is a subset of the master dataset available at: https://robotmoon.com/nnue-training-data/ T60T70wIsRightFarseerT60T74T75T76.binpack is available at: https://drive.google.com/drive/folders/1S9-ZiQa_3ApmjBtl2e8SyHxj4zG4V8gG Local elo at 25k nodes per move vs. nn-e1fb1ade4432.nnue (L1 size 1024): nn-epoch759.nnue : 26.9 +/- 1.6 Failed STC https://tests.stockfishchess.org/tests/view/64742485d29264e4cfa75f97 LLR: -2.94 (-2.94,2.94) <0.00,2.00> Total: 13728 W: 3588 L: 3829 D: 6311 Elo -6.10 Ptnml(0-2): 71, 1661, 3610, 1482, 40 Failing LTC https://tests.stockfishchess.org/tests/view/64752d7c4a36543c4c9f3618 LLR: -1.91 (-2.94,2.94) <0.50,2.50> Total: 35424 W: 9522 L: 9603 D: 16299 Elo -0.79 Ptnml(0-2): 24, 3579, 10585, 3502, 22 Passed VLTC 180+1.8 https://tests.stockfishchess.org/tests/view/64752df04a36543c4c9f3638 LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 47616 W: 13174 L: 12863 D: 21579 Elo +2.27 Ptnml(0-2): 13, 4261, 14952, 4566, 16 Passed VLTC SMP 60+0.6 th 8 https://tests.stockfishchess.org/tests/view/647446ced29264e4cfa761e5 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 19942 W: 5694 L: 5451 D: 8797 Elo +4.23 Ptnml(0-2): 6, 1504, 6707, 1749, 5 closes https://github.com/official-stockfish/Stockfish/pull/4593 bench 2222567 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: windfishballad
Date: Sun May 28 20:05:50 2023 +0200 Timestamp: 1685297150 Removed quadratic term in optimism Remove term which is quadratic in optimism in the eval. Simplifies and should also remove the bias towards side to move making the eval better for analysis. STC: https://tests.stockfishchess.org/tests/view/6470a9d8c29e0d4352b0bca5 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 154432 W: 41127 L: 41040 D: 72265 Elo +0.20 Ptnml(0-2): 380, 17094, 42190, 17163, 389 LTC: https://tests.stockfishchess.org/tests/view/6471e9b3e549d9cf2fb219ef LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 127926 W: 34474 L: 34369 D: 59083 Elo +0.29 Ptnml(0-2): 43, 12505, 38776, 12582, 57 closes https://github.com/official-stockfish/Stockfish/pull/4590 Bench: 2541211 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 May 28 20:03:33 2023 +0200 Timestamp: 1685297013 Update CPU contributors list update CPU contributors list, the previous update was a couple of months ago, and unfortunately, was not quite accurate for the number of games played. This version is based clean calculation from the DB and an updated script that tracks things (see https://github.com/glinscott/fishtest/pull/1702). closes https://github.com/official-stockfish/Stockfish/pull/4589 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: Thu May 25 20:49:11 2023 +0200 Timestamp: 1685040551 Remove ss->ttHit condition where ttValue != VALUE_NONE Simplification is done at 3 separate places in the code. Thanks to peregrineshahin for helping me find 2 of such places. (See original PR #4584) Passed non-regression test LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 120256 W: 32204 L: 32085 D: 55967 Elo +0.34 Ptnml(0-2): 292, 12473, 34483, 12584, 296 https://tests.stockfishchess.org/tests/view/646f045968661bfd984325e3 closes https://github.com/official-stockfish/Stockfish/pull/4587 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: Thu May 25 20:42:43 2023 +0200 Timestamp: 1685040163 Simplify Futility pruning for captures Passed STC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 412928 W: 109433 L: 109620 D: 193875 Elo -0.16 Ptnml(0-2): 1071, 45929, 112650, 45744, 1070 https://tests.stockfishchess.org/tests/view/6468eac40db5177f2b76ef4d Passed LTC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 190200 W: 51465 L: 51420 D: 87315 Elo +0.08 Ptnml(0-2): 58, 18585, 57788, 18592, 77 https://tests.stockfishchess.org/tests/view/646b66520db5177f2b772a84 closes https://github.com/official-stockfish/Stockfish/pull/4583 bench: 2486604 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: Thu May 25 20:40:09 2023 +0200 Timestamp: 1685040009 Simplify Prune moves with negative SEE Passed STC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 57760 W: 15472 L: 15286 D: 27002 Elo +1.12 Ptnml(0-2): 123, 6025, 16430, 6147, 155 https://tests.stockfishchess.org/tests/view/6468eb6b0db5177f2b76ef62 Passed LTC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 93966 W: 25274 L: 25141 D: 43551 Elo +0.49 Ptnml(0-2): 33, 8498, 29792, 8623, 37 https://tests.stockfishchess.org/tests/view/6469570b0db5177f2b76f81b closes: https://github.com/official-stockfish/Stockfish/pull/4579 Bench: 2304063 see source |