Squashed commit of the following:

TierynnB · TierynnB · commit 49f321304ac1 · 2024-02-23T10:48:13.000+10:00
commit 524083a Merge: 8a0206f 4a5ba40 Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Fri Feb 23 08:42:30 2024 +1000 Merge branch 'TM_Change_2' of https://github.com/TierynnB/Stockfish into TM_Change_2 commit 8a0206f Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Mon Feb 19 07:13:26 2024 +1000 use current time instead of '1' for timeLeft formula. make timeLeft a double, timepoint seemed unecessary since it was always casting back to double anyway. fixed comments Squashed commits commit 4a5ba40 Merge: ce952bf 676a1d7 Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Fri Feb 23 08:01:21 2024 +1000 Merge branch 'TM_Change_2' of https://github.com/TierynnB/Stockfish into TM_Change_2 commit ce952bf Author: cj5716 <125858804+cj5716@users.noreply.github.com> Date: Tue Feb 13 17:46:37 2024 +0800 Simplify PV node reduction Reduce less on PV nodes even with an upperbound TT entry. Passed STC: https://tests.stockfishchess.org/tests/view/65cb3a861d8e83c78bfd0497 LLR: 2.96 (-2.94,2.94) <-1.75,0.25> Total: 118752 W: 30441 L: 30307 D: 58004 Ptnml(0-2): 476, 14179, 29921, 14335, 465 Passed LTC: https://tests.stockfishchess.org/tests/view/65cd3b951d8e83c78bfd2b0d LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 155058 W: 38549 L: 38464 D: 78045 Ptnml(0-2): 85, 17521, 42219, 17632, 72 closes official-stockfish#5057 Bench: 1303971 commit 4acf810 Author: Linmiao Xu <linmiao.xu@gmail.com> Date: Tue Feb 6 11:21:15 2024 -0500 Update default main net to nn-b1a57edbea57.nnue Created by retraining the previous main net `nn-baff1edbea57.nnue` with: - some of the same options as before: ranger21, more WDL skipping - the addition of T80 nov+dec 2023 data - increasing loss by 15% when prediction is too high, up from 10% - use of torch.compile to speed up training by over 25% ```yaml experiment-name: 2560--S9-514G-T80-augtodec2023-more-wdl-skip-15p-more-loss-high-q-sk28 training-dataset: # official-stockfish#4782 - /data/S6-514G-1ee1aba5ed.binpack - /data/test80-aug2023-2tb7p.v6.min.binpack - /data/test80-sep2023-2tb7p.binpack - /data/test80-oct2023-2tb7p.binpack - /data/test80-nov2023-2tb7p.binpack - /data/test80-dec2023-2tb7p.binpack early-fen-skipping: 28 start-from-engine-test-net: True nnue-pytorch-branch: linrock/nnue-pytorch/r21-more-wdl-skip-15p-more-loss-high-q-torch-compile num-epochs: 1000 lr: 4.375e-4 gamma: 0.995 start-lambda: 1.0 end-lambda: 0.7 ``` Epoch 819 trained with the above config led to this PR. Use of torch.compile decorators in nnue-pytorch model.py was found to speed up training by at least 25% on Ampere gpus when using recent pytorch compiled with cuda 12: https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch See recent main net PRs for more info on - ranger21 and more WDL skipping: official-stockfish#4942 - increasing loss when Q is too high: official-stockfish#4972 Training data can be found at: https://robotmoon.com/nnue-training-data/ Passed STC: https://tests.stockfishchess.org/tests/view/65cd76151d8e83c78bfd2f52 LLR: 2.98 (-2.94,2.94) <0.00,2.00> Total: 78336 W: 20504 L: 20115 D: 37717 Ptnml(0-2): 317, 9225, 19721, 9562, 343 Passed LTC: https://tests.stockfishchess.org/tests/view/65ce5be61d8e83c78bfd43e9 LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 41016 W: 10492 L: 10159 D: 20365 Ptnml(0-2): 22, 4533, 11071, 4854, 28 closes official-stockfish#5056 Bench: 1351997 commit 40c6cdf Author: cj5716 <125858804+cj5716@users.noreply.github.com> Date: Tue Feb 13 17:50:16 2024 +0800 Simplify TT PV reduction This also removes some incorrect fail-high logic. Passed STC: https://tests.stockfishchess.org/tests/view/65cb3b641d8e83c78bfd04a9 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 87968 W: 22634 L: 22468 D: 42866 Ptnml(0-2): 315, 10436, 22323, 10588, 322 Passed LTC: https://tests.stockfishchess.org/tests/view/65cccee21d8e83c78bfd222c LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 70794 W: 17846 L: 17672 D: 35276 Ptnml(0-2): 44, 7980, 19189, 8126, 58 closes official-stockfish#5055 Bench: 1474424 commit 9299d01 Author: Gahtan Nahdi <155860115+gahtan-syarif@users.noreply.github.com> Date: Sat Feb 10 03:51:05 2024 +0700 Remove penalty for quiet ttMove that fails low Passed STC non-reg: https://tests.stockfishchess.org/tests/view/65c691a7c865510db0286e6e LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 234336 W: 60258 L: 60255 D: 113823 Ptnml(0-2): 966, 28141, 58918, 28210, 933 Passed LTC non-reg: https://tests.stockfishchess.org/tests/view/65c8d0d31d8e83c78bfcd4a6 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 235206 W: 59134 L: 59132 D: 116940 Ptnml(0-2): 135, 26908, 63517, 26906, 137 official-stockfish#5054 Bench: 1287996 commit 676a1d7 Merge: 7d0cd7b 3c3f88b Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Fri Feb 23 07:58:38 2024 +1000 Merge branch 'TM_Change_2' of https://github.com/TierynnB/Stockfish into TM_Change_2 commit 7d0cd7b Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Mon Feb 19 07:13:26 2024 +1000 parent 8b67b7e author Tierynn Byrnes <t.byrnes47@gmail.com> 1708290806 +1000 committer Tierynn Byrnes <t.byrnes47@gmail.com> 1708638981 +1000 use current time instead of '1' for timeLeft formula. make timeLeft a double, timepoint seemed unecessary since it was always casting back to double anyway. commit 3c3f88b Merge: 76c50a0 61e8083 Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Fri Feb 23 07:54:46 2024 +1000 Merge branch 'TM_Change_2' of https://github.com/TierynnB/Stockfish into TM_Change_2 commit 76c50a0 Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Mon Feb 19 07:13:26 2024 +1000 use current time instead of '1' for timeLeft formula. make timeLeft a double, timepoint seemed unecessary since it was always casting back to double anyway. fixed comments commit 61e8083 Merge: 5cf3f49 8afec41 Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Thu Feb 22 19:44:21 2024 +1000 Merge branch 'TM_Change_2' of https://github.com/TierynnB/Stockfish into TM_Change_2 commit 5cf3f49 Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Mon Feb 19 07:13:26 2024 +1000 use current time instead of '1' for timeLeft formula. make timeLeft a double, timepoint seemed unecessary since it was always casting back to double anyway. commit 8afec41 Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Mon Feb 19 07:50:30 2024 +1000 fixed comments commit de4a3c4 Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Mon Feb 19 07:32:09 2024 +1000 make timeLeft a double, timepoint seemed unecessary since it was always casting back to double anyway. commit e1f6b87 Merge: 8b67b7e fc41f64 Author: Lemmy <10430540+TierynnB@users.noreply.github.com> Date: Mon Feb 19 07:14:27 2024 +1000 Merge branch 'official-stockfish:master' into TM_Change_2 commit 8b67b7e Author: Tierynn Byrnes <t.byrnes47@gmail.com> Date: Mon Feb 19 07:13:26 2024 +1000 use current time instead of '1' for timeLeft formula.
diff --git a/src/timeman.cpp b/src/timeman.cpp
@@ -81,15 +81,22 @@ void TimeManagement::init(Search::LimitsType& limits,
         limits.npmsec = npmsec;
     }
 
-    // Maximum move horizon of 50 moves
+    // Maximum and default move horizon of 50 moves
     int mtg = limits.movestogo ? std::min(limits.movestogo, 50) : 50;
 
-    // Make sure timeLeft is > 0 since we may use it as a divisor
-    TimePoint timeLeft = std::max(TimePoint(1), limits.time[us] + limits.inc[us] * (mtg - 1)
-                                                  - moveOverhead * (2 + mtg));
+    // Make sure timeLeft is > 0 since we use it as a divisor
+    double timeLeft =
+      std::max(limits.time[us], limits.time[us] + limits.inc[us] * (mtg - 1) - moveOverhead * mtg);
+
+    // Use extra time with larger increments
+    double optExtra = std::clamp(1.0 + 12.5 * limits.inc[us] / limits.time[us], 1.0, 1.11);
+
+    // Calculate time constants based on current time left.
+    double optConstant = std::min(0.00334 + 0.0003 * std::log10(limits.time[us] / 1000.0), 0.0049);
+    double maxConstant = std::max(3.4 + 3.0 * std::log10(limits.time[us] / 1000.0), 2.76);
 
     // x basetime (+ z increment)
-    // If there is a healthy increment, timeLeft can exceed actual available
+    // If there is a healthy increment and low mtg, timeLeft can exceed actual available
     // game time for the current move, so also cap to 20% of available game time.
     if (limits.movestogo == 0)
     {
@@ -102,15 +109,15 @@ void TimeManagement::init(Search::LimitsType& limits,
         double maxConstant = std::max(3.4 + 3.0 * std::log10(limits.time[us] / 1000.0), 2.76);
 
         optScale = std::min(0.0120 + std::pow(ply + 3.1, 0.44) * optConstant,
-                            0.21 * limits.time[us] / double(timeLeft))
+                            0.21 * limits.time[us] / timeLeft)
                  * optExtra;
         maxScale = std::min(6.9, maxConstant + ply / 12.2);
     }
 
     // x moves in y seconds (+ z increment)
     else
     {
-        optScale = std::min((0.88 + ply / 116.4) / mtg, 0.88 * limits.time[us] / double(timeLeft));
+        optScale = std::min((0.88 + ply / 116.4) / mtg, 0.88 * limits.time[us] / timeLeft);
         maxScale = std::min(6.3, 1.5 + 0.11 * mtg);
     }
 
