Commit Graph
3 Commits
Author SHA1 Message Date
Daniel MonroeandDisservin c76c179361 Remove non-functional std::min()
closes https://github.com/official-stockfish/Stockfish/pull/5749

No functional change
2025-01-06 00:48:05 +01:00
Daniel MonroeandJoost VandeVondele 91ec31dac4 Grade countermove bonus for low statscores
Passed STC:
LLR: 2.96 (-2.94,2.94) <0.00,2.00>
Total: 338592 W: 88396 L: 87627 D: 162569
Ptnml(0-2): 1161, 40201, 85788, 41000, 1146
https://tests.stockfishchess.org/tests/view/6679d40c0c2db3fa2dcecbcc

Passed LTC:
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 83526 W: 21429 L: 21010 D: 41087
Ptnml(0-2): 54, 9173, 22913, 9546, 77
https://tests.stockfishchess.org/tests/view/667c5f2980450dba965911fc

closes https://github.com/official-stockfish/Stockfish/pull/5418

bench: 1489815
2024-07-01 19:53:45 +02:00
Daniel MonroeandJoost VandeVondele ef94f77f8c Update default net to nn-a3d1bfca1672.nnue
faster permutation of master net weights

Activation data taken from https://drive.google.com/drive/folders/1Ec9YuuRx4N03GPnVPoQOW70eucOKngQe?usp=sharing
Permutation found using https://github.com/Ergodice/nnue-pytorch/blob/836387a0e5e690431d404158c46648710f13904d/ftperm.py
See also https://github.com/glinscott/nnue-pytorch/pull/254

The algorithm greedily selects 2- and 3-cycles that can be permuted to increase the number of runs of zeroes. The percent of zero runs from the master net increased from 68.46 to 70.11 from 2-cycles and only increased to 70.32 when considering 3-cycles. Interestingly, allowing both halves of L1 to intermix when creating zero runs can give another 0.5% zero-run density increase with this method.

Measured speedup:

```
CPU: 16 x AMD Ryzen 9 3950X 16-Core Processor
Result of 50 runs

base (./stockfish.master ) = 1561556 +/- 5439
test (./stockfish.patch ) = 1575788 +/- 5427
diff = +14231 +/- 2636

speedup = +0.0091
P(speedup > 0) = 1.0000
```

closes https://github.com/official-stockfish/Stockfish/pull/4640

No functional change
2023-07-01 12:59:28 +02:00