!! latest version !!Windows x64 for Haswell CPUsWindows x64 for modern computers + AVX2Windows x64 for modern computersWindows x64 + SSSE3Windows x64Windows 32Linux x64 for Haswell CPUsLinux x64 for modern computers + AVX2Linux x64 for modern computersLinux x64 + SSSE3Linux x64Author: Stéphane Nicolet
Date: Thu May 27 01:21:56 2021 +0200
Timestamp: 1622071316
Do not use lazy evaluation inside NNUE
This simplification patch implements two changes:
1. it simplifies away the so-called "lazy" path in the NNUE evaluation internals,
where we trusted the psqt head alone to avoid the costly "positional" head in
some cases;
2. it raises a little bit the NNUEThreshold1 in evaluate.cpp (from 682 to 800),
which increases the limit where we switched from NNUE eval to Classical eval.
Both effects increase the number of positional evaluations done by our new net
architecture, but the results of our tests below seem to indicate that the loss
of speed will be compensated by the gain of eval quality.
STC:
LLR: 2.95 (-2.94,2.94) <-2.50,0.50>
Total: 26280 W: 2244 L: 2137 D: 21899
Elo +1.41Ptnml(0-2): 72, 1755, 9405, 1810, 98
https://tests.stockfishchess.org/tests/view/60ae73f112066fd299795a51 LTC:
LLR: 2.95 (-2.94,2.94) <-2.50,0.50>
Total: 20592 W: 750 L: 677 D: 19165
Elo +1.23Ptnml(0-2): 9, 614, 8980, 681, 12
https://tests.stockfishchess.org/tests/view/60ae88e812066fd299795a82 closes
https://github.com/official-stockfish/Stockfish/pull/3503 Bench: 3817907
see source