mirror of
https://github.com/sockspls/badfish
synced 2025-07-13 04:29:15 +00:00
f193778446
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 Ptnml(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 Ptnml(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 |
||
|---|---|---|
| .. | ||
| incbin | ||
| nnue | ||
| syzygy | ||
| benchmark.cpp | ||
| bitbase.cpp | ||
| bitboard.cpp | ||
| bitboard.h | ||
| endgame.cpp | ||
| endgame.h | ||
| evaluate.cpp | ||
| evaluate.h | ||
| main.cpp | ||
| Makefile | ||
| material.cpp | ||
| material.h | ||
| misc.cpp | ||
| misc.h | ||
| movegen.cpp | ||
| movegen.h | ||
| movepick.cpp | ||
| movepick.h | ||
| pawns.cpp | ||
| pawns.h | ||
| position.cpp | ||
| position.h | ||
| psqt.cpp | ||
| psqt.h | ||
| search.cpp | ||
| search.h | ||
| thread.cpp | ||
| thread.h | ||
| thread_win32_osx.h | ||
| timeman.cpp | ||
| timeman.h | ||
| tt.cpp | ||
| tt.h | ||
| tune.cpp | ||
| tune.h | ||
| types.h | ||
| uci.cpp | ||
| uci.h | ||
| ucioption.cpp | ||