mirror of
https://github.com/HChaZZY/Stockfish.git
synced 2025-12-25 11:36:51 +08:00
Add NNUE evaluation
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish. Both the NNUE and the classical evaluations are available, and can be used to assign a value to a position that is later used in alpha-beta (PVS) search to find the best move. The classical evaluation computes this value as a function of various chess concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation computes this value with a neural network based on basic inputs. The network is optimized and trained on the evalutions of millions of positions at moderate search depth. The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward. It can be evaluated efficiently on CPUs, and exploits the fact that only parts of the neural network need to be updated after a typical chess move. [The nodchip repository](https://github.com/nodchip/Stockfish) provides additional tools to train and develop the NNUE networks. This patch is the result of contributions of various authors, from various communities, including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather, rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler, dorzechowski, and vondele. This new evaluation needed various changes to fishtest and the corresponding infrastructure, for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged. The first networks have been provided by gekkehenker and sergiovieri, with the latter net (nn-97f742aaefcd.nnue) being the current default. The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option, provided the `EvalFile` option points the the network file (depending on the GUI, with full path). The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest: 60000 @ 10+0.1 th 1 https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c ELO: 92.77 +-2.1 (95%) LOS: 100.0% Total: 60000 W: 24193 L: 8543 D: 27264 Ptnml(0-2): 609, 3850, 9708, 10948, 4885 40000 @ 20+0.2 th 8 https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58 ELO: 89.47 +-2.0 (95%) LOS: 100.0% Total: 40000 W: 12756 L: 2677 D: 24567 Ptnml(0-2): 74, 1583, 8550, 7776, 2017 At the same time, the impact on the classical evaluation remains minimal, causing no significant regression: sprt @ 10+0.1 th 1 https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b LLR: 2.94 (-2.94,2.94) {-6.00,-4.00} Total: 34936 W: 6502 L: 6825 D: 21609 Ptnml(0-2): 571, 4082, 8434, 3861, 520 sprt @ 60+0.6 th 1 https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d LLR: 2.93 (-2.94,2.94) {-6.00,-4.00} Total: 10088 W: 1232 L: 1265 D: 7591 Ptnml(0-2): 49, 914, 3170, 843, 68 The needed networks can be found at https://tests.stockfishchess.org/nns It is recommended to use the default one as indicated by the `EvalFile` UCI option. Guidelines for testing new nets can be found at https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests Integration has been discussed in various issues: https://github.com/official-stockfish/Stockfish/issues/2823 https://github.com/official-stockfish/Stockfish/issues/2728 The integration branch will be closed after the merge: https://github.com/official-stockfish/Stockfish/pull/2825 https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip closes https://github.com/official-stockfish/Stockfish/pull/2912 This will be an exciting time for computer chess, looking forward to seeing the evolution of this approach. Bench: 4746616
This commit is contained in:
nodchip
committed by
Joost VandeVondele
Joost VandeVondele
parent
9587eeeb5e
commit
84f3e86790
62
src/misc.cpp
62
src/misc.cpp
@@ -1,8 +1,6 @@
|
||||
/*
|
||||
Stockfish, a UCI chess playing engine derived from Glaurung 2.1
|
||||
Copyright (C) 2004-2008 Tord Romstad (Glaurung author)
|
||||
Copyright (C) 2008-2015 Marco Costalba, Joona Kiiski, Tord Romstad
|
||||
Copyright (C) 2015-2020 Marco Costalba, Joona Kiiski, Gary Linscott, Tord Romstad
|
||||
Copyright (C) 2004-2020 The Stockfish developers (see AUTHORS file)
|
||||
|
||||
Stockfish is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
@@ -46,6 +44,7 @@ typedef bool(*fun3_t)(HANDLE, CONST GROUP_AFFINITY*, PGROUP_AFFINITY);
|
||||
#include <iostream>
|
||||
#include <sstream>
|
||||
#include <vector>
|
||||
#include <cstdlib>
|
||||
|
||||
#if defined(__linux__) && !defined(__ANDROID__)
|
||||
#include <stdlib.h>
|
||||
@@ -147,10 +146,8 @@ const string engine_info(bool to_uci) {
|
||||
ss << setw(2) << day << setw(2) << (1 + months.find(month) / 4) << year.substr(2);
|
||||
}
|
||||
|
||||
ss << (Is64Bit ? " 64" : "")
|
||||
<< (HasPext ? " BMI2" : (HasPopCnt ? " POPCNT" : ""))
|
||||
<< (to_uci ? "\nid author ": " by ")
|
||||
<< "T. Romstad, M. Costalba, J. Kiiski, G. Linscott";
|
||||
ss << (to_uci ? "\nid author ": " by ")
|
||||
<< "the Stockfish developers (see AUTHORS file)";
|
||||
|
||||
return ss.str();
|
||||
}
|
||||
@@ -215,7 +212,33 @@ const std::string compiler_info() {
|
||||
compiler += " on unknown system";
|
||||
#endif
|
||||
|
||||
compiler += "\n __VERSION__ macro expands to: ";
|
||||
compiler += "\nCompilation settings include: ";
|
||||
compiler += (Is64Bit ? " 64bit" : " 32bit");
|
||||
#if defined(USE_AVX512)
|
||||
compiler += " AVX512";
|
||||
#endif
|
||||
#if defined(USE_AVX2)
|
||||
compiler += " AVX2";
|
||||
#endif
|
||||
#if defined(USE_SSE42)
|
||||
compiler += " SSE42";
|
||||
#endif
|
||||
#if defined(USE_SSE41)
|
||||
compiler += " SSE41";
|
||||
#endif
|
||||
#if defined(USE_SSSE3)
|
||||
compiler += " SSSE3";
|
||||
#endif
|
||||
#if defined(USE_SSE3)
|
||||
compiler += " SSE3";
|
||||
#endif
|
||||
compiler += (HasPext ? " BMI2" : "");
|
||||
compiler += (HasPopCnt ? " POPCNT" : "");
|
||||
#if !defined(NDEBUG)
|
||||
compiler += " DEBUG";
|
||||
#endif
|
||||
|
||||
compiler += "\n__VERSION__ macro expands to: ";
|
||||
#ifdef __VERSION__
|
||||
compiler += __VERSION__;
|
||||
#else
|
||||
@@ -293,6 +316,29 @@ void prefetch(void* addr) {
|
||||
|
||||
#endif
|
||||
|
||||
/// Wrappers for systems where the c++17 implementation doesn't guarantee the availability of aligned_alloc.
|
||||
/// Memory allocated with std_aligned_alloc must be freed with std_aligned_free.
|
||||
///
|
||||
|
||||
void* std_aligned_alloc(size_t alignment, size_t size) {
|
||||
#if defined(__APPLE__)
|
||||
return aligned_alloc(alignment, size);
|
||||
#elif defined(_WIN32)
|
||||
return _mm_malloc(size, alignment);
|
||||
#else
|
||||
return std::aligned_alloc(alignment, size);
|
||||
#endif
|
||||
}
|
||||
|
||||
void std_aligned_free(void* ptr) {
|
||||
#if defined(__APPLE__)
|
||||
free(ptr);
|
||||
#elif defined(_WIN32)
|
||||
_mm_free(ptr);
|
||||
#else
|
||||
free(ptr);
|
||||
#endif
|
||||
}
|
||||
|
||||
/// aligned_ttmem_alloc() will return suitably aligned memory, and if possible use large pages.
|
||||
/// The returned pointer is the aligned one, while the mem argument is the one that needs
|
||||
|
||||
Reference in New Issue
Block a user