Since you’re here...

We hope you will consider supporting us today. We need your support to continue to exist, because good entries are more and more work time. Every reader contribution, however big or small, is so valuable. Support "Chess Engines Diary" even a small amount– and it only takes a minute. Thank you.
============================== My email: jotes@go2.pl



Chess engine: PlentyChess 3.0.1

on

 


PlentyChess - A UCI chess engine with a neural network based evaluation.
Rating Chess Engines Diary CEDR=3711

Building on Windows

For the build to work on Windows, you need to install MinGW as well as the required packages (make, g++, pthread, etc.).
Then you can use the makefile as you would on a unix system.

v.3.0.1:
This release contains bugfixes concerning the ucinewgame command for ChessBase and Fritz GUIs.
It is otherwise identical to version 3.0.0.

v.3.0.0:
This release is a huge milestone for PlentyChess. Previous versions used Lc0 data for training the networks, but the data used from this point forth is completely self-generated, with no connection to the previous networks.

Trained on 7.2 billion positions, the network in this release is estimated to be about 15 elo weaker than the Lc0 data network used up to version 2.1.0, but the much improved architecture and many many other improvements make this the strongest version of PlentyChess ever.

Performance vs. PlentyChess 2.0.0
All progression tests are run against PlentyChess 2.0.0, which is about 30 elo weaker than version 2.1.0.

STC
Elo   | 64.19 +- 2.64 (95%)
Conf  | 8.0+0.08s Threads=1 Hash=16MB
Games | N: 20020 W: 7075 L: 3418 D: 9527
Penta | [30, 1181, 4280, 4140, 379]
https://chess.aronpetkovski.com/test/6119/

LTC
Elo   | 55.93 +- 3.42 (95%)
Conf  | 40.0+0.40s Threads=1 Hash=64MB
Games | N: 10000 W: 3340 L: 1744 D: 4916
Penta | [4, 566, 2334, 2022, 74]
https://chess.aronpetkovski.com/test/6122/

DFRC
Elo   | 62.88 +- 6.66 (95%)
Conf  | 8.0+0.08s Threads=1 Hash=16MB
Games | N: 5016 W: 1827 L: 929 D: 2260
Penta | [62, 381, 925, 877, 263]
https://chess.aronpetkovski.com/test/6120/
Binary Guide
generic: Slowest
ssse3: Slightly faster, requires a CPU with SSSE3 support
fma: Faster, requires a CPU with FMA support
avx2: Faster, requires a CPU with AVX2 support
bmi2: Faster, requires a CPU with AVX2 and BMI2 support. Not recommended for Zen1 and Zen2 CPUs
avx512: Faster, requires a CPU with AVX512 support
avx512vnni: Fastest, requires a CPU with AVX512 and VNNI support
If you're unsure about what binary to use, start with avx512vnni and find the first one that does not crash on your machine. There is a chance that the AVX2 binary is faster on your system, despite it supporting AVX512.


Comments

Post a Comment