Skip to content

v3.2.0
Compare
Choose a tag to compare
@github-actions github-actions released this 05 Feb 10:01
· 314 commits to master since this release
v3.2.0
6a3c320

This release improves the neural network based evaluation

Estimated strength increase: ~ 130 Elo

Changes

  • Neural network trainer

    • fixed a bug which prevented successful training of networks with bigger hidden layers
    • added data compression support for trained network files

  • Neural network evaluation

    • increased hidden layer size from 64 to 256
    • implemented some optimizations:
      • defer updates and calculations until eval is called
      • remove additional hidden layers

Installation

The chess engine is available for Windows and Linux and requires a 64 Bit CPU.
There are optimized executables available for different CPU micro-architecture generations.

If you have a relatively modern CPU (2013+) with AVX2 support, then the ...-x86_64-avx2 executable is highly recommended for best performance.

Executable Description Min. CPU Generation Required Instruction Sets
x86_64-avx2 Recommended for best performance on a modern CPU Intel Haswell / Zen1 AVX2, BMI1
x86_64-sse4-popcnt Lower performance, recommended for CPUs without AVX2 support Intel Nehalem / AMD Bulldozer SSE4.2, SSE3, POPCNT
x86_64-nopopcnt Lowest performance, but compatible with most x86_64 CPUs --- SSE2, CMOV
Assets 9
Loading