Skip to content

@mooskagh mooskagh released this Jun 9, 2019 · 12 commits to master since this release

Changes since v0.21.2-rc3

  • Centipawn formula retweaked to show 128.00 instead of 127.99 pawns for checkmate.

Since v0.21.1

Highlights:

  • --sticky-engames (minimal version of certainty propagation)
  • New centipawn formula
  • Way to exit training gracefully
  • Optimizations for GTX 16xx videocards (cudnn-fp16 works now)
  • Optimizations for larger filter sizes
Assets 5
Pre-release

@mooskagh mooskagh released this Jun 8, 2019 · 12 commits to master since this release

The only change from RC2 is a centipawn formula:

centipawn = 295 * Q / (1 - 0.976953125 * Q^14)
Assets 5
Pre-release

@mooskagh mooskagh released this May 22, 2019 · 12 commits to master since this release

Changes

  • Add 320 and 352 channel support for fused SE layer (#855)
  • SE layer fix when not using fused kernel (#852)
  • Fp16 nchw for cudnn-fp16 backend (support GTX 16xx GPUs) (#849)
  • Install lc0 on openSUSE - Full documentation, Install script and links to experimental RPM packages (#675)
Assets 5
Pre-release

@mooskagh mooskagh released this May 5, 2019 · 16 commits to master since this release

  • Make --sticky-endgames on by default (still off in training) (#844)
  • update download links in README (#842)
  • Recalibrate centipawn formula (#841)
  • Also make parents Terminal if any move is a win or all moves are loss or draw. (#822)
  • Use parent Q as a default score instead of 0 for unvisited pv. (#828)
  • Add stop command to selfplay interactive mode to allow for graceful exit. (#810)
  • Increased hard limit on batch size in opencl backend to 32 (#807)
Assets 5

@Tilps Tilps released this Mar 23, 2019 · 20 commits to release/0.21 since this release

  • FPU can now be independently controlled at root vs in general using the new AtRoot variants. Default value for StrategyAtRoot is 'same' which means it uses the values from the normal parameters. The reduction parameter has been removed - strategy reduction now uses the value parameter as the reduction amount. NOTE: If you are using a UCI host that remembers settings over restarts (like cutechess) be careful to ensure that when upgrading to this new version you reset settings back to defaults - or you may get a bad combination of fpu settings.
  • TempVisitOffset option now allows you to specify values less than -1, and its documentation has been fixed.
  • A small performance improvement in movegen.
  • Windows packages should include v22 of the Client.
Assets 5

@Tilps Tilps released this Mar 8, 2019 · 28 commits to release/0.21 since this release

  • Change version number to indicate final. No other changes since v0.21.0-rc2.
Assets 5
Pre-release

@Tilps Tilps released this Mar 6, 2019 · 29 commits to release/0.21 since this release

  • Add support for cudnn7.0 (#717)
  • Informative Tournament Stats (#698)
  • Memory leak fix cuda backend (#747)
  • cudnn-fp16 fallback path for unusual se-ratios. (#739)
  • Cudnn 7.4.2 in packaged binary and warning for using old cudnn with new gpu (#741)
  • Move mode specific options to end of help. (#745)
  • LogLiveStats hidden option (#754)
  • Optional markdown support for help output (#769)
  • Improved folding of batch norm into weights and biases - fixes negative gamma bug. (#779)
Assets 5
Pre-release
Pre-release

@Tilps Tilps released this Feb 16, 2019 · 44 commits to release/0.21 since this release

Major new features in this release are support for WDL value head, and convolution direct output (AZ-style) policy head.

  • Check Syzygy tablebase file sizes for corruption (#690)
  • search for nvcc on the path first (#709)
  • AZ-style policy head support (#712)
  • Implement V4TrainingData (#722)
  • WDL value head support (#635)
  • Add option for doing kldgain thresholding rather than absolute visit limiting (#721)
  • Easily run latest releases of lc0 and client using NVIDIA docker (#621)
  • Add WDL style resign option. (#724)
  • Add a uniform output option for random backend to support a0 seed data style (#725)
  • Fix c hw switching in cudnn-fp16 mode with convolution policy head. (#729)
  • misc (non-functional) changes to cudnn backend (#731)
  • handle 64 filter SE networks (#624)
Assets 5

@mooskagh mooskagh released this Feb 1, 2019 · 54 commits to master since this release

Changes

(relative to v0.20.2-rc1)

  • Favor winning moves that minimize DTZ to reduce shuffling by assuming repeated position by default (#708)
  • Print cuda and gpu info, warn if mismatches are noticed (#711)
Assets 5
Pre-release

@mooskagh mooskagh released this Jan 27, 2019 · 56 commits to master since this release

Changes

  • no terminal multivisits (#683)
  • better fix for issue 651 (#693)
  • Changed output of --help flag to stdout rather than stderr (#687)
  • Movegen speedup via magic bitboards (#640)
  • modify default benchmark setting to run for 10 seconds (#681)
  • Fix incorrect index in OpenCL Winograd output transform (#676)
  • Update OpenCL (#655)
Assets 5
You can’t perform that action at this time.