lc0-win-20180512-cuda90-cudnn712-00

[Albert Silver]

Then he should follow my step-by-manual:


How to run Leela CUDA (should be around 4x faster, than Leela GPU(!)) in Fritz/Shredder GUI:

Important: Leela CUDA needs 3 .dll-files from the NVIDIA-developer-website, otherwise it can not run!
And - of course - you need a NVIDIA CUDA GPU in your PC...

1) Update your Nvidia driver for your GPU to the latest version here: http://www.nvidia.de/Download/index.aspx
After that: reboot your PC.
2) Get LC0.exe for the cuDNN version from: https://crem.xyz/lc0/ and unpack it and put it in your Leela CUDA folder.
3) Install CUDA v9.2 from https://developer.nvidia.com/cuda-92-download-archive (you need an account) and get cublas64_92.dll and cudart64_92.dll from the bin directory of CUDA v9.2 and copy it to your Leela CUDA-folder (Alternatively if you don't want to install CUDA, you can just unpack the installer and search in the unpacked folder and files for the .dlls with <Strg>+F in the Windows-Explorer, that was, what I did). Put the 2 files in your Leela CUDA-folder.
4) Get cuDNN for CUDA 9.2 from https://developer.nvidia.com/rdp/cudnn-download (you also need an account for this) and get cudnn64_7.dll from the bin directory of the zip and extract it and put it in your Leela CUDA-folder.
5) Download the latest network from http://lczero.org/networks and unpack it (Leela CUDA will autodetect it in any form either as weights.txt or however it is named) and put it in your Leela CUDA-folder.
6) Create the UCI-Engine in Fritz/Shredder.

Done.

7) I strongly recommend to change the UCI-settings of Leela CUDA to this:

Scale thinking time = 2.500000
FPU reduction = -0.068300
Cpuct MCTS = 3.168000

Why these values? Because FPU reduction and Cpuct were optimized with the CLOP-tool to these values.
And raising Scale thinking time to 2.5 makes Leela moving slower, which means a better use of the game-time.
In my testing, Leela plays definitly stronger with this settings.

Thank you so much for your time and help.
Unfortunately I still don’t see any nps improvement.
Also the engine seems a little buggi as when analyzing the depth seems to be at around 1 or 2 instead of I.e. 23

How about analyzing it for one minute on the opening position and pasting her the entire output?

[Lion]

Sure,

How do I copy/paste the output?

Rgds

[Albert Silver]

Sure,

How do I copy/paste the output?

Rgds

Depends on the interface, but as a rule, right-click on the analysis and choose the option that applies. You can paste in Notepad as test.

[Lion]

Sure,

How do I copy/paste the output?

Rgds

Depends on the interface, but as a rule, right-click on the analysis and choose the option that applies. You can paste in Notepad as test.

So here you go

641: lczero v0.10 - Stockfish 9 64 POPCNT Line, LC0_fast, Rapid 15m+2s-1 2018
rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1

Analysis by The Lc0 chess engine._DBtest:

1.d4 Nf6 2.c4 e6 3.Nf3 d5 4.cxd5 exd5 5.Nc3 Bf5 6.Bf4 Bd6 7.Bxd6 Qxd6 8.e3 Nbd7 9.Nb5 Qb6 10.Qc1 Rc8 11.Be2 0-0
The position is equal: = (0.13) Depth: 2/37 00:00:35 28kN
(Bouddha, Bouddha 27.05.2018)

[Werewolf]

Then he should follow my step-by-manual:

7) I strongly recommend to change the UCI-settings of Leela CUDA to this:

Scale thinking time = 2.500000
FPU reduction = -0.068300
Cpuct MCTS = 3.168000

Why these values? Because FPU reduction and Cpuct were optimized with the CLOP-tool to these values.
And raising Scale thinking time to 2.5 makes Leela moving slower, which means a better use of the game-time.
In my testing, Leela plays definitly stronger with this settings.

How does one change these values?

Which file needs to be edited?

Thanks.

EDIT: I've got it working in Aquarium and changed the values you mention. I cannot see how to do it Arena as it doesn't show detailed options. But Aquarium will do