Your approach has indeed been done for several decades.
It works at first, but then it becomes clearer that tuning for a test set is not the same as actual game strength.
Recall the early focus on WAC 300 scores...
Search found 480 matches
- Thu Dec 10, 2020 4:50 pm
- Forum: Computer Chess Club: General Topics
- Topic: A different way to develop chess engines
- Replies: 7
- Views: 937
- Mon Dec 07, 2020 10:03 pm
- Forum: Computer Chess Club: General Topics
- Topic: Another Lc0 problem
- Replies: 6
- Views: 671
Re: Another Lc0 problem
Works just fine for me from a cmd window...
- Thu Nov 26, 2020 10:14 pm
- Forum: Computer Chess Club: Programming and Technical Discussions
- Topic: On-line engine blitz tourney November
- Replies: 56
- Views: 7296
Re: On-line engine blitz tourney November
Thanks, I have not tried that one yet.
- Thu Nov 26, 2020 7:07 pm
- Forum: Computer Chess Club: Programming and Technical Discussions
- Topic: On-line engine blitz tourney November
- Replies: 56
- Views: 7296
Re: On-line engine blitz tourney November
Is there a tourney manager that uses the higher precision timers?
- Thu Nov 26, 2020 10:31 am
- Forum: Computer Chess Club: Programming and Technical Discussions
- Topic: On-line engine blitz tourney November
- Replies: 56
- Views: 7296
Re: On-line engine blitz tourney November
I would be surprised if most engines would benefit from more accurate (i.e. msec) specification of the time on their clocks. The clocks they use for their own timing decisions typically also ticks only once every 16 msec. And scheduling delays would become very important at the msec level. You shou...
- Thu Nov 26, 2020 7:58 am
- Forum: Computer Chess Club: Programming and Technical Discussions
- Topic: On-line engine blitz tourney November
- Replies: 56
- Views: 7296
Re: On-line engine blitz tourney November
True. UCI wouldn't have this issue, but the Winboard side is CECP only. However, it doesn't make much sense to use a GUI for such fast games because the display will cost a disproportionate amount of time. It would make more sense to use a CLI solution. You may not know that Winboard has a no GUI o...
- Fri Nov 13, 2020 6:46 pm
- Forum: Computer Chess Club: General Topics
- Topic: CPU NN question
- Replies: 12
- Views: 1689
Re: CPU NN question
There are many different NN sizes and architectures.
The larger ones like Lc0 uses are only really practical on GPUs.
The smaller ones like SF-NNUE run on CPUs (and are very cleverly incrementally updated to make even faster).
The larger ones like Lc0 uses are only really practical on GPUs.
The smaller ones like SF-NNUE run on CPUs (and are very cleverly incrementally updated to make even faster).
- Thu Nov 05, 2020 11:23 am
- Forum: Computer Chess Club: General Topics
- Topic: What is the magical incantation to make LC0 use both?
- Replies: 12
- Views: 1082
Re: What is the magical incantation to make LC0 use both?
This was just posted on the Discord: TilpsToday at 6:09 AM !2gpus Little TeapotBOTToday at 6:09 AM To run Lc0 on 2 GPUs: Specify the following UCI parameters: Backend: multiplexing BackendOpts: backend=cudnn-fp16,(gpu=0),(gpu=1) Threads: 3 OR add the following in command line: --backend=multiplexing...
- Tue Oct 20, 2020 2:30 pm
- Forum: Computer Chess Club: General Topics
- Topic: New AMD Zen 3 and Ryzen processors
- Replies: 34
- Views: 5541
Re: New AMD Zen 3 and Ryzen processors
I also have an old i920 that I was able to comfortably overclock to 4GHz (from 2.6GHz). Over the years I added more RAM, SSD, faster GPU (GTX770 to 1070 to 2060), etc. It was fine for most things. My even older Q6600 (also easily OC'd, but so old no popcnt) would get the "hand me down" components fr...
- Sun Oct 11, 2020 9:52 pm
- Forum: Computer Chess Club: General Topics
- Topic: Interrupting Cutechess-Cli with CTRL+C yields to unpredictable results.
- Replies: 10
- Views: 1009
Re: Interrupting Cutechess-Cli with CTRL+C yields to unpredictable results.
I am only using a few of the 7 piece: Volume in drive E has no label. Volume Serial Number is 9449-A788 Directory of E:\Syzygy-7 10/11/2020 05:50 PM <DIR> . 10/11/2020 05:50 PM <DIR> .. 10/11/2020 05:50 PM 0 7.txt 06/16/2020 01:33 AM 30,746,474,768 KBPPvKBP.rtbw 06/16/2020 01:55 AM 5,561,195,536 KBP...