Long thinking-time testrun of LC0 CUDA v0.16.0 Net 512 finished. A huge step forward (+34 Elo (!)) to the testrun before. But it is the first result with my parameter-change of the really awful time-management of LC0 (I changed "Scale thinking time" from 1.95 to 1.55). This improves the time-management a lot and should give a measureable Elo-gain. So it is not clear, how much Elo-gain the Net 512 has given...
The problem is, that the thinking-time ratio in my testruns (12'+5'' = 720''+5'' = 144:1) is very close to the TCEC ratio (30'+10'' = 1800''+10'' = 180:1). So, if the default setting of Leelas awful time-management will stay as it is now, a lot of Elo will be lost in TCEC!
http://www.sp-cc.de
(Perhaps you have to clear your browsercache or reload the website)
In the CEGT-ratinglist, LC0 would have passed Gull 3 (Elo 3078) with her performance in my latest testrun (Elo 3087) and would have climbed to position #11: http://www.cegt.net/40_40%20Rating%20Li ... liste.html
SPCC: Testrun of LC Zero Net 512 finished
Moderators: hgm, Rebel, chrisw
-
- Posts: 2435
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
-
- Posts: 358
- Joined: Thu Jan 22, 2015 3:21 pm
- Location: Zurich, Switzerland
- Full name: Jonathan Rosenthal
Re: SPCC: Testrun of LC Zero Net 512 finished
LC0 is certainly very strong, but is it not misleading to claim it is number 11 on a single core rating list when you let it use a GPU? I understand letting it use a GPU, but then the other engines shouldn't be restricted to a single core for a comparison. Think about it, essentially you are restricting the other engines to technology which was available 15 years ago (2Ghz single core) but are letting LC0 use a GPU.
-Jonathan
-
- Posts: 2435
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
Re: SPCC: Testrun of LC Zero Net 512 finished
First of all, my notebookCPU has 2.6 GHz, not 2. And the GPU is a mobileGPU GTX 950M, which is much slower than a normal, modern GPU (gtx 1070 or 1080). The Leela-Ratio on my machine is 1.37, which is pretty close to the Google AlphaZero vs. Stockfish match.
But it is definitly very hard to compare Leela on a GPU with normal engines. That is a real problem.
But it is definitly very hard to compare Leela on a GPU with normal engines. That is a real problem.
-
- Posts: 2283
- Joined: Sat Jun 02, 2012 2:13 am
Re: SPCC: Testrun of LC Zero Net 512 finished
A GPU standard could be useful for testers, in the same way of 1CPU, 4CPU, etc.
What is the most common GPU available at a reasonable price?
Maybe the community can agree on a common-denominator GPU for testing Leela-like entities ?!
What is the most common GPU available at a reasonable price?
Maybe the community can agree on a common-denominator GPU for testing Leela-like entities ?!
-
- Posts: 2435
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
Re: SPCC: Testrun of LC Zero Net 512 finished
The Leela-Ratio is a good possibility to measure the GPU/CPU(-cores) speed relationship on a machine.
https://blog.lczero.org/2018/07/04/leela-ratio
A value in the range 0.5 to 1.5 seems quite “fair“, when testing Leela against “normal“-CPU-Engines, I believe.
https://blog.lczero.org/2018/07/04/leela-ratio
A value in the range 0.5 to 1.5 seems quite “fair“, when testing Leela against “normal“-CPU-Engines, I believe.
-
- Posts: 4606
- Joined: Wed Oct 01, 2008 6:33 am
- Location: Regensburg, Germany
- Full name: Guenther Simon
Re: SPCC: Testrun of LC Zero Net 512 finished
I think giving a bench and the used hardware should be sufficient for all users to judge on their own.pohl4711 wrote: ↑Mon Jul 30, 2018 8:02 pm The Leela-Ratio is a good possibility to measure the GPU/CPU(-cores) speed relationship on a machine.
https://blog.lczero.org/2018/07/04/leela-ratio
A value in the range 0.5 to 1.5 seems quite “fair“, when testing Leela against “normal“-CPU-Engines, I believe.
(the so called alphazero ratio is completely arbitrary IMHO and relies on data which cannot be verified and probably never will,
because google never published enough data, thus the L-ratio only uses averaged guess-numbers of a few games)
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: SPCC: Testrun of LC Zero Net 512 finished
A common denominator should be cost. 1060 costs like very fast 6 cores or slow 8 cores CPU.
So basically running 1060 vs single core for fairness one should give at least 6x time odds to CPU.
-
- Posts: 708
- Joined: Mon Jan 16, 2012 6:34 am
Re: SPCC: Testrun of LC Zero Net 512 finished
Oh well, Leela fans already hyped that Leela is 4th best chess engine in the world.
Check out!!
https://groups.google.com/forum/#!topic ... ibaDc3dpeg
Check out!!
https://groups.google.com/forum/#!topic ... ibaDc3dpeg
-
- Posts: 1346
- Joined: Sat Apr 19, 2014 1:47 pm
Re: SPCC: Testrun of LC Zero Net 512 finished
Maybe she is if she plays with a good GPU card against 1CPU engine. But of course it is not fair for the others engines.Nay Lin Tun wrote: ↑Tue Jul 31, 2018 3:25 am Oh well, Leela fans already hyped that Leela is 4th best chess engine in the world.
Check out!!
https://groups.google.com/forum/#!topic ... ibaDc3dpeg
-
- Posts: 708
- Joined: Mon Jan 16, 2012 6:34 am
Re: SPCC: Testrun of LC Zero Net 512 finished
If we assume 2x1080ti vs 43 cores as a fair match in TCEC, I am pretty sure that Leela will stand around 7th or 8th position in premier division, 4th is too optimistic though.JJJ wrote: ↑Tue Jul 31, 2018 5:48 pmMaybe she is if she plays with a good GPU card against 1CPU engine. But of course it is not fair for the others engines.Nay Lin Tun wrote: ↑Tue Jul 31, 2018 3:25 am Oh well, Leela fans already hyped that Leela is 4th best chess engine in the world.
Check out!!
https://groups.google.com/forum/#!topic ... ibaDc3dpeg
There were a series of leela games already on bonus matches and her performance was minimally lower than Andascacs.