Search found 42 matches

by grahamj
Wed Mar 18, 2020 8:22 pm
Forum: Computer Chess Club: General Topics
Topic: Use the crisis to solve crisis
Replies: 11
Views: 939

Re: Use the crisis to solve crisis

Dann Corbit wrote:
Tue Mar 17, 2020 4:18 pm
It is using OpenCL in my Nvidia 2080 TI Supers
How can you tell?

Thanks for reminding me about FAH.
by grahamj
Mon Mar 09, 2020 9:42 am
Forum: Computer Chess Club: General Topics
Topic: GPU rumors 2020
Replies: 19
Views: 2746

Re: GPU rumors 2020

The SLIDE algorithm is not going to make GPUs redundant. I doubt it will make much dent in their sales. SLIDE only applies to fully connected nets, not to convolutional nets as used in LCZero, and I think, almost all processing of visual information. SLIDE was only shown to speed up certain 'extreme...
by grahamj
Sun Jan 05, 2020 8:11 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Simulated game trees
Replies: 0
Views: 1094

Simulated game trees

Last year I wrote some code to generate simulated game trees. I am mainly interested in algorithms like PUCT (LC0,A0) and realisation probabilities (which I've only seen used for Shogi). I'm not personally interested in alpha-beta pruning, but perhaps the simulator is of general interest. The simula...
by grahamj
Fri Jan 03, 2020 10:23 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: RMO - Randomized Move Order - yet another Lazy SMP derivate
Replies: 113
Views: 11362

Re: RMO - Randomized Move Order - yet another Lazy SMP derivate

But this is not a realistic "chess like" tree. In chess neighboring positions in the tree are heavily correlated. Moreover evaluation errors are also heavily correlated. Modern chess engines (A/B and MCTS) exploit these correlations. You will not capture this with a simple random tree. Generating r...
by grahamj
Fri Jan 03, 2020 8:08 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: RMO - Randomized Move Order - yet another Lazy SMP derivate
Replies: 113
Views: 11362

Re: RMO - Randomized Move Order - yet another Lazy SMP derivate

Another algorithm that REALLY sticks in my craw is MCTS. Monte Carlo, for gambling, of course. So, instead of intelligent and guided search, we cast a net blindly left right and center. Maybe it lands in the water. Maybe it lands on a tree. Maybe it catches a bunch of fish. Why should this turn out...
by grahamj
Fri Nov 15, 2019 9:17 pm
Forum: Computer Chess Club: General Topics
Topic: GPU rumors 2020
Replies: 19
Views: 2746

Re: GPU rumors 2020

I meant the host-device latencies also known as kernel launch overhead, can vary between 5ms and 100ms on different systems for null-kernels, this is primary not caused by the PCIe connection, but (speculation) by the little embedded CPU controller in all GPUs that launches the kernels, I admit the...
by grahamj
Thu Aug 29, 2019 4:34 pm
Forum: Computer Chess Club: General Topics
Topic: Lc0 Evaluation Explanation
Replies: 15
Views: 3377

Re: Lc0 Evaluation Explanation

LC0 chooses the move with the most visits. Searching the explanation for 'visits' may help.
by grahamj
Tue Aug 20, 2019 9:15 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: deepdebt
Replies: 8
Views: 2413

Re: deepdebt

Ok the company is betting on reinforcement learning but other research instititures (univ.) could explore the other avenues that could get us there. But as the author says "Every dollar invested in reinforcement learning is a dollar not invested somewhere else..." I watched neural nets being massiv...
by grahamj
Fri Jun 21, 2019 1:29 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Lazy-evaluation of futures for parallel work-efficient Alpha-Beta search
Replies: 53
Views: 18123

Re: Lazy-evaluation of futures for parallel work-efficient Alpha-Beta search

Thanks for the further details. I won't pretend I understand them yet, but your project sounds interesting. You have at least understood that the main problem with using a GPU for chess is how to implement the search tree.