[WEP-M+2] P2203:180000000 wu's (of 10000 trials each equiv.) processed!

Thanks to all the users. (Please keep crunching!)

View article · Sat, 19 Jun 2021 10:57:48 +0000

[WEP-M+2] 12-digit factor of P2203 has now been found by the project...

...300316 times - still no sign of any larger factors

View article · Sat, 19 Jun 2021 10:52:53 +0000

[GPUGrid.net] Experimental Python tasks (beta) - task description

Hello everyone, just wanted to give some updates about the machine learning - python jobs that Toni mentioned earlier in the "Experimental Python tasks (beta) " thread. What are we trying to accomplish? We are trying to train populations of intelligent agents in a distributed computational setting to solve reinforcement learning problems. This idea is inspired in the fact that human societies are knowledgeable as a whole, while individual agents have limited information. Also, every new generation of individuals attempts to expand and refine the knowledge inherited from previous ones, and the most interesting discoveries become part of a corpus of common knowledge. The idea is that small groups of agents will train in GPUgrid machines, and report their discoveries and findings. Information of multiple agents can be put in common and conveyed to new generations of machine learning agents. To the best of our knowledge this is the first time something of this sort is attempted in a GPUGrid-like platform, and has the potential to scale to solve problems unattainable in smaller scale settings. Why most jobs were failing a few weeks ago? It took us some time and testing to make simple agents work, but we managed to solve the problems in the previous weeks. Now, almost all agents train successfully. Why are GPUs being underutilized? and why are CPU used for? In the previous weeks we were running small scale tests, with small neural networks models that occupied little GPU memory. Also, some reinforcement learning environments, especially simple ones like those used in the test, run on CPU. Our idea is to scale to more complex models and environments to exploit the GPU capacity of the grid. More information: We use mainly PyTorch to train our neural networks. We only use Tensorboard because it is convenient for logging. We might remove that dependency in the future.

View article · Thu, 17 Jun 2021 10:40:32 +0000

Developers:   Help maintain and develop BOINC

Contact · Papers · Graphics · · Computing power

2021 BOINC workshop
The workshop, showcasing BOINC-based research and providing an open forum, will be held online, on three Wednesdays in April: 14, 21, 28. Learn more and register at boincworkshop.org.
31 Mar 2021, 20:59:44 UTC · Discuss

Android client available on F-Droid
The latest BOINC client for Android is now available from F-Droid, a repository of open-source apps.
4 Mar 2021, 20:50:06 UTC · Discuss

New BOINC Android client released
Version 7.16.16 of the BOINC Android client has been released. This is the first new Android version in over 4 years, and is a major rewrite of the GUI. Thanks to Vitalii Koshura, Tal Regev, and Isira Seneviratne for their work on this.

The new version is available from the BOINC web site and (for Amazon Fire tablets) from the Amazon app store. It's not on the Google play store because of new restrictions imposed by Google; hopefully this will be resolved in a future version.
15 Feb 2021, 23:47:10 UTC · Discuss

News is available as an RSS feed