Last daily update:
2021-07-30 16:10:40 UTC
Last incremental update:
2021-07-31 10:28:44 UTC
2021-07-31 11:04:31 UTC
The research team continues their data analysis, and lab testing is ongoing for potential COVID-19 treatments.
The results of the ODLK1 BOINC project for March - December 2020 have been published.
See the topic
For March - December 2020, 2306590 unique CF ODLS were found in the project.
The processed part of the project database contains 11299868 unique CF ODLS.
Looking for a project to support? Mapping Cancer Markers has a large amount of work to be done to help fight a devastating collection of diseases.
On 09th of July, vaughan, a member of the team AMD Users found the last prime for base S470.
The prime 32*470^683151+1 has 1.825.448 digits and entered the TOP5000 in Chris Caldwell's The Largest Known Primes Database.
Further to the news Ya!vaConf 2021 a presentation (PDF) is available online. Title in polish: "BOINC + ElasticStack = architektura zbierania, gromadzenia, przetwarzania i archiwizowania danych w kontek?cie projektu oblicze? rozproszonych iThena".
English translation of the title: "BOINC + Elastic Stack = architecture for data collection, gathering, processing and archiving in the context of the iThena distributed computing project".
CAIDA catalogue data: https://catalog.caida.org/details/media/2021_yavaconf_ithena
PDF link: https://cybercomplex.net/docs/YAVA_CONF_2021_BOINC_ELK_ITHENA.pdf
The researchers are getting ready to analyze their data using new methods.
We are updating the operating system on our servers on Friday, July 23, beginning at 13:00 UTC.
We are updating the operating system on our servers on Friday, July 23, beginning at 13:00 UTC.
We are currently looking at making a GPU version of N-Body. This code has been under development for quite some time, and the base code is finally working, though we would still need to implement some other features to run it alongside the CPU version. However, due to the complexity of our code and our need for double precision, the GPU version has a similar runtime to that of the CPU version, though there may be some speed-up on professional grade GPU cards. For reference, the GPU version of the Separation code is roughly 50-60 times faster than its CPU counterpart depending on the machine. Keeping that in mind, do you guys still want a GPU version of N-Body? I have put up a basic straw poll on https://www.strawpoll.me/45510486. If you wish to elaborate on your choice, please feel free to comment below.
Thank you all for your input, time, and consideration,
As requested there are now new badges / levels available. These will compensate the TF app with 500M, 1G, 2G, 5G and 10G max. You can find all in the FAQ.
The researchers continue to do lab testing based on data from their most recent work on World Community Grid.
I will be updating the separation validator starting at 3PM ET. The server will go down for a short time and then come back up. In the case that the new validator causes problems, the server will go back down again to revert to the old validator. I will be monitoring the situation and would appreciate input on any workunits that fail validation after the new validator goes live.
The server may go down/back up a few times during this process. Thanks for your patience. I'll keep you all posted on the status of things as they happen.
If you are currently donating computing power to this project, you can make a simple change to your settings to help speed up the progress.
The fifth challenge of the 2021 Series will be a 3-day challenge in celebration of what is arguably the internet's most momentous and culturally significant holiday: World Emoji Day. The challenge will be offered on the GFN-17-Low subproject, beginning 17 July 22:00 UTC and ending 20 July 22:00 UTC.
To participate in the Challenge, please select only the GFN-17-Low subproject in your PrimeGrid preferences section.
For more info, check out the forum thread for this challenge: https://www.primegrid.com/forum_thread.php?id=9706&nowrap=true#150796
Best of luck!
As we announced last month, the Microbiome Immunity Project's time on World Community Grid is ending, but their data analysis is in full swing. This will be the final monthly update for this project.
The last set of N-body runs has converged beautifully. Thus, we have replaced the old runs with a set of new ones:
Since the last set ran without problems, we expect this one to run smoothly, too. Thank you all for your continued support.
From July 10, 2021 to July 11, 2021 there will be temporary problems with access to the project.
These problems are related to the changes in infrastructure.
Our research is going on! Collaborators just started biological evaluation of 30 chemical compounds selected in SiDock@home for targets 3CLpro and PLpro. Biological evaluation in vitro works with the most prospective results that your computers have selected in silico. The process is iterative and will involve hundreds of experiments.
With your help, we have already processed 4 targets and 43% of the fifth one. Further workunits will be created basing on the biological evaluation and the latest scientific knowledge about the targets.
Many thanks and best wishes,
Team of SiDock@home
Drug development is a time-consuming and costly process. With help of your computers, our team is able to speed up discovery of prospective candidates for in vitro tests. At the same time, the volume of biological evaluation is limited by funding. We are in constant search for additional sources, and, since SiDock@home allows the participants to earn Gridcoins, we find it a good idea to accept voluntary donations. If you feel like donating to the project, please use one of the listed options.
The recent stress test run on World Community Grid allowed the researchers to quickly run simulations for 300 million small molecules.
We are experiencing multiple issues, e.g. hitting an undocumented upload size limit, and others. Please be patient.
The range 72-73bit is nearly done. There is starting new work for 73-74bit. The runtime is around 45min on a RX5500XT and decreasing.
The following websites are now accessible from the Tor network:
ithenash .. pv425zid.onion
cybercom .. kivkbqyd.onion
howfastm .. mdmfomid.onion
We encourage you to use the anonymous version of these sites ;)
This Month in MLC@Home
Notes for July 1 2021
A monthly summary of news and notes for MLC@Home
Happy first birthday to MLC@Home! This project went live on July 1, 2020, and caught on pretty quickly in the BOINC community. We've remained focused on our goal, which is breaking open the black box of neural networks to explain why they make the choices they do. This is so important as machine learning permeates more and more of our everyday life; from autonomous cars, to banking decisions, and medical diagnoses. We need research to understand how to keep bias out of these systems.
We are also the first, and to date only, public machine learning focused BOINC project. This means that while we could leverage the BOINC framework for job management, we have to build most of the ML client infrastructure from the ground up. This hasn't always been smooth, but we've accomplished so much in the past year regardless.
In the past year, we have:
Received contributions from over 2500+ volunteers and 9200+ hosts Processed over 3.4 million BOINC workunits Trained over 1.1 million neural networks for analysis over 3 different datasets, the largest datasets of their kind Generated over 4.3TB of data for analysis Published one academic paper (more coming..) Presented at the 2021 BOINC Workshop Released 47 client versions targeting 3 different CPU architectures, 2 GPU architectures, and multiple versions of Windows and Liunx. Outgrew the initial server within the first few months!
I'm overwhelmed by our community and what we've accomplished together. We've already shown that networks trained with the same data cluster together in weight space, despite the randomness associated with neural network training. We've also shown we can use this clustering to detect networks trained with poisoned data versus clean data, a significant finding in the field.
But there's still soo much more to do! So while we want to acknowledge and celebrate what we've jointly accomplished so far, let's also look forward and set some loose goals for the next year of MLC@Home:
MLDS will continue near term!
DS4 is (almost) ready and expands the dataset to include CNN network types as well as RNNs used in DS1-3. DS5 will likely vary the shape and size of each network slightly to see if clustering still happens when shape is varies. Future MLDS work beyond DS5 is TBD, but we expect there to be plenty DS4/DS5 WUs for many months to come. We expect to update the paper with the latest runs over the next month.
We'd like to expand beyond MLDS!
We are the first project to do ML on a BOINC-sized scale. We would like to expand to supporting other areas of research, and want to commit to bringing at least one other ML project online within the next year. Please contact us if you are a researcher who is interested in working with the platform!
We need to improve the technical side of the project
From the client supporting AMD GPUs and OSX to optimizing utilization of graphics cards to a better validation process for WUs, there's a laundry list of technical issues we'd like to address, and have not done so effectively in the past three months. We're also hitting some corner-cases of the BOINC software stack that are tricky to work around. If you are a developer and want to help, we'd welcome the support.
We'd like to improve outreach
To get more people involved, we'd like to produce a few short videos about the project, what we've found and how others can help. These should be short, easily accessible, and easy to share. We'd like to produce at least one of these within the next 6 months.
These are loose goals but should give you an idea where we're concentrating our efforts for the next year. If you have further insights, please share them below or on Discord.
Thanks again for supporting MLC@Home, and here to many more years of successful, important research in an important field.
DS3 is all but complete (just a last few 130+ trickling in!). I consider DS3 to be the most important dataset and can't wait to run our analysis on the whole thing! From now on we'll be blasting DS1 (then DS2) WUs into both the GPU and CPU queues until that completes and/or until DS4 is ready. We'll try to get those over the hump ASAP. Some fun news! MLC Discord user Tankbuster has updated our banner graphic! See the updated banner on project and home pages! Even more exciting, Tankbuster built a prototype graphics app for MLC@Home! You can see mockups and videos and follow the discussion at the MLC Discord server (link at the bottom). Screenshot: Reminder: the MLC client is open source, and has an issues list at gitlab. If you're a programmer or data scientist and want to help, feel free to look over the issues and submit a pull request.
Project status snapshot:
(note these numbers are approximations)
Last month's TMIM Notes: Jun 8 2021
Thanks again to all our volunteers!
-- The MLC@Home Admins(s)
Discord invite: https://discord.gg/BdE4PGpX2y
On 1 March 2021, 02:47:51 UTC, PrimeGrid's Fermat Divisor Search found the Mega Prime:
The prime is 2,645,643 digits long and enters Chris Caldwell's ?The Largest Known Primes Database? ranked 75th overall.
The discovery was made by Tom Greer (tng) of the United States using an Authentic AMD Ryzen 9 5950X CPU @ 4.90GHz with 32GB RAM, running Microsoft Windows 10 Professional. This computer took about 2 hours and 46 minutes to complete the primality test using LLR2. Tom Greer is a member of the Antarctic Crunchers team.
For more details, please see the official announcement.
I deployed the new app, which now requires cuda 11.2 and hopefully support all the latest cards. Touching the cuda versions is always a nightmare in boinc scheduler so expect problems.
The researchers recently welcomed a new team member who will be designing machine-learning approaches.
since today, SiDock@home is whitelisted in Gridcoin. It means that you can receive the Gridcoin cryptocurrency for contributing to SiDock@home. For instructions, please refer to the official website of Gridcoin. For a description how Gridcoin works, refer to their whitepaper. This technology is yet new to our team, but we will do our best to understand it and help you to use it.
The researchers are beginning to analyze the enormous amount of data generated during last month's stress test, when 30,000 batches of work were run in eight days.
We invite you to the conference Ya!vaConf 2021.
Looking for an additional project to support? Please add Mapping Cancer Markers to your list.
Thanks to all the users. (Please keep crunching!)
...300316 times - still no sign of any larger factors
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.
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.
Due to unforeseen circumstances, we at MilkyWay@home are temporarily deprecating our newest version of Nbody (v1.80) and un-deprecating the previous version (v1.76) in its place. Since the lua files associated with each version are incompatible with each other, we have replaced the previous optimizations with a new set:
We have cancelled all jobs pertaining to the previous set of runs. However, there still may be a few which we were not able to cancel in time. These runs will most likely error out if you get them, but should do so rather quickly (about 2 seconds).
If any complications arise from this, please notify us immediately, and we will quickly find a solution.
Thank you all for your time and continued support,
With the recent addition of a new permanent team member, the researchers can begin leveraging machine learning techniques to help with data analysis.
A research team member hits an important academic milestone this month.
I've just put some new separation runs up on the server. Remember those stripe 84 and 85 runs that would start to throw validate errors as they became more optimized? I've been testing and comparing runs on different builds and *hopefully* that problem has been resolved.
The names of the new runs are:
Please keep an eye on these runs and let me know if anything odd happens (validate errors or otherwise). With any luck, everything will work perfectly! These are the last runs that need to optimized before the latest results of separation can be submitted to a journal to be published.
Additionally, I have taken down the following runs:
As always, the stopped runs will continue to show up in your workunit queue for a few days as they finish up. This is normal and expected. Thank you all for your support and help with this project.
We are updating the operating system on our servers on Thursday, June 10, beginning at 13:00 UTC.