| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
 |
World Community Grid Forums
Category: Active Research
Forum: OpenPandemics - COVID-19 Project
Thread: Work unit availability |
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 822
|
|
| Author |
|
|
Dayle Diamond
Senior Cruncher Joined: Jan 31, 2013 Post Count: 452 Status: Offline Project Badges: 
|
Amalthea, I added the prior day's OPN and MIP years of crunching power per day.
The current day's totals are not updated in real time. Is it possible you're looking at the project averages instead of the most recent numbers? There were times when we had many simultaneous projects, so the individual daily throughput was smaller. |
||
|
|
nanoprobe
Master Cruncher Classified Joined: Aug 29, 2008 Post Count: 2998 Status: Offline Project Badges: 
|
I have both nvidia and amd cards. With 81,600 tasks per day available to run on OPNG and assuming each task takes 10 mins on average, the total cpu time (elapsed time) is about 567 days or 1.55 years (less for amd cards by about 1/3, based on my estimate) assuming running one task per gpu (more if you run more than one task per gpu) but the total work done in terms of credit granted is probably half a billion WCG credits! Elapsed time and CPU time are almost equal on a Nvidia GPUs. Never more a few seconds difference. On AMD CPU time is <5% of elapsed time at the most. IE: a task that runs for 30 minutes on Nvidia will use and be awarded 30 minutes of CPU run time. That same 30 minute task on AMD will only use 2 minutes of CPU run time and get awarded 2 minutes of CPU run time. Nvidia gets 15 times more badge time than AMD for the same task. How is that justified?
In 1969 I took an oath to defend and protect the U S Constitution against all enemies, both foreign and Domestic. There was no expiration date.
  |
||
|
|
kittyman
Advanced Cruncher Joined: May 14, 2020 Post Count: 140 Status: Offline Project Badges: 
|
Well, the kitties just keep munching with their lone nVidia GTX980. They are happy with points, badges, or more OPNG kibbles in return.
----------------------------------------Meowmeowmeow  |
||
|
|
hnapel
Advanced Cruncher Netherlands Joined: Nov 17, 2004 Post Count: 82 Status: Offline Project Badges: 
|
It sounds to me as if there is a lot of unfairness, injustice or harm done. So what would be the harm? It´s just an idea, but given the update there´s enough processing power from both CPU / GPU available for openpandemics so I´m actually pulling out altogether and do some work for ARP and MCM. The GPU´s are then better dedicated to folding@home, especially the covid moonshot effort for which they still run jobs are appealing since they look at engineered molecules which seems a bit smarter than to try repurpose existing libraries. If any snake oil would linger there I guess it should have been found already. |
||
|
|
Grumpy Swede
Master Cruncher Svíþjóð Joined: Apr 10, 2020 Post Count: 2526 Status: Offline Project Badges:
|
Still trying to get blood from a stone. No success.......
|
||
|
|
Speedy51
Veteran Cruncher New Zealand Joined: Nov 4, 2005 Post Count: 1326 Status: Offline Project Badges: 
|
The obvious solution, suggested many months ago, is to eliminate the CPU work units. There will still be more than enough GPU power to handle the work. I couldn't agree more that there is enough GPU power to handle work load. I believe where the issue lies is the server capacity as we saw when the stress test was in full swing. Parts of the system couldn't keep up  |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
i believe if you eliminate the CPU work units most of the people will work on projects like Mapping Cancer Markers as that is what a lot of people doing now.My solution would be to increase GPU work units higher then it is now but not up to work unit numbers that they were sending out during the stress test.
|
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
According to Kevin, there are currently too many GPU work units. To reach the 500 batches/day, they would have to eliminate all CPU work and trim back the GPU work.
|
||
|
|
Speedy51
Veteran Cruncher New Zealand Joined: Nov 4, 2005 Post Count: 1326 Status: Offline Project Badges:
|
According to Kevin, there are currently too many GPU work units. To reach the 500 batches/day, they would have to eliminate all CPU work and trim back the GPU work. Thanks entity, this backs up what I was saying a few posts above |
||
|
|
nanoprobe
Master Cruncher Classified Joined: Aug 29, 2008 Post Count: 2998 Status: Offline Project Badges:
|
According to Kevin, there are currently too many GPU work units. To reach the 500 batches/day, they would have to eliminate all CPU work and trim back the GPU work. I disagree. GPU work was cut almost in half from 727 batches. Say they are now doing 400 batches per day of GPU work. By eliminating the CPU work they could add at least 100 more batches to GPU work, probably more.
In 1969 I took an oath to defend and protect the U S Constitution against all enemies, both foreign and Domestic. There was no expiration date.
|
||
|
|
|