| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
 |
World Community Grid Forums
Category: Completed Research
Forum: Discovering Dengue Drugs - Together
Thread: Faster New Batches of Work |
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 26
|
|
| Author |
|
|
Sekerob
Ace Cruncher Joined: Jul 24, 2005 Post Count: 20043 Status: Offline |
That's a bit slow, my P4 2.53 has ram running at 266mhz. One last ditch... the Cache page L1 & L2.... here has 512kb of L2....if that's inoperative, it may
----------------------------------------Edit for stutter 
WCG
----------------------------------------Please help to make the Forums an enjoyable experience for All! [Edit 1 times, last edit by Sekerob at Oct 28, 2007 1:17:02 PM] |
||
|
|
Dataman
Ace Cruncher Joined: Nov 16, 2004 Post Count: 4865 Status: Offline Project Badges: 
|
That's a bit slow, my P4 2.53 has ram running at 266mhz. One last ditch... the Cache page L1 & L2.... here has 512kb of L2....if that's inoperative, it may the the cause. Thanks L1 D-Cache 8KBytes Trace Cache 12Kuops L2 Cache 512KBytes  |
||
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges: 
|
Thanks for all the feedback so far. The new batches which are 0201 are estimated to run at about an hour for the 0201a0001 batch to be specific. This was an assumption on my part that all 0201 work units would run in about the same time.
However, I was looking into some of the work units that ran longer and those run times looked on par with the formula we generated for runtime per work unit. This was based off some of the initial values given by the researchers. Also, about people getting 0101 batches, these batches have not all been completed. For example if someone errors out on a work unit, then that work unit will need to be sent out again to a reliable host for computation. We are also not done with the original 0101 batches and have some left in the queue if we run through the 0201 batches too quickly. Hope this helps, -Uplinger |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Well that is interesting . many thanks Uplinger
 |
||
|
|
Dataman
Ace Cruncher Joined: Nov 16, 2004 Post Count: 4865 Status: Offline Project Badges:
|
Thank you ... that resolves my inquiry.
---------------------------------------- Thanks for all the feedback so far. The new batches which are 0201 are estimated to run at about an hour for the 0201a0001 batch to be specific. This was an assumption on my part that all 0201 work units would run in about the same time. However, I was looking into some of the work units that ran longer and those run times looked on par with the formula we generated for runtime per work unit. This was based off some of the initial values given by the researchers. Also, about people getting 0101 batches, these batches have not all been completed. For example if someone errors out on a work unit, then that work unit will need to be sent out again to a reliable host for computation. We are also not done with the original 0101 batches and have some left in the queue if we run through the 0201 batches too quickly. Hope this helps, -Uplinger |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
I like the faster workunits.. feels like crunching the Genome Project all over again.. :) my 1 Ghz system was doing many of those a day. when I assigned it to that that project only while the 3.6 Ghz Dual did that and everything else.
|
||
|
|
|