| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
 |
World Community Grid Forums
Category: Beta Testing
Forum: Beta Test Support Forum
Thread: Beta Test for Help Conquer Cancer - GPU v6.56 |
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 89
|
|
| Author |
|
|
Simplex0
Advanced Cruncher Sweden Joined: Aug 14, 2008 Post Count: 83 Status: Offline Project Badges: 
|
These aren't Intel CPUs on the GPU we are talking about. The next-generation Nvidia GPU (Maxwell) is going to include an ARM processor, to handle various OpenCL chores that I don't understand, but should be good news for reducing the usage of the system CPU. With the continued advance in semiconductor processing (reducing lithography size), I expect that it will be at least as power efficient as the present-generation GPUs, and probably more so. You can only hope but a quad AMD 7970 desktop computer reaching 16TFlops of single-precision, 4 TFlops of double-precision computing performance. I will be really supriced if a CPU with intigrated GPU funktions or vice versa will com anyway near that performance any time soon. [Edit 1 times, last edit by Simplex0 at Oct 6, 2012 8:36:10 PM] |
||
|
|
Jim1348
Veteran Cruncher USA Joined: Jul 13, 2009 Post Count: 1066 Status: Offline Project Badges: 
|
If you are referring to an AMD or Intel CPU with some GPU support (as in Haswell), I am sure you are right that the TFlops won't be as high as an AMD or Nvidia GPU. But it seems that Nvidia will be going to OpenCL by the next generation also, and so they undoubtedly want to minimize the load on the CPUs. I presume the AMD GPUs will do something similar, but have not looked into that.
|
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Hi :)
I have selected the project "Help conquer cancer" and ticked the box to receive GPU units, but it seems that i've never received any task on GPU. What can I do about this? Thank you :) |
||
|
|
Jim1348
Veteran Cruncher USA Joined: Jul 13, 2009 Post Count: 1066 Status: Offline Project Badges:
|
What can I do about this? Wait. The project hasn't started yet, and there are no betas at the moment. |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Wait. The project hasn't started yet, and there are no betas at the moment. Me, I'm waiting for some feedback or a partial post-mortem from the WCG-Techs.; |
||
|
|
[VENETO] boboviz
Senior Cruncher Joined: Aug 17, 2008 Post Count: 183 Status: Offline Project Badges: 
|
A question: when the project will start, will be possible to run multiple wu on gpu?? Now, with custom config.xml file, i'm crunching 5 wu gpu poem@home concurrently (reserving 3 cpu cores)...
|
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Hello [VENETO] boboviz,
----------------------------------------I may be wrong, but I don't think it will be possible to run multiple work units on one GPU because I have not seen any announcement that it can be done. Lawrence Added: knreed speaks! Maybe. See https://secure.worldcommunitygrid.org/forums/...ad,33914_offset,60#394941 [Edit 1 times, last edit by Former Member at Oct 9, 2012 8:23:53 PM] |
||
|
|
nanoprobe
Master Cruncher Classified Joined: Aug 29, 2008 Post Count: 2998 Status: Offline Project Badges: 
|
A question: when the project will start, will be possible to run multiple wu on gpu?? Now, with custom config.xml file, i'm crunching 5 wu gpu poem@home concurrently (reserving 3 cpu cores)... The techs would have to allow the GPU app to run on an anonymous platform configuration which I doubt will happen. Since the HCC GPU app pretty much maxes out your GPU there would be no advantage to running more than 1.
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.
----------------------------------------  [Edit 1 times, last edit by nanoprobe at Oct 8, 2012 1:51:41 PM] |
||
|
|
Sabrina Tarson
Advanced Cruncher United States Joined: Jun 27, 2012 Post Count: 149 Status: Offline Project Badges:
|
I have a question. If I were to run a Primegrid application on my GPU while there is no GPU work for World Community Grid, it would uses around .82CPU per GPU. Will it then spread the 3.2 CPU's left for World Community Grid out to the work units, or will one workunit just go slower?
---------------------------------------- |
||
|
|
nanoprobe
Master Cruncher Classified Joined: Aug 29, 2008 Post Count: 2998 Status: Offline Project Badges:
|
I have a question. If I were to run a Primegrid application on my GPU while there is no GPU work for World Community Grid, it would uses around .82CPU per GPU. Will it then spread the 3.2 CPU's left for World Community Grid out to the work units, or will one workunit just go slower? I have no experience running PG but I can give you some general rules when it comes to GPU crunching. The HCC GPU app will by default use one of your cores. That will leave the other 3 to run whatever you want. If PG requires .82 of 1 core to run and doesn't use one by default then you have 2 choices. First, you and just run PG without any changes by you. It will take longer for the PG task to complete because it will be fighting the CPU for cycles while the CPU is crunching. Or you could assign 1 of you cores to run the PG task and let the other 3 CPU cores crunch by themselves. This will allow the PG task to run as it should and it will finish much faster. It will lower your CPU output because you're now only crunching with 3 cores. The choice of how you proceed is up to you. My personal recommendation would be to let PG have a dedicated core and run the other 3 as you wish.
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.
|
||
|
|
|