1)
Message boards :
Number crunching :
Linux CUDA 'Special' App finally available, featuring Low CPU use
(Message 1930483)
Posted 17 Apr 2018 by ![]() Post: Thanks Brent for this advice. Cheers |
2)
Message boards :
Number crunching :
Linux CUDA 'Special' App finally available, featuring Low CPU use
(Message 1930468)
Posted 17 Apr 2018 by ![]() Post: Ok, thanks. Can I had command line options to increase GPU occupation ? |
3)
Message boards :
Number crunching :
Linux CUDA 'Special' App finally available, featuring Low CPU use
(Message 1930463)
Posted 17 Apr 2018 by ![]() Post: Hi all, I have now a GTX 1060 6Go and a GTX 1070 using zi3v-Cuda9.0 under Linux Fedora 27. However, the computation is not always using GPU, sometimes down to 70 %. Is there a way to improve this ? Can I run two tasks in parallel on each GPU or wil it give unreliable results? For information, I have at this time 0 error, 0 invalid, 24 inconclusive, 626 valid and 987 pending tasks. |
4)
Message boards :
Number crunching :
Linux CUDA 'Special' App finally available, featuring Low CPU use
(Message 1898972)
Posted 3 Nov 2017 by ![]() Post: Interesting, that 1050Ti has only OpenCL 1.2 support. I'm afraid you won't find a nVidia GPU with anything above OpenCL 1.2 as they stopped any further development to concentrate on CUDA. OpenCL 2.0 is officially supported since nvidia driver 378.66. However it is not clear which hardware will support it. On a windows host with driver 388.XX, all opencl tasks on all projects where failing until I reverted to 377.XX. However, CUDA gpugrid tasks were working correctly. So OpenCL 2.0 seems not ready yet :-/ |
5)
Message boards :
Number crunching :
Linux CUDA 'Special' App finally available, featuring Low CPU use
(Message 1898964)
Posted 3 Nov 2017 by ![]() Post: You linked to a post about a 780, Please look above where you will see it is Common Knowledge the Kepler CC 3.5 GPUs DO NOT WORK CORRECTLY with anything above CUDA 6.0. Hi Tbar, Thank you for all your work. I think the phrase in bold is really important and should be highlighted in the download area. At this time, it is written The CUDA 6.0 Special App is for the older Kepler CC 3.5 GPUs that might not work well with CUDA 8 and above.which is less clear. In my case, with both a GTX 780 and a GTX 1060 on the same Linux Fedora 25 host, I thought I could use Cuda 8. Thanks ! |
6)
Message boards :
Number crunching :
Linux CUDA 'Special' App finally available, featuring Low CPU use
(Message 1854146)
Posted 9 Mar 2017 by ![]() Post: I've been looking over my last build which has the gaussfit fix and it appears to be a little better than the x41p_zi+ build. It still has the pulsefind bug, but it might be worth changing over to the version that has one less bug. The Inconclusives on the Mac running the same source has come down quite a bit. I picked up one of those Highly clocked 1050s and replaced one of the 750Ti cards. The 'spare' 750Ti is running the last build by itself and if it continues to work well I might post the App this weekend. This is the Host I just started with the test App, it had been running two ATI cards and had a low Inconclusive list, http://setiathome.berkeley.edu/results.php?hostid=6906726&offset=80 Great ! Tell me if you need me to do some tests. |
7)
Message boards :
Number crunching :
Linux CUDA 'Special' App finally available, featuring Low CPU use
(Message 1853407)
Posted 6 Mar 2017 by ![]() Post: So what are the recommendations for a) desktop and b) install version of Ununtu? Hi Stephen, From my point of view, the easiest version to use and configure is Ubuntu with Gnome. I really not recommend Fedora, which I am using, because it is too hard to configure. Moreover, Ubuntu has a very important and reactive community. In order to burn your USB key, I will suggest you to use rufus and keep default options. Cheers |
8)
Message boards :
Number crunching :
What ever happened to CUDA 50/42/etc
(Message 1848911)
Posted 15 Feb 2017 by ![]() Post: @ Keith, Thanks for this precision. Have a good day. For me it's the night ;-) |
9)
Message boards :
Number crunching :
What ever happened to CUDA 50/42/etc
(Message 1848874)
Posted 15 Feb 2017 by ![]() Post: The SoG app is much faster on the current BLC tasks for the most part. The servers send you the appropriate app based on which app has the largest APR rate for your systems. That has been the SoG app for about half a year now. This is the case if you are running stock apps. You have a choice of which app you want to run if you run an Anonymous platform like the Lunatics apps. If you want to run CUDA work again you can either choose to run the Lunatics apps and select CUDA50 or install a Linux platform and run the special Linux CUDA app developed by Petri. His CUDA app absolutely blows any other app out of the water with its processing rate. Tasks that take 30 minutes on the old CUDA50 app or 15 minutes on the SoG app are finished in 90 seconds with the special app. Hi all, and thank you for all your developments. Any news from the Linux Cuda 6 special application ? I would like to test it on a GTX 780 and a GTX 1060 under Fedora 24 but for now it is unavailable there In the mean time, should I use nVidia_OpenCL_r3567 or should I prefer the stock application ? By the way, I was missing a place to find the last optimized application, as there was on the previous seti website. Could it be possible to highlight this information somewhere ? So here is my question : under Windows 10, is Lunatics 0.45 beta 6 still the fastest one, either with nvidia and amd gpu ? I am asking that because more recent stock application are available. Many thanks |
10)
Message boards :
Number crunching :
Open Beta test: SoG for NVidia, Lunatics v0.45 - Beta6 (RC again)
(Message 1815247)
Posted 5 Sep 2016 by ![]() Post: Hi all, Thank you Richard Haselgrove for this application. I have installed lunatics v0.45 beta 4 without any troubles, working on a GTX 780, a HD 4600 and a i5 4670k. In progress tasks were not killed and they seems to work much faster. Especially, v0.44 was only using 60-90% of the gpu and it is now above 90%. Cheers |
©2023 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.