Using only one CUDA GPU?

Questions and Answers : GPU applications : Using only one CUDA GPU?

To post messages, you must log in.

AuthorMessage
Profile EVE: Katana Seiko

Send message
Joined: 18 Nov 05
Posts: 3
Credit: 53,338
RAC: 0
Germany
Message 950438 - Posted: 28 Nov 2009, 9:32:39 UTC

I have two CUDA enabled GPUs on my machine. However, BOINC doesn't want to use the second one.

NVIDIA GPU 0: GeForce GTX 260 (driver version 19038, CUDA Version 2030, compute capability 1.3, 896MB, 537 GFLOPS peak)
NVIDIA GPU 1 (not used): GeForce 8300 (driver version 19038, CUDA Version 2030, compute capability 1.1, 256MB, 24 GFLOPS peak)

I know, the second GPU is slightly less powerfull than the first one, but it's still able to compute data.. Is there a way to make BOINC use the second GPU too?
ID: 950438 · Report as offensive
Profile Gundolf Jahn

Send message
Joined: 19 Sep 00
Posts: 3184
Credit: 386,829
RAC: 41
Germany
Message 950451 - Posted: 28 Nov 2009, 10:45:00 UTC - in response to Message 950438.  
Last modified: 28 Nov 2009, 10:50:02 UTC

Check your BOINC data directory for a file named cc_config.xml. The path to the data directory is listed in the Messages tab of BOINC manager after a reboot. The directory may be hidden by windows and it contains the file client_state.xml (and many others).

If you don't have a cc_config.xml, create one using notepad (Editor) and paste
<cc_config>
	<options>
		<use_all_gpus>1</use_all_gpus>
	</options>
</cc_config>
into it. When saving, make sure that no other suffix (.txt) is appended to the filename.

If you already have created a cc_config.xml file, add the <use_all_gpus> line to the <options> section.

After that, select "Read config file" from the Advanced menu or, better yet, restart BOINC.

Gruß,
Gundolf
[edit]See also the Nvidia CUDA & ATI Stream (CAL) FAQ at the BOINC FAQ Service.[/edit]
Computer sind nicht alles im Leben. (Kleiner Scherz)

SETI@home classic workunits 3,758
SETI@home classic CPU time 66,520 hours
ID: 950451 · Report as offensive

Questions and Answers : GPU applications : Using only one CUDA GPU?


 
©2016 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.