[Paraview] Sharing GPUs Amongst Processes

[Biddiscombe, John A.]

On the Wiki, there is a discussion of using multiple cores per GPU
http://www.paraview.org/Wiki/Setting_up_a_ParaView_Server#Sharing_GPUs_Amongst_Processes

One key phrase "GPUs can be implicitly shared by pointing multiple processes to the same display on the same host" tells me that the selection of the display, assumes that an X server is running and you tell each node to use DISPLAY:0.0 etc etc depending on number of GPUs shared between CPUs. In fact later in the wiki this is explicitly written.

Question : Supposing you have no Xserver running but you wish to take advantage of hardware acceleration. Is it possible to create an offscreen buffer for each pvserver without the X server. We'd like to share one GPU between 4 cores, but without starting X.

Can either OpenGL or Mesa (but using GPU not software) be told to do this.

JB

--
John Biddiscombe,                            email:biddisco @ cscs.ch
http://www.cscs.ch/
CSCS, Swiss National Supercomputing Centre  | Tel:  +41 (91) 610.82.07
Via Cantonale, 6928 Manno, Switzerland      | Fax:  +41 (91) 610.82.82

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.paraview.org/pipermail/paraview/attachments/20100224/cd63a574/attachment.htm>