Re: [VirtualGL-Users] (no subject)

2013-09-19 Thread DRC
I have heard from at least one person that it is possible, but I have not personally tried it. I'm not sure why you bothered with all the help wanted ads. All you had to do was e-mail me. I'm the guy who founded the VirtualGL Project, has been solely maintaining it for 10 years, and has

Re: [VirtualGL-Users] (no subject)

2013-09-19 Thread Morgan Ross
Thank you for taking the time to respond. I'm honored, I have been reading your posts for a long time, I did not address you directly because I didn't want to waste your time, at this point I am not able to commit fully to learning 3D over IP yet. (3DoIP first?). I agree that it is best to be

Re: [VirtualGL-Users] gpu vs cpu

2013-09-19 Thread Amanda Tumminello
I am currently working in a blade server environment. It consists of 13 blades with dual Intel Xeon E5-2680 8 core processors 2.7Ghz sandy bridge processors within each blade. If i were to add GPUs i would end up losing a processing blade. sorry for my naivte. On Thu, Sep 19, 2013 at 10:52

Re: [VirtualGL-Users] gpu vs cpu

2013-09-19 Thread DRC
Yeah, but a single high-end GPU is going to render OpenGL faster than all of the 200-some-odd cores in your cluster combined. Seems like a good trade-off to me. On 9/19/13 1:27 PM, Amanda Tumminello wrote: I am currently working in a blade server environment. It consists of 13 blades with

Re: [VirtualGL-Users] gpu vs cpu

2013-09-19 Thread Arthur Huillet
On Thu, 19 Sep 2013 10:56:42 -0500 Amanda Tumminello tumminel...@gmail.com wrote: We have some servers with adequate processing that i have been told should be able to handle the graphics load. Whoever told you that is highly likely to be wrong - or you are running very un-demanding

Re: [VirtualGL-Users] gpu vs cpu

2013-09-19 Thread Amanda Tumminello
ok. Thank you for the information. I will definately continue down the gpu path then... On Thu, Sep 19, 2013 at 2:07 PM, DRC dcomman...@users.sourceforge.netwrote: Yeah, but a single high-end GPU is going to render OpenGL faster than all of the 200-some-odd cores in your cluster combined.

Re: [VirtualGL-Users] automatically choosing GPU with vglrun

2013-09-19 Thread DRC
I don't know why you're getting different screen numbers, but like I said, the generic solution for this needs to be able to handle an arbitrary mapping anyhow, since some people will choose to configure multiple GPUs as multiple independent X servers instead of multiple screens. I would

[VirtualGL-Users] TurboVNC: Retiring the X11 viewer + better Java viewer integration on Windows

2013-09-19 Thread DRC
I've just put out a new pre-release of TurboVNC (http://virtualgl.sourceforge.net/vnc.nightly.13) that gives a sneak preview of one of the biggest changes in TurboVNC 1.3: Retiring the X11 viewer --- It has been decided to get rid of the X11 viewer, although it will still