The new GPU workunits for the HCC project at WCG do not seem to cooperate well with GPUGRID workunits. For computers running both, the GPUGRID workunits have long delays at the last checkpoint (the one within 5 minutes of finishing), and therefore will not finish as quickly as they used to for the same computers.

If the work after that checkpoint is CPU-only, could you investigate whether it is useful and possible to give up use of the GPU just before that checkpoint?

Also, could you contact the HCC project at WCG to see if the two projects can cooperate better at allowing long workunits to finish?

with 2x GTX 660 Ti in a system, 1 on GPUGrid and 1 on the WCG HCC GPU, I had to reduce number of cores/threads used by BOINC. Before I did that the HCC task was jumping all over the graph of gpu utilization.

Also of note, the HCC gpu tasks are very laggy when trying to actually use the machine for normal usage (browsing, etc). Definitely not so mature as GPUGRID :D <3<3<3 Not to mention large time periods in which the GPU goes idle :/
____________
XtremeSystems.org - #1 Team in GPUGrid

In order for to work around the screen display lag issue....

I have made it a habit to suspend GPU tasks of certain applications, that are known to always generate lag, whenever I sit down at the computer, and then resume them before I leave. I also suspend other GPU tasks if I notice they are causing lag.

Right now, when I sit down at the computer, I always suspend World Community Grid Help Conquer Cancer tasks (since they always cause display lag for me), and I sometimes will suspend a GPUGrid.net task (if its a task that generates display lag that I notice after sitting down to my computer).

That way, while I'm working, my GPU can still crunch the tasks that don't generate lag (like Poem@Home tasks, or most GPUGrid.net tasks), and then when I leave, since I've resumed the other tasks before I leave, the scheduler will eventually complete them too.

That's the only workaround I have. I don't like it, but I cannot otherwise control the lag in some of these GPUGrid.net tasks.

GPUGrid.net Techs:
Should I be keeping track of which GPUGrid.net task types are generating display lag, and reporting them somewhere?