Does a Titan Z count as one or two processors when used to crunch for GPUGRID? Perhaps I am mistaken, but I would assume that the card counts as two processors when not run in SLI mode. I already know that SLI is not supported for GPUGRID, so I would not run the card in SLI mode.

Thanks.

---

Does a Titan Z count as one or two processors when used to crunch for GPUGRID?

That's correct, it counts as two coprocessors.

Perhaps I am mistaken, but I would assume that the card counts as two processors when not run in SLI mode.

Your assumption is correct.

I already know that SLI is not supported for GPUGRID, so I would not run the card in SLI mode.

As far as I know, there's no such GPGPU application to date which could use the card in SLI mode.
It became possible only in the latest CUDA version (7.5).
I think if there will be a client which could use SLIed cards for computing, the acceleration wouldn't scale in direct ratio. Also the WDDM overhead's impact on performance is getting more and more severe as GPUs gets faster & faster, so you'd better off with two coprocessors, than with one SLIed (as far as every workunit can be returned in 24 hours).

Thanks.

---

Just to help clarify, it counts as having two processors (GPUs) whether being in SLI or not. SLI basically just lets some specific applications utilize both GPUs at the same time.

I have SLI enabled on my Titan Black cards, since I use some of those applications, but I've also set up a custom config file to run 2 long run work tasks for GPUGrid per GPU (4 total).

To get the most out of your Titan Z, you'll want to do something similar, though it is recommend to not use SLI. For GPUGrid, there is no reason to use SLI (even if GPUGrid could take advantage of it), because of the ability to assign multiple tasks to use the available resources more efficiently, and because SLI wastes card memory, effectively cutting it in half by mirroring it between GPUs.

---

My BOINC Cruncher, Minecraft Multiserver, Mobile Device Mainframe, and Home Entertainment System/Workstation: http://www.overclock.net/lists/display/view/id/4678036#

The application does not allow you to run one task on two GPU cores simultaneously. The app could be adapted to do so but for GPUGrid research via Boinc it's not suitable. Even if GPUGrid wanted to do this (and overall it would probably be slower), it would only work on some cards and not the cards for which it might be most useful; the GTX 750 and GTX750Ti for example cannot support Sli but the user (credits) and the project (turnaround) would be most likely to benefit. Things might change with Pascal.

---

FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help