[Bf-cycles] Cycles criteria to set the default CUDA computing device

[Brecht Van Lommel]

No, that's not really the right behavior. If all devices are display
devices, we should really enable all of them by default. It seems
strange though that these Tesla cards would have a timeout, maybe it's
very big, otherwise that could make rendering unreliable.

Brecht.

On Mon, Jan 14, 2013 at 11:26 PM, Dalai Felinto <dfelinto at gmail.com> wrote:
> Hi Brecht,
>
> You explained me about the CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT over IRC,
> but I wanted to double-check if I got it right.
> I have a system with three GPUs, all of them setup as "Display GPU".
>
> In this case, should we have the CUDA_MULTI* as the automatic option if we
> set CUDA as device?
> Or to have CUDA_0 as the default (as it is now) is the expected behaviour?
>
> The available computing devices:
> ('Intel Xeon CPU', 'Tesla M2070', 'Tesla M2070', 'Tesla M2070', 'Tesla M2070
> (3x)')
> (‘CUDA_0′, ‘CUDA_1′, ‘CUDA_2′, ‘CUDA_MULTI_2′)
>
> And with this patch [1] I get the following info:
> [1] http://www.pasteall.org/38837
>
> *** Begin CUDA Debug
> CUDA device 0 is a Display GPU
> CUDA device 0 has "14"
> CUDA device 1 is a Display GPU
> CUDA device 1 has "14"
> CUDA device 2 is a Display GPU
> CUDA device 2 has "14"
> *** End CUDA Debug
>
> Is this the expected behaviour?
>
> Thanks,
> Dalai
>
> blendernetwork.org/member/dalai-felinto
> www.dalaifelinto.com
>
> _______________________________________________
> Bf-cycles mailing list
> Bf-cycles at blender.org
> http://lists.blender.org/mailman/listinfo/bf-cycles
>