[Bf-cycles] CUDA Memory usage: Call for testing
wfaehnle at freenet.de
Sun Jan 10 22:12:55 CET 2016
Hi, check several files, the usual suspects!
All scenes need slightly less memory with experimental kernel.
Some render times:
Supported = 01:10.30
Experimental = 01:19.00
Supported = 01:01.77
Experimental = 01:06.04
Supported = 00:25.47
Experimental = 00:27.54
Intel i5 3770K
GTX 760 4 GB /Display card
GTX 670 2 GB
Am 10.01.2016, 20:41 Uhr, schrieb Thomas Dinges <blender at dingto.org>:
> Hi everyone,
> For Blender 2.72 we added the CUDA Experimental kernel, to have SSS
> working on the GPU.
> The reason we added an extra kernel was mainly an increased memory usage
> during render.
> Good news is, this extra memory usage has been fixed by Sergey. I ran
> some tests and rendering several scenes with the Experimental kernel
> results in no or very little extra memory. I only checked GPU memory
> usage (using GPU-Z), not render time.
> So please, could people run some tests on their own and report here?
> It's very easy:
> - Download latest build for your OS from the Buildbot
> - Render using the GPU, once with the Supported feature set enabled,
> once with the Experimental one.
> - Compare render time and GPU memory usage.
> If you compile Blender yourself, make sure you use CUDA Toolkit 6.5 and
> latest master.
> You can use scenes from here:
> - Simple scenes:
> - Larger ones:
> If there is no or little memory / render time increase we can drop the
> extra CUDA kernel, improving Code maintenance and CUDA compilation time.
> Bf-cycles mailing list
> Bf-cycles at blender.org
Erstellt mit Operas E-Mail-Modul: http://www.opera.com/mail/
More information about the Bf-cycles