[Bf-committers] Blender and OpenCL

[Jeroen Bakker]

Hi,

I have done a proof of concept on Blender and OpenCL. My victim is the 
compositing node system. I learned a lot during these 4 hours and put it 
on my website including the patch.

http://sicg.atmind.nl/index.php?option=com_content&view=article&id=21:blender-compositor-and-opencl&catid=8:blender&Itemid=12

I am wondering if this patch works on other systems.

Regards,
Jeroen

On 08/25/2010 01:42 PM, Jeroen Bakker wrote:
> On 08/25/2010 07:36 AM, Lukas Tönne wrote:
>    
>> You may have noticed the new simulation nodes i am currently working
>> on ( http://phonybone.planetblender.org/ ). Until now i didn't really
>> pay attention to OpenCL, in fact i even made my own multithreaded
>> batch processing system for object data like vertices and particles.
>> Yesterday i took a closer look at what OpenCL can actually do and i
>> have to say i'm quite intrigued now :) Coding the node execution
>> process is just one half of the journey, currently i am working on
>> further improvements of ui features. When that is done i definitely
>> want to give OpenCL a try and such a general framework could be very
>> helpful.
>>
>>
>>      
> This is really a good situation where OpenCL can have good benefits.
> Based on your node system a custom OpenCL source code can be generated
> (like the current Material->PixelShaders) and can be performed and
> cached. OpenCL has an event system that can be used for joining threads
> etc. You should really look into that aspect of OpenCL.
>
> As you could have read am I looking into Node systems as these can
> become very complex for normal CPU based things. And your node system
> can also have a very large dataset. That is also a very good requirement
> for going to OpenCL.
>
> Jeroen
> _______________________________________________
> Bf-committers mailing list
> Bf-committers at blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers
>
>