Thing is, with these modern GPU cards, usually on a PCI-Express bus, is
that you can have as many as you like... 

Also it's not OpenGL that you'll be using to implement anything, more
likely OpenCL (looking good currently, very C-like) 
http://www.khronos.org/opencl/
or NVIDIA's CUDA.

Don't know if anything will come of it, but still fun to speculate...


On Tue, 2011-03-01 at 13:07 -0500, Raul Miller wrote:
> http://rastergrid.com/blog/2010/02/instance-culling-using-geometry-shaders/
> 
> Here, it looks like someone has implemented something very like
> 
>    (#~ filter) data
> 
> in a modern GPU.
> 
> I wonder how long it will be until OpenGL with a modern GPU will be
> powerful enough to implement J, and fast enough to have significant
> speed advantages over the current pure cpu implementation?  (Though I
> imagine we would want to have enough resources left over to support
> some kind of gui -- perhaps
> http://www.cegui.org.uk/wiki/index.php/Main_Page? -- I imagine some
> people would be disappointed to have a GPU based J that could not
> afford to render anything.)
> 


----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm

Reply via email to