[Openmcl-devel] Speed, compilers and multi-core processors

[Raffael Cavallaro]

On May 20, 2009, at 2:12 PM, Dan Weinreb wrote:

> One source says that CUDA can do anything you can do in C
> other than function pointers and recursion.  Probably this
> means no stack, locals are allocated at fixed addresses
> just like globals, each procedure has one global cell
> as a return address, etc.

Here's an overview of OpenCL (Nvidia has OpenCL drivers, Apple are  
including OpenCL in Snow Leopard, and Intel, AMD, IBM, ARM, Sony, etc.  
are all signed on as well).

<http://www.khronos.org/developers/library/overview/opencl_overview.pdf>

Here's a quick refererence to the api:

<http://www.khronos.org/files/opencl-quick-reference-card.pdf>


Raffael Cavallaro, Ph.D.
raffaelcavallaro at mac.com