Date:
Monday , January 18, 2010
Category:
GPU / Video Cards
Manufacturers:
AMD
Author:
Kyle Bennett

Geeking Out with AMD and OpenCL

If running a canned benchmark is something you consider a challenge, this is not for you! In fact, it is not for most of us. But if you feel the need to get under the covers when it comes to OpenCL, this is your chance. AMD has put together a short series of videos about OpenCL from a programming viewpoint.

Introduction

If you are a gamer that likes video card tech, it is doubtful that you have not heard the term "OpenCL" thrown around a bit. OpenCL stands for "Open Computer Language" and represents a way to program that gives its users a "heterogeneous" environment. What this means is that this code can be executed on an GPU, CPU, or other processing unit. Many gamers and GPGPU coders are looking forward to the implementation of this type of code as it will break the bonds of some of the proprietary languages used in the market such as CUDA.

OpenCL™ is the first open, royalty-free standard for cross-platform, parallel programming of modern processors found in personal computers, servers and handheld/embedded devices. OpenCL (Open Computing Language) greatly improves speed and responsiveness for a wide spectrum of applications in numerous market categories from gaming and entertainment to scientific and medical software.

If you want to know more about OpenCL, check out this page as is it is full of OpenCL goodness.

Geeking Out with AMD

Today we have a series of videos below from AMD that talk about AMD and OpenCL usage. To put it plainly, these videos are more pointed toward programmers rather than someone looking the latest physics demo.

OpenCL Design Goals and Execution Model

OpenCL Platform and Memory Modules

OpenCL Resource Setup

OpenCL Kernel Execution

OpenCL and Programming Features and Functions

Discussion