Past Issues November 2011 
AMD Developer Central - Code Faster. Faster Code.
 
 
In this issue:
» New Webinar: Write Once Run Anywhere
» Heterogeneous Compute Tools from MulticoreWare Inc.
» Coming soon to a browser near you!
» OpenCL™: the leading choice for GPGPU developers
» Software Update: AMD CodeAnalyst Windows 3.4 & AMD CodeAnalyst for Linux 3.1
» OpenCL™ Optimization Case Study Fast Fourier Transform - Part I and II
» Recently Added to developer.amd.com
» Upcoming Sponsored Events
 
 developer.amd.com
    Tools
SDKs
Libraries
Technology Zones
Documentation & Articles
Sample Code & Apps
Community
Member Benefits
Events
 
 
 
New Webinar: Write Once Run Anywhere

New Webinar: Write Once Run Anywhere
 Links
    RSS
Login
 

HotItem
Aparapi, an API for expressing data parallel workloads in Java, can extend Java's promise of 'Write Once, Run Anywhere' to include GPU devices. Aparapi allows developers to code against a simple Java data parallel API. At runtime Aparapi attempts to execute on the GPU by converting bytecode to OpenCL; if OpenCL is unavailable Aparapi will fall back to executing using a Java thread pool. We contrast Aparapi with other OpenCL Java bindings, describe how it works, and walk through some real world examples. We also discuss how to determine whether Aparapi is a viable option for your application.

When: December 22nd, 11am PST

Register
 
 
Heterogeneous Compute Tools from MulticoreWare Inc Heterogeneous Compute Tools from MulticoreWare Inc.

We are excited to announce the beta availability of their tools to our developers. Three new tools provide capabilities such as global memory, global task management and path analysis to ensure developers can achieve maximum benefit from their OpenCL investment. Get the beta tools today and give feedback in the MCW forums, you might qualify for a chance at a free graphics card for feedback that qualifies, details to come!

Learn More
 
 
Coming soon to a browser near you! Coming soon to a browser near you!

A whole new way for AMD Developer Central members to find answers, collaborate with experts, and stay up to date on new hardware and software features. You can help choose an alternate ending by taking a very short survey on our upcoming forums and networking platform.

Take Survey
 
 
OpenCL™: the leading choice for GPGPU developers OpenCL™: the leading choice for GPGPU developers

A recent survey by Evans Data Corporation shows the inevitable success of OpenCL. In this survey respondents ranked the most popular APIs for multi-threaded development. OpenCL is ranked #2 in North America, #2 in Europe and Middle East, and #3 in Asia-Pacific countries.

Learn More

 
 
Software Update:  AMD CodeAnalyst Windows 3.4 & AMD CodeAnalyst for Linux 3.1 Software Update: AMD CodeAnalyst Windows 3.4 & AMD CodeAnalyst for Linux 3.1

Download the new version to get support for the latest AMD processors, added support for new Linux operating systems, and a variety of bug fixes.

Download Now
 
 
OpenCL™ Optimization Case Study Fast Fourier Transform - Part I and II OpenCL™ Optimization Case Study Fast Fourier Transform - Part I and II

This article series dives into the implementation of a Fast Fourier Transform (FFT) on an AMD GPU using OpenCL™. Article I starts from the very basics and builds on itself covering an introduction to the FFT algorithm, how to build an FFT on an AMD GPU, then present performance results. By the end of the second article, we will have reasonably high performance 1-D and 2-D FFT implementations for AMD GPUs.

Learn More
 
 
Code Faster Recently Added to developer.amd.com

 New Blog Post: AMD CodeAnalyst 3.4 support for newest chips
 Compiler Options Quick Reference Guide for AMD Opteron™ 6100 Series Processors ("Magny-Cours") and AMD Opteron™ 4100 Series Processors ("Lisbon")
 Compiler Options Quick Reference Guide for AMD Opteron™ Processors codenamed "Interlagos" and AMD Opteron™ Processors codenamed "Valencia"



 
 
Upcoming Sponsored Events Upcoming Sponsored Events
  • High-Performance and Embedded Architectures and Compilers (HiPEAC) and Programmability Issues for Heterogeneous Multicores (MULTIPROG-2012)
    January 23-25: Paris, France
 See all Events