Matthieu Delahaye, Solutions Architect, MulticoreWare Inc.

I joined MulticoreWare in 2011 where my principal occupation is to support the development of new compiler technologies related to GPU compute. Before joining Multicoreware, I was a Research Engineer at the University of Illinois where I have been involved in different projects, always focusing on increasing software performance.... Read More and Join us for his webinar on Quickly Optimizing OpenCL™ with SlotMaximizer

Going to OSCON? Don't miss Gary Frost's Aparapi talk
If you're going to be at O'Reilly's OSCON in Portland this year, you should catch Gary Frost's Aparapi talk. Aparapi allows developers to code entirely in Java (via a data parallel API). At runtime, Aparapi is capable of converting Java bytecode to OpenCL so that it can be executed on the GPU. Gary's talk will contrast Aparapi with other OpenCL Java bindings, describe how it works, & walk through some real world examples. » Learn more about Aparapi.

DirectCompute Code Sample
This sample presents a highly optimized technique for accelerating separable filters using DirectCompute, with a fall back Pixel Shader path also provided. It also allows developers to easily create their own specific filters, using just a handful of user defined macros. » Learn More

CodeAnalyst Performance Analyzer Update Now Available
The latest update now allows Windows developers to use CodeAnalyst integrated into Visual Studio 2012. And now Linux developers have performance monitoring counter (PCM) events and Instruction-Based Sampling (IBS) and support for new processors and Linxu distributions. » Download the latest versions here

Updates from Around the Globe
Check out the New India AMD Developer Zone website with local news, events and job listings. And from China we just got permission to translate and republish the interview that the China Software Developer Network (CSDN) did with AMD's Leendert Van Doorn, Corporate Fellow & CVP, titled Heterogeneous System Architecture Programming: Today and Tomorrow.

Submit suggestions for news to

OpenCL Programming Webinar Series Date Time
Quickly Optimize OpenCL Applications with SlotMaximizer (Asia time slot) July 25, 2012 9:30AM India /
12:00PM China
Graphics Core Next Architecture Overview August 14, 2012 10:00AM Pacific Time
 Conferences  Date  Location
OSCon July 16-20, 2012 Portland, OR
Siggraph August 5-9, 2012 Los Angeles, CA
"Travelling in Style" C++ AMP Programming Contest Enter by August 31, 2012 Hosted by Beyod3D
 Training  Date  Location
C++ AMP Training by Acceleware (Use promotional code AXAMD2012 to save $350 off your course fee!) July 24, 2012 Mountain View, CA
OpenCL Programming Course by Acceleware (Use promotional code AXAMD2012 to save $350 off your course fee!) August, 21-24 Houston, TX
OpenCL Programming Course by Acceleware (Use promotional code AXAMD2012 to save $350 off your course fee!) Sepetember 11-14 Los Angeles, CA
OpenCL Programming Course by Acceleware (Use promotional code AXAMD2012 to save $350 off your course fee!) October 16-19 Calgary, AB
OpenCL Software Development Downloads

OpenCL Training Online

Recommended Reading

University Programs

Send comments and suggestions for the newsletter to and follow us on Twitter @hcNewsFlash


Very often a GPU kernel has to return a few values to the host for inspection. For example, to check optimization criterion, get a result of a dot product or similar reduction operator. The data copy from the video memory to the host memory is a costly operation on a discrete GPU and still on APU right now, disproportionally so for a small chunk of data.
It's possible to reduce such cost to nearly zero. Learn how

Submit your Tips&Tricks to

AMD is Hiring!

Engineering and Engineering Manager Jobs who have OpenCL and C++ AMP backgrounds

Submit Heterogeneous Compute job listings to

Connect with the heterogeneous community and be a part of this new era of computing!

     LinkedIn FaceBook  Twitter YouTube
©2012 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo, Radeon and combinations thereof are trademarks of Advanced Micro Devices, Inc.

Advanced Micro Devices, Inc., One AMD Place, P.O. Box 3453, Sunnyvale, California 94088-3453 USA
AMD Developer Central | RSS | Copyright | Privacy | Trademark Info