Past Issues September 2010
AMD Developer Central

IN THIS ISSUE:
» “Bulldozer” Processor Topology
» Just Released: Aparapi, an API for Data Parallel Workloads in Java
» New: ATI GPU Services (AGS) Library
» OpenCL™ Optimization Case Study: Simple Reductions
» Featured on Code Project: OpenCL™ – Portable Parallelism, Part 1
» Now Available: Chinese Language OpenCL™ Programming Guide (pdf)
» Recently Added to developer.amd.com
» Upcoming Sponsored Events
 developer.amd.com
  CPU Tools
GPU Tools
Technology Zones
Documentation & Articles
Sample Code & Apps
Community
Member Benefits
Events
 
 
 
“Bulldozer” Processor Topology

“Bulldozer” Processor Topology
 Links
  Quick Poll
RSS
Login
 

HotItem   

Processor Topology has changed dramatically over the years and will continue to evolve.  Elsie Wahlig, AMD Fellow in the Software Division, steps through a processor block diagram for the “Bulldozer” Module and highlights the areas that have changed over what is currently available today with the “Magny-Cours” Processor.  She also talks about what kind of developer really needs to know this level of processor detail and what tools they can use to get all the topology information they need.

View Now

 
 
Just Released: Aparapi, an API for Data Parallel Workloads in Java Just Released: Aparapi, an API for Data Parallel Workloads in Java

Aparapi is an API for expressing data parallel workloads in Java and running those workloads on a compatible GPU if possible.  Using the ATI Stream SDK with a compatible GPU, if your Java parallel code avoids any constructs that would make it untranslatable to OpenCL™, Aparapi will translate your workload to OpenCL™ and will run your workload on the GPU.
OpenCL and the OpenCL logo are trademarks of Apple Inc. used by permission by Khronos.

Download Now

 
 
New: ATI GPU Services (AGS) Library New: ATI GPU Services (AGS) Library

This library provides software developers with the ability to query ATI GPU software and hardware state information that is not normally available through standard operating system or graphic APIs. Version 1.0 of the library includes support for querying graphics driver version info, Crossfire (ATI’s multi-GPU rendering technology) configuration info, as well as Eyefinity (ATI’s multi-display rendering technology) configuration info.

Download Now

 
 
OpenCL™ Optimization Case Study: Simple Reductions OpenCL™ Optimization Case Study: Simple Reductions

Reductions, which take a vector of data and reduce it to a single element, are widely used in data-parallel programming. In this article, we examine strategies for efficiently mapping reductions onto the ATI Radeon™ HD 5870 GPU and AMD Phenom™ II X4 965 CPU. Taking advantage of properties of the reduction being performed, as well as matching the style of reduction to the hardware platform, can result in performance improvements of up to 15x, compared to native code.

Learn More

 
 
Featured on Code Project:  OpenCL™ – Portable Parallelism, Part 1 Featured on Code Project: OpenCL™ – Portable Parallelism, Part 1

This first article in a series on portable multithreaded programming using OpenCL™ briefly discusses the thought behind the standard and demonstrates how to download and use the ATI Stream software development kit (SDK) to build and run an OpenCL program.  Includes example code that can run on both CPU and GPU device types.

Learn More

 
 
OpenGL ES 2.0 Coming to a Desktop Near You Now Available: Chinese Language OpenCL™ Programming Guide (pdf)

This Chinese language programming guide covers the following topics:

  • What is OpenCL™
  • ATI Stream Technology
  • OpenCL™ Platform Module
  • OpenCL™ Memory Model
  • OpenCL™ Execution Model
  • OpenCL™ Programming Model
Download Now
 
 
Code Faster Recently Added to developer.amd.com

 Hardware Accelerated Web with AMD and Internet Explorer 9
 ATI Stream SDK v2.2
 Updated: Lightweight Profiling Specification


 
 
Upcoming Sponsored Events Upcoming Sponsored Events
  • VMWorld Europe
    October 11-14:  Copenhagen, Denmark
  • SEG
    October 17-22:  Denver, Colorado
  • Supercomputing 2010
    November 13-19:  New Orleans, Louisiana
 See all Events


AMD.comAMD.com