When DirectCompute, a component of the Microsoft DirectX 11 API, was released with Windows 7 last fall, the ATI Radeon™ HD 5800 Series graphics were the only graphics processors on the market to fully support DirectX 11. Today, AMD offers a wide range of graphics solutions, including ATI Radeon™, ATI FirePro™ and ATI FireStream™ graphics, which can take advantage of DirectCompute through support for ATI Stream technology.[1] DirectCompute allows access to the shader cores/pipeline for Stream Computing (graphics acceleration) applications and physics acceleration; it is fundamentally designed to enable compute intensive applications to take advantage of the massively parallel power of the GPU. Since that initial launch, AMD has been working with Microsoft to ensure our hardware can be fully leveraged through DirectCompute, and AMD firmly believes the key to ensuring long-term success and mainstream adoption of stream processing is through the use and support of industry standards like DirectX and Open CL™.

As we’ve mentioned before, one of the biggest technology breakthroughs of the past five years has undoubtedly been the notion that processing can be moved from the traditional CPU to the much more parallel GPU. With the forthcoming AMD Fusion family of Accelerated Processing Units (APUs), we’ll make significant strides in combining high-performance serial computing and parallel graphics processing cores onto a single die to improve visual and data-intensive tasks that are pervasive in today’s computing environments.

For developers coding applications in a Windows environment, DirectCompute provides better access to the GPU as a compute resource, which will enable new capabilities that were not possible previously. In order to provide developers with the information they need to leverage DirectCompute and the compute acceleration capabilities of the GPU, Microsoft has put together a DirectCompute Lecture Series. AMD’s take on DirectCompute can be found in these video sessions:

1. AMD’s Justin Hensley, Senior MTS, AMD Office of CTO is featured in the opening video lecture, which was a round table discussion of thought leaders in parallel computing.
2. Jason Yang, MTS Software Engineer of AMD presented on the Basics of DirectCompute Application Development on June 25th.
3. On July 2nd, Lee Howes, Sr. Software Development Engineer of AMD gave a video lecture on DirectCompute GPU Accelerated Physics

These videos should give you a solid point of reference on DirectCompute and GPU acceleration. Of course we’re always interested to hear how you’re using DirectCompute and leveraging the GPU. We welcome your comments below.

Clarice Simmons is a Product Marketing Manager at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

---

[1] Not all graphics models that support ATI Stream Technology support Microsoft DirectX 11. Check with the manufacturer for specific model support information.