OEMs can now add the parallel processing power of the AMD Radeon 6310 GPU to their applications. By doing this, it's possible to add supercomputer-like performance to small-form-factor embedded designs and obtain a previously unachievable performance-per-watt ratio. Additionally, with the support for OpenCL 1.1 and Microsoft DirectCompute, parallel processing executed by the graphics core will speed up vector processing applications such as situational awareness and video surveillance in the industrial automation, military and medical markets.
Common to all the performance levels of the new boards and modules based on the AMD Embedded G-Series platform are their discrete-level graphics capabilities. Providing support for the latest DirectX® 11 API, they enhance all conventional graphics-intensive small-form-factor applications.
Implementing the hardware is only one part of the game. OEMs also face the challenge of implementing this state-of-the-art technology in their new or existing applications, including validation and verification of the applications’ functionality and access to hardware functions and I/Os. To reduce the amount of R&D work, lower costs and shorten their products’ time to market, they seek ways to cut down their initial development and migration tasks. One approach is to make use of a hardware vendor’ migration services.