In the wake of its latest version 7.0 update to the Intel Concurrent Collections for C++ library, the company has also this month released the Intel SDK for OpenCL Applications 2012.
- Consolidation: The Foundation for IT Business Transformation
- Build a Business Case: Developing Custom Apps
- Strategy: The Hybrid Enterprise Data Center
- SaaS 2011: Adoption Soars, Yet Deployment Concerns Linger
- Simple, Effective Patch Management: From Dilemma to Done Deed
- OpenStack: Blueprint for Deployment Success
If you are questioning why this should be significant, Intel asserts that this is the first time OpenCL developers using Intel architecture will be able to utilize compute resources across both Intel Processors and Intel HD Graphics Driver 4000/2500 technology.
Nvidia defines OpenCL (Open Computing Language) as a low-level API for heterogeneous computing that runs on CUDA architecture GPUs. Using the OpenCL API, developers can launch compute kernels written using a limited subset of the C programming language on a GPU.
Intel's Arnon Peleg details the fact that it is less than a year since the OpenCL SDK 1.1 was made available as the first production OpenCL implementation from Intel targeting the firm's processors on Windows.
"OpenCL on the 3rd Generation Intel Core Processor Family extends Intel's line of tools and APIs on Intel platforms and adds interoperability with other graphics APIs like DirectX, OpenGL, and Intel Media SDK, directly on the Intel HD Graphics device," said Peleg.
Intel specifies that a single OpenCL platform now enables interoperability with the Intel Media SDK with no memory copy overhead as well as improved performance for OpenCL applications running on Xeon Processors and Intel Core Processors. This CPU support is also available for Linux OS developers.
Intel SDK for OpenCL applications development tools includes an offline compiler and a step-by-step OpenCL Kernel debugger (for CPU) integrated in Microsoft Visual Studio 2010 integrated development environment.