S. Somasegar is the corporate vice president of the Developer Division at Microsoft. Learn more about Somasegar.
As an industry trend, advancement in heterogeneous hardware has progressed at a rapid pace. This in turn has fueled developer desire to target such hardware for accelerated computation, necessitating a significant step forward in programming models to enable such practices.
C++ Accelerated Massive Parallelism (C++ AMP) is a new technology implemented in Visual Studio 11 that helps C++ developers use accelerators such as the GPU for parallel programming. I’ve blogged about it since its initial disclosure, including discussing our intention to share the C++ AMP specification so as to help bring general purpose GPU programming to all C++ developers, regardless of whether they’re using Visual C++. I am excited today to deliver on that commitment.
Today at the GoingNative 2012 event, Microsoft announced publication, under the Microsoft Community Promise license, of the C++ AMP open specification. This release means compiler developers and vendors now have the ability to implement C++ AMP in their compilers, just as Microsoft has done, broadening access for C++ developers everywhere to the possibilities offered by heterogeneous hardware.
Please send any feedback you have on this to the C++ AMP team via their blog.