Maybe it's the holiday season that has big corporations in a giving mood this month, but there's definitely something in the air that's spreading the love of open source software. Whatever it is, Hewlett-Packard caught wind of it last week and flipped the open source switch on webOS, and now Nvidia is announcing plans to provide the source code for the new CUDA LLVM-based compiler to academic researchers and software-tool vendors to help make it easier to add GPU support for more programming languages and support CUDA applications on alternative processor architectures.
"Opening up the CUDA platform is a significant step," said Sudhakar Yalamanchili, professor at Georgia Institute of Technology and lead of the Ocelot project, which maps software written in CUDA C to different processor architectures. "The future of computing is heterogeneous, and the CUDA programming model provides a powerful way to maximize performance on many different types of processors, including AMD GPUs and Intel x86 CPUs."
LLVM is a popular open source compiler infrastructure used for a range of programing requirements by big companies like Adobe, Apple, Cray, Electronic Arts, and others, Nvidia says. The new LLVM-based CUDA compiler is enhanced with architecture support for Nvidia's parallel GPUs and is included in the latest release of the CUDA Toolkit (v4.1).