LLVM's Clang Is Working On Unified Offloading Support

There's more work going on in the CUDA/OpenMP space for the LLVM Clang compiler.

Landing this week in Clang SVN/Git is generic offload toolchains for the concept of an offloading tool chain plus related work. The initial patch explains, "This patch is the first of a series of three that attempts to make the current support of CUDA more generic and easier to extend to other programming models, namely OpenMP."

This work has been ongoing for several months and a broader look at this generic/unified offloading tool-chain work for Clang can be found via this mailing list thread.