POCL 1.6 Released For Portable OpenCL Atop CPUs, Other Accelerators
POCL 1.6 is out as the latest feature release and continues providing OpenCL 1.2 support and a subset of OpenCL 2.0 functionality. POCL is most well known for OpenCL on CPUs but thanks to LLVM also allows targeting NVIDIA GPUs with CUDA, AMD GPUs with HSA, and other possible accelerator targets. POCL makes use of LLVM's Clang OpenCL front-end.
POCL 1.6 brings support for LLVM Clang 11 while training backwards compatibility down to LLVM ~6, improved OpenCL debugging support, much faster NVIDIA CUDA based execution, restores PowerPC support, and offers better packaging support.
More details on the changes to find with POCL 1.6 as well as source and binary downloads can be found via PortableCL.org.