OpenMP Device Offloading to FPGAs Using the Nymble Infrastructure.

Next to GPUs, FPGAs are an attractive target for OpenMP device offloading, as they allow to implement highly efficient, applications-specific accelerators. However, prior approaches to support OpenMP device offloading for FPGAs have been limited by the interfaces provided by the FPGA vendors' HLS tool interfaces or their integration with the OpenMP runtime, e.g., for data mapping. This work presents an approach to OpenMP device offloading for FPGAs based on the LLVM compiler infrastructure and the Nymble HLS compiler. The automatic compilation flow uses LLVM IR for HLS-specific optimizations and transformation and for the interaction with the Nymble HLS compiler. Parallel OpenMP constructs are automatically mapped to hardware threads executing simultaneously in the generated FPGA accelerator and the accelerator is integrated into libomptarget to support data-mapping. In a case study, we demonstrate the use of the compilation flow and evaluate its performance.