2019 · 17 citations · 7 references
EngineeringComputer ScienceHigh-performance ComputingComputer ArchitectureField-programmable Gate ArraysParallel ComputingData ParallelismField-programmable Gate Array ArchitectureFpga ArchitectureHardware AccelerationHigh-level SynthesisField-programmable Gate Arrays (Fpgas)Fpga OffloadingFpga PrototypingHigh-performance Computing SystemsOpencl ProgrammingOpenmpParallel Data ProcessingParallel Processing
Field-programmable gate arrays (FPGAs) are of great interest for future high-performance computing and data analytics systems, since they are capable of efficient, highly-parallel data processing. Even though high-level synthesis became more popular in the last years, the effort of porting existing scientific software onto FPGAs is still considerable. We propose to use OpenMP target offloading as a solution, which we implement in a first prototype, making use of the preexisting OpenCL SDK of the FPGA vendor. Early results demonstrate the feasibility of this approach and also reveal that further optimizations will be necessary such that code can be written in an FPGA-agnostic way.
7
The Promise of High-Performance Reconfigurable Computing
Tarek El‐Ghazawi, Esam El‐Araby, Miaoqing Huang et al. · Computer · 2008 · 155 citations
Engineering, Computer Science, High-performance Computing +16
OpenMP device offloading to FPGA accelerators
Lukáš Sommer, Jens Korinth, Andreas Koch · 2017 · 50 citations
Engineering, Computer Science, High-performance Computing +17
Generating hardware from OpenMP programs
Y.Y. Leow, Chun-Kit Ng, Weng‐Fai Wong · 2006 · 44 citations