Nuclear Reactor Simulation on OpenCL FPGA
Zheming Jin, Hal Finkel · 2018
Field-programmable gate arrays (FPGAs) are becoming a promising choice as a heterogeneous computing component for scientific computing when floating-point optimized architectures are added to the current FPGAs. The emerging high-level synthesis tools such as the Intel OpenCL SDK for FPGA highlight a streamlined design flow to facilitate the use of FPGAs in scientific computing. Investigating the characteristics of supercomputing applications, such as nuclear reactor simulation, with the emerging HLS development flow is important for researchers to evaluate and adopt FPGA-based heterogeneous programming models in research facilities and laboratories. In this paper, we evaluate the OpenCL-based FPGA design of a nuclear reactor simulation application RSBench. We describe the OpenCL implementations and optimization methods on an Intel Arria10-based FPGA platform. Compared with the naïve OpenCL kernel, the optimizations of the kernel increase the performance by a factor of 295 on the FPGA. Compared with an Intel Xeon 16-core CPU and an Nvidia K80 GPU, the performance per watt on the FPGA is 3.59 X better than the CPU and 5.8X lower than the GPU.