Efficient custom computing of fully-streamed lattice boltzmann method on tightly-coupled FPGA cluster

Abstract

This paper presents the detailed design of a custom computing machine for fully-streamed LBM computation on multiple FPGAs, and evaluates its efficiency with prototype implementation. We design a unit for completely streamed computation including boundary treatment with a newly introduced cell attribute. Experimental results demonstrate that the proposed machine achieves high utilization of PEs, 99 % of the peak performance, for one and two FPGAs computing a large lattice. This is due to our fully-streamed design to allow all arithmetic units to be efficienly utilized with a constant memory bandwidth, and the architecture to exploit a low-latency accelerator domain network (ADN) of a tightly-coupled FPGA cluster for scalable computation.