A Heterogeneous Architecture for Evaluating Real-Time One-Dimensional Computational Fluid Dynamics on FPGAs

Isaac Liu1,  Matthew Viele2,  Guoqiang Wang3,  Edward Lee1,  Hugo Andrade3
1UC Berkeley, 2Drivven, Inc., 3NI


Abstract

Many fuel systems for diesel engines are developed with the help of commercial one-dimensional computational fluid dynamics (1D CFD) solvers that model and simulate the behavior of fluid flow through the interconnected pipes off-line. This paper presents a novel framework to evaluate 1D CFD models in real time on an FPGA to improve fuel pressure estimation and close the loop on fuel delivery, allowing for a cleaner and more efficient engine. The real-time requirements are defined by the physics and geometry of the problem being solved, which determine how long a time step should be. In this framework, the interconnected pipes are partitioned into individual sub-volumes that compute their pressure and flow rate every time step based upon neighboring values. We use timing-based synchronization and multiple Precision Timed (PRET) processor cores to ensure the real-time constraints are met. Leveraging the programmability of FPGAs, we use a configurable heterogeneous architecture to save hardware resources. Several examples are presented along with the synthesis results on a Xilinx Virtex 6 FPGA. The results demonstrate the resource savings and scalability of our framework, confirming the feasibility of our approach -- solving 1D CFD models in real time on FPGAs.