High-Performance Spectral Element Methods on Field-Programmable Gate Arrays

TL;DR

This paper explores the use of modern FPGAs to accelerate the Spectral Element Method in computational fluid dynamics, demonstrating performance and power efficiency improvements over traditional systems and modeling future FPGA capabilities.

Contribution

It introduces a custom double-precision SEM hardware accelerator on Stratix 10 FPGAs and compares its performance with existing high-performance computing systems.

Findings

FPGAs can significantly accelerate SEM in CFD applications.

The FPGA-based accelerator shows competitive performance and power efficiency.

A performance model predicts future FPGA capabilities for CFD acceleration.

Abstract

Improvements in computer systems have historically relied on two well-known observations: Moore's law and Dennard's scaling. Today, both these observations are ending, forcing computer users, researchers, and practitioners to abandon the general-purpose architectures' comforts in favor of emerging post-Moore systems. Among the most salient of these post-Moore systems is the Field-Programmable Gate Array (FPGA), which strikes a convenient balance between complexity and performance. In this paper, we study modern FPGAs' applicability in accelerating the Spectral Element Method (SEM) core to many computational fluid dynamics (CFD) applications. We design a custom SEM hardware accelerator operating in double-precision that we empirically evaluate on the latest Stratix 10 GX-series FPGAs and position its performance (and power-efficiency) against state-of-the-art systems such as ARM ThunderX2, NVIDIA Pascal/Volta/Ampere Tesla-series cards, and general-purpose manycore CPUs. Finally, we develop a performance model for our SEM-accelerator, which we use to project future FPGAs' performance and role to accelerate CFD applications, ultimately answering the question: what characteristics would a perfect FPGA for CFD applications have?