Accelerating CFD simulation with high order finite difference method on curvilinear coordinates for modern GPU clusters

TL;DR

This paper presents a hardware-aware GPU acceleration approach for high order finite difference CFD simulations on curvilinear grids, achieving up to 2000x speedup over CPU implementations.

Contribution

It introduces a set of hardware-aware optimizations for high order finite difference CFD solvers on GPUs, enabling efficient simulations on modern heterogeneous HPC systems.

Findings

Achieved up to 2000x speedup over CPU-based solvers.

Demonstrated significant acceleration across different GPU models.

Validated the effectiveness of hardware-aware data transfer and communication optimizations.

Abstract

A high fidelity flow simulation for complex geometries for high Reynolds number ($Re$) flow is still very challenging, which requires more powerful computational capability of HPC system. However, the development of HPC with traditional CPU architecture suffers bottlenecks due to its high power consumption and technical difficulties. Heterogeneous architecture computation is raised to be a promising solution of difficulties of HPC development. GPU accelerating technology has been utilized in low order scheme CFD solvers on structured grid and high order scheme solvers on unstructured meshes. The high order finite difference methods on structured grid possess many advantages, e.g. high efficiency, robustness and low storage, however, the strong dependence among points for a high order finite difference scheme still limits its application on GPU platform. In present work, we propose a set of hardware-aware technology to optimize the efficiency of data transfer between CPU and GPU, and efficiency of communication between GPUs. An in-house multi-block structured CFD solver with high order finite difference methods on curvilinear coordinates is ported onto GPU platform, and obtain satisfying performance with speedup maximum around 2000x over a single CPU core. This work provides efficient solution to apply GPU computing in CFD simulation with certain high order finite difference methods on current GPU heterogeneous computers. The test shows that significant accelerating effects can been achieved for different GPUs.