Reduced and mixed precision turbulent flow simulations using explicit finite difference schemes

TL;DR

This paper investigates mixed and reduced precision arithmetic in turbulent flow simulations, demonstrating that carefully chosen mixed precision strategies can enhance performance while maintaining accuracy on modern HPC hardware.

Contribution

It extends simulation frameworks to support customizable precision levels and evaluates mixed precision strategies for turbulent flow simulations, highlighting performance benefits and accuracy considerations.

Findings

Mixed precision strategies improve computational speed and reduce memory usage.

Pure half-precision leads to unacceptable accuracy loss.

Careful precision selection balances performance and accuracy.

Abstract

The use of reduced and mixed precision computing has gained increasing attention in high-performance computing (HPC) as a means to improve computational efficiency, particularly on modern hardware architectures like GPUs. In this work, we explore the application of mixed precision arithmetic in compressible turbulent flow simulations using explicit finite difference schemes. We extend the OPS and OpenSBLI frameworks to support customizable precision levels, enabling fine-grained control over precision allocation for different computational tasks. Through a series of numerical experiments on the Taylor-Green vortex benchmark, we demonstrate that mixed precision strategies, such as half-single and single-double combinations, can offer significant performance gains without compromising numerical accuracy. However, pure half-precision computations result in unacceptable accuracy loss, underscoring the need for careful precision selection. Our results show that mixed precision configurations can reduce memory usage and communication overhead, leading to notable speedups, particularly on multi-CPU and multi-GPU systems.