Development and performance of a HemeLB GPU code for human-scale blood flow simulation

DOI10.1016/J.CPC.2022.108548MaRDI QIDQ6155474zbMATH OpenOpenAlexFDO

Authors I. Zacharoudiou, J. W. S. McCullough, Peter V. Coveney

Publication date 5 June 2023

Published in Computer Physics Communications (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2202.11770

zbMATH Keywords

lattice Boltzmann methodhigh performance computingblood flow modelling

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX) Fluid mechanics (76-XX)

Abstract: In recent years, it has become increasingly common for high performance computers (HPC) to possess some level of heterogeneous architecture - typically in the form of GPU accelerators. In some machines these are isolated within a dedicated partition, whilst in others they are integral to all compute nodes - often with multiple GPUs per node - and provide the majority of a machine's compute performance. In light of this trend, it is becoming essential that codes deployed on HPC are updated to execute on accelerator hardware. In this paper we introduce a GPU implementation of the 3D blood flow simulation code HemeLB that has been developed using CUDA C++. We demonstrate how taking advantage of NVIDIA GPU hardware can achieve significant performance improvements compared to the equivalent CPU only code on which it has been built whilst retaining the excellent strong scaling characteristics that have been repeatedly demonstrated by the CPU version. With HPC positioned on the brink of the exascale era, we use HemeLB as a motivation to provide a discussion on some of the challenges that many users will face when deploying their own applications on upcoming exascale machines.

Recommendations

• GPU-based simulation of 3D blood flow in abdominal aorta using OpenFOAM
• Parallel performance of a lattice-Boltzmann/finite element cellular blood flow solver on the IBM blue gene/P architecture
• LBM based flow simulation using GPU computing processor
• GPU-accelerated DNS of compressible turbulent flows
• Multi-GPU Based Lattice Boltzmann Method for Hemodynamic Simulation in Patient-Specific Cerebral Aneurysm

Cites work

• A Model for Collision Processes in Gases. I. Small Amplitude Processes in Charged and Neutral One-Component Systems
• An evaluation of lattice Boltzmann schemes for porous medium flow simulation
• Hemelb: A high performance parallel lattice-Boltzmann code for large scale fluid flow in complex geometries
• Hydrokinetic approach to large-scale cardiovascular blood flow
• Lattice Boltzmann method and its applications in engineering
• Lattice Boltzmann method. Fundamentals and engineering applications with computer codes
• Lattice-Boltzmann simulations of particle-fluid suspensions.
• Multi-GPU Based Lattice Boltzmann Method for Hemodynamic Simulation in Patient-Specific Cerebral Aneurysm
• Multi-GPU implementation of the lattice Boltzmann method
• Multi-scale computational model of three-dimensional hemodynamics within a deformable full-body arterial network
• Numerical simulations of particulate suspensions via a discretized Boltzmann equation. Part 1. Theoretical foundation
• Palabos: parallel lattice Boltzmann solver
• The lattice Boltzmann equation. For complex states of flowing matter
• The lattice Boltzmann equation. For fluid dynamics and beyond
• The lattice Boltzmann method. Principles and practice
• \textsc{waLBerla}: a block-structured high-performance framework for multiphysics simulations

Cited in

(1)

• Efficient multi-GPU implementation of a moving boundary approach in rotor flow simulation using LBM and level-set method

This page was built for publication: Development and performance of a HemeLB GPU code for human-scale blood flow simulation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6155474)