Analyzing and Modeling the Performance of the HemeLB Lattice-Boltzmann Simulation Environment

TL;DR

This paper evaluates the performance of the HemeLB lattice-Boltzmann simulator for cerebrovascular blood flow, demonstrating its high scalability, efficiency in sparse geometries, and providing a performance prediction model for clinical use.

Contribution

It introduces a performance model for HemeLB that helps optimize simulation parameters for accurate and timely cerebrovascular blood flow analysis.

Findings

Maximum performance of 29.5 billion site updates per second.

Only 11% slowdown in highly sparse problems.

Performance prediction model for simulation optimization.

Abstract

We investigate the performance of the HemeLB lattice-Boltzmann simulator for cerebrovascular blood flow, aimed at providing timely and clinically relevant assistance to neurosurgeons. HemeLB is optimised for sparse geometries, supports interactive use, and scales well to 32,768 cores for problems with ~81 million lattice sites. We obtain a maximum performance of 29.5 billion site updates per second, with only an 11% slowdown for highly sparse problems (5% fluid fraction). We present steering and visualisation performance measurements and provide a model which allows users to predict the performance, thereby determining how to run simulations with maximum accuracy within time constraints.