Computational Fluid and Particle Dynamics Simulations for Respiratory System

Abstract

Computational fluid and particle dynamics simulations (CFPD) are of paramount importance for studying and improving drug effectiveness. Computational requirements of CFPD codes involves high-performance computing (HPC) resources. For these reasons we introduce and evaluate in this paper system software techniques for improving performance and tolerate load imbalance on a stateof-the-art production CFPD code. We demonstrate benefits of these techniques on both Intel-and Arm-based HPC clusters showing the importance of using mechanisms applied at runtime to improve the performance independently of the underlying architecture. We run a real CFPD simulation of particle tracking on the human respiratory system, showing performance improvements of up to 2×, keeping the computational resources constant. CCS CONCEPTS • Computing methodologies → Parallel programming languages; • Applied computing → Systems biology; • Computer systems organization → Multicore architectures; • Hardware → Emerging architectures;

Runtime mechanisms to survive new HPC architectures: A use case in human respiratory simulations

“…Within the code of Alya, we already tested runtime mechanisms to mitigate load imbalance penalties on an Intel-based HPC cluster (Garcia-Gasulla et al, 2018a). This work is an extension of our previous work (Garcia-Gasulla et al, 2018b). While the underlying runtime techniques are substantially the same in the two articles, we include in this extension a more extensive evaluation, including state-of-the-art HPC CPU architectures.…”

GOPHER, an HPC Framework for Large Scale Graph Exploration and Inference

“…This work opens a wide range of future work opportunities, we plan to study in detail the performance of GOPHER to find optimization opportunities in different architectures, including the use of a Dynamic Load Balancing library [2,8]. We will apply GOPHER to actionable use cases, such as anticancer treatment recommendations, as well as other biological ontologies, such as those of key model organisms (mouse and fruitfly).…”

TensorFlow on State-of-the-Art HPC Clusters: A Machine Learning use Case

“…Finally, for the work on Dibona, our Arm-based platform, we acknowledge the previous work of the Mont-Blanc project [6] as well es the evaluation of more recent Arm-based architectures [19], [20].…”