Skip to main navigation Skip to search Skip to main content

A Portable and Efficient Lagrangian Particle Capability for Idealized Atmospheric Phenomena

  • University of Notre Dame

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

The Cloud Model version 1 is an atmospheric model that allows for idealized studies of atmospheric phenomena. A new Lagrangian microphysics capability has been added, enabling a significantly more accurate representation than the traditional bulk or multi-moment approaches frequently found in mesoscale atmospheric models. We have utilized a directive-based approach to enable a single source code to efficiently support execution on both CPU and GPU-based computing platforms. In addition to the use of accelerator directives, changes to the data structures and the message-passing approach used by the Lagrangian particle-based microphysics module were necessary to enable efficient execution for a large number of particles. We focus on a configuration that will be used to investigate the impact of oceanic sea spray on the atmospheric boundary layer within a hurricane. We observe a factor of 5.1× reduction in time to the solution when comparing the execution time for 256 NVIDIA A100 GPUs versus 256 AMD EPYC™ Milan-based compute nodes using 1 billion particles.

Original languageEnglish
Title of host publicationPASC 2024 - Proceedings of the Platform for Advanced Scientific Computing Conference
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9798400706394
DOIs
StatePublished - Jun 3 2024
EventPlatform for Advanced Scientific Computing Conference, PASC 2024 - Zurich, Switzerland
Duration: Jun 3 2024Jun 5 2024

Publication series

NamePASC 2024 - Proceedings of the Platform for Advanced Scientific Computing Conference

Conference

ConferencePlatform for Advanced Scientific Computing Conference, PASC 2024
Country/TerritorySwitzerland
CityZurich
Period06/3/2406/5/24

Keywords

  • GPU
  • MPI
  • OpenACC
  • power efficiency
  • roofline

Fingerprint

Dive into the research topics of 'A Portable and Efficient Lagrangian Particle Capability for Idealized Atmospheric Phenomena'. Together they form a unique fingerprint.

Cite this