Adapting Atmospheric Chemistry Components for Efficient GPU Accelerators

Christian Guzman Ruiz, Matthew Dawson, Mario C. Acosta, Oriol Jorba, Eduardo Cesar Galobardes, Carlos Pérez García-Pando, Kim Serradell

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

Abstract

Atmospheric models demand a lot of computational power, and solving the chemical processes is one of its most computationally intensive components. This work shows how to improve the computational performance of the Multiscale Online Nonhydrostatic AtmospheRe CHemistry (MONARCH), a chemical weather prediction system developed by the Barcelona Supercomputing Center. The model implements the new flexible external package chemistry across multiple phases (CAMP) for the solving of gas- and aerosol-phase chemical processes that allows multiple chemical processes to be solved simultaneously as a single system. We introduce a novel strategy to simultaneously solve multiple instances of a chemical mechanism, represented in the model as grid cells, obtaining a speedup up to 9$$\times $$ using thousands of cells. In addition, we present a GPU strategy for the most time-consuming function of CAMP. The GPU version achieves up to 1.2$$\times $$ speedup compared to CPU. Also, we optimize the memory access in the GPU to increase its speedup up to 1.7$$\times $$.

Original languageEnglish
Title of host publicationProceedings of 8th International Congress on Information and Communication Technology - ICICT 2023
EditorsXin-She Yang, R. Simon Sherratt, Nilanjan Dey, Amit Joshi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages129-138
Number of pages10
ISBN (Print)9789819930906
DOIs
StatePublished - 2023
Event8th International Congress on Information and Communication Technology, ICICT 2023 - London, United Kingdom
Duration: Feb 20 2023Feb 23 2023

Publication series

NameLecture Notes in Networks and Systems
Volume694 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference8th International Congress on Information and Communication Technology, ICICT 2023
Country/TerritoryUnited Kingdom
CityLondon
Period02/20/2302/23/23

Keywords

  • Chemistry
  • Parallelism and concurrency
  • Performance

Fingerprint

Dive into the research topics of 'Adapting Atmospheric Chemistry Components for Efficient GPU Accelerators'. Together they form a unique fingerprint.

Cite this