GPU acceleration of numerical weather prediction

John Michalakes, Manish Vachharajani

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

83 Scopus citations

Abstract

Weather and climate prediction software has enjoyed the benefits of exponentially increasing processor power for almost 50 years. Even with the advent of large-scale parallelism in weather models, much of the performance increase has come from increasing processor speed rather than increased parallelism. This free ride is nearly over. Recent results also indicate that simply increasing the use of large-scale parallelism will prove ineffective for many scenarios. We present an alternative method of scaling model performance by exploiting emerging architectures using the fine-grain parallelism once used in vector machines. The paper shows the promise of this approach by demonstrating a 20x speedup for a computationally intensive portion of the Weather Research and Forecast (WRF) model on an NVIDIA 8800 GTX Graphics Processing Unit (GPU). We expect an overall 1.3x speedup from this change alone.

Original languageEnglish
Title of host publicationIPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM
DOIs
StatePublished - 2008
Externally publishedYes
EventIPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium - Miami, FL, United States
Duration: Apr 14 2008Apr 18 2008

Publication series

NameIPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM

Conference

ConferenceIPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium
Country/TerritoryUnited States
CityMiami, FL
Period04/14/0804/18/08

Fingerprint

Dive into the research topics of 'GPU acceleration of numerical weather prediction'. Together they form a unique fingerprint.

Cite this