The Fused Multiply-Add and Global Atmospheric Models: A Distributional Investigation into a Surprising Correctness Scenario

Teo Price-Broncucia, Allison H. Baker, Michael Duda

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

Abstract

In a series of related works developing an ensemble consistency testing approach for multiple popular global climate models (GCMs), one test scenario has repeatedly stood out. Why does the use of the Fused Multiply-Add (FMA) operation result in model configurations getting flagged as failures, while changes to compiler choice, optimization level, processor type and number, etc. are passed as expected? This work explores the impacts of FMA on GCM simulation output from a distributional perspective and provides directions for future work to enable model developers and users to use numerical optimization techniques with confidence.

Original languageEnglish
Title of host publicationProceedings of SC 2024-W
Subtitle of host publicationWorkshops of the International Conference for High Performance Computing, Networking, Storage and Analysis
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages140-147
Number of pages8
ISBN (Electronic)9798350355543
DOIs
StatePublished - 2024
Event2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024 - Atlanta, United States
Duration: Nov 17 2024Nov 22 2024

Publication series

NameProceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024
Country/TerritoryUnited States
CityAtlanta
Period11/17/2411/22/24

Keywords

  • climate-models
  • correctness
  • ensemble-methods

Fingerprint

Dive into the research topics of 'The Fused Multiply-Add and Global Atmospheric Models: A Distributional Investigation into a Surprising Correctness Scenario'. Together they form a unique fingerprint.

Cite this