Skip to main navigation Skip to search Skip to main content

Efficient and Cost-Effective HPC on the Cloud

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

HPC applications are increasingly utilizing cloud resources due to their cost-effectiveness. Among these resources, spot compute instances present an opportunity to run applications at deep discounts compared to on-demand instances. However, they present unique challenges for tightly-coupled HPC applications due to potential interruptions. Traditional parallel programming models like MPI are not inherently fault-tolerant, and existing methods to handle these interruptions are inefficient and require significant programmer effort. In this paper, we present Charm++ as an alternative solution that natively supports fault tolerance, dynamic load balancing, and resource rescaling. We present a tool to run Charm++ applications with a mix of on-demand and spot instances which can detect and efficiently handle spot interruptions without a shared filesystem. We show that using spot instances can result in up to 60% cost savings for our benchmark application.

Original languageEnglish (US)
Title of host publicationHPDC 2025 - Proceedings of the 34th International Symposium on High-Performance Parallel and Distributed Computing
PublisherAssociation for Computing Machinery
ISBN (Electronic)9798400718694
DOIs
StatePublished - Sep 9 2025
Event34th International Symposium on High-Performance Parallel and Distributed Computing - Notre Dame, United States
Duration: Jul 20 2025 → Jul 23 2025

Publication series

NameHPDC 2025 - Proceedings of the 34th International Symposium on High-Performance Parallel and Distributed Computing

Conference

Conference34th International Symposium on High-Performance Parallel and Distributed Computing
Country/TerritoryUnited States
CityNotre Dame
Period7/20/25 → 7/23/25

Keywords

  • HPC
  • cost-efficiency
  • fault-tolerance
  • spot instances

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Information Systems
  • Software

Fingerprint

Dive into the research topics of 'Efficient and Cost-Effective HPC on the Cloud'. Together they form a unique fingerprint.

Cite this