Understanding Layered Portability from HPC to Cloud in Containerized Environments

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Medeiros, Daniel, Schieffer, Gabin, Wahlgren, Jacob, Peng, Ivy
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913393655414784
author Medeiros, Daniel
Schieffer, Gabin
Wahlgren, Jacob
Peng, Ivy
author_facet Medeiros, Daniel
Schieffer, Gabin
Wahlgren, Jacob
Peng, Ivy
contents Recent development in lightweight OS-level virtualization, containers, provides a potential solution for running HPC applications on the cloud platform. In this work, we focus on the impact of different layers in a containerized environment when migrating HPC containers from a dedicated HPC system to a cloud platform. On three ARM-based platforms, including the latest Nvidia Grace CPU, we use six representative HPC applications to characterize the impact of container virtualization, host OS and kernel, and rootless and privileged container execution. Our results indicate less than 4\% container overhead in DGEMM, miniMD, and XSBench, but 8\%-10\% overhead in FFT, HPCG, and Hypre. We also show that changing between the container execution modes results in negligible performance differences in the six applications.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11760
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Understanding Layered Portability from HPC to Cloud in Containerized Environments
Medeiros, Daniel
Schieffer, Gabin
Wahlgren, Jacob
Peng, Ivy
Distributed, Parallel, and Cluster Computing
Recent development in lightweight OS-level virtualization, containers, provides a potential solution for running HPC applications on the cloud platform. In this work, we focus on the impact of different layers in a containerized environment when migrating HPC containers from a dedicated HPC system to a cloud platform. On three ARM-based platforms, including the latest Nvidia Grace CPU, we use six representative HPC applications to characterize the impact of container virtualization, host OS and kernel, and rootless and privileged container execution. Our results indicate less than 4\% container overhead in DGEMM, miniMD, and XSBench, but 8\%-10\% overhead in FFT, HPCG, and Hypre. We also show that changing between the container execution modes results in negligible performance differences in the six applications.
title Understanding Layered Portability from HPC to Cloud in Containerized Environments
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2406.11760