Skip to Main content Skip to Navigation
Conference papers

On the Overhead of Topology Discovery for Locality-aware Scheduling in HPC

Abstract : The increasing complexity of parallel computing platforms requires a deep knowledge of the hardware and of the application needs. Locality a key criteria for performance optimization. It involves software tools to expose information about the hardware topology to high performance runtime libraries. We show that the overhead of gathering such information from the operating system is significant on large computing nodes that run Linux. This overhead also increases more than linearly with the number of processes that perform it simultaneously. We then study the actual needs of the HPC software ecosystem in terms of topology information. We propose some ways to avoid multiple expensive topology discovery and to share topology information between components such as the resource manager or the runtime libraries.
Complete list of metadatas

https://hal.inria.fr/hal-01402755
Contributor : Brice Goglin <>
Submitted on : Friday, November 25, 2016 - 10:22:42 AM
Last modification on : Wednesday, May 15, 2019 - 5:24:04 PM
Long-term archiving on: : Tuesday, March 21, 2017 - 10:15:32 AM

File

article.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01402755, version 1

Citation

Brice Goglin. On the Overhead of Topology Discovery for Locality-aware Scheduling in HPC. Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP2017), Mar 2017, St Petersburg, Russia. pp.9. ⟨hal-01402755v1⟩

Share

Metrics

Record views

94

Files downloads

77