Flexible and Effective Object Tiering for Heterogeneous Memory Systems

Brandon Kammerdiener, J. Zach Mcmichael, Michael R. Jantz, Kshitij A. Doshi, Terry Jones

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

1 Scopus citations

Abstract

Computing platforms that package multiple types of memory, each with their own performance characteristics, are quickly becoming mainstream. To operate efficiently, heterogeneous memory architectures require new data management solutions that are able to match the needs of each application with an appropriate type of memory. As the primary generators of memory usage, applications create a great deal of information that can be useful for guiding memory tiering, but the community still lacks tools to collect, organize, and leverage this information effectively. To address this gap, this work introduces a novel software framework that collects and analyzes object-level information to guide memory tiering. Using this framework, this study evaluates and compares the impact of a variety of data tiering choices, including how the system prioritizes objects for faster memory as well as the frequency and timing of migration events. The results, collected on a modern Intel platform with conventional DRAM as well as non-volatile RAM, show that guiding data tiering with object-level information can enable significant performance and efficiency benefits compared to standard hardware- and software-directed data tiering strategies.

Original languageEnglish
Title of host publicationISMM 2023 - Proceedings of the 2023 ACM SIGPLAN International Symposium on Memory Management, Co-located with PLDI 2023
EditorsStephen M. Blackburn, Erez Petrank
PublisherAssociation for Computing Machinery
Pages163-175
Number of pages13
ISBN (Electronic)9798400701795
DOIs
StatePublished - Jun 6 2023
Event2023 ACM SIGPLAN International Symposium on Memory Management, ISMM 2023 - Orlando, United States
Duration: Jun 18 2023Jun 18 2023

Publication series

NameInternational Symposium on Memory Management, ISMM

Conference

Conference2023 ACM SIGPLAN International Symposium on Memory Management, ISMM 2023
Country/TerritoryUnited States
CityOrlando
Period06/18/2306/18/23

Funding

We thank the anonymous reviewers for their thoughtful comments and feedback. This research was supported by the U.S. DOE Exascale Computing Project (17-SC-20-SC) and the National Science Foundation under CNS-1943305.

FundersFunder number
National Science FoundationCNS-1943305
U.S. Department of Energy17-SC-20-SC

    Keywords

    • NVM
    • heterogeneous memory systems
    • memory management
    • profiling
    • runtime systems

    Fingerprint

    Dive into the research topics of 'Flexible and Effective Object Tiering for Heterogeneous Memory Systems'. Together they form a unique fingerprint.

    Cite this