Skip to main navigation Skip to search Skip to main content

SoPHy: A software platform for hybrid resource management of homogeneous many-core accelerators

    • Seoul National University

    Research output: Contribution to conference › Conference paper › peer-review

    Abstract

    As demand of higher computing power is steadily increasing, it becomes popular to equip a many-core accelerator in a computer system to run current applications. Efficient management of compute resources in such a system is challenging because various factors such as workload variation, QoS requirement change, and hardware failure may cause dynamic change of system status. Recently a variety of resource management techniques for many-core accelerators have been proposed. They are usually tailored to a specific target architecture. In this paper, we propose a software platform, SoPHy, which supports various types of many-core architectures, based on a hybrid resource management technique. SoPHy has been implemented on two different many-core architectures: the Xeon Phi coprocessor and a NoC virtual prototype. Experimental results prove that SoPHy is capable of adapting to the runtime workload variation effectively with affordable overhead of runtime resource management.

    Original languageEnglish
    Title of host publication3rd ACM International Workshop on Many-Core Embedded Systems, MES 2015 - in conjunction with the 42nd International Symposium on Computer Architecture, ISCA 2015
    PublisherAssociation for Computing Machinery
    Pages17-24
    Number of pages8
    ISBN (Electronic)9781450334082
    DOIs
    StatePublished - 2015.06.13
    Event3rd ACM International Workshop on Many-Core Embedded Systems, MES 2015 - Portland, United States
    Duration: 2015.06.13 → 2015.06.17

    Publication series

    NameACM International Conference Proceeding Series
    Volume13-17-June-2015

    Conference

    Conference3rd ACM International Workshop on Many-Core Embedded Systems, MES 2015
    Country/TerritoryUnited States
    CityPortland
    Period15.06.13 → 15.06.17

    Keywords

    • Many-core accelerator
    • Resource management
    • Run-time mapping
    • Software platform
    • Throughput

    Quacquarelli Symonds(QS) Subject Topics

    • Computer Science & Information Systems
    • Data Science

    Fingerprint

    Dive into the research topics of 'SoPHy: A software platform for hybrid resource management of homogeneous many-core accelerators'. Together they form a unique fingerprint.

    Cite this