Memory capacity aware non-blocking data transfer on GPGPU

Hao Wei Liu, Hsien Kai Kuo, Kuan Ting Chen, Bo-Cheng Lai

    研究成果: Conference contribution同行評審

    2 引文 斯高帕斯(Scopus)

    摘要

    The massive data demand of GPGPUs requires expensive memory modules, such as GDDR, to support high data bandwidth. The high cost poses constraints on the total memory capacity available to GPGPUs, and the data need to be transferred between the host CPUs and GPGPUs. However, the long latency of data transfers has resulted in significant performance overhead. To alleviate this issue, the modern GPGPUs have implemented the non-blocking data transfer allowing a GPGPU to perform computing while the data is being transmitted. This paper proposes a capacity aware scheduling algorithm that exploits the non-blocking data transfer in modern GPGPUs. By effectively taking the advantage of non-blocking transfers, experiment results demonstrate an average of 24.01% performance improvement when compared to existing approaches that only consider memory capacity.

    原文English
    主出版物標題2013 IEEE Workshop on Signal Processing Systems, SiPS 2013
    發行者Institute of Electrical and Electronics Engineers Inc.
    頁面395-400
    頁數6
    ISBN(列印)9781467362382
    DOIs
    出版狀態Published - 1 1月 2013
    事件2013 IEEE Workshop on Signal Processing Systems, SiPS 2013 - Taipei, Taiwan
    持續時間: 16 10月 201318 10月 2013

    出版系列

    名字IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation
    ISSN(列印)1520-6130

    Conference

    Conference2013 IEEE Workshop on Signal Processing Systems, SiPS 2013
    國家/地區Taiwan
    城市Taipei
    期間16/10/1318/10/13

    指紋

    深入研究「Memory capacity aware non-blocking data transfer on GPGPU」主題。共同形成了獨特的指紋。

    引用此