GPUfs: The Case for Operating System Services on GPUs.

The article focuses on making core operating system abstractions available to graphics processing unit (GPU) code and the lessons learned in building GPUf file system layer. Topics discussed include how GPU have acquired increasingly general-purpose parallel processing capabilities, the traditional...

Full description

Bibliographic Details
Published in:Communications of the ACM Vol. 57; no. 12; pp. 68 - 80
Main Authors: SILBERSTEIN, MARK, FORD, BRYAN, WITCHEL, EMMETT
Format: Article
Published: Association for Computing Machinery Dec2014
Subjects:
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=99744610&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 99744610
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00010782
        ACM
      jtl: Communications of the ACM
      issn: 00010782
      maglogo: N
    pubinfo:
      dt: Dec2014
      vid: 57
      iid: 12
      pid: 68
      pub: Association for Computing Machinery
    artinfo:
      ui:
        99744610
        10.1145/2656206
      ppf: 68
      ppct: 12
      formats:
      tig:
        atl: GPUfs: The Case for Operating System Services on GPUs.
      aug:
        au:
          SILBERSTEIN, MARK
          FORD, BRYAN
          WITCHEL, EMMETT
        affil:
          Assistant professor, Department of Electrical Engineering, The Technion -- Israel Institute of Technology, Haifa, Israel
          Associate professor, Department of Computer Science, Yale University, New Haven, CT
          Associate professor, Department of Computer Science, University of Texas, Austin
      su:
        Graphics processing units
        Computer operating systems
        Parallel processing
        Computer software
        Computer input-output equipment
        Computer systems
      sug:
        subj:
          Graphics processing units
          Computer operating systems
          Parallel processing
          Computer software
          Computer input-output equipment
          Computer systems
      ab: The article focuses on making core operating system abstractions available to graphics processing unit (GPU) code and the lessons learned in building GPUf file system layer. Topics discussed include how GPU have acquired increasingly general-purpose parallel processing capabilities, the traditional CPU-centric programming model and how GPUfs demonstrates the productivity and performance benefits of allowing GPU to guide data flow in a system. An overview of the GPU software/hardware model is given.
      pubtype: Periodical
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2014
    holdings:
      @attributes:
        islocal: N