学位论文详细信息
Enhancing manageability of execution and data for GPGPU computing
GPU;Multi tenancy;In situ analytics;Bandwidth sharing
Goswami, Anshuman ; Wolf, Matthew Computer Science Schwan, Karsten Vuduc, Richard Liu, Ling Kim, Hyesoon Yalamanchili, Sudhakar ; Wolf, Matthew
University:Georgia Institute of Technology
Department:Computer Science
关键词: GPU;    Multi tenancy;    In situ analytics;    Bandwidth sharing;   
Others  :  https://smartech.gatech.edu/bitstream/1853/58206/1/GOSWAMI-DISSERTATION-2017.pdf
美国|英语
来源: SMARTech Repository
PDF
【 摘 要 】

GPGPUs are useful for many types of compute-intensive workloads from scientific simulations to cloud-focused applications like machine learning and graph analytics. However, unlike CPUs they do not allow for software-controlled sharing of resources. This leads to underutilization, unfair use and reduced programmability. This thesis looks at three different areas, 1) in situ analysis in scientific workflows, 2) multi tenancy in cloud computing environments, and 3) network sharing between evolving distributed GPU frameworks. The thesis presents four distinct software-scheduling based constructs to handle problems in each of these spaces.

【 预 览 】
附件列表
Files Size Format View
Enhancing manageability of execution and data for GPGPU computing 2918KB PDF download
  文献评价指标  
  下载次数:4次 浏览次数:4次