Skip to main content
USENIX
  • Conferences
  • Students
Sign in
  • HotPar '12 Home
  • Registration and Lodging
  • Organizers
  • Workshop Program
  • Poster Session
  • Birds-of-a-Feather Sessions
  • Travel
  • Calendar
  • Students
  • Questions?
  • For Participants
  • Call for Papers
  • Past Proceedings

sponsors

Gold Sponsor
Bronze Sponsor
Bronze Sponsor
Bronze Sponsor

twitter

Tweets by @usenix

usenix conference policies

  • Event Code of Conduct
  • Conference Network Policy
  • Statement on Environmental Responsibility Policy

You are here

Home » Fine-Grained Resource Sharing for Concurrent GPGPU Kernels
Tweet

connect with us

http://twitter.com/usenix
http://www.facebook.com/usenixassociation

Fine-Grained Resource Sharing for Concurrent GPGPU Kernels

Authors: 

Chris Gregg, Jonathan Dorn, Kim Hazelwood, and Kevin Skadron, University of Virginia

Abstract: 

General purpose GPU (GPGPU) programming frameworks such as OpenCL and CUDA allow running individual computation kernels sequentially on a device. However, in some cases it is possible to utilize device resources more efficiently by running kernels concurrently. This raises questions about load balancing and resource allocation that have not previously warranted investigation. For example, what kernel characteristics impact the optimal partitioning of resources among concurrently executing kernels? Current frameworks do not provide the ability to easily run kernels concurrently with fine-grained and dynamic control over resource partitioning. We present KernelMerge, a kernel scheduler that runs two OpenCL kernels concurrently on one device. KernelMerge furnishes a number of settings that can be used to survey concurrent or single kernel configurations, and to investigate how kernels interact and influence each other, or themselves. KernelMerge provides a concurrent kernel scheduler compatible with the OpenCL API.

We present an argument on the benefits of running kernels concurrently. We demonstrate how to use KernelMerge to increase throughput for two kernels that efficiently use device resources when run concurrently, and we establish that some kernels show worse performance when running concurrently. We also outline a method for using KernelMerge to investigate how concurrent kernels influence each other, with the goal of predicting runtimes for concurrent execution from individual kernel runtimes. Finally, we suggest GPU architectural changes that would improve such concurrent schedulers in the future.

Chris Gregg, University of Virginia

Jonathan Dorn, University of Virginia

Kim Hazelwood, University of Virginia

Kevin Skadron, University of Virginia

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {181265,
author = {Chris Gregg and Jonathan Dorn and Kim Hazelwood and Kevin Skadron},
title = {{Fine-Grained} Resource Sharing for Concurrent {GPGPU} Kernels},
booktitle = {4th USENIX Workshop on Hot Topics in Parallelism (HotPar 12)},
year = {2012},
address = {Berkeley, CA},
url = {https://www.usenix.org/conference/hotpar12/workshop-program/presentation/gregg},
publisher = {USENIX Association},
month = jun,
}
Download
Gregg PDF

Presentation Audio

MP3 Download OGG Download

Download Audio

  • Log in or    Register to post comments

Gold Sponsors

Bronze Sponsors

© USENIX

  • Privacy Policy
  • Contact Us