Skip to main navigation Skip to search Skip to main content

Resource-constrained spatial multi-tasking for embedded GPU

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

For recent smart devices, the embedded GPU is an indispensable unit and multi-task scheduling on the GPU becomes an important issue. To prevent the performance degradation on foreground GPU task by competing background GPU tasks, we propose a novel spatial multi-tasking which limits the number of available GPU cores for each task based on its priority. The proposed algorithm improved the performance of high priority task by up to 14% over the temporal budget based multi-tasking.

Original languageEnglish
Title of host publication2014 IEEE International Conference on Consumer Electronics, ICCE 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages339-340
Number of pages2
ISBN (Print)9781479912919
DOIs
StatePublished - 2014
Event2014 IEEE International Conference on Consumer Electronics, ICCE 2014 - Las Vegas, NV, United States
Duration: 10 Jan 201413 Jan 2014

Publication series

NameDigest of Technical Papers - IEEE International Conference on Consumer Electronics
ISSN (Print)0747-668X

Conference

Conference2014 IEEE International Conference on Consumer Electronics, ICCE 2014
Country/TerritoryUnited States
CityLas Vegas, NV
Period10/01/1413/01/14

Fingerprint

Dive into the research topics of 'Resource-constrained spatial multi-tasking for embedded GPU'. Together they form a unique fingerprint.

Cite this