Skip to main navigation Skip to search Skip to main content

Task partitioning upon memory-constrained multiprocessors

  • Nathan Fisher
  • , James H. Anderson
  • , Sanjoy Baruah

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

Abstract

Most prior theoretical research on partitioning algorithms for real-time multiprocessor platforms has focused on ensuring that the cumulative computing requirements of the tasks assigned to each processor does not exceed the processor's processing power. However, many multiprocessor platforms have only limited amounts of local per-processor memory; if the memory limitation of a processor is not respected, thrashing between "main" memory and the processor's local memory may occur during run-time and may result in performance degradation. We formalize the problem of task partitioning in a manner that is cognizant of both memory and processing capacity constraints as the memory constrained multiprocessor partitioning problem, prove that this problem is intractable, and present efficient algorithms for solving it under certain - well-defined - conditions.

Original languageEnglish
Title of host publicationProceedings - 11th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications
Pages416-421
Number of pages6
DOIs
StatePublished - 2005
Event11th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications - Hong Kong, China
Duration: Aug 17 2005Aug 19 2005

Publication series

NameProceedings - 11th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications

Conference

Conference11th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications
Country/TerritoryChina
CityHong Kong
Period08/17/0508/19/05

Keywords

  • Memory-constrained systems
  • Multiprocessor systems
  • Partitioned scheduling
  • Utilization-based schedulability tests

Fingerprint

Dive into the research topics of 'Task partitioning upon memory-constrained multiprocessors'. Together they form a unique fingerprint.

Cite this