Skip to main navigation Skip to search Skip to main content

Optimal partitioning and balanced scheduling with the maximal overlap of data footprints

  • Z. Wang*
  • , E. H.M. Sha
  • , Y. Wang
  • *Corresponding author for this work
  • University of Notre Dame

Research output: Contribution to journalConference articlepeer-review

Abstract

The paper proposes a scheme to tolerate the slow memory access latency for loop intensive applications in the system with memory hierarchy. The scheme takes into consideration of both the intermediate data and maximal overlap of data footprints for initial data. Furthermore, a schedule is presented to balance the ALU computation and memory operations. The memory requirement under such schedule is calculated. This schedule's improvement in total execution time is approximately 20% over existing methods.

Original languageEnglish
Pages (from-to)31-36
Number of pages6
JournalProceedings of the IEEE Great Lakes Symposium on VLSI
DOIs
StatePublished - 2001
Externally publishedYes
Event11th Great Lakes Sysmposium on VLSI (GLSVLSI 2001) - West Lafayette, IN, United States
Duration: 22 Mar 200123 Mar 2001

Fingerprint

Dive into the research topics of 'Optimal partitioning and balanced scheduling with the maximal overlap of data footprints'. Together they form a unique fingerprint.

Cite this