Effective loop partitioning and scheduling under memory and register dual constraints

Chun Jason Xue, Edwin H.M. Sha, Zili Shao, Meikang Qiu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

11 Citations (Scopus)

Abstract

Loops arc the most important sections for embedded applications. To achieve high performance, two loop transformation techniques are often applied, namely loop pipelining and loop partitioning. Loop pipelining is an effective approach to increase parallelism and reduce schedule length. Loop partitioning with prefetching increases data locality and hides memory latency. However, loop pipelining increases register pressure and loop partitioning increases local memory requirement. As most embedded systems have limited number of registers and limited memory, without careful study, these two techniques can not be applied effectively. In this paper, we propose an effective scheduling framework, Register and Memory Sensitive Partitioning(RMSP), to minimize average schedule length per iteration under register and memory dual constraints for parallel embedded systems. Experiments show that RMSP reduces schedule length by 14.1% in average compared to previous methods applied directly.
Original languageEnglish
Title of host publicationDesign, Automation and Test in Europe, DATE 2008
Pages1202-1207
Number of pages6
DOIs
Publication statusPublished - 25 Aug 2008
EventDesign, Automation and Test in Europe, DATE 2008 - Munich, Germany
Duration: 10 Mar 200814 Mar 2008

Conference

ConferenceDesign, Automation and Test in Europe, DATE 2008
CountryGermany
CityMunich
Period10/03/0814/03/08

ASJC Scopus subject areas

  • Engineering(all)

Cite this