The Impact of Exploiting Instruction-Level Parallelism on Shared-Memory Multiprocessors

Simple item page
dc.citation.bibtexNamearticleen_US
dc.citation.firstpage218en_US
dc.citation.issueNumber2en_US
dc.citation.journalTitleIEEE Transactions on Computersen_US
dc.citation.lastpage226en_US
dc.citation.volumeNumber48en_US
dc.contributor.authorPai, Vijay S.en_US
dc.contributor.authorRanganathan, Parthasarathyen_US
dc.contributor.authorAbdel-Shafi, Hazimen_US
dc.contributor.authorAdve, Sarita V.en_US
dc.contributor.orgCITI (http://citi.rice.edu/)en_US
dc.date.accessioned2007-10-31T00:57:20Zen_US
dc.date.available2007-10-31T00:57:20Zen_US
dc.date.issued1999-02-20en_US
dc.date.modified2002-03-20en_US
dc.date.submitted2002-03-20en_US
dc.descriptionJournal Paperen_US
dc.description.abstractCurrent microprocessors incorporate techniques to aggressively exploit instruction-level parallelism (ILP). This paper evaluates the impact of such processors on the performance of shared-memory multiprocessors, both without and with the latency-hiding optimization of software prefetching. Our results show that, while ILP techniques substantially reduce CPU time in multiprocessors, they are less effective in removing memory stall time. Consequently, despite the inherent latency tolerance features of ILP processors, we find memory system performance to be a larger bottleneck and parallel efficiencies to be generally poorer in ILP- based multiprocessors than in previous generation multiprocessors. The main reasons for these deficiencies are insufficient opportunities in the applications to overlap multiple load misses and increased contention for resources in the system. We also find that software prefetching does not change the memory bound nature of most of our applications on our ILP multiprocessor, mainly due to a large number of late prefetches and resource contention. Our results suggest the need for additional latency hiding or reducing techniques for ILP systems, such as software clustering of load misses and producer-initiated communication.en_US
dc.identifier.citationV. S. Pai, P. Ranganathan, H. Abdel-Shafi and S. V. Adve, "The Impact of Exploiting Instruction-Level Parallelism on Shared-Memory Multiprocessors," <i>IEEE Transactions on Computers,</i> vol. 48, no. 2, 1999.en_US
dc.identifier.doihttp://dx.doi.org/10.1109/12.752663en_US
dc.identifier.urihttps://hdl.handle.net/1911/20183en_US
dc.language.isoengen_US
dc.subjectShared-memory multiprocessorsen_US
dc.subjectinstruction-level parallelismen_US
dc.subjectsoftware prefetchingen_US
dc.subjectperformance evaluationen_US
dc.subject.keywordShared-memory multiprocessorsen_US
dc.subject.keywordinstruction-level parallelismen_US
dc.subject.keywordsoftware prefetchingen_US
dc.subject.keywordperformance evaluationen_US
dc.titleThe Impact of Exploiting Instruction-Level Parallelism on Shared-Memory Multiprocessorsen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Pai1999Feb1TheImpacto.PDF
Size:
487.6 KB
Format:
Adobe Portable Document Format
Download
Collections
ECE Publications