ILP-based energy minimization techniques for banked memories

Simple item page
dc.citation.epage50:40en_US
dc.citation.issueNumber3en_US
dc.citation.spage50:1en_US
dc.citation.volumeNumber13en_US
dc.contributor.authorOzturk, O.en_US
dc.contributor.authorKandemir, M.en_US
dc.date.accessioned2016-02-08T10:08:30Z
dc.date.available2016-02-08T10:08:30Z
dc.date.issued2008-07en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractMain memories can consume a significant portion of overall energy in many data-intensive embedded applications. One way of reducing this energy consumption is banking, that is, dividing available memory space into multiple banks and placing unused (idle) memory banks into low-power operating modes. Prior work investigated code-restructuring- and data-layout-reorganization-based approaches for increasing the energy benefits that could be obtained from a banked memory architecture. This article explores different techniques that can potentially coexist within the same optimization framework for maximizing benefits of low-power operating modes. These techniques include employing nonuniform bank sizes, data migration, data compression, and data replication. By using these techniques, we try to increase the chances for utilizing low-power operating modes in a more effective manner, and achieve further energy savings over what could be achieved by exploiting low-power modes alone. Specifically, nonuniform banking tries to match bank sizes with application-data access patterns. The goal of data migration is to cluster data with similar access patterns in the same set of banks. Data compression reduces the size of the data used by an application, and thus helps reduce the number of memory banks occupied by data. Finally, data replication increases bank idleness by duplicating select read-only data blocks across banks. We formulate each of these techniques as an ILP (integer linear programming) problem, and solve them using a commercial solver. Our experimental analysis using several benchmarks indicates that all the techniques presented in this framework are successful in reducing memory energy consumption. Based on our experience with these techniques, we recommend to compiler writers for banked memories to consider data compression, replication, and migration. © 2008 ACM.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T10:08:30Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2008en
dc.identifier.doi10.1145/1367045.1367059en_US
dc.identifier.issn1084-4309
dc.identifier.urihttp://hdl.handle.net/11693/23069
dc.language.isoEnglishen_US
dc.publisherAssociation for Computing Machineryen_US
dc.relation.isversionofhttp://dx.doi.org/10.1145/1367045.1367059en_US
dc.source.titleACM Transactions on Design Automation of Electronic Systemsen_US
dc.subjectCompilersen_US
dc.subjectCS for this articleen_US
dc.subjectSoftware and its engineeringen_US
dc.subjectSoftware notations and toolsen_US
dc.subjectSoftware organization and propertiesen_US
dc.subjectContextual software domainsen_US
dc.subjectOperating systemsen_US
dc.subjectMemory managementen_US
dc.subjectGarbage collectionen_US
dc.titleILP-based energy minimization techniques for banked memoriesen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ILP-based energy minimization techniques for banked memories.pdf
Size:
1.01 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Computer Engineering