Improving application behavior on heterogeneous manycore systems through kernel mapping

Simple item page
buir.advisorÖztürk, Özcan
dc.contributor.authorAlbayrak, Ömer Erdil
dc.date.accessioned2016-01-08T20:06:11Z
dc.date.available2016-01-08T20:06:11Z
dc.date.issued2013
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionAnkara : The Department of Computer Engineering and the Graduate School of Engineering and Science of Bilkent Univ., 2013.en_US
dc.descriptionThesis (Master's) -- Bilkent University, 2013.en_US
dc.descriptionIncludes bibliographical references leaves 53-57.en_US
dc.description.abstractMany-core accelerators are being more frequently deployed to improve the system processing capabilities. In such systems, application mapping must be enhanced to maximize utilization of the underlying architecture. Especially, in graphics processing units (GPUs), mapping kernels that are part of multi-kernel applications has a great impact on overall performance, since kernels may exhibit different characteristics on different CPUs and GPUs. While some kernels run faster on GPUs, others may perform better in CPUs. Thus, heterogeneous execution may yield better performance than executing the application only on a CPU or only on a GPU. In this thesis, we investigate on two approaches: a novel profiling-based adaptive kernel mapping algorithm to assign each kernel of an application to the proper device, and a Mixed Integer Programming (MIP) implementation to determine optimal mapping. We utilize profiling information for kernels on different devices and generate a map that identifies which kernel should run where in order to improve the overall performance or energy consumption of an application. Initial experiments show that our approach can efficiently map kernels on CPUs and GPUs, and outperforms CPU-only and GPU-only approaches. Some part of this work is published in 41st International Conference on Parallel Processing Workshops (ICPPW), 2012 [1], and submitted to Parallel Computing journal (ParCo) [2].en_US
dc.description.degreeM.S.en_US
dc.description.statementofresponsibilityAlbayrak, Ömer Erdilen_US
dc.format.extentxiii, 57 leaves, graphics, tablesen_US
dc.identifier.itemidB123492
dc.identifier.urihttp://hdl.handle.net/11693/17072
dc.language.isoEnglishen_US
dc.publisherBilkent Universityen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectMixed Integer Programmingen_US
dc.subjectKernel Mappingen_US
dc.subjectHeterogeneous Systemsen_US
dc.subjectGPGPUen_US
dc.subjectOpenCLen_US
dc.subject.lccQA76.88 .A43 2013en_US
dc.subject.lcshHeterogeneous computing.en_US
dc.subject.lcshOpenCL (Computer program language)en_US
dc.subject.lcshMultiprocessors.en_US
dc.subject.lcshConformal mapping.en_US
dc.subject.lcshKernel functions.en_US
dc.subject.lcshGraphics processing units.en_US
dc.subject.lcshInteger programming.en_US
dc.titleImproving application behavior on heterogeneous manycore systems through kernel mappingen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0007045.pdf
Size:
1.81 MB
Format:
Adobe Portable Document Format
Download

Collections

Dept. of Computer Engineering - Master's degree