An Adaptive Framework for Managing Heterogeneous Many-Core Clusters

Simple item page
dc.contributor.authorRafique, Muhammad Mustafaen
dc.contributor.committeechairButt, Ali R.en
dc.contributor.committeememberCameron, Kirk W.en
dc.contributor.committeememberFeng, Wu-chunen
dc.contributor.committeememberNazhandali, Leylaen
dc.contributor.committeememberNikolopoulos, Dimitrios S.en
dc.contributor.committeememberTilevich, Elien
dc.contributor.departmentComputer Scienceen
dc.date.accessioned2014-03-14T20:16:51Zen
dc.date.adate2011-10-21en
dc.date.available2014-03-14T20:16:51Zen
dc.date.issued2011-09-22en
dc.date.rdate2011-10-21en
dc.date.sdate2011-09-27en
dc.description.abstractThe computing needs and the input and result datasets of modern scientific and enterprise applications are growing exponentially. To support such applications, High-Performance Computing (HPC) systems need to employ thousands of cores and innovative data management. At the same time, an emerging trend in designing HPC systems is to leverage specialized asymmetric multicores, such as IBM Cell and AMD Fusion APUs, and commodity computational accelerators, such as programmable GPUs, which exhibit excellent price to performance ratio as well as the much needed high energy efficiency. While such accelerators have been studied in detail as stand-alone computational engines, integrating the accelerators into large-scale distributed systems with heterogeneous computing resources for data-intensive computing presents unique challenges and trade-offs. Traditional programming and resource management techniques cannot be directly applied to many-core accelerators in heterogeneous distributed settings, given the complex and custom instruction sets architectures, memory hierarchies and I/O characteristics of different accelerators. In this dissertation, we explore the design space of using commodity accelerators, specifically IBM Cell and programmable GPUs, in distributed settings for data-intensive computing and propose an adaptive framework for programming and managing heterogeneous clusters. The proposed framework provides a MapReduce-based extended programming model for heterogeneous clusters, which distributes tasks between asymmetric compute nodes by considering workload characteristics and capabilities of individual compute nodes. The framework provides efficient data prefetching techniques that leverage general-purpose cores to stage the input data in the private memories of the specialized cores. We also explore the use of an advanced layered-architecture based software engineering approach and provide mixin-layers based reusable software components to enable easy and quick deployment of heterogeneous clusters. The framework also provides multiple resource management and scheduling policies under different constraints, e.g., energy-aware and QoS-aware, to support executing concurrent applications on multi-tenant heterogeneous clusters. When applied to representative applications and benchmarks, our framework yields significantly improved performance in terms of programming efficiency and optimal resource management as compared to conventional, hand-tuned, approaches to program and manage accelerator-based heterogeneous clusters.en
dc.description.degreePh. D.en
dc.identifier.otheretd-09272011-232811en
dc.identifier.sourceurlhttp://scholar.lib.vt.edu/theses/available/etd-09272011-232811/en
dc.identifier.urihttp://hdl.handle.net/10919/29119en
dc.publisherVirginia Techen
dc.relation.haspartRafique_MM_D_2011.pdfen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectHeterogeneous Computingen
dc.subjectHigh-Performance Computingen
dc.subjectResource Sharingen
dc.subjectResource Management and Schedulingen
dc.subjectProgramming Modelsen
dc.titleAn Adaptive Framework for Managing Heterogeneous Many-Core Clustersen
dc.typeDissertationen
thesis.degree.disciplineComputer Scienceen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.leveldoctoralen
thesis.degree.namePh. D.en

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Rafique_MM_D_2011.pdf
Size:
1.76 MB
Format:
Adobe Portable Document Format
Download

Collections

Doctoral Dissertations