Pipelined MapReduce: A Decoupled MapReduce RunTime for Shared-Memory Multi-Proccessors

Ηλιάκης, Κωνσταντίνος; Iliakis, Konstantinos

dc.contributor.author	Ηλιάκης, Κωνσταντίνος	el
dc.contributor.author	Iliakis, Konstantinos	en
dc.date.accessioned	2017-07-18T07:11:06Z
dc.date.available	2017-07-18T07:11:06Z
dc.date.issued	2017-07-18
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/45239
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.14042
dc.rights	Default License
dc.subject	Συστήματα Υψηλών Επιδόσεων	el
dc.subject	Παράλληλος Προγραμματισμός	el
dc.subject	Συναρισιακός Προγραμματισμός	el
dc.subject	Πολυπύρηνοι επεξεργαστές	el
dc.subject	Τεχνική Διοχέτευσης Λογισμικού	el
dc.subject	MapReduce	en
dc.subject	Multi-processors	en
dc.subject	Parallel Computing	en
dc.subject	Software Pipeline	en
dc.subject	Phoenix Library	el
dc.title	Pipelined MapReduce: A Decoupled MapReduce RunTime for Shared-Memory Multi-Proccessors	en
dc.contributor.department	Microprocessors and digital systems laboratory	el
heal.type	bachelorThesis
heal.classification	Computer science	en
heal.classification	High performance computing--Congresses	en
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh89003285
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh2008105591
heal.language	el
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2017-03-13
heal.abstract	Modern multi-processors embody up to hundreds of cores in a single chip, in an attempt to attain TFlops/sec performance. Many subtle programming frameworks have emerged in order to facilitate the development of parallel, efficient and scalable applications. The MapReduce programming model, after having indisputably, demonstrated its usability and effectiveness in the area of Large-Scale Distributed Systems computation, has been adapted to the needs of shared-memory multi-core and multi-processor systems. The scope of this thesis is to enhance the existing, traditional MapReduce Architecture, by decoupling Map from Combine into two separate phases. These independent phases are interleaved and executed in parallel. We argue that, interleaving Map and Combine computation, leads to more efficient hardware utilization and competent run-time improvements. A high-performance, shared queue data structure has been introduced in order to pipeline intermediate data from Map to Combine phase and allow for concurrent execution. Furthermore, an Inter-thread communication aware thread-to-cpu binding policy has been designed to minimize data exchange overhead. The Pipelined Architecture is evaluated into two inherently diverse multi-core systems and demonstrates execution speedup of up to 5.34X compared to a state-of-the art MapReduce Library, Phoenix++. Nevertheless, we observe that not all type of workloads profit from our Pipelined Architecture and reason about the application characteristics that define its suitability to our Runtime.	en
heal.advisorName	Ξύδης, Σωτήριος	el
heal.committeeMemberName	Σούντρης, Δημήτριος	el
heal.committeeMemberName	Κοζύρης, Νεκτάριος	el
heal.committeeMemberName	Πεκμεστζή, Κιαμάλ	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών. Εργαστήριο Υπολογιστικών Συστημάτων	el
heal.academicPublisherID	ntua
heal.numberOfPages	104 σ.	el
heal.fullTextAvailability	true