ERA

Download the full-sized PDF of Do Inputs Matter? Using Data-Dependence Profiling to Evaluate Thread Level Speculation in the BlueGene/QDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R3XX1X

Download

Export to: EndNote  |  Zotero  |  Mendeley

Communities

This file is in the following communities:

Graduate Studies and Research, Faculty of

Collections

This file is in the following collections:

Theses and Dissertations

Do Inputs Matter? Using Data-Dependence Profiling to Evaluate Thread Level Speculation in the BlueGene/Q Open Access

Descriptions

Other title
Subject/Keyword
Thread Level Speculation
Data-Dependence Profiling
BlueGene/Q
Type of item
Thesis
Degree grantor
University of Alberta
Author or creator
Bhattacharyya,Arnamoy
Supervisor and department
Amaral,Jose Nelson (Computing Science)
Examining committee member and department
Cockburn,Bruce F. (Department of Electrical and Computer Engineering)
Hindle,Abram (Computing Science)
Department
Department of Computing Science
Specialization

Date accepted
2013-08-13T13:27:00Z
Graduation date
2013-11
Degree
Master of Science
Degree level
Master's
Abstract
In the era of many-core architectures, it is necessary to fully exploit the maximum available parallelism in computer programs. Thread Level Speculation (TLS) is a hardware/software technique that guarantees correct speculative parallel execution of the program even in the presence of may dependences. This thesis investigates the variability of dependence behaviour of loops across program inputs with the help of data-dependence profiling. This thesis also presents SpecEval, a new automatic speculative parallelization framework that uses single-input data-dependence profiles to evaluate the TLS hardware support in the IBM’s BlueGene/Q (BG/Q) supercomputer. A performance evaluation of TLS applied along with the traditional automatic parallelization techniques indicates that various factors such as: the number of loops speculatively parallelized and their coverage, mispeculation overhead due to dependences introduced from function calls inside loop body, increase in L1 cache misses due to long running (LR) mode in BG/Q and dynamic instruction path length increase impact the performance of TLS.
Language
English
DOI
doi:10.7939/R3XX1X
Rights
Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.
Citation for previous publication
Arnamoy Bhattacharyya. 2012. Using combined profiling to decide when thread level speculation is profitable. In Proceedings of the 21st international conference on Parallel architectures and compilation techniques (PACT '12). ACM, New York, NY, USA, 483-484.Arnamoy Bhattacharyya and José Nelson Amaral. 2013. Automatic speculative parallelization of loops using polyhedral dependence analysis. In Proceedings of the First International Workshop on Code OptimiSation for MultI and many Cores (COSMIC '13). ACM, New York, NY, USA, , Article 1 , 9 pages.

File Details

Date Uploaded
Date Modified
2014-04-30T22:34:39.198+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 3005169
Last modified: 2015:10:12 12:45:50-06:00
Filename: Bhattacharyya_Arnamoy_Fall 2013.pdf
Original checksum: ba5d5173542049e50e697d7b0c495adc
Well formed: false
Valid: false
Status message: No document catalog dictionary offset=0
Activity of users you follow
User Activity Date