Repository logo
 

Polyhedral optimizations of RNA-RNA interaction computations

Simple item page
dc.contributor.authorVaradarajan, Swetha, author
dc.contributor.authorRajopadhye, Sanjay, advisor
dc.contributor.authorBohm, Wim, committee member
dc.contributor.authorWilson, Jesse, committee member
dc.date.accessioned2018-01-17T16:45:47Z
dc.date.available2018-01-17T16:45:47Z
dc.date.issued2017
dc.description.abstractStudying RNA-RNA interaction has led to major successes in the treatment of some cancers, including colon, breast and pancreatic cancer by suppressing the gene expression involved in the development of these diseases. The problem with such programs is that they are computationally and memory intensive: O(N4) space and O(N6) time complexity. Moreover, the entire application is complicated, and involves many mutually recursive data variables. We address the problem of speeding up a surrogate kernel (named OSPSQ) that captures the main dependence pattern found in two widely used RNA-RNA interaction applications IRIS and piRNA. The structure of the OSPSQ kernel perfectly fits the constraints of the polyhedral model, a well-developed technology for optimizing codes that belong to many specialized domains. However, the current state-of-the-art automatic polyhedral tools do not significantly improve the performance of the baseline implementation of OSPSQ. With simple techniques like loop permutation and skewing, we achieve an average of 17x sequential and 31x parallel speedup on a standard modern multi-core platform (Intel Broadwell, E5-1650v4). This performance represents 75% and 88% of attainable single-core and multi-core L1 bandwidth. For further performance improvement, we describe how to tile all six dimensions and also formulate the associated memory trade-off. In the future, we plan to implement these tiling strategies, explore the performance of the code for various tile sizes and optimize the whole piRNA application.
dc.format.mediumborn digital
dc.format.mediummasters theses
dc.identifierVaradarajan_colostate_0053N_14512.pdf
dc.identifier.urihttps://hdl.handle.net/10217/185694
dc.languageEnglish
dc.language.isoeng
dc.publisherColorado State University. Libraries
dc.relation.ispartof2000-2019
dc.relation.referencesVaradarajan, Swetha (2017). Dataset associated with "Polyhedral Optimizations of RNA-RNA Interaction Computations." Colorado State University. https://hdl.handle.net/10217/191189
dc.rightsCopyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright.
dc.subjectICC
dc.subjectpolyhedral optimization
dc.subjecttiling
dc.subjectperformance tuning
dc.subjectbandwidth
dc.subjectRNA-RNA
dc.titlePolyhedral optimizations of RNA-RNA interaction computations
dc.typeText
dcterms.rights.dplaThis Item is protected by copyright and/or related rights (https://rightsstatements.org/vocab/InC/1.0/). You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
thesis.degree.disciplineElectrical and Computer Engineering
thesis.degree.grantorColorado State University
thesis.degree.levelMasters
thesis.degree.nameMaster of Science (M.S.)

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Varadarajan_colostate_0053N_14512.pdf
Size:
393.16 KB
Format:
Adobe Portable Document Format
Description:
Download

Collections

2000-2019
Theses and Dissertations