Repository logo
 

Dataset associated with "Polyhedral optimizations of RNA-RNA interaction computations"

Simple item page
dc.contributor.authorVaradarajan, Swetha
dc.coverage.spatialFort Collins (Colo.)en_US
dc.coverage.temporal2017en_US
dc.date.accessioned2018-09-04T19:54:15Z
dc.date.available2018-09-04T19:54:15Z
dc.date.issued2017
dc.descriptionThese files can be used to re-create the results in the thesis manuscript: "Polyhedral Optimizations of RNA-RNA Interaction Computations". One will need to use the AlphaZ tool (http://www.cs.colostate.edu/AlphaZ/wiki/doku.php) to produce result from the .ab and .cs file. For users not aware of AlphaZ can use the C codes.en_US
dc.descriptionDepartment of Electrical and Computer Engineering
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 applicationis 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 foundin 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.mediumZIP
dc.format.mediumPNG
dc.format.mediumTXT
dc.format.mediumPY
dc.format.mediumSH
dc.format.mediumSource Code
dc.identifier.urihttps://hdl.handle.net/10217/191189
dc.identifier.urihttp://dx.doi.org/10.25675/10217/191189
dc.languageEnglish
dc.language.isoeng
dc.publisherColorado State University. Librariesen_US
dc.relation.ispartofResearch Data
dc.relation.isreferencedbyVaradarajan, Swetha, Polyhedral Optimizations of RNA-RNA Interaction Computations. (Unpublished doctoral dissertation), Colorado State University, 2017. https://hdl.handle.net/10217/185694
dc.subjectAlphaZ
dc.subjectpolyhedral
dc.subjectparallel programming
dc.titleDataset associated with "Polyhedral optimizations of RNA-RNA interaction computations"en_US
dc.typeDataseten_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Varadarajan-Thesis-files_2018_10217_191189.zip
Size:
277.44 KB
Format:
Zip File
Description:
Download

Collections

Research Data
Research Data