Explicit Fourth-Order Runge-Kutta Method on Intel Xeon Phi Coprocessor.
Saved in:
| Title: | Explicit Fourth-Order Runge-Kutta Method on Intel Xeon Phi Coprocessor. |
|---|---|
| Authors: | Bylina, Beata1 beatas@hektor.umcs.lublin.pl, Potiopa, Joanna1 joannap@hektor.umcs.lublin.pl |
| Source: | International Journal of Parallel Programming. Oct2017, Vol. 45 Issue 5, p1073-1090. 18p. |
| Subjects: | Sparse matrices, Sparse matrix software, Multiprocessors, Markovian jump linear systems, Euler method, Vector algebra |
| Abstract: | This paper concerns an Intel Xeon Phi implementation of the explicit fourth-order Runge-Kutta method (RK4) for very sparse matrices with very short rows. Such matrices arise during Markovian modeling of computer and telecommunication networks. In this work an implementation based on Intel Math Kernel Library (Intel MKL) routines and the authors' own implementation, both using the CSR storage scheme and working on Intel Xeon Phi, were investigated. The implementation based on the Intel MKL library uses the high-performance BLAS and Sparse BLAS routines. In our application we focus on OpenMP style programming. We implement SpMV operation and vector addition using the basic optimizing techniques and the vectorization. We evaluate our approach in native and offload modes for various number of cores and thread allocation affinities. Both implementations (based on Intel MKL and made by the authors) were compared in respect of the time, the speedup and the performance. The numerical experiments on Intel Xeon Phi show that the performance of authors' implementation is very promising and gives a gain of up to two times compared to the multithreaded implementation (based on Intel MKL) running on CPU (Intel Xeon processor) and even three times in comparison with the application which uses Intel MKL on Intel Xeon Phi. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Parallel Programming is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 124504600 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Explicit Fourth-Order Runge-Kutta Method on Intel Xeon Phi Coprocessor. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Bylina%2C+Beata%22">Bylina, Beata</searchLink><relatesTo>1</relatesTo><i> beatas@hektor.umcs.lublin.pl</i><br /><searchLink fieldCode="AR" term="%22Potiopa%2C+Joanna%22">Potiopa, Joanna</searchLink><relatesTo>1</relatesTo><i> joannap@hektor.umcs.lublin.pl</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Parallel+Programming%22">International Journal of Parallel Programming</searchLink>. Oct2017, Vol. 45 Issue 5, p1073-1090. 18p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Sparse+matrices%22">Sparse matrices</searchLink><br /><searchLink fieldCode="DE" term="%22Sparse+matrix+software%22">Sparse matrix software</searchLink><br /><searchLink fieldCode="DE" term="%22Multiprocessors%22">Multiprocessors</searchLink><br /><searchLink fieldCode="DE" term="%22Markovian+jump+linear+systems%22">Markovian jump linear systems</searchLink><br /><searchLink fieldCode="DE" term="%22Euler+method%22">Euler method</searchLink><br /><searchLink fieldCode="DE" term="%22Vector+algebra%22">Vector algebra</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: This paper concerns an Intel Xeon Phi implementation of the explicit fourth-order Runge-Kutta method (RK4) for very sparse matrices with very short rows. Such matrices arise during Markovian modeling of computer and telecommunication networks. In this work an implementation based on Intel Math Kernel Library (Intel MKL) routines and the authors' own implementation, both using the CSR storage scheme and working on Intel Xeon Phi, were investigated. The implementation based on the Intel MKL library uses the high-performance BLAS and Sparse BLAS routines. In our application we focus on OpenMP style programming. We implement SpMV operation and vector addition using the basic optimizing techniques and the vectorization. We evaluate our approach in native and offload modes for various number of cores and thread allocation affinities. Both implementations (based on Intel MKL and made by the authors) were compared in respect of the time, the speedup and the performance. The numerical experiments on Intel Xeon Phi show that the performance of authors' implementation is very promising and gives a gain of up to two times compared to the multithreaded implementation (based on Intel MKL) running on CPU (Intel Xeon processor) and even three times in comparison with the application which uses Intel MKL on Intel Xeon Phi. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Parallel Programming is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=124504600 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s10766-016-0458-x Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 18 StartPage: 1073 Subjects: – SubjectFull: Sparse matrices Type: general – SubjectFull: Sparse matrix software Type: general – SubjectFull: Multiprocessors Type: general – SubjectFull: Markovian jump linear systems Type: general – SubjectFull: Euler method Type: general – SubjectFull: Vector algebra Type: general Titles: – TitleFull: Explicit Fourth-Order Runge-Kutta Method on Intel Xeon Phi Coprocessor. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Bylina, Beata – PersonEntity: Name: NameFull: Potiopa, Joanna IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 10 Text: Oct2017 Type: published Y: 2017 Identifiers: – Type: issn-print Value: 08857458 Numbering: – Type: volume Value: 45 – Type: issue Value: 5 Titles: – TitleFull: International Journal of Parallel Programming Type: main |
| ResultId | 1 |
