A performance model for the communication in fast multipole methods on high-performance computing platforms.
Saved in:
| Title: | A performance model for the communication in fast multipole methods on high-performance computing platforms. |
|---|---|
| Authors: | Ibeid, Huda1 huda.ibeid@kaust.edu.sa, Yokota, Rio1, Keyes, David1 |
| Source: | International Journal of High Performance Computing Applications. Winter2016, Vol. 30 Issue 4, p423-437. 15p. |
| Subjects: | Computer architecture, COM (Computer architecture), Computing platforms, Email systems, Giant multipole resonance |
| Abstract: | Exascale systems are predicted to have approximately 1 billion cores, assuming gigahertz cores. Limitations on affordable network topologies for distributed memory systems of such massive scale bring new challenges to the currently dominant parallel programing model. Currently, there are many efforts to evaluate the hardware and software bottlenecks of exascale designs. It is therefore of interest to model application performance and to understand what changes need to be made to ensure extrapolated scalability. The fast multipole method (FMM) was originally developed for accelerating N-body problems in astrophysics and molecular dynamics but has recently been extended to a wider range of problems. Its high arithmetic intensity combined with its linear complexity and asynchronous communication patterns make it a promising algorithm for exascale systems. In this paper, we discuss the challenges for FMM on current parallel computers and future exascale architectures, with a focus on internode communication. We focus on the communication part only; the efficiency of the computational kernels are beyond the scope of the present study. We develop a performance model that considers the communication patterns of the FMM and observe a good match between our model and the actual communication time on four high-performance computing (HPC) systems, when latency, bandwidth, network topology, and multicore penalties are all taken into account. To our knowledge, this is the first formal characterization of internode communication in FMM that validates the model against actual measurements of communication time. The ultimate communication model is predictive in an absolute sense; however, on complex systems, this objective is often out of reach or of a difficulty out of proportion to its benefit when there exists a simpler model that is inexpensive and sufficient to guide coding decisions leading to improved scaling. The current model provides such guidance. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of High Performance Computing Applications is the property of Sage Publications Inc. 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 | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 119450168 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A performance model for the communication in fast multipole methods on high-performance computing platforms. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Ibeid%2C+Huda%22">Ibeid, Huda</searchLink><relatesTo>1</relatesTo><i> huda.ibeid@kaust.edu.sa</i><br /><searchLink fieldCode="AR" term="%22Yokota%2C+Rio%22">Yokota, Rio</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Keyes%2C+David%22">Keyes, David</searchLink><relatesTo>1</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+High+Performance+Computing+Applications%22">International Journal of High Performance Computing Applications</searchLink>. Winter2016, Vol. 30 Issue 4, p423-437. 15p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+architecture%22">Computer architecture</searchLink><br /><searchLink fieldCode="DE" term="%22COM+%28Computer+architecture%29%22">COM (Computer architecture)</searchLink><br /><searchLink fieldCode="DE" term="%22Computing+platforms%22">Computing platforms</searchLink><br /><searchLink fieldCode="DE" term="%22Email+systems%22">Email systems</searchLink><br /><searchLink fieldCode="DE" term="%22Giant+multipole+resonance%22">Giant multipole resonance</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Exascale systems are predicted to have approximately 1 billion cores, assuming gigahertz cores. Limitations on affordable network topologies for distributed memory systems of such massive scale bring new challenges to the currently dominant parallel programing model. Currently, there are many efforts to evaluate the hardware and software bottlenecks of exascale designs. It is therefore of interest to model application performance and to understand what changes need to be made to ensure extrapolated scalability. The fast multipole method (FMM) was originally developed for accelerating N-body problems in astrophysics and molecular dynamics but has recently been extended to a wider range of problems. Its high arithmetic intensity combined with its linear complexity and asynchronous communication patterns make it a promising algorithm for exascale systems. In this paper, we discuss the challenges for FMM on current parallel computers and future exascale architectures, with a focus on internode communication. We focus on the communication part only; the efficiency of the computational kernels are beyond the scope of the present study. We develop a performance model that considers the communication patterns of the FMM and observe a good match between our model and the actual communication time on four high-performance computing (HPC) systems, when latency, bandwidth, network topology, and multicore penalties are all taken into account. To our knowledge, this is the first formal characterization of internode communication in FMM that validates the model against actual measurements of communication time. The ultimate communication model is predictive in an absolute sense; however, on complex systems, this objective is often out of reach or of a difficulty out of proportion to its benefit when there exists a simpler model that is inexpensive and sufficient to guide coding decisions leading to improved scaling. The current model provides such guidance. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of High Performance Computing Applications is the property of Sage Publications Inc. 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=119450168 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1177/1094342016634819 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 15 StartPage: 423 Subjects: – SubjectFull: Computer architecture Type: general – SubjectFull: COM (Computer architecture) Type: general – SubjectFull: Computing platforms Type: general – SubjectFull: Email systems Type: general – SubjectFull: Giant multipole resonance Type: general Titles: – TitleFull: A performance model for the communication in fast multipole methods on high-performance computing platforms. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Ibeid, Huda – PersonEntity: Name: NameFull: Yokota, Rio – PersonEntity: Name: NameFull: Keyes, David IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 12 Text: Winter2016 Type: published Y: 2016 Identifiers: – Type: issn-print Value: 10943420 Numbering: – Type: volume Value: 30 – Type: issue Value: 4 Titles: – TitleFull: International Journal of High Performance Computing Applications Type: main |
| ResultId | 1 |
