Academic Journal
Fast classification of MPI applications using Lamport’s logical clocks.
| Τίτλος: | Fast classification of MPI applications using Lamport’s logical clocks. |
|---|---|
| Συγγραφείς: | Tong, Zhou1 tong@cs.fsu.edu, Pakin, Scott2 pakin@lanl.gov, Lang, Michael2 mlang@lanl.gov, Yuan, Xin1 xyuan@cs.fsu.edu |
| Πηγή: | Journal of Parallel & Distributed Computing. Oct2018, Vol. 120, p77-88. 12p. |
| Θεματικοί όροι: | *Logical clocks, *Counters (Computer science), *Distributed computing, *Computer networks, *Cloud computing |
| Περίληψη: | We present a novel trace-based analysis tool that rapidly classifies an MPI application as bandwidth-bound, latency-bound, load-imbalance-bound, or computation-bound for different interconnection networks. The tool uses an extension of Lamport’s logical clock to track application progress in the trace replay. It has two unique features. First, it can predict application performance for many latency and bandwidth parameters from a single replay of the trace. Second, it infers the performance characteristics of an application and classifies the application using the predicted performance trend for a range of network configurations instead of using the predicted performance for a particular network configuration. We describe the techniques used in the tool and its design and implementation, and report our performance study of the tool and our experience with classifying twelve applications and mini-apps from the DOE DesignForward project as well as the NAS Parallel Benchmarks. [ABSTRACT FROM AUTHOR] |
| Βάση Δεδομένων: | Academic Search Index |
| FullText | Links: – Type: other Text: Availability: 0 CustomLinks: – Url: https://www.doi.org/10.1016/j.jpdc.2018.05.005? Name: ScienceDirect (all content) (s7799221) Category: fullText Text: View record from ScienceDirect MouseOverText: View record from ScienceDirect |
|---|---|
| Header | DbId: asx DbLabel: Academic Search Index An: 131146813 RelevancyScore: 1232 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1231.64807128906 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Fast classification of MPI applications using Lamport’s logical clocks. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Tong%2C+Zhou%22">Tong, Zhou</searchLink><relatesTo>1</relatesTo><i> tong@cs.fsu.edu</i><br /><searchLink fieldCode="AR" term="%22Pakin%2C+Scott%22">Pakin, Scott</searchLink><relatesTo>2</relatesTo><i> pakin@lanl.gov</i><br /><searchLink fieldCode="AR" term="%22Lang%2C+Michael%22">Lang, Michael</searchLink><relatesTo>2</relatesTo><i> mlang@lanl.gov</i><br /><searchLink fieldCode="AR" term="%22Yuan%2C+Xin%22">Yuan, Xin</searchLink><relatesTo>1</relatesTo><i> xyuan@cs.fsu.edu</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Parallel+%26+Distributed+Computing%22">Journal of Parallel & Distributed Computing</searchLink>. Oct2018, Vol. 120, p77-88. 12p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Logical+clocks%22">Logical clocks</searchLink><br />*<searchLink fieldCode="DE" term="%22Counters+%28Computer+science%29%22">Counters (Computer science)</searchLink><br />*<searchLink fieldCode="DE" term="%22Distributed+computing%22">Distributed computing</searchLink><br />*<searchLink fieldCode="DE" term="%22Computer+networks%22">Computer networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Cloud+computing%22">Cloud computing</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: We present a novel trace-based analysis tool that rapidly classifies an MPI application as bandwidth-bound, latency-bound, load-imbalance-bound, or computation-bound for different interconnection networks. The tool uses an extension of Lamport’s logical clock to track application progress in the trace replay. It has two unique features. First, it can predict application performance for many latency and bandwidth parameters from a single replay of the trace. Second, it infers the performance characteristics of an application and classifies the application using the predicted performance trend for a range of network configurations instead of using the predicted performance for a particular network configuration. We describe the techniques used in the tool and its design and implementation, and report our performance study of the tool and our experience with classifying twelve applications and mini-apps from the DOE DesignForward project as well as the NAS Parallel Benchmarks. [ABSTRACT FROM AUTHOR] |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=asx&AN=131146813 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.jpdc.2018.05.005 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 12 StartPage: 77 Subjects: – SubjectFull: Logical clocks Type: general – SubjectFull: Counters (Computer science) Type: general – SubjectFull: Distributed computing Type: general – SubjectFull: Computer networks Type: general – SubjectFull: Cloud computing Type: general Titles: – TitleFull: Fast classification of MPI applications using Lamport’s logical clocks. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Tong, Zhou – PersonEntity: Name: NameFull: Pakin, Scott – PersonEntity: Name: NameFull: Lang, Michael – PersonEntity: Name: NameFull: Yuan, Xin IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 10 Text: Oct2018 Type: published Y: 2018 Identifiers: – Type: issn-print Value: 07437315 Numbering: – Type: volume Value: 120 Titles: – TitleFull: Journal of Parallel & Distributed Computing Type: main |
| ResultId | 1 |