Analytical performance modeling and validation of Intel's Xeon Phi architecture

Sudheer Chunduri, Prasanna Balaprakash, Vitali Morozov, Venkatram Vishwanath, Kalyan Kumaran

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Modeling the performance of scientific applications on emerging hardware plays a central role in achieving extreme-scale computing goals. Analytical models that capture the interaction between applications and hardware characteristics are attractive because even a reasonably accurate model can be useful for performance tuning before the hardware is made available. In this paper, we develop a hardware model for Intel's second-generation Xeon Phi architecture code-named Knights Landing (KNL) for the SKOPE framework. We validate the KNL hardware model by projecting the performance of minibenchmarks and application kernels. The results show that our KNL model can project the performance with prediction errors of 10% to 20%. The hardware model also provides informative recommendations for code transformations and tuning.

Original languageEnglish
Title of host publicationACM International Conference on Computing Frontiers 2017, CF 2017
PublisherAssociation for Computing Machinery, Inc
Pages247-250
Number of pages4
ISBN (Electronic)9781450344876
DOIs
StatePublished - May 15 2017
Externally publishedYes
Event14th ACM International Conference on Computing Frontiers, CF 2017 - Siena, Italy
Duration: May 15 2017May 17 2017

Publication series

NameACM International Conference on Computing Frontiers 2017, CF 2017

Conference

Conference14th ACM International Conference on Computing Frontiers, CF 2017
Country/TerritoryItaly
CitySiena
Period05/15/1705/17/17

Keywords

  • Analytical modeling
  • Benchmark
  • KNL
  • Performance
  • Projection

Fingerprint

Dive into the research topics of 'Analytical performance modeling and validation of Intel's Xeon Phi architecture'. Together they form a unique fingerprint.

Cite this