Assessing representativeness of kernels using descriptive statistics

Youngsung Kim, John M. Dennis, Christopher Kerr

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

4 Scopus citations

Abstract

A kernel or mini-App is a self-contained small application that retains certain characteristics of the original application [7]. Working on a kernel or mini-App in the place of the original application can dramatically reduce the resources and effort required for performing software tasks such as performance optimization and porting to new platforms. However, using kernel as a proxy is based on the assumption that it represents the original application in the context of how it is being used. In this paper, we introduce an extension to the Fortran Kernel Generator (KGen) which is an automated kernel extraction tool [1]. The extension allows comparison of the execution characteristics between the original application and the generated kernel using descriptive statistics. From the comparison, the user is provided with statistics that provide information on the degree and context of representativeness of the kernel. KGen also utilizes the information generated to help it to automatically improve representativeness of the kernels whilst reducing the size of the workload generated. We applied this extension to three kernels. One is generated from a Fortran scientific library and the remaining two are generated from an earth system model. We have demonstrated that the descriptive statistics provided in the enhancement provide not only quantitative metrics and context of representativeness but also a way to improve the quality of representativeness of the kernels generated.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Cluster Computing, CLUSTER 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages818-825
Number of pages8
ISBN (Electronic)9781538623268
DOIs
StatePublished - Sep 22 2017
Event2017 IEEE International Conference on Cluster Computing, CLUSTER 2017 - Honolulu, United States
Duration: Sep 5 2017Sep 8 2017

Publication series

NameProceedings - IEEE International Conference on Cluster Computing, ICCC
Volume2017-September
ISSN (Print)1552-5244

Conference

Conference2017 IEEE International Conference on Cluster Computing, CLUSTER 2017
Country/TerritoryUnited States
CityHonolulu
Period09/5/1709/8/17

Funding

* This work was supported by National Science Foundation (NSF) and Intel Corporation 1 National Center for Atmospheric Research, 1850 Table Mesa Dr, Boulder, CO 80305, USA ncar.ucar.edu ACKNOWLEDGMENT This work was supported by NSF Cooperative Grant NSF01 which funds the National Center for Atmospheric Research (NCAR), and by Intel Parallel Computing Center focused on Weather and Climate Simulation (IPCC-WACS) program.

Keywords

  • Automated kernel extraction
  • Codesign
  • Descriptive statistics
  • Kernel
  • Python
  • Representativeness

Fingerprint

Dive into the research topics of 'Assessing representativeness of kernels using descriptive statistics'. Together they form a unique fingerprint.

Cite this