Locality-aware dynamic mapping for multithreaded applications

Betul Demiroz, Haluk Rahmi Topcuoglu, Mahmut Kandemir, Oguz Tosun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Locality analysis of an application helps us extract data access patterns and predict runtime cache behavior. In this paper, we propose a locality-aware dynamic mapping algorithm for multithreaded applications, which assigns computations with similar data access patterns to same cores.We collect the amounts of shared and distinct data used by all computations, called chunks and calculate sharing among those chunks. Then, chunks with the similar data access patterns are grouped into bins, which are subsequently assigned to threads for improving cache reuse and program performance. Our algorithm is illustrated with sparse matrix-vector multiply (SpMV), which is one of the most widely used kernel in engineering and scientific computing and suffers from irregular and indirect memory access patterns. Five inputs with different shapes and characteristics are considered for testing the performance of our algorithm. Based on the results of experimental study, our algorithm outperforms Linux scheduler with an average of 12.5% performance improvement for various scenarios considered.

Original languageEnglish (US)
Title of host publicationProceedings - 20th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2012
Pages185-189
Number of pages5
DOIs
StatePublished - Jun 15 2012
Event20th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2012 - Garching, Germany
Duration: Feb 15 2012Feb 17 2012

Publication series

NameProceedings - 20th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2012

Other

Other20th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2012
CountryGermany
CityGarching
Period2/15/122/17/12

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Locality-aware dynamic mapping for multithreaded applications'. Together they form a unique fingerprint.

Cite this