CApRI: CAche-conscious data Reordering for Irregular codes

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

Abstract

Caches play a critical role in today's computer systems and optimizing their performance has been a critical objective in the last couple of decades. Unfortunately, compared to a plethora of work in software and hardware directed code/data optimizations, much less effort has been spent in under- standing the fundamental characteristics of data access pat- terns exhibited by application programs and their interac- tion with the underlying cache hardware. Therefore, in gen- eral it is hard to reason about cache behavior of a program running on a target system. Motivated by this observation, we first set up a \locality model" that can help us deter- mine the theoretical bounds of the cache misses caused by irregular data accesses. We then explain how this locality model can be used for different data locality optimization purposes. After that, based on our model, we propose a data reordering (data layout reorganization) scheme that can be applied after any existing data reordering schemes for irreg- ular applications to improve cache performance by further reducing the cache misses. We evaluate the effectiveness of our scheme using a set of 8 programs with irregular data ac- cesses, and show that it brings significant improvements over the state-of-the-art on two commercial multicore machines.

Original languageEnglish (US)
Title of host publicationSIGMETRICS 2014 - Proceedings of the 2014 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems
PublisherAssociation for Computing Machinery
Pages477-489
Number of pages13
ISBN (Print)9781450327893
DOIs
StatePublished - Jan 1 2014
Event2014 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS 2014 - Austin, TX, United States
Duration: Jun 16 2014Jun 20 2014

Publication series

NameSIGMETRICS 2014 - Proceedings of the 2014 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems

Other

Other2014 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS 2014
CountryUnited States
CityAustin, TX
Period6/16/146/20/14

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Modeling and Simulation

Cite this

Ding, W., & Kandemir, M. T. (2014). CApRI: CAche-conscious data Reordering for Irregular codes. In SIGMETRICS 2014 - Proceedings of the 2014 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (pp. 477-489). (SIGMETRICS 2014 - Proceedings of the 2014 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems). Association for Computing Machinery. https://doi.org/10.1145/2591971.2591992