Parallel performance prediction using lost cycles analysis

Mark E. Crovella, Thomas J. LeBlanc

Research output: Contribution to journalConference article

40 Scopus citations

Abstract

Most performance debugging and tuning of parallel programs is based on the 'measure-modify' approach, which is heavily dependent on detailed measurements of programs during execution. This approach is extremely time-consuming and does not lend itself to predicting performance under varying conditions. Analytic modeling and scalability analysis provide predictive power, but are not widely used in practice, due primarily to their emphasis on asymptotic behavior and the difficulty of developing accurate models that work for real-world programs. In this paper we describe a set of tools for performance tuning of parallel programs that bridges this gap between measurement and modeling. Our approach is based on lost cycles analysis which involves measurement and modeling of all sources of overhead in a parallel program. We first describe a tool for measuring overheads in parallel programs that we have incorporated into the runtime environment for Fortran programs on the Kendall Square KSR1. We then describe a tool that fits these overhead measurements to analytic forms. We illustrate the use of these tools by analyzing the performance tradeoffs among parallel implementation of 2D FFT. These examples show how our tools enable programmers to develop accurate performance models of parallel applications without requiring extensive performance modeling expertise.

Original languageEnglish (US)
Pages (from-to)600-609
Number of pages10
JournalProceedings of the ACM/IEEE Supercomputing Conference
StatePublished - Dec 1 1994
EventProceedings of the 1994 Supercomputing Conference - Washington, DC, USA
Duration: Nov 14 1994Nov 18 1994

    Fingerprint

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this