Special paper
Realistic parallel performance estimation

https://doi.org/10.1016/S0167-8191(96)00093-2Get rights and content

Abstract

This paper presents an account of two tools which enable realistic parallel performance estimates to be obtained in reasonable time. The first tool, PERFORM (performance estimator for RISC microprocessors), is a general purpose package for sequential program performance estimation on modern RISC microprocessor nodes with complex memory hierarchies. The novelty of the tool is that we have chosen an intermediate level of abstraction between simple statement counting and full simulation of the node architecture. The second tool, LEBEP, generates synthetic parallel programs from a simple communication specification. In particular, it can generate communication operations that incurs typical communication overhead, including data movements across different levels in the memory hierarchy.

References (33)

  • R. Hockney

    The Communication Challenge for MPP: Intel Paragon and Meiko CS-2

    Parallel Comput.

    (1994)
  • G.C. Fox et al.
  • C.A. Addison et al.

    The genesis distributed-memory benchmarks

  • J. Dongarra et al.

    The PARKBENCH Benchmark Collection

    Supercomputer

    (1995)
  • K. Hockney

    Performance parameters and benchmarking of supercomputers

    Parallel Comput.

    (1991)
  • R. Hockney

    Computational similarity

    Concurrency Pract. Exp.

    (1995)
  • V. Getov

    1-Dimensional Parallel FFT Benchmark on SUPRENUM

    Lecture Notes Comput. Sci.

    (1992)
  • V. Balasundaram et al.

    A Static Performance Estimator to Guide Data Partitioning Decisions

    ACM Sigplan Notices

    (1991)
  • N. MacDonald

    Predicting the Execution time of Sequential Scientific Codes

  • K. Kennedy et al.

    Static Performance Estimation in a Parallelising Compiler

  • Y. Seo et al.

    Static Performance Prediction in PCASE: A Programming Environment for Parallel Supercomputers

  • A. Dunlop et al.

    An Evaluation of the Statement Counting Method for Performance Prediction

    (1996)
  • T. Fahringer

    Using the P3T to Guide the Parallelisation and Optimisation Effort under the Vienna Fortran Compilation System

  • P. Banerjee et al.

    The Paradigm Compiler for Distributed-Memory MultiComputers

    IEEE Comput.

    (1995)
  • A.N. Dunlop et al.

    Parallel Performance Estimator

  • E.E. Hernández

    Parallel Computing System Evaluation using Automatically Synthesized Benchmarks

    internal Report

    (1995)
    • View full text
    Copyright © 1997 Published by Elsevier B.V.