• Home
  • Search
  • Optimizing array distributions in data-parallel programs
  • Cite Icon5
  • https://doi.org/10.1007/bfb0025897Copy DOI Icon

Optimizing array distributions in data-parallel programs

  • Jan 1, 1995
  • Krishna Kunchithapadam +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Data parallel programs are sensitive to the distribution of data across processor nodes. We formulate the reduction of inter-node communication as an optimization on a colored graph. We present a technique that records the run time inter-node communication caused by the movement of array data between nodes during execution and builds the colored graph, and provide a simple algorithm that optimizes the coloring of this graph to describe new data distributions that would result in less inter-node communication. From the distribution information, we write compiler pragmas to be used in the application program.Using these techniques, we traced the execution of a real data-parallel application (written in CM Fortran) and collected the array access information. We computed new distributions that should provide an overall reduction in program execution time. However, compiler optimizations and poor interfaces between the compiler and runtime systems counteracted any potential benefit from the new data layouts. In this context, we provide a set of recommendations for compiler writers that we think are needed to both write efficient programs and to build the next generation of tools for parallel systems.The techniques that we have developed form the basis for future work in monitoring array access patterns and generate on-the-fly redistributions of arrays.KeywordsParallel MachineAccess PatternRuntime SystemData LayoutFortran CompilerThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Similar Papers
  • Dissertation
  • Citations1

Formal implementation of high-level languages for data-parallel programming

  • Jan 01, 1992
  • Deb Banerjee
  • Book Chapter

Chapter 5 - Collective Communication Support

  • Jan 01, 2003
  • Interconnection Networks
  • José Duato +2
  • Book Chapter
  • Citations27

Compiler Transformation of Pointers to Explicit Array Accesses in DSP Applications

  • Jan 01, 2001
  • Björn Franke +1
  • Research Article
  • Citations3

A Hybrid Parallel Delaunay Image-to-mesh Conversion Algorithm Scalable on Distributed-memory Clusters

  • Jan 01, 2016
  • Procedia Engineering
  • Daming Feng +2
  • Book Chapter

An Analysis of Programmer Productivity versus Performance for High Level Data Parallel Programming

  • Jan 01, 2011
  • Cole Alex +2
  • Conference Article
  • Citations4

Load balancing and performance issues for the data parallel simulation of stiff chemical nonequilibrium flows

  • Jan 09, 1995
  • 33rd Aerospace Sciences Meeting and Exhibit
  • James Weber +4
  • Research Article
  • Citations4

Load Balancing and Performance Issues for Data Parallel

  • Mar 01, 1997
  • AIAA Journal
  • James W Weber +3
  • Research Article
  • Citations1

Load balancing and performance issues for data parallel simulation of stiff chemical nonequilibrium flows

  • Jan 01, 1997
  • AIAA Journal
  • James W Weber +3
  • Book Chapter
  • Citations10

Adaptor: A Compilation System for Data Parallel Fortran Programs

  • Jan 01, 1994
  • Thomas Brandes
  • Research Article
  • Citations3

FUZZY NUMBER SUBTRACTION CONVOLUTION ON THE CM-2

  • Feb 01, 1993
  • International Journal of Modern Physics C
  • Nikolay Petkov
  • Book Chapter
  • Citations8

A Methodology to Characterize Critical Section Bottlenecks in DSM Multiprocessors

  • Jan 01, 2009
  • Benjamín Sahelices +3
  • Research Article

PPTran: SOURCE TO SOURCE TRANSLATOR FOR HIGH PERFORMANCE FORTRAN

  • Jun 01, 1996
  • Parallel Algorithms and Applications
  • Taegeun Kim +3
  • Research Article

Modified efficiency-NTU method (m-ε-NTU) for calculating air coolers in dehumidifying or frost conditions. Part IV

  • Mar 22, 2024
  • Refrigeration Technology
  • Vladimir A Portyanikhin
  • Research Article
  • Citations3

An integrated performance analysis tool for SPMD data-parallel programs

  • Aug 01, 1997
  • Parallel Computing
  • Ajit Singh +1
  • Research Article

A multi-thread approach reducing program execution time in a heterogeneous reconfigurable multi-processor architecture

  • Mar 01, 1997
  • Journal of Systems Architecture
  • Miroslaw Thor
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.