Chapter

Tools for High Performance Computing

pp 157-167

Usage of the SCALASCA toolset for scalable performance analysis of large-scale parallel applications

  • Felix WolfAffiliated withJülich Supercomputing Centre, Forschungszentrum JülichDepartment of Computer Science and Aachen Institute for Advanced Study in Computational Engineering Science, RWTH Aachen University Email author 
  • , Brian J. N. WylieAffiliated withJülich Supercomputing Centre, Forschungszentrum Jülich
  • , Erika ÁbrahámAffiliated withJülich Supercomputing Centre, Forschungszentrum Jülich
  • , Daniel BeckerAffiliated withJülich Supercomputing Centre, Forschungszentrum JülichDepartment of Computer Science and Aachen Institute for Advanced Study in Computational Engineering Science, RWTH Aachen University
  • , Wolfgang FringsAffiliated withJülich Supercomputing Centre, Forschungszentrum Jülich
  • , Karl FürlingerAffiliated withInnovative Computing Laboratory, University of Tennessee
  • , Markus GeimerAffiliated withJülich Supercomputing Centre, Forschungszentrum Jülich
  • , Marc-André HermannsAffiliated withJülich Supercomputing Centre, Forschungszentrum Jülich
  • , Bernd MohrAffiliated withJülich Supercomputing Centre, Forschungszentrum Jülich
    • , Shirley MooreAffiliated withInnovative Computing Laboratory, University of Tennessee
    • , Matthias PfeiferAffiliated withJülich Supercomputing Centre, Forschungszentrum JülichDepartment of Computer Science and Aachen Institute for Advanced Study in Computational Engineering Science, RWTH Aachen University
    • , Zoltán SzebenyiAffiliated withJülich Supercomputing Centre, Forschungszentrum JülichDepartment of Computer Science and Aachen Institute for Advanced Study in Computational Engineering Science, RWTH Aachen University

* Final gross prices may vary according to local VAT.

Get Access

Abstract

scalasca is a performance toolset that has been specifically designed to analyze parallel application behavior on large-scale systems, but is also well-suited for small- and medium-scale hpc platforms. scalasca offers an incremental performance-analysis process that integrates runtime summaries with in-depth studies of concurrent behavior via event tracing, adopting a strategy of successively refined measurement configurations. A distinctive feature of scalasca is its ability to identify wait states even for very large processor counts. The current version supports the mpi, Openmp and hybrid programming constructs most widely used in highly-scalable hpc applications.