A performance spectrum for parallel computational frameworks that solve PDEs
Authors:
- 20 December 2017
- journal article
- research article
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 30 (11)
Abstract
Summary: Important computational physics problems are often large‐scale in nature, and it is highly desirable to have robust and high performing computational frameworks that can quickly address these problems. However, it is no trivial task to determine whether a computational framework is performing efficiently or is scalable. The aim of this paper is to present various strategies for better understanding the performance of any parallel computational frameworks for solving PDEs. Important performance issues that negatively impact time‐to‐solution are discussed, and we propose a performance spectrum analysis that can enhance one's understanding of critical aforementioned performance issues. As proof of concept, we examine commonly used finite element simulation packages and software and apply the performance spectrum to quickly analyze the performance and scalability across various hardware platforms, software implementations, and numerical discretizations. It is shown that the proposed performance spectrum is a versatile performance model that is not only extendable to more complex PDEs such as hydrostatic ice sheet flow equations but also useful for understanding hardware performance in a massively parallel computing environment. Potential applications and future extensions of this work are also discussed.Keywords
All Related Versions
Funding Information
- Oak Ridge Institute for Science and Education (DE-SC0014664)
- U.S. Department of Energy (DE-AC02-06CH11357)
This publication has 40 references indexed in Scilit:
- Tibidabo: Making the case for an ARM-based HPC systemFuture Generation Computer Systems, 2014
- The Scalasca performance toolset architectureConcurrency and Computation: Practice and Experience, 2010
- Thin-Film Flows with Wall Slip: An Asymptotic Analysis of Higher Order Glacier Flow ModelsQuarterly Journal of Mechanics and Applied Mathematics, 2010
- HPCTOOLKIT: tools for performance analysis of optimized parallel programsConcurrency and Computation: Practice and Experience, 2009
- RooflineCommunications of the ACM, 2009
- deal.II—A general-purpose object-oriented finite element libraryACM Transactions on Mathematical Software, 2007
- A variational approach to ice stream flowJournal of Fluid Mechanics, 2006
- OpenMP: an industry standard API for shared-memory programmingIEEE Computational Science and Engineering, 1998
- Hitting the memory wallACM SIGARCH Computer Architecture News, 1995
- The input/output complexity of sorting and related problemsCommunications of the ACM, 1988