Preservation of Non-uniform Memory Architecture Characteristics when Going from a Nested OpenMP to a Hybrid MPI/OpenMP Approach

M. Ali Rostami, H. Martin Bücker

Abstract

While the noticeable shift from serial to parallel programming in simulation technologies progresses, it is increasingly important to better understand the interplay of different parallel programming paradigms. We discuss some corresponding issues in the context of transforming a shared-memory parallel program that involves two nested levels of parallelism into a hybrid parallel program. Here, hybrid programming refers to a combination of shared and distributed memory. In particular, we focus on performance aspects arising from shared-memory parallel programming where the time to access a memory location varies with the threads. Rather than analyzing these issues in general, the focus of this position paper is on a particular case study from geothermal reservoir engineering.

References

  1. Bartels, J., Kühn, M., and Clauser, C. (2003). Numerical simulation of reactive flow using SHEMAT. In Clauser, C., editor, Numerical Simulation of Reactive Flow in Hot Aquifers, pages 5-74. Springer Berlin Heidelberg.
  2. Bhuyan, L., Iyer, R., Wang, H.-J., and Kumar, A. (2000). Impact of CC-NUMA memory management policies on the application performance of multistage switching networks. IEEE Transactions on Parallel and Distributed Systems, 11(3):230-246.
  3. Chapman, B., Jost, G., Van der Pas, R., and Kuck, D. J. (2008). Using OpenMP: Portable shared memory parallel programming. MIT Press, Cambridge, Mass., London.
  4. Gropp, W., Huss-Lederman, S., Lumsdaine, A., Lusk, E. L., Nitzberg, B., Saphir, W., and Snir, M. (1998). MPIThe Complete Reference: Volume 2, The MPI-2 Extensions. MIT Press, Cambridge, MA, USA.
  5. Jost, G. and Robins, B. (2010). Experiences using hybrid MPI/OpenMP in the real world: Parallelization of a 3D CFD solver for multi-core node clusters. Scientific Programming, 18(3-4):127-138.
  6. O'Donncha, F., Ragnoli, E., and Suits, F. (2014). Parallelisation study of a three-dimensional environmental flow model. Computers & Geosciences, 64:96-103.
  7. OpenMP Architecture Review Board (2013). OpenMP Application Program Interface, Version 4.0. http://www.openmp.org.
  8. Rath, V., Wolf, A., and Bücker, H. M. (2006). Joint three-dimensional inversion of coupled groundwater flow and heat transfer based on automatic differentiation: Sensitivity calculation, verification, and synthetic examples. Geophysical Journal International, 167(1):453-466.
  9. Snir, M., Otto, S. W., Huss-Lederman, S., Walker, D. W., and Dongarra, J. (1998). MPI-The Complete Reference: Volume 1, The MPI Core. MIT Press, Cambridge, MA, USA, 2nd edition.
  10. Tarantola, A. (2004). Inverse Problem Theory and Methods for Model Parameter Estimation. Society for Industrial and Applied Mathematics, Philadelphia, PA, USA.
  11. Wolf, A. (2011). Ein Softwarekonzept zur hierarchischen Parallelisierung von stochastischen und deterministischen Inversionsproblemen auf modernen ccNUMAPlattformen unter Nutzung automatischer Programmtransformation. Dissertation, Department of Computer Science, RWTH Aachen University.
  12. Wu, X. and Taylor, V. (2013). Performance modeling of hybrid MPI/OpenMP scientific applications on largescale multicore supercomputers. Journal of Computer and System Sciences, 79(8):1256-1268.
Download


Paper Citation


in Harvard Style

Rostami M. and Bücker H. (2014). Preservation of Non-uniform Memory Architecture Characteristics when Going from a Nested OpenMP to a Hybrid MPI/OpenMP Approach . In Proceedings of the 4th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH, ISBN 978-989-758-038-3, pages 286-291. DOI: 10.5220/0005110902860291


in Bibtex Style

@conference{simultech14,
author={M. Ali Rostami and H. Martin Bücker},
title={Preservation of Non-uniform Memory Architecture Characteristics when Going from a Nested OpenMP to a Hybrid MPI/OpenMP Approach},
booktitle={Proceedings of the 4th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,},
year={2014},
pages={286-291},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005110902860291},
isbn={978-989-758-038-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,
TI - Preservation of Non-uniform Memory Architecture Characteristics when Going from a Nested OpenMP to a Hybrid MPI/OpenMP Approach
SN - 978-989-758-038-3
AU - Rostami M.
AU - Bücker H.
PY - 2014
SP - 286
EP - 291
DO - 10.5220/0005110902860291