Performance Evaluation of NWChem Ab-Initio Molecular Dynamics (AIMD) Simulations on the Intel® Xeon Phi™ Processor
Abstract
Ab-initio Molecular Dynamics (AIMD) methods are an important class of algorithms, as they enable scientists to understand the chemistry and dynamics of molecular and condensed phase systems while retaining a first-principles-based description of their interactions. Many-core architectures such as the Intel® Xeon Phi™ processor are an interesting and promising target for these algorithms, as they can provide the computational power that is needed to solve interesting problems in chemistry. In this paper, we describe the efforts of refactoring the existing AIMD plane-wave method of NWChem from an MPI-only implementation to a scalable, hybrid code that employs MPI and OpenMP to exploit the capabilities of current and future many-core architectures. We describe the optimizations required to get close to optimal performance for the multiplication of the tall-and-skinny matrices that form the core of the computational algorithm. We present strong scaling results on the complete AIMD simulation for a test case that simulates 256 water molecules and that strong-scales well on a cluster of 1024 nodes of Intel Xeon Phi processors. We compare the performance obtained with a cluster of dual-socket Intel® Xeon® E5–2698v3 processors.
- Authors:
- Publication Date:
- Research Org.:
- Pacific Northwest National Laboratory (PNNL), Richland, WA (US), Environmental Molecular Sciences Laboratory (EMSL)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1411925
- Report Number(s):
- PNNL-SA-130899
49691; KC0302060
- DOE Contract Number:
- AC05-76RL01830
- Resource Type:
- Conference
- Resource Relation:
- Conference: International Conference on High Performance Computing, June 18-22, 2017, Frankfurt, Germany. Lecture Notes in Computer Science, 10524:404-418
- Country of Publication:
- United States
- Language:
- English
- Subject:
- Environmental Molecular Sciences Laboratory
Citation Formats
Bylaska, Eric J., Jacquelin, Mathias, De Jong, Wibe A., Hammond, Jeff R., and Klemm, Michael. Performance Evaluation of NWChem Ab-Initio Molecular Dynamics (AIMD) Simulations on the Intel® Xeon Phi™ Processor. United States: N. p., 2017.
Web. doi:10.1007/978-3-319-67630-2_30.
Bylaska, Eric J., Jacquelin, Mathias, De Jong, Wibe A., Hammond, Jeff R., & Klemm, Michael. Performance Evaluation of NWChem Ab-Initio Molecular Dynamics (AIMD) Simulations on the Intel® Xeon Phi™ Processor. United States. https://doi.org/10.1007/978-3-319-67630-2_30
Bylaska, Eric J., Jacquelin, Mathias, De Jong, Wibe A., Hammond, Jeff R., and Klemm, Michael. Fri .
"Performance Evaluation of NWChem Ab-Initio Molecular Dynamics (AIMD) Simulations on the Intel® Xeon Phi™ Processor". United States. https://doi.org/10.1007/978-3-319-67630-2_30.
@article{osti_1411925,
title = {Performance Evaluation of NWChem Ab-Initio Molecular Dynamics (AIMD) Simulations on the Intel® Xeon Phi™ Processor},
author = {Bylaska, Eric J. and Jacquelin, Mathias and De Jong, Wibe A. and Hammond, Jeff R. and Klemm, Michael},
abstractNote = {Ab-initio Molecular Dynamics (AIMD) methods are an important class of algorithms, as they enable scientists to understand the chemistry and dynamics of molecular and condensed phase systems while retaining a first-principles-based description of their interactions. Many-core architectures such as the Intel® Xeon Phi™ processor are an interesting and promising target for these algorithms, as they can provide the computational power that is needed to solve interesting problems in chemistry. In this paper, we describe the efforts of refactoring the existing AIMD plane-wave method of NWChem from an MPI-only implementation to a scalable, hybrid code that employs MPI and OpenMP to exploit the capabilities of current and future many-core architectures. We describe the optimizations required to get close to optimal performance for the multiplication of the tall-and-skinny matrices that form the core of the computational algorithm. We present strong scaling results on the complete AIMD simulation for a test case that simulates 256 water molecules and that strong-scales well on a cluster of 1024 nodes of Intel Xeon Phi processors. We compare the performance obtained with a cluster of dual-socket Intel® Xeon® E5–2698v3 processors.},
doi = {10.1007/978-3-319-67630-2_30},
url = {https://www.osti.gov/biblio/1411925},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2017},
month = {10}
}
Works referenced in this record:
SUMMA: scalable universal matrix multiplication algorithm
journal, April 1997
- Van De Geijn, R. A.; Watts, J.
- Concurrency: Practice and Experience, Vol. 9, Issue 4
Utilizing high performance computing for chemistry: parallel computational chemistry
journal, January 2010
- de Jong, Wibe A.; Bylaska, Eric; Govind, Niranjan
- Physical Chemistry Chemical Physics, Vol. 12, Issue 26
Molecular dynamics without effective potentials via the Car-Parrinello approach
journal, August 1990
- Remler, Dahlia K.; Madden, Paul A.
- Molecular Physics, Vol. 70, Issue 6
NWChem for materials science
journal, October 2003
- Aprà, Edoardo; Bylaska, Eric J.; Dean, David J.
- Computational Materials Science, Vol. 28, Issue 2
Iterative minimization techniques for ab initio total-energy calculations: molecular dynamics and conjugate gradients
journal, October 1992
- Payne, M. C.; Teter, M. P.; Allan, D. C.
- Reviews of Modern Physics, Vol. 64, Issue 4
Unified Approach for Molecular Dynamics and Density-Functional Theory
journal, November 1985
- Car, R.; Parrinello, M.
- Physical Review Letters, Vol. 55, Issue 22
OpenMP: an industry standard API for shared-memory programming
journal, January 1998
- Dagum, L.; Menon, R.
- IEEE Computational Science and Engineering, Vol. 5, Issue 1
Roofline: an insightful visual performance model for multicore architectures
journal, April 2009
- Williams, Samuel; Waterman, Andrew; Patterson, David
- Communications of the ACM, Vol. 52, Issue 4
Self-Consistent Equations Including Exchange and Correlation Effects
journal, November 1965
- Kohn, W.; Sham, L. J.
- Physical Review, Vol. 140, Issue 4A, p. A1133-A1138