Methodology to define a static allocation mapping based  on memory access patterns and the Signature of MPI  applications in HPC systems

Gerard Enrique; Eva Bruballa; Remo Suppi; Alvaro Wong; Emilio Luque; Dolores Rexachs

doi:10.24215/16666038.24.e12

Authors

Gerard Enrique Escoles. Universitaries Gimbernat, Computer Science School, Universitat Autonoma de Barcelona, Spain https://orcid.org/0000-0002-4991-2196
Eva Bruballa Escoles. Universitaries Gimbernat, Computer Science School, Universitat Autonoma de Barcelona, Spain https://orcid.org/0000-0002-5094-3563
Remo Suppi Dept. Arquitectura de Computadors i Sistemes operatius, Universitat Autònoma de Barcelona, Spain https://orcid.org/0000-0002-0373-8292
Alvaro Wong Dept. Arquitectura de Computadors i Sistemes operatius, Universitat Autònoma de Barcelona, Spain https://orcid.org/0000-0002-8394-9478
Emilio Luque Dept. Arquitectura de Computadors i Sistemes operatius, Universitat Autònoma de Barcelona, Spain https://orcid.org/0000-0002-2884-3232
Dolores Rexachs Dept. Arquitectura de Computadors i Sistemes operatius, Universitat Autònoma de Barcelona, Spain https://orcid.org/0000-0001-5500-850X

DOI:

https://doi.org/10.24215/16666038.24.e12

Keywords:

Cache memory, HPC performance, MPI parallel applications, Process mapping

Abstract

Tools for identifying problems and improving MPI applications performance running on an HPC system require information from both the application and the system. In this work, we will focus on defining a methodology to analyze how memory usage affects an MPI application’s performance running on an HPC system. This methodology will obtain valid and comparable data based on different memory access patterns, which will allow us to define key performance values used to characterize the HPC system behaviour facing these access patterns, as well as to characterize the Application Signature behaviour. This is obtained from Parallel Application Signatures for Performance Prediction (PAS2P) tool which obtains the representative phases of the MPI application, facing these same access patterns. With this methodology, we will be able to detect memory access application problems, suggest improvements and define a mapping policy for this application in this HPC system, in order to improve its performance and to determine limits to these improvements.

Downloads

Download data is not yet available.

References

A. Wong, D. Rexachs, and E. Luque, “Parallel Application Signature for Performance Analysis and Prediction", IEEE Transactions on Parallel and Distributed Systems, 2015, vol. 26, no. 7, pp. 2009- 2019

C.R. Rangel, A. Wong, D. Rexachs and E. Luque, “Using the application signature to detect inefficiencies generated by mapping policies in parallel applications”, International Conference on High Performance Computing Simulation (HPCS), 2017, pp. 534–540, doi: 10.1109/HPCS.2017.85.

J. Panadero, A. Wong, D. Rexachs, and E. Luque, “A tool for selecting the right target machine for parallel scientific applications”, Proc. Int. Conf. Comput. Sci., 2013, pp. 1824–1833.

Agung, M., Amrizal, M. A., Egawa, R., & Takizawa, H. (2020). Online MPI process mapping for coordinating locality and memory congestion on NUMA systems. Supercomputing Frontiers and Innovations, 7(1), 71-90.

I. Chung, Ch. Lee, J. Zhou, andY. Chung, “Hierarchical mapping for HPC applications”. Parallel Processing Letters, 2011, Vol. 21, No. 03, pp. 279- 299.

T. Sherwood, E. Perelman, and B. Calder. “Basic block distribution analysis to find periodic behavior and simulation points in applications”. In Proceedings of the International Conference on Parallel Architectures and Compilation Techniques (PACT), 2001, pp. 3-14.

E. Perelman, M. Polito, J.-Y. Bouguet, J. Sampson, B. Calder, and C. Dulong. “Detecting phases in parallel applications on shared memory architectures”. Parallel and Distributed Processing Symposium, International, 2006, pp. 0-10.

D. Terpstra, H. Jagode, H. You, and J. Dongarra. “Collecting performance data with papi-c. In Tools for High Performance Computing” Springer, 2010, pp. 157–173.

L. Lamport and C. Time, “The ordering of events in a distributed system,” Commun. ACM, 1978, vol. 21, no. 7, pp. 558–565.

J. Panadero, A. Wong, D. Rexachs, E. Luque. “P3S: a methodology to analyze and predict application scalability”, IEEE Trans Parallel Distrib Syst, 2017, 29 (3):642–658.

F. Tirado, A. Wong, D. Rexachs, E. Luque, “Analyzing the data behavior of parallel application for extracting performance knowledge”, IEEE 21th International Conference on High Performance Computing and Communications, 2019.

F. Tirado, A. Wong, D. Rexachs, E. Luque, “Scalable performance analysis method for SPMD applications. The Journal of Supercomputing, 2022, 78, 19346– 19371. https://doi.org/10.1007/s11227-022-04588-z