Abstract
Today’s multi- and many-core systems have NUMA nodes, sockets, tiles, cores, and Symmetric Multi-Threading (SMT) which may require complicated affinity settings to optimally map processes to processors. In many-core systems with hundreds of processors, evaluating the affinity of a single process by surveying a list of processor numbers is time consuming and error prone. Comparing two or more process affinities is even more troublesome. The amask tool displays all process affinities as an easy-to-read matrix of processor-ids versus ranks and/or thread-ids, allowing researchers to quickly confirm default settings and the effect of manipulating affinity, either before or during a parallel execution (through a stand-alone executable or API, respectively).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Lonestar5 Second Petascale System Deployed at TACC (2017). https://www.tacc.utexas.edu/systems/lonestar
Broquedis, F., Clet-Ortega, J., Moreaud, S., Furmento, N., Goglin, B., Mercier, G., Thibault, S., Namyst, R.: hwloc: A generic framework for managing hardware affinities in HPC applications. In: 2010 18th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), pp. 180–186. IEEE (2010)
Eichenberger, A.E., Terboven, C., Wong, M., an Mey, D.: The design of OpenMP thread affinity. In: Chapman, B.M., Massaioli, F., Müller, M.S., Rorro, M. (eds.) IWOMP 2012. LNCS, vol. 7312, pp. 15–28. Springer, Heidelberg (2012). doi:10.1007/978-3-642-30961-8_2
Milfeld, K.: amask, reports affinity masks of parallel processes (2017). https://github.com/tacc/amask
Proctor, C., Gignac, D., McLay, R., Liu, S., James, D., Minyard, T., Stanzione, D.: Lonestar 5: Customizing the cray xc40 software environment
Rabenseifner, R., Hager, G., Jost, G.: Hybrid MPI/OpenMP parallel programming on clusters of multi-core SMP nodes. In: 2009 17th Euromicro International Conference on Parallel, Distributed and Network-based Processing, pp. 427–436. IEEE (2009)
Sodani, A., Gramunt, R., Corbal, J., Kim, H.S., Vinod, K., Chinthamani, S., Hutsell, S., Agarwal, R., Liu, Y.C.: Knights landing: second-generation Intel Xeon Phi product. IEEE Micro 36(2), 34–46 (2016)
Stanzione, D., Barth, B., Gaffney, N., Gaither, K., Hempel, C., Minyard, T., Mehringer, S., Werner, E., Tuffo, H., Panda, D.K., Teller, P.: Stampede2: the Evolution of an XSEDE Supercomputer. In: PEARC, Practice and Experience in Advanced Research Computing, New Orleans (2017, to appear)
Zhang, C., Yuan, X., Srinivasan, A.: Processor affinity and MPI performance on SMP-CMP clusters. In: 2010 IEEE International Symposium on Parallel and Distributed Processing, Workshops and Phd Forum (IPDPSW), pp. 1–8. IEEE (2010)
Acknowledgments
The author would like to acknowledge the support and cooperation of the HPC Group at TACC (Texas Advanced Computing Center) in the perparation of this paper. Thanks to Antonio Gomez and Roberto Garza for reviewing this document. Financial support for this work was provided by the National Science Foundation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Milfeld, K. (2017). amask: A Tool for Evaluating Affinity Masks in Many-Core Processors. In: Kunkel, J., Yokota, R., Taufer, M., Shalf, J. (eds) High Performance Computing. ISC High Performance 2017. Lecture Notes in Computer Science(), vol 10524. Springer, Cham. https://doi.org/10.1007/978-3-319-67630-2_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-67630-2_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67629-6
Online ISBN: 978-3-319-67630-2
eBook Packages: Computer ScienceComputer Science (R0)