Top

The Journal of Supercomputing

Published in:

08-02-2023

PAARes: an efficient process allocation based on the available resources of cluster nodes

Authors: J. L. Quiroz-Fabián, G. Román-Alonso, M. A. Castro-García, M. Aguilar-Cornejo

Published in: The Journal of Supercomputing | Issue 9/2023

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

The process allocation is a problem in high performance computing, especially when using heterogeneous architectures involving diverse performance characteristics such as number of cores and their frequencies, multithreading technologies, cache memory etc. In order to improve the application performance, it is necessary to consider which processing units are the most suitable to execute the application processes. In this paper, PAARes (Process Allocation based on the Available Resources) strategy is implemented that automatically collects the system information for the process distribution by considering the processing capacity of each node in a cluster and their available resources. To demonstrate the efficiency and efficacy of the proposed strategy, the NAS (NASA Advanced Supercomputing) parallel benchmark is run on homogeneous and heterogeneous clusters under both dedicated and non-dedicated environments.

previous article An efficient centralized DDoS attack detection approach for Software Defined Internet of Things

next article Secure data outsourcing based on seed-residual shares and order-shuffling encryption

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

In OpenMPI a slot is an allocation unit for a process.

Communications where the sender, receiver and message are well defined

Process that generates load on the CPU performing floating point operations.

Acun B, Hardy DJ, Kale LV, Li K, Phillips JC, Stone JE (2018) Scalable molecular dynamics with NAMD on the summit system. IBM J Res Dev 62(6):4–149. https://doi.org/10.1147/JRD.2018.2888986CrossRef

Guo Z, Lu D, Yan Y, Hu S, Liu R, Tan G, Sun N, Jiang W, Liu L, Chen Y, Zhang L, Chen M, Wang H, Jia W (2022) Extending the limit of molecular dynamics with ab initio accuracy to 10 billion atoms. In: Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. PPoPP’22. Association for Computing Machinery, New York, pp 205–218. https://doi.org/10.1145/3503221.3508425

Morillo J, Vassaux M, Coveney PV, Garcia-Gasulla M (2022) Hybrid parallelization of molecular dynamics simulations to reduce load imbalance. J Supercomput 78(7):9184–9215. https://doi.org/10.1007/s11227-021-04214-4CrossRef

Pérez-Espinosa A, Aguilar-Cornejo M, Dagdug L (2020) First-passage, transition path, and looping times in conical varying-width channels: comparison of analytical and numerical results. AIP Adv 10(5):055201. https://doi.org/10.1063/5.0004026CrossRef

Qiu H, Xu C, Li D, Wang H, Li J, Wang Z (2022) Parallelizing and balancing coupled DSMC/PIC for large-scale particle simulations. In: 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp 390–401. https://doi.org/10.1109/IPDPS53621.2022.00045

Mata AN, Castellanos Abrego NP, Alonso GR, Castro García MA, Garza GL, God ínez Fernández JR (2018) Parallel simulation of sinoatrial node cells synchronization. In: 2018 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP), pp 126–133. https://doi.org/10.1109/PDP2018.2018.00025

Cordero-Sánchez S, Rojas-González F, Román-Alonso G, Castro-García MA, Aguilar-Cornejo M, Matadamas-Hernández J (2016) Pore networks subjected to variable connectivity and geometrical restrictions: a simulation employing a multicore system. J Comput Sci 16:177–189. https://doi.org/10.1016/j.jocs.2016.06.003CrossRef

Ando S, Kaneda M, Suga K (2022) Permeability prediction of fibrous porous media by the lattice Boltzmann method with a fluid-structure boundary reconstruction scheme. J Ind Text 51(4_suppl):6902–6923CrossRef

Pearson C, Javeed A, Devine K (2022) Machine learning for CUDA+MPI design rules. In: 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp 880–889. https://doi.org/10.1109/IPDPSW55747.2022.00144

10.

Alemany S, Nucciarone J, Pissinou N (2021) Jespipe: a plugin-based, open MPI framework for adversarial machine learning analysis. In: 2021 IEEE International Conference on Big Data (Big Data), pp 3663–3670. https://doi.org/10.1109/BigData52589.2021.9671385

11.

Al-Rahayfeh A, Atiewi S, Abuhussein A, Almiani M (2019) Novel approach to task scheduling and load balancing using the dominant sequence clustering and mean shift clustering algorithms. Future Internet. https://doi.org/10.3390/fi11050109CrossRef

12.

Tyagi R, Gupta SK (2018) A survey on scheduling algorithms for parallel and distributed systems. In: Mishra A, Basu A, Tyagi V (eds) Silicon Photonics & High Performance Computing. Springer, Singapore, pp 51–64CrossRef

13.

Nasa: NASA Advanced Supercomputing Division. https://www.nas.nasa.gov/publications/npb.html#url. Accessed April 2022

14.

Feng H, Misra V, Rubenstein D (2007) PBS: a unified priority-based scheduler. SIGMETRICS Perform Eval Rev 35(1):203–214. https://doi.org/10.1145/1269899.1254906CrossRef

15.

Zhao T, Gu J, Zhang X (2021) Two-level scheduling technology for heterogeneous clusters using analytical hierarchy processes. In: 2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS), pp 121–127. https://doi.org/10.1109/ICCCS52626.2021.9449223

16.

Intel: Running an MPI Program. https://www.intel.com/content/www/us/en/develop/documentation/mpi-developer-guide-linux/top/running-applications/running-an-mpi-program.html. Accessed April 2022

17.

mpich: Using the Hydra Process Manager. https://wiki.mpich.org/mpich/index.php/Using_the_Hydra_Process_Manager. Accessed April 2022

18.

openmpi: Running MPI jobs. https://www.open-mpi.org/faq/?category=running. Accessed April 2022

19.

Li K (2008) Optimal load distribution in nondedicated heterogeneous cluster and grid computing environments. J Syst Architect 54(1):111–123. https://doi.org/10.1016/j.sysarc.2007.04.003CrossRef

20.

Skenteridou K, Karatza HD (2015) Job scheduling in a grid cluster. In: 2015 International Conference on Computer, Information and Telecommunication Systems (CITS), pp 1–5. https://doi.org/10.1109/CITS.2015.7297738

21.

Ullman J (1975) Np-complete scheduling problems. J Comput Syst Sci 10:384–393CrossRefMATHMathSciNet

22.

Cao H, Jin H, Wu X, Wu S, Shi X (2010) DAGMap: efficient and dependable scheduling of DAG workflow job in grid. J Supercomput 51(2):201–223. https://doi.org/10.1007/s11227-009-0284-7CrossRef

23.

Ganapathi RB, Gopalakrishnan A, McGuire RW (2017) MPI process and network device affinitization for optimal HPC application performance. In: 2017 IEEE 25th Annual Symposium on High-Performance Interconnects (HOTI), pp 80–86. https://doi.org/10.1109/HOTI.2017.12

24.

Jeannot E, Mercier G (2010) Near-optimal placement of MPI processes on hierarchical NUMA architectures. In: Proceedings of the 16th International Euro-Par Conference on Parallel Processing: Part II. Euro-Par’10. Springer, Berlin, pp 199–210. http://dl.acm.org/citation.cfm?id=1885276.1885299

25.

Jeannot E, Mercier G, Tessier F (2014) Process placement in multicore clusters: algorithmic issues and practical techniques. IEEE Trans Parallel Distrib Syst 25(4):993–1002. https://doi.org/10.1109/TPDS.2013.104CrossRef

26.

Gabriel E, Fagg GE, Bosilca G, Angskun T, Dongarra JJ, Squyres JM, Sahay V, Kambadur P, Barrett B, Lumsdaine A, Castain RH, Daniel DJ, Graham RL, Woodall TS (2004) Open MPI: Goals, concept, and design of a next generation MPI implementation. In: Proceedings, 11th European PVM/MPI Users’ Group Meeting, Budapest, Hungary, pp 97–104

27.

Goglin B (2014) Managing the topology of heterogeneous cluster nodes with hardware locality (HWLOC). In: 2014 International Conference on High Performance Computing Simulation (HPCS), pp 74–81. https://doi.org/10.1109/HPCSim.2014.6903671

28.

Gropp W (2002) MPICH2: a new start for MPI implementations. In: Kranzlmüller D, Volkert J, Kacsuk P, Dongarra J (eds) Recent Advances in Parallel Virtual Machine and Message Passing Interface. Springer, Berlin, pp 7–7

29.

Hursey J, Squyres JM (2013) Advancing application process affinity experimentation: Open MPI’s lama-based affinity interface. In: Proceedings of the 20th European MPI Users’ Group Meeting. EuroMPI’13. ACM, New York, pp 163–168. https://doi.org/10.1145/2488551.2488603

30.

Goglin B (2017) On the overhead of topology discovery for locality-aware scheduling in HPC. In: PDP2017—25th Euromicro International Conference on Parallel, Distributed and Network-Based Processing. Proceedings of the 25th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP2017). IEEE Computer Society, St Petersburg, p 9. https://doi.org/10.1109/PDP.2017.35

31.

Goglin B (2018) Memory footprint of locality information on many-core platforms. In: IEEE (ed.) 6th Workshop on Runtime and Operating Systems for the Many-core Era (ROME 2018), Held in Conjunction with IPDPS, Vancouver, BC, Canada, p 10. https://hal.inria.fr/hal-01644087

32.

Leng T, Ali R, Hsieh J, Mashayekhi V, Rooholamini R (2002) An empirical study of hyper-threading in high performance computing clusters

33.

Marr DT, Binns F, Hill DL, Hinton G, Koufaty DA, Miller AJ, Upton M (2002) Hyper-threading technology architecture and microarchitecture. Intel Technol J 6(1)

34.

openmpi: mpirun. https://www.open-mpi.org/doc/v4.1/man1/mpirun.1.php. Accessed April 2022

Title: PAARes: an efficient process allocation based on the available resources of cluster nodes
Authors: J. L. Quiroz-Fabián
G. Román-Alonso
M. A. Castro-García
M. Aguilar-Cornejo
Publication date: 08-02-2023
Publisher: Springer US
Published in: The Journal of Supercomputing / Issue 9/2023
Print ISSN: 0920-8542
Electronic ISSN: 1573-0484
DOI: https://doi.org/10.1007/s11227-023-05085-7

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Springer Professional "Wirtschaft+Technik"

Other articles of this Issue 9/2023

Row-based hierarchical graph network for multi-hop question answering over textual and tabular data

Implementation of a motion estimation algorithm for Intel FPGAs using OpenCL

GHDC: a dual-centric data center network architecture by using multi-port servers with greater incremental scalability

Correction to: Improve customer churn prediction through the proposed PCA‑PSO‑K means algorithm in the communication industry

Secure data outsourcing based on seed-residual shares and order-shuffling encryption

A proposed cloud‑based platform for facilitating donation services in support to needy-students

Premium Partner