Skip to main content
Top

2019 | OriginalPaper | Chapter

SHCOLL - A Standalone Implementation of OpenSHMEM-Style Collectives API

Authors : Srđan Milaković, Zoran Budimlić, Howard Pritchard, Anthony Curtis, Barbara Chapman, Vivek Sarkar

Published in: OpenSHMEM and Related Technologies. OpenSHMEM in the Era of Extreme Heterogeneity

Publisher: Springer International Publishing

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

search-config
loading …

Abstract

The performance of collective operations has a large impact on overall performance in many HPC applications. Implementing multiple algorithms and selecting optimal one depending on message size and the number of processes involved in the operation is essential to achieve good performance. In this paper, we will present SHCOLL, a collective routines library that was developed on top of OpenSHMEM API point to point operations: puts, gets, atomic memory update, and memory synchronization routines. The library is designed to serve as a plug-in to OpenSHMEM implementations and will be used by the OSSS OpenSHMEM reference implementation to support OpenSHMEM collective operations. In this paper, we describe the algorithms that have been incorporated in the implementation of each OpenSHMEM API collective routine and evaluate them on a Cray XC30 system. For long messages, SHCOLL shows an improvement by up to a factor of 12 compared to the vendor’s implementation. We also discuss future development of the library, as well as how it will be incorporated into the OSSS OpenSHMEM reference implementation.

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

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!

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!

Literature
5.
go back to reference Awan, A.A., Hamidouche, K., Chu, C.H., Panda, D.: A case for non-blocking collectives in OpenSHMEM: design, implementation, and performance evaluation using MVAPICH2-X. In: Gorentla Venkata, M., Shamis, P., Imam, N., Lopez, M.G. (eds.) OpenSHMEM 2014. LNCS, vol. 9397, pp. 69–86. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-26428-8_5CrossRef Awan, A.A., Hamidouche, K., Chu, C.H., Panda, D.: A case for non-blocking collectives in OpenSHMEM: design, implementation, and performance evaluation using MVAPICH2-X. In: Gorentla Venkata, M., Shamis, P., Imam, N., Lopez, M.G. (eds.) OpenSHMEM 2014. LNCS, vol. 9397, pp. 69–86. Springer, Cham (2015). https://​doi.​org/​10.​1007/​978-3-319-26428-8_​5CrossRef
6.
go back to reference Barnett, M., Shuler, L., van De Geijn, R., Gupta, S., Payne, D.G., Watts, J.: Interprocessor collective communication library (intercom). In: Proceedings of the Scalable High-Performance Computing Conference, pp. 357–364. IEEE (1994) Barnett, M., Shuler, L., van De Geijn, R., Gupta, S., Payne, D.G., Watts, J.: Interprocessor collective communication library (intercom). In: Proceedings of the Scalable High-Performance Computing Conference, pp. 357–364. IEEE (1994)
7.
go back to reference Bauer, M.E.: Legion: programming distributed heterogeneous architectures with logical regions (2014) Bauer, M.E.: Legion: programming distributed heterogeneous architectures with logical regions (2014)
8.
go back to reference Bonachea, D.: GASNet specification, v1.1. Technical report, Computer Science Department, University of California, Berkeley (2002) Bonachea, D.: GASNet specification, v1.1. Technical report, Computer Science Department, University of California, Berkeley (2002)
9.
go back to reference Bruck, J., Ho, C.T., Kipnis, S., Upfal, E., Weathersby, D.: Efficient algorithms for all-to-all communications in multiport message-passing systems. IEEE Trans. Parallel Distrib. Syst. 8(11), 1143–1156 (1997)CrossRef Bruck, J., Ho, C.T., Kipnis, S., Upfal, E., Weathersby, D.: Efficient algorithms for all-to-all communications in multiport message-passing systems. IEEE Trans. Parallel Distrib. Syst. 8(11), 1143–1156 (1997)CrossRef
10.
go back to reference ten Buggencate, M., Roweth, D.: DMAPP: an API for one-sided programming models on baker systems. In: Proceedings of Cray User Group (2010) ten Buggencate, M., Roweth, D.: DMAPP: an API for one-sided programming models on baker systems. In: Proceedings of Cray User Group (2010)
13.
go back to reference Cray, Inc.: Chapel Language Specification. Technical report, Cray, Inc. (2010) Cray, Inc.: Chapel Language Specification. Technical report, Cray, Inc. (2010)
14.
go back to reference Cray Inc.: Using the GNI and DMAPP APIs (2011) Cray Inc.: Using the GNI and DMAPP APIs (2011)
16.
go back to reference Faanes, G., et al.: Cray cascade: a scalable HPC system based on a dragonfly network. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC 2012), November 2012 Faanes, G., et al.: Cray cascade: a scalable HPC system based on a dragonfly network. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC 2012), November 2012
17.
go back to reference Jose, J., Kandalla, K., Zhang, J., Potluri, S., Panda, D.: Optimizing collective communication in openshmem. In: 7th International Conference on PGAS Programming Models, p. 185 (2013) Jose, J., Kandalla, K., Zhang, J., Potluri, S., Panda, D.: Optimizing collective communication in openshmem. In: 7th International Conference on PGAS Programming Models, p. 185 (2013)
19.
go back to reference Namashivayam, N., Eachempati, D., Khaldi, D., Chapman, B.M.: OpenSHMEM as a portable communication layer for PGAS models: a case study with coarray fortran. In: 2015 IEEE International Conference on Cluster Computing, CLUSTER 2015, Chicago, IL, USA, 8–11 September 2015, pp. 438–447 (2015). http://dx.doi.org/10.1109/CLUSTER.2015.66 Namashivayam, N., Eachempati, D., Khaldi, D., Chapman, B.M.: OpenSHMEM as a portable communication layer for PGAS models: a case study with coarray fortran. In: 2015 IEEE International Conference on Cluster Computing, CLUSTER 2015, Chicago, IL, USA, 8–11 September 2015, pp. 438–447 (2015). http://​dx.​doi.​org/​10.​1109/​CLUSTER.​2015.​66
23.
go back to reference Chauvin, S., Saha, P., Cantonnet, F., Annareddy, S., El-Ghazawi, T.: UPC Manual (2003) Chauvin, S., Saha, P., Cantonnet, F., Annareddy, S., El-Ghazawi, T.: UPC Manual (2003)
24.
go back to reference Shamis, P., et al.: UCX: an open source framework for HPC network APIS and beyond. In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 40–43, August 2015 Shamis, P., et al.: UCX: an open source framework for HPC network APIS and beyond. In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 40–43, August 2015
25.
go back to reference Tam, A., Wang, C.L.: Efficient scheduling of complete exchange on clusters. In: 13th International Conference on Parallel and Distributed Computing Systems (PDCS 2000), Las Vegas, vol. 4 (2000) Tam, A., Wang, C.L.: Efficient scheduling of complete exchange on clusters. In: 13th International Conference on Parallel and Distributed Computing Systems (PDCS 2000), Las Vegas, vol. 4 (2000)
26.
go back to reference Thakur, R., Rabenseifner, R., Gropp, W.: Optimization of collective communication operations in MPICH. Int. J. High Perform. Comput. Appl. 19(1), 49–66 (2005)CrossRef Thakur, R., Rabenseifner, R., Gropp, W.: Optimization of collective communication operations in MPICH. Int. J. High Perform. Comput. Appl. 19(1), 49–66 (2005)CrossRef
Metadata
Title
SHCOLL - A Standalone Implementation of OpenSHMEM-Style Collectives API
Authors
Srđan Milaković
Zoran Budimlić
Howard Pritchard
Anthony Curtis
Barbara Chapman
Vivek Sarkar
Copyright Year
2019
DOI
https://doi.org/10.1007/978-3-030-04918-8_6

Premium Partner