Skip to main content

2018 | OriginalPaper | Buchkapitel

Efficient Communication/Computation Overlap with MPI+OpenMP Runtimes Collaboration

verfasst von : Marc Sergent, Mario Dagrada, Patrick Carribault, Julien Jaeger, Marc Pérache, Guillaume Papauré

Erschienen in: Euro-Par 2018: Parallel Processing

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Overlap network communications and computations is a major requirement to ensure scalability of HPC applications on future exascale machines. To this purpose the de-facto MPI standard provides non-blocking routines for asynchronous communication progress. In various implementations, a dedicated progress thread (PT) is deployed on the host CPU to actually achieve this overlap. However, current PT solutions struggle to find a balance between efficient detection of network events and minimal impact on the application computations. In this paper we propose a solution inspired from the PT approach which benefits from idle time of compute threads to make MPI communication progress in background. We implement our idea in the context of MPI+OpenMP collaboration using the OpenMP Tools interface which will be part of the OpenMP 5.0 standard. Our solution shows an overall performance gain on unbalanced workloads such as the AMG CORAL benchmark.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

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!

Literatur
4.
Zurück zum Zitat Barrett, B.W., et al.: The Portals 4.0 network programming interface. Technical Report, Sandia National Laboratories, SAND2013-3181 (2013) Barrett, B.W., et al.: The Portals 4.0 network programming interface. Technical Report, Sandia National Laboratories, SAND2013-3181 (2013)
5.
Zurück zum Zitat Brightwell, R., Riesen, R., Underwood, K.D.: Analyzing the impact of overlap, offload, and independent progress for message passing interface applications. HPCA J. 19, 103–117 (2005) Brightwell, R., Riesen, R., Underwood, K.D.: Analyzing the impact of overlap, offload, and independent progress for message passing interface applications. HPCA J. 19, 103–117 (2005)
6.
Zurück zum Zitat Cardellini, V., Fanfarillo, A., Filippone, S.: Overlapping communication with computation in MPI applications. Technical Report, Universita di Roma Tor Vergata, DICII RR-16.09 (2016) Cardellini, V., Fanfarillo, A., Filippone, S.: Overlapping communication with computation in MPI applications. Technical Report, Universita di Roma Tor Vergata, DICII RR-16.09 (2016)
7.
Zurück zum Zitat Derradji, S., Palfer-Sollier, T., Panziera, J.P., Poudes, A., Atos, F.W.: The BXI interconnect architecture. IEEE, August 2015 Derradji, S., Palfer-Sollier, T., Panziera, J.P., Poudes, A., Atos, F.W.: The BXI interconnect architecture. IEEE, August 2015
8.
Zurück zum Zitat Dongarra, J., et al.: The international exascale software project roadmap. HPCA J. 25, 3–60 (2011) Dongarra, J., et al.: The international exascale software project roadmap. HPCA J. 25, 3–60 (2011)
10.
Zurück zum Zitat Hoefler, T., Lumsdaine, A.: Message progression in parallel computing - to thread or not to thread? In: IEEE CLUSTER (2008) Hoefler, T., Lumsdaine, A.: Message progression in parallel computing - to thread or not to thread? In: IEEE CLUSTER (2008)
11.
Zurück zum Zitat Isaacs, K.E., Gamblin, T., Bhatele, A., Schulz, M., Hamann, B., Bremer, P.T.: Ordering traces logically to identify lateness in message passing programs. IEEE Trans. Parallel Distrib. Syst. 27, 829–840 (2016)CrossRef Isaacs, K.E., Gamblin, T., Bhatele, A., Schulz, M., Hamann, B., Bremer, P.T.: Ordering traces logically to identify lateness in message passing programs. IEEE Trans. Parallel Distrib. Syst. 27, 829–840 (2016)CrossRef
12.
Zurück zum Zitat Lewis, J.G., Van de Geijn, R.A.: Distributed memory matrix-vector multiplication and conjugate gradient algorithms. In: Proceedings of the 1993 ACM/IEEE Conference on Supercomputing (1993) Lewis, J.G., Van de Geijn, R.A.: Distributed memory matrix-vector multiplication and conjugate gradient algorithms. In: Proceedings of the 1993 ACM/IEEE Conference on Supercomputing (1993)
13.
Zurück zum Zitat Mellor-Crummey, J.: Performance Analysis of MPI+OpenMP Programs with HPCToolkit, March 2015 Mellor-Crummey, J.: Performance Analysis of MPI+OpenMP Programs with HPCToolkit, March 2015
14.
Zurück zum Zitat Message Passing Interface Forum: MPI: a message-passing interface standard, version 3.1, June 2015 Message Passing Interface Forum: MPI: a message-passing interface standard, version 3.1, June 2015
15.
Zurück zum Zitat OpenMP Language Working Group: OpenMP\(\textregistered \)RTechnical Report 4: Version 5.0 Preview 2. Technical report, The OpenMP Architecture Review Board, November 2017 OpenMP Language Working Group: OpenMP\(\textregistered \)RTechnical Report 4: Version 5.0 Preview 2. Technical report, The OpenMP Architecture Review Board, November 2017
18.
Zurück zum Zitat Pfister, G.F.: An introduction to the InfiniBand\(^{\rm {TM}}\) architecture. In: High Performance Mass Storage and Parallel I/O (2001) Pfister, G.F.: An introduction to the InfiniBand\(^{\rm {TM}}\) architecture. In: High Performance Mass Storage and Parallel I/O (2001)
19.
Zurück zum Zitat Rabenseifner, R.: Hybrid parallel programming on HPC platforms. In: Proceedings of the Fifth European Workshop on OpenMP, EWOMP (2003) Rabenseifner, R.: Hybrid parallel programming on HPC platforms. In: Proceedings of the Fifth European Workshop on OpenMP, EWOMP (2003)
20.
Zurück zum Zitat Si, M., Pea, A.J., Balaji, P., Takagi, M., Ishikawa, Y.: MT-MPI: multithreaded MPI for many-core environments. ACM Press (2014) Si, M., Pea, A.J., Balaji, P., Takagi, M., Ishikawa, Y.: MT-MPI: multithreaded MPI for many-core environments. ACM Press (2014)
21.
Zurück zum Zitat Trahay, F., Brunet, E., Denis, A.: An analysis of the impact of multi-threading on communication performance. In: IEEE IPDPS (2009) Trahay, F., Brunet, E., Denis, A.: An analysis of the impact of multi-threading on communication performance. In: IEEE IPDPS (2009)
22.
Zurück zum Zitat Trahay, F., Denis, A.: A scalable and generic task scheduling system for communication libraries. In: IEEE CLUSTER (2009) Trahay, F., Denis, A.: A scalable and generic task scheduling system for communication libraries. In: IEEE CLUSTER (2009)
23.
Zurück zum Zitat Valiant, L.G.: A bridging model for parallel computation. Commun. ACM 33, 103–111 (1990)CrossRef Valiant, L.G.: A bridging model for parallel computation. Commun. ACM 33, 103–111 (1990)CrossRef
Metadaten
Titel
Efficient Communication/Computation Overlap with MPI+OpenMP Runtimes Collaboration
verfasst von
Marc Sergent
Mario Dagrada
Patrick Carribault
Julien Jaeger
Marc Pérache
Guillaume Papauré
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-319-96983-1_40