skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: An implementation and evaluation of the MPI 3.0 one-sided communication interface

Journal Article · · Concurrency and Computation. Practice and Experience
DOI:https://doi.org/10.1002/cpe.3758· OSTI ID:1346728
ORCiD logo [1];  [1];  [1];  [1];  [2];  [1]
  1. Argonne National Lab. (ANL), Lemont, IL (United States)
  2. Univ. of Illinois at Urbana-Champaign, Urbana, IL (United States)
+ Show Author Affiliations

Summary The Message Passing Interface (MPI) 3.0 standard includes a significant revision to MPI's remote memory access (RMA) interface, which provides support for one‐sided communication. MPI‐3 RMA is expected to greatly enhance the usability and performance of MPI RMA. We present the first complete implementation of MPI‐3 RMA and document implementation techniques and performance optimization opportunities enabled by the new interface. Our implementation targets messaging‐based networks and is publicly available in the latest release of the MPICH MPI implementation. Using this implementation, we explore the performance impact of new MPI‐3 functionality and semantics. Results indicate that the MPI‐3 RMA interface provides significant advantages over the MPI‐2 interface by enabling increased communication concurrency through relaxed semantics in the interface and additional routines that provide new window types, synchronization modes, and atomic operations. Copyright © 2016 John Wiley & Sons, Ltd.

Research Organization:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Organization:
USDOE Office of Science (SC); Argonne National Laboratory - Argonne Leadership Computing Facility
Grant/Contract Number:
AC02-06CH11357
OSTI ID:
1346728
Alternate ID(s):
OSTI ID: 1400534
Journal Information:
Concurrency and Computation. Practice and Experience, Vol. 28, Issue 17; ISSN 1532-0626
Publisher:
WileyCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 19 works
Citation information provided by
Web of Science

References (25)

Designing truly one-sided MPI-2 RMA intra-node communication on multi-core systems journal April 2010
Revealing the Performance of MPI RMA Implementations book January 2007
Algorithms for scalable synchronization on shared-memory multiprocessors journal February 1991
Analysis of Implementation Options for MPI-2 One-Sided book January 2007
Exploiting transparent remote memory access for non-contiguous- and one-sided-communication conference January 2002
Implementing MPI-IO atomic mode without file system support conference January 2005
Adaptive Strategy for One-Sided Communication in MPICH2 book January 2012
The Implementation of MPI-2 One-Sided Communication for the NEC SX-5 conference January 2000
Supporting the Global Arrays PGAS Model Using MPI One-Sided Communication
  • Dinan, James; Balaji, Pavan; Hammond, Jeff R.
  • 2012 IEEE International Symposium on Parallel & Distributed Processing (IPDPS), 2012 IEEE 26th International Parallel and Distributed Processing Symposium https://doi.org/10.1109/IPDPS.2012.72
conference May 2012
Advances, Applications and Performance of the Global Arrays Shared Memory Programming Toolkit journal May 2006
A new vision for coarray Fortran
  • Mellor-Crummey, John; Adhianto, Laksono; Scherer, William N.
  • Proceedings of the Third Conference on Partitioned Global Address Space Programing Models - PGAS '09 https://doi.org/10.1145/1809961.1809969
conference January 2009
X10: an object-oriented approach to non-uniform cluster computing journal October 2005
Implementing MPI-IO Atomic Mode and Shared File Pointers Using MPI One-Sided Communication journal May 2007
NWChem: A comprehensive and scalable open-source solution for large scale molecular simulations journal September 2010
Optimizing the Synchronization Operations in Message Passing Interface One-Sided Communication journal May 2005
Efficient Implementation of MPI-2 Passive One-Sided Communication on InfiniBand Clusters book January 2004
ScalaBLAST: A Scalable Implementation of BLAST for High-Performance Data-Intensive Bioinformatics Analysis journal August 2006
Problems with using MPI 1.1 and 2.0 as compilation targets for parallel language implementations journal January 2004
Implementing MPI’s One-Sided Communications for WMPI book January 1999
Parallel Programmability and the Chapel Language journal August 2007
Co-array Fortran for parallel programming journal August 1998
Scalable Earthquake Simulation on Petascale Supercomputers
  • Cui, Yifeng; Olsen, Kim B.; Jordan, Thomas H.
  • 2010 SC - International Conference for High Performance Computing, Networking, Storage and Analysis, 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis https://doi.org/10.1109/SC.2010.45
conference November 2010
ARMCI: A portable remote memory copy library for distributed array libraries and compiler run-time systems book January 1999
Using MPI-2 book January 1999
X10: an object-oriented approach to non-uniform cluster computing
  • Charles, Philippe; Grothoff, Christian; Saraswat, Vijay
  • Proceedings of the 20th annual ACM SIGPLAN conference on Object oriented programming systems languages and applications - OOPSLA '05 https://doi.org/10.1145/1094811.1094852
conference January 2005

Cited By (4)

Leveraging MPI RMA to optimize halo‐swapping communications in MONC on Cray machines journal September 2018
WOMBAT: A Scalable and High-performance Astrophysical Magnetohydrodynamics Code journal February 2017
Evaluation of parallel programming teaching methodologies: On‐campus versus online methodologies journal December 2019
Leveraging MPI RMA to optimise halo-swapping communications in MONC on Cray machines text January 2020

Similar Records

A new deadlock resolution protocol and message matching algorithm for the extreme-scale simulator
Journal Article · Tue Mar 22 00:00:00 EDT 2016 · Concurrency and Computation. Practice and Experience · OSTI ID:1346728
Performance modeling of microsecond scale biological molecular dynamics simulations on heterogeneous architectures.
Journal Article · Tue Oct 23 00:00:00 EDT 2012 · Concurrency and Computation. Practice and Experience · OSTI ID:1346728
+3 more
CILogon: A federated X.509 certification authority for cyberinfrastructure logon
Journal Article · Fri Apr 04 00:00:00 EDT 2014 · Concurrency and Computation. Practice and Experience · OSTI ID:1346728

Related Subjects

97 MATHEMATICS AND COMPUTING
MPICH
Message Passing Interface (MPI)
one-sided communication
remote memory access
remote memory access (RMA)