Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation

By Edgar Gabriel, Graham Edward Fagg, George Bosilca, Thara Angskun, Jack J. Dongarra, Jeffrey M. Squyres, Vishal Sahay, Prabhanjan Kambadur, Brian W. Barrett, Andrew Lumsdaine and 4 more. PVM/MPI, 2004

1,782 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/b27542559edf6cc867afdc1637fe36b9a4e250e6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Hardware and Architecture

Citations in the corpus

Integral reduction with Kira 2.0 and finite field methods (2020, methodology): “This is known to work best with OpenMPI [83, 84].”
Tune: A Research Platform for Distributed Model Selection and Training (2018, methodology): “In contrast to popular distributed frameworks such as Spark (Zaharia et al. (2012)), or MPI (Gabriel et al. (2004)), Ray oﬀers a more ﬂexible programming model.”
Horovod: fast and easy distributed deep learning in TensorFlow (2018, methodology): “Users utilize a Message Passing Interface (MPI) [10] implementation such as Open MPI [11] to launch all copies of the TensorFlow program.”
Heterogeneity-Aware Asynchronous Decentralized Training (2019, methodology): “Utilizing All-Reduce algorithms based on MPIs [9, 11, 14] and NCCL [6], Horovod [41] enables high-performance data parallelism and is proved to be effective and efficient — based on All-Reduce algorithms and high performance implementations, researchers were able to use the fastest supercomputer , S”
hwloc: A Generic Framework for Managing Hardware Affinities in HPC Applications (2010, neutral): “MPI libraries such as OPEN MPI [9] and MPICH2 often run a single thread or process per core, binding them improves performance and reproducibility.”
Performance analysis of MPI collective operations (2005, methodology): “For example, this work is currently being used to produce decision function within the tuned collective module in the Open MPI library [21].”
Distributed Newton Methods for Regularized Logistic Regression (2015, methodology): “Implementation We implement both ADMM and the proposed Newton method TRON in C++ with OpenMPI [Gabriel et al., 2004].”
Parallel distributed computing using Python (2011, neutral): “Implementations are available from vendors of high-performance computers to well known open source projects like MPICH [20,21] and Open MPI [22,23].”
NEURON and Python (2008, neutral): “This requires a version of MPI to be installed, for example MPICH2 (Gropp, 2002) or openMPI (Gabriel et al., 2004 ).”
How to use MIGRATE or why are Markov chain Monte Carlo programs difficult to use (2009, methodology): “Several free programs, such as OPENMPI (Gabriel et al. 2004), LAM-MPI (Burns et al. 1994; Squyres and Lumsdaine 2003) and MPICH2 (http://wwwunix .mcs.anl.gov/mpi/mpich/index.htm) are available to set up a virtual cluster on top of the real computer cluster.”