Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Impact of the implementation of MPI point-to-point communications on the performance of two general sparse solvers

Journal Article · · Parallel Computing
OSTI ID:861282

We examine the mechanics of the send and receive mechanism of MPI and in particular how we can implement message passing in a robust way so that our performance is not significantly affected by changes to the MPI system. This leads us to using the Isend/Irecv protocol which will entail sometimes significant algorithmic changes. We discuss this within the context of two different algorithms for sparse Gaussian elimination that we have parallelized. One is a multifrontal solver called MUMPS, the other is a supernodal solver called SuperLU. Both algorithms are difficult to parallelize on distributed memory machines. Our initial strategies were based on simple MPI point-to-point communication primitives. With such approaches, the parallel performance of both codes are very sensitive to the MPI implementation, the way MPI internal buffers are used in particular. We then modified our codes to use more sophisticated nonblocking versions of MPI communication. This significantly improved the performance robustness (independent of the MPI buffering mechanism) and scalability, but at the cost of increased code complexity.

Research Organization:
Ernest Orlando Lawrence Berkeley National Laboratory, Berkeley, CA (US)
Sponsoring Organization:
USDOE Director. Office of Science. Office of Advanced Computing Research. Division of Mathematical Information and Computational Science; National Science Foundation Cooperative Agreement ACI-9619020 and Grant ACI-9813362; France-Berkeley Fund, Engineering and Physical Sciences Research Council Grant GR/M78502
DOE Contract Number:
AC03-76SF00098
OSTI ID:
861282
Report Number(s):
LBNL--48968; BnR: KJ0102000
Journal Information:
Parallel Computing, Journal Name: Parallel Computing Journal Issue: 7 Vol. 29; ISSN PACOEJ; ISSN 0167-8191
Country of Publication:
United States
Language:
English

Similar Records

Exploring MPI Communication Models for Graph Applications Using Graph Matching as a Case Study
Conference · Mon Sep 02 00:00:00 EDT 2019 · OSTI ID:1572673

High performance sparse multifrontal solvers on modern GPUs
Journal Article · Fri Feb 04 23:00:00 EST 2022 · Parallel Computing · OSTI ID:1960514

A GPU-Accelerated Structurally-Symmetric Sparse Multifrontal Solver
Conference · Wed Aug 07 00:00:00 EDT 2019 · OSTI ID:1605252