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

Toward efficient support for multithreaded MPI communication.

Conference · · Lect. Notes Comput. Sci.
OSTI ID:1009780

To make the most effective use of parallel machines that are being built out of increasingly large multicore chips, researchers are exploring the use of programming models comprising a mixture of MPI and threads. Such hybrid models require efficient support from an MPI implementation for MPI messages sent from multiple threads simultaneously. In this paper, we explore the issues involved in designing such an implementation. We present four approaches to building a fully thread-safe MPI implementation, with decreasing levels of critical-section granularity (from coarse-grain locks to fine-grain locks to lock-free operations) and correspondingly increasing levels of complexity. We describe how we have structured our implementation to support all four approaches and enable one to be selected at build time. We present performance results with a message-rate benchmark to demonstrate the performance implications of the different approaches.

Research Organization:
Argonne National Laboratory (ANL)
Sponsoring Organization:
SC
DOE Contract Number:
AC02-06CH11357
OSTI ID:
1009780
Report Number(s):
ANL/MCS/CP-61879
Journal Information:
Lect. Notes Comput. Sci., Journal Name: Lect. Notes Comput. Sci. Journal Issue: 2008 Vol. 5205
Country of Publication:
United States
Language:
ENGLISH

Similar Records

Fine-grained multithreading support for hybrid threaded MPI programming.
Journal Article · Sun Jan 31 23:00:00 EST 2010 · Int. J. High Perform. Comput. Appl. · OSTI ID:1015545

Test suite for evaluating performance of multithreaded MPI communication.
Journal Article · Mon Nov 30 23:00:00 EST 2009 · Parallel Comput. · OSTI ID:977356

Test suite for evaluating performance of MPI implementations that support MPI_THREAD_MULTIPLE.
Conference · Wed Dec 31 23:00:00 EST 2008 · Parallel Comput. · OSTI ID:971467