Search NASA⌕ Search

DOE OSTI · 1004675

MPI Support for Multi-core Architectures: Optimized Shared Memory Collectives

Abstract

With local core counts on the rise, taking advantage of shared memory to optimize collective operations can improve performance. We study several on-host shared memory optimized algorithms for MPI Bcast, MPI Reduce, and MPI Allreduce, using tree-based, and reduce-scatter algorithms. For small data operations with relatively large synchronization costs fan-in/fan-out algorithms generally perform best. For large messages data manipulation constitute the largest cost and reduce-scatter algorithms are best for reductions. These optimization improve performance by up to a factor of three. Memory and cache sharing effect require deliberate process layout and careful radix selection for tree-based methods

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Graham, Richard L, Shipman, Galen M. 2008-01-01. MPI Support for Multi-core Architectures: Optimized Shared Memory Collectives. https://searchnasa.com/record/osti%3A1004675/mpi-support-for-multi-core-architectures-optimized-shared-memory-collectives

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related reports

Fire Protection Design

The purpose of this project is to design the demolition and installation of a deluge valve swap from a DV-5 to a DV-5A valve.

99 GENERAL AND MISCELLANEOUS↗