Parallel Matrix Multiplication: A Systematic Journey
Authors:
- Martin D. SchatzMSMartin D. Schatz
- Robert A. van de GeijnRGRobert A. van de Geijn
- Jack PoulsonJPJack Poulson
- 1 January 2016
- journal article
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 38 (6) , C748-C781
Abstract
We expose a systematic approach for developing distributed-memory parallel matrix-matrix multiplication algorithms. The journey starts with a description of how matrices are distributed to meshes o...Keywords
Funding Information
- National Science Foundation (OCI-0850750, CCF-0917167, ACI-1148125/1340293, CCF-1320112)
This publication has 25 references indexed in Scilit:
- Communication lower bounds and optimal algorithms for numerical linear algebraActa Numerica, 2014
- Anatomy of high-performance matrix multiplicationACM Transactions on Mathematical Software, 2008
- Collective communication: theory, practice, and experienceConcurrency and Computation: Practice and Experience, 2007
- FLAMEACM Transactions on Mathematical Software, 2001
- Efficient algorithms for all-to-all communications in multiport message-passing systemsIEEE Transactions on Parallel and Distributed Systems, 1997
- A three-dimensional approach to parallel matrix multiplicationIBM Journal of Research and Development, 1995
- AN EFFICIENT PARALLEL ALGORITHM FOR MATRIX-VECTOR MULTIPLICATIONInternational Journal of High Speed Computing, 1995
- A high-performance matrix-multiplication algorithm on a distributed-memory parallel computer, using overlapped communicationIBM Journal of Research and Development, 1994
- Pumma: Parallel universal matrix multiplication algorithms on distributed memory concurrent computersConcurrency: Practice and Experience, 1994
- The Torus-Wrap Mapping for Dense Matrix Calculations on Massively Parallel ComputersSIAM Journal on Scientific Computing, 1994