Automatic tuning of PDGEMM towards optimal performance

Authors:
Sascha Hunold;Thomas Rauber
Affiliations:
Department of Mathematics and Physics, University of Bayreuth, Germany;Department of Mathematics and Physics, University of Bayreuth, Germany
Venue:
Euro-Par'05 Proceedings of the 11th international Euro-Par conference on Parallel Processing
Year:
2005

Citing 5
Cited 2

A set of level 3 basic linear algebra subprograms

ACM Transactions on Mathematical Software (TOMS)
A scalable cross-platform infrastructure for application performance tuning using hardware counters

Proceedings of the 2000 ACM/IEEE conference on Supercomputing
LAPACK Working Note 95: ScaLAPACK: A Portable Linear Algebra Library for Distributed Memory Computers -- Design Issues and Performance

LAPACK Working Note 95: ScaLAPACK: A Portable Linear Algebra Library for Distributed Memory Computers -- Design Issues and Performance
Automatically Tuned Linear Algebra Software

Automatically Tuned Linear Algebra Software
Multilevel hierarchical matrix multiplication on clusters

Proceedings of the 18th annual international conference on Supercomputing

Parallel Performance Modeling using a Genetic Programming-based Error Correction Procedure

Simulation
Combining building blocks for parallel multi-level matrix multiplication

Parallel Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Sophisticated parallel matrix multiplication algorithms like PDGEMM exhibit a complex structure and can be controlled by a large set of parameters including blocking factors and block sizes used for the serial execution on one of the participating processors. But it requires a deep understanding of both the parallel algorithm and the execution platform to select the parameters such that a minimum execution time results. In this article, we describe a simple mechanism that automatically selects a suitable set of parameters for PDGEMM which leads to a minimum execution time in most cases.