Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

13

EUROPAR
2005
Springer

favoriteEmaildiscussreport

149views Distributed And Parallel Com...» more EUROPAR 2005»

Automatic Tuning of PDGEMM Towards Optimal Performance

13 years 10 months ago

Automatic Tuning of PDGEMM Towards Optimal Performance

Download www.icsi.berkeley.edu

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.

Sascha Hunold, Thomas Rauber

Real-time Traffic

EUROPAR 2005 | Minimum Execution Time | Parallel Matrix Multiplication | Serial Execution |

claim paper

Related Content

» A Comparison of TCP Automatic Tuning Techniques for Distributed Computing

» Oracles SelfTuning Architecture and Solutions

» Towards automatic optimization of MapReduce programs

» Rating Compiler Optimizations for Automatic Performance Tuning

» Fast and Effective Orchestration of Compiler Optimizations for Automatic Performance Tunin...

» Computer aided hand tuning CAHT applying casebased reasoning to performance tuning

» Fast automatic procedurelevel performance tuning

» Performance Prediction and Automated Tuning of Randomized and Parametric Algorithms

» Exposing a Bias Toward ShortLength Numbers in Grammatical Evolution

Post Info
More Details (n/a)

Added	27 Jun 2010
Updated	27 Jun 2010
Type	Conference
Year	2005
Where	EUROPAR
Authors	Sascha Hunold, Thomas Rauber

Comments (0)