Automatic performance tuning using the ATMathCoreLib tool: Two experimental studies related to dense symmetric eigensolvers
-
Published:2023-06-30
Issue:
Volume:
Page:
-
ISSN:1532-0626
-
Container-title:Concurrency and Computation: Practice and Experience
-
language:en
-
Short-container-title:Concurrency and Computation
Author:
Kobayashi Masato1,
Hirota Yusuke2,
Kudo Shuhei1,
Hoshi Takeo3,
Yamamoto Yusaku1ORCID
Affiliation:
1. Department of Computer and Network Engineering The University of Electro‐Communications Chofu Japan
2. Department of Information Science The University of Fukui Fukui Japan
3. Department of Mechanical and Physical Engineering Tottori University Tottori Japan
Abstract
SummaryWe consider automatic performance tuning of dense symmetric eigenvalue problems using ATMathCoreLib, which is a library to assist automatic tuning. We deal with two problems, namely, automatic code selection for the symmetric generalized eigenvalue problem in distributed‐memory parallel environments and automatic parameter tuning in tridiagonalization of dense symmetric matrices on multicore processors. As for the first problem, numerical experiments show that ATMathCoreLib can choose the fastest solver for a given computing environment and problem size quickly even if the fluctuation in the execution time is as high as 40%. As for the second problem, ATMathCoreLib was able to select nearly optimal combinations of the algorithm and its parameter reliably and efficiently for various computing environments and matrix sizes. The performance of auto‐tuning was further enhanced by incorporating a user‐provided execution‐time model into ATMathCoreLib.
Subject
Computational Theory and Mathematics,Computer Networks and Communications,Computer Science Applications,Theoretical Computer Science,Software
Reference32 articles.
1. ScaLAPACK Users' Guide
2. Software Automatic Tuning
3. SudaR.ATMathCoreLib: mathematical core library for automatic tuning (in Japanese). IPSJ SIG Technical Report 2011.2011;1‐12.