Welcome!
To use the personalized features of this site, please log in or register.
If you have forgotten your username or password, we can help.
|
 |
Performance Analysis and Derived Parallelization Strategy for a SCF Program at the Hartree Fock Level
| Book Series | Lecture Notes in Computer Science |
| Publisher | Springer Berlin / Heidelberg |
| ISSN | 0302-9743 (Print) 1611-3349 (Online) |
| Volume | Volume 1557/1999 |
| Book | Parallel Computation |
| DOI | 10.1007/3-540-49164-3 |
| Copyright | 1999 |
| ISBN | 978-3-540-65641-8 |
| DOI | 10.1007/3-540-49164-3_16 |
| Pages | 163-172 |
| Subject Collection | Computer Science |
| SpringerLink Date | Friday, January 01, 1999 |
| |
|
Performance Analysis and Derived Parallelization Strategy for a SCF Program at the Hartree Fock Level
Siegfried Höfinger7  , Othmar Steinhauser7 and Peter Zinterhof8
| (7) |
Institute for Theoretical Chemistry, Molecular Dynamics Group, University of Vienna, Währingerstr. 17 Ground Floor, A-1090 Vienna, Austria |
| (8) |
Institute for Mathematics, University of Salzburg, Hellbrunnerstr. 34, A-5020 Salzburg, Austria |
Abstract
General performance measurement tools, as provided on a SGI-Power Challenge/R10000 (194 MHz) running IRIX 6.2, which are the
shell-commands perfex - a a.out and ssrun - [pcsampl, ideal, usertime] a.out, have been used for profiling a new SCF-program based on the Hartree Fock theory. The main cpu-time-consuming subroutine
was detected and a parallel version with PVM 3.3 at a host-node model has been deduced. Speed-up parameters are presented
and discussed.
Fulltext Preview (Small, Large)
 References secured to subscribers.
|
|
|
|
|
|