Abstract
This paper presents an extension of a performance evaluation library called Fast to handle parallel routines. Fast is a dynamic performance forecasting tool in a grid environment. We propose to combine estimations given by Fast about sequential computation routines and network availability to parallel routine models coming from code analysis.
Original language | English |
---|---|
Pages (from-to) | 57-69 |
Number of pages | 13 |
Journal | Scalable Computing |
Volume | 6 |
Issue number | 1 |
State | Published - 2005 |
Externally published | Yes |
Funding
This work was supported in part by the projects ACI GRID-GRID ASP and RNTL GASP funded by the French Ministery of research. We would like to thank the ID laboratory for granting access to its Cluster Computing Center, this work having been done on the ID/HP cluster (http://icluster.imag.fr/).
Keywords
- Parallel routines
- Performance forecasting and modeling