Graphical analysis for clustered systems -- a performance tool
PublicOne of the most challenging procedures in parallel programming is to convert an algorithm written in sequential code to an efficient parallel version. This paper discusses a program monitoring tool, Graphical Analysis of Clustered Systems (GACS), that was created to assist in analyzing a parallel program's execution by displaying its trace in a graphical interface. The goal of GACS is to help programmers to determine where the bottlenecks are in a parallel application and, subsequently, to allow them to improve the performance of their code. GACS accomplishes this by allowing the developer to see when certain code and message passing functions occur on each of the processors relative to similar functions on the other processors.
- This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
- Creator
- Publisher
- Identifier
- 01B008M
- Advisor
- Year
- 2001
- Date created
- 2001-01-01
- Resource type
- Major
- Rights statement
Relations
- Dans Collection:
Contenu
Permanent link to this page: https://digital.wpi.edu/show/vd66w280z