Abstract
A visualization model has been developed to analyse the performance of a massively parallel algorithm. Most visualization tools that have been developed so far for performance analysis are based generally on individual processor information and communication patterns (eg. processor load, message traffic etc.). These tools, however, are inadequate for massively parallel computations. It is difficult to comprehend the visual information for many processors. The model, SMil...l (Scientific visualization in Multicomputing for Interpretation of Large amounts of Information), addresses this problem by using abstract representations to attain a composite picture which gives better insight to the behavior of the algorithm. Chernoff's Faces have been selected to represent the multidimensional data because of their ability to portray multidimensional data in a very perceptible manner.
SMIT..,I has been used on an asynchronous massively parallel PDE (partial differential equation) solver that is based on the multigrid paradigm. The visualization tool helps in tuning the control parameters of the multigrid algorithm to get optimal results. In asynchronous algorithms, the non-deterministic way in which messages are exchanged may lead to some unforeseeable behaviour. SMILI helps detect the anomalies and possibly indicates the causes of the irregularities that may arise during the execution. Once the causes have been determined, the control parameters can be further tuned to eliminate the erroneous behavior in the consecutive executions.
Recommended Citation
Khanna, Rashi and McMillin, Bruce M., "SMILI-Visualization of Asynchronous Massively Parallel Programs" (1991). Computer Science Technical Reports. 128.
https://scholarsmine.mst.edu/comsci_techreports/128
Department(s)
Computer Science
Report Number
CSc-91-08
Document Type
Technical Report
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 1991 University of Missouri - Rolla, All rights reserved
Publication Date
1991-06-06
Comments
The first Author is a Graduate Student.
This work was supported in part by the National Science Foundation under Grant Numbers MIP-8909749 and CDA-8820714, and in part by the AMOCO Faculty Development Program.