A task allocation framework for biological sequence comparison applications in heterogeneous environments

Abstract

Biological Sequence Comparison is a very important operation in computational biology since it is used to relate organisms and understand evolutionary processes. This article presents the design and evaluation of an allocation framework for biological sequence comparison applications that use dynamic programming and run in heterogeneous environments. Its goal is to determine which processors will execute the application, considering some characteristics of the heterogeneous environment, such as observed processor power and network bandwidth. The results obtained with four different task allocation policies in a 10-machine heterogeneous environment show that, for some sequence sizes, we were able to reduce the execution time of the parallel application in more than a half, when the appropriate number of processors is used.