A parallel computing approach to genetic sequence comparison: the master-worker paradigm with interworker communication

Abstract

We have implemented a parallel version of a dynamic programming biological sequence comparison algorithm to study the potential applicability of using parallel computers for genetic sequence comparisons. Our parallel program is built using C-Linda, a machine-independent parallel programming language, and was tested on both a 10 CPU Sequent Symmetry and a 64 CPU Intel Hypercube. C-Linda implements a shared associative memory model, "tuple space," through which multiple processes can communicate and coordinate control. In our master-worker (MW) parallel implementation, a master process creates several worker processes, extracts a test sequence and multiple library sequences from a database and stores them in tuple space. Each worker reads the test sequence and then repeatedly extracts library strings from tuple space, performs pairwise sequence comparison using a local comparison algorithm to generate a similarity score, and returns the similarity scores to tuple space. The master collects the scores from tuple space and identifies the best match over all library sequences. We also implemented a method of global interworker communication to reduce the total search time by stopping those string comparisons that had no chance of improving on the current best match. Comparisons of the total run time, speedup, and efficiency were made for parallel and sequential versions of a basic MW implementation as well as versions with the global abort threshold.