Computer Engineering Board of Studies
University of California, Santa Cruz
Technical Report UCSC-CRL-93-14
April 2, 1993
Massive parallelism is required for the analysis of the rapidly growing biosequence databases. First, this paper compares and benchmarks methods for dynamic programming sequence analysis on several parallel platforms. Next, a new hidden Markov model method and its implementation on several parallel machines is discussed. Finally, the results of a series of experiments using this massively parallel implementation are described.
Keywords: Computational biology, dynamic programming, parallel algorithms, systolic co-processors, hidden Markov models.