Monday, September 27, 2010

Pervasive Claims Performance Record

Austin-base dPervasive Software, a developer of database software, claimed today that its implementation of an algorithm used for genetic analysis has broken a performance throughput record. The firm said that its implementation of the Smith-Waterman algorithm, which is used to perform local protein sequence alignment used in genetic analysis, analyzed 10 million combinations of protein sequences in 81.1 seconds, a record. The firm's software was running on an SGI Altix UV 1000 with 384 cores. Pervasive claims it beat existing records by 43 percent. The Smith Waterman algorithm is heavily used in bioinformatics and genomic research for analyzing the difference between genetic sequences and proteins.