“…The resultant hardware was a linear systolic array whose processing elements could differentiate between the alphabet and scores as perform comparison and addition operations. Newer architectures [21,22] have built upon this Lipton and Lopresti work by adding markers in processing elements to trace back optimal similarity paths.…”
“…The resultant hardware was a linear systolic array whose processing elements could differentiate between the alphabet and scores as perform comparison and addition operations. Newer architectures [21,22] have built upon this Lipton and Lopresti work by adding markers in processing elements to trace back optimal similarity paths.…”
“…In terms of the AM matrix, this means that the anti-diagonal values can be calculated concurrently, see Figure 2c. This property is effectively used for algorithm acceleration using dedicated hardware (Hoang and Lopresti, 1992) (Lavenier, 1998) (Yu et al, 2003) (Court and Herbordt, 2004). Typical hardware architecture is based on a systolic array of Processing Elements (PE) (see Figure 2c).…”
We report the latest details on improvements made or planned for the VPCR simulation software currently accessible on the Internet (installed on servers in Padova and Brno). We describe the inner workings of the dynamic amplification simulation model, concentrating mostly on the time-and sensitivity-critical step of sequence matching. Replacement of BLAST by the more sensitive and faster PRIMEX similarity search program resulted in a marked improvement of PCR product predictions. Further speed improvements were acheived using hardware acceleration of approximate sequence matching. We report our theorethical computation time estimates and results of the first tests using the Arabidopis and human genome sequences as PCR templates.
“…al. [2], [3] implemented the Needleman-Wunsch and dynamic programming algorithms using systolic array implementation on SPLASH 2 in order to achieve orders of magnitude higher performance than the conventional computers of that time. Using JBits S. Guccione et.…”
Section: Hardware Efforts For Sequence Comparisonmentioning
confidence: 99%
“…For that reason, the acceleration of BLAST through custom hardware architectures seems an appropriate first step in the speedup of DNA sequence comparison, and this is the purpose of this work. Historically, DNA string matching is one of the first applications of reconfigurable computing [2,3].…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.