A Comparison of the BioSCAN Algorithm on Multiple Architectures

Source: CiteSeer


This paper compares the performance characteristics of the BioSCAN biological sequence matching algorithm on several different computer architectures. The architectures examined are a conventional RISC general purpose uni-processor, a vector oriented "supercomputer", and a Single Instruction Multi Data (simd) massively parallel computer. These architectures are represented by the following hardware platforms: a Sun 490 RISC, a Convex 240, and a MasPar MP-1. The performance of these three platforms is compared with that of the custom built BioSCAN hardware. 2 Background 2.1 The BioSCAN Project

7 Reads
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The paper has as objective to implement, in hardware-making use of FPGA technology, the algorithms that are considered as standard for the comparison and the global and local alignment of the DNA genetic sequences. These algorithms use the dynamic programming technique. These algorithms were implemented in software (C language) and, later, the hardware implementation (using VHDL and FPGAs). We compare our obtained software and hardware results, by the execution time of the algorithms, and it was possible to verify that our hardware implementation is better than our software version and others bioinformatics-platforms.
    IEEE Latin America Transactions 01/2009; 6(7-6):579 - 586. DOI:10.1109/TLA.2008.4917428 · 0.33 Impact Factor