The paper presents optimized hardware structure applied to genome alignment search. The proposed methodology is based on dynamic programming. The authors show how starting from the original Smith-Waterman approach, the algorithm can be optimized and the evaluation process simplified and speeded-up. The main idea is based on the observations of growth trends in the adjacent cells of the systolic array, which leads to the incremental approach. Moreover various coding styles are discussed and the best technique allowing further reduction of resources is selected. The entire processing unit utilizes fully pipelined structure that is well balanced trade-off between performance and resource requirements. The proposed technique is implemented in modern FPGA structures and obtained results proved efficiency of the methodology comparing to other approaches in the field.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.