Hybrid Computing Clusters To Study Protein Structure, Function And Regulation
Дмитрий Андреевич Суплатов, Нина Николаевна Попова, Kirill Kopylov, Максим Викторович Шегай, Владимир Валентинович Воеводин, В.К. Швядас · Bulletin of the South Ural State University Series Computational Mathematics and Software Engineering · 2017
Studying protein structure, function and regulation using bioinformatics and molecular modeling is a complex task that requires a combination of various methods and ways to implement them. The process can be seen as a pipeline of sequential steps executed by various programs which benefit from customized hardware. Hybrid computing clusters characterized by a significant performance and a variety of hardware capabilities are necessary to optimally execute each individual step of the complex solution. It can be specifically noted that GPU accelerators open new opportunities for efficient solution of resource-intensive tasks of bioinformatics and molecular modeling.