RUS  ENG
Full version
JOURNALS // Vestnik Yuzhno-Ural'skogo Gosudarstvennogo Universiteta. Seriya "Vychislitelnaya Matematika i Informatika" // Archive

Vestn. YuUrGU. Ser. Vych. Matem. Inform., 2017 Volume 6, Issue 4, Pages 74–90 (Mi vyurv179)

This article is cited in 2 papers

Supercomputer modeling

Hybrid computing clusters to study protein structure, function and regulation

D. A. Suplatov, N. N. Popova, K. E. Kopylov, M. V. Shegay, Vl. V. Voevodin, V. K. Švedas

Lomonosov Moscow State University (GSP-1, Leninskie Gory 1, Moscow, 119991 Russia)

Abstract: 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.

Keywords: Hybrid computing clusters, bioinformatics, molecular modeling, computational pipeline, sequential steps, co-design, GPU accelerators.

UDC: 004.021, 620.186

Received: 11.09.2017

DOI: 10.14529/cmse170406



Bibliographic databases:


© Steklov Math. Inst. of RAS, 2024