Exploiting OpenMP and OpenACC to accelerate a geometric approach to molecular docking in heterogeneous HPC nodes

In drug discovery, molecular docking is the task in charge of estimating the position of a molecule when interacting with the docking site. This task is usually used to perform screening of a large library of molecules, in the early phase of the process. Given the amount of candidate molecules and t...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of supercomputing 2019-07, Vol.75 (7), p.3374-3396
Main Authors: Vitali, Emanuele, Gadioli, Davide, Palermo, Gianluca, Beccari, Andrea, Cavazzoni, Carlo, Silvano, Cristina
Format: Article
Language:English
Subjects:
Accelerators
Compilers
Computation
Computer Science
Interpreters
Molecular docking
Platforms
Processor Architectures
Programming Languages
Screening
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In drug discovery, molecular docking is the task in charge of estimating the position of a molecule when interacting with the docking site. This task is usually used to perform screening of a large library of molecules, in the early phase of the process. Given the amount of candidate molecules and the complexity of the application, this task is usually performed using high-performance computing (HPC) platforms. In modern HPC systems, heterogeneous platforms provide a better throughput with respect to homogeneous platforms. In this work, we ported and optimized a molecular docking application to a heterogeneous system, with one or more GPU accelerators, leveraging a hybrid OpenMP and OpenACC approach. The target application focuses on the virtual screening phases in the drug discovery process, and it is based on geometric transformations of the target ligands. We prove that our approach has a better exploitation of the node compared to pure CPU/GPU data splitting approaches, reaching a throughput improvement up to 25% while considering the same computing node.
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-019-02875-w