학술논문

Parallel Bipartite Graph Algorithm for Protein Structure Matching Using OpenMP
Document Type
Conference
Source
2010 Second International Conference on Computer Research and Development Computer Research and Development, 2010 Second International Conference on. :25-29 May, 2010
Subject
Computing and Processing
Communication, Networking and Broadcast Technologies
Bipartite graph
Concurrent computing
Databases
Protein engineering
Multicore processing
Research and development
Multithreading
Parallel processing
parallel bipartite graph matching
protein structure matching
multicore systems
Language
Abstract
Current work on bipartite graph-based algorithm for protein tertiary structure matching shows that the algorithm demands heavy computation and extensive processing time during graph preparation and matching. In this work, we deployed multithreading approach using OpenMP to enhance the performance of the algorithm. The experiment on dual quad core machines shows that the speedup is 4.9 on 8 threads with the minimum execution time of 121.39 seconds, before it gradually increases as more threads are added. The parallel code has successfully utilized the available multi-cores resources and it extends the capability of the algorithm to match more structures in a given time.