Affiliation:
1. Dalian Neusoft Institute of Information
Abstract
To take full advantage of multi-core processor resources, this paper examines the multi-core platform using OpenMP implementation of two kinds of pi parallel algorithms, numerical integration and Monte Carlo. The experimental results show that optimized algorithm with the OpenMP pragmas compared with the serial code has been improved speed significantly, also achieved satisfactory speedup and parallel efficiency that effectively improve the utilization of computer resources of the multi-core, parallel algorithm for the realization of Pi provides a new way of thinking.
Publisher
Trans Tech Publications, Ltd.
Reference5 articles.
1. SUE , TIAN X , GIRKAR M. Compiler Support for the Workqueuting Execution Model for Intel SMP Architectures[C]. In Proceeding of the Fourth European Workshop on OpenMP, Roma, (2002).
2. GONZALEZ M, OLIVER, MARTORELL. OpenMP Extensions for Thread Groups and Their Run-time Support[C]. 13th Intel Workshop on Languages and Compilers for Parallel Computing (LCPC'2000), New York(USA)( 2000).
3. BIRSAK J, CRAIG P, CROWELL.R. Offner. Extending OpenMP for NUMA machines[J]. Scientific Programming(2000). 8(3), pp.163-164.
4. Doucet A, Godsill s, Andrieu C．On Sequential Monte Carlo sam—pling methods for bayesian filtering[J]. Statistics and Compu—ring, 2000, 10(3), pp.197-208.
5. Jourdan DB，Deyst J J，Win JMZ. Monte Carlo localization in dense muhipath environments using UWB ranging [C] IEEE International Conference on Ultra—Wideband(2005), p.314.