ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Evaluation of WIEN2K Performance on MPICH2 vs. MPICH1

Proceeding: The International Conference on Digital Information, Networking, and Wireless Communications (DINWC)

Publication Date:

Authors : ; ; ;

Page : 112-119

Keywords : Parallel Processing; Message Passing Interface MPI; MPICH1; MPICH2; performance; multi-core systems; WIEN2K.;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

The emerging multi-core computer architecture attracts the researchers to utilize this architecture as an adequate and inexpensive solution to achieve high performance computation for many problems. Where, the multi-core architecture enables us to implement shared memory and/or message passing parallel processing paradigms. Therefore, we need appropriate standard software libraries in order to utilize the resources efficiently for a given computational problem. In this work we evaluate the performance of two versions of the well known massage passing interface (MPI) library: MPICH1 vs. MPICH2. In our experiments we used two benchmarks. The first one is the WIEN2K application which is based on Density Function Theory, and the second is a Matrix multiplication. The results show that we achieve better performance when MPICH2 is used than MPICH1.

Last modified: 2014-07-04 00:04:24