Evaluation of Performance Prediction Method for Master/Slave Parallel Programs(Computer Systems)
スポンサーリンク
概要
- 論文の詳細を見る
This paper describes the design and implementation of a testbed for predicting master/slave (M/S) programs written using Message Passing Interface (MPI) programs. The testbed, named M/S Emulator (MSE), aims at assisting developers in evaluating the performance of M/S programs and dynamic load-balancing strategies on clusters of PCs. In order to realize this, MSE predicts the communication time by using a realistic parallel computational model, an extension of the LogGPS model. This extended model improves the prediction accuracy on a large number of processors, because it captures the master's bottleneck: the overhead required for retrieving arrival messages from the slaves. Current MSE also employs a best effort emulation method for predicting the calculation time. In our experiments, MSE demonstrated an accurate prediction on clusters, especially on a larger number of nodes. Therefore, we believe that our extended model enables us to analyze the scalability of the M/S program performance.
- 社団法人電子情報通信学会の論文
- 2004-04-01
著者
-
INO Fumihiko
Graduate School of Information Science and Technology, Osaka University
-
HAGIHARA Kenichi
Graduate School of Information Science and Technology, Osaka University
-
Hagihara K
Graduate School Of Information Science And Technology Osaka University
-
Ino Fumihiko
Graduate School Of Information Science And Technology Osaka University
-
MIZUTANI Yasuharu
Faculty of Information Science and Technology, Osaka Institute of Technology
-
MIZUTANI Yasuharu
Graduate School of Information Science and Technology, Osaka University
-
Hagihara Kenichi
Graduate School Of Information Science And Technology Osaka University
関連論文
- Accelerating Smith-Waterman Algorithm for Biological Database Search on CUDA-Compatible GPUs
- Parallel Adaptive Estimation of Hip Range of Motion for Total Hip Replacement Surgery(Parallel Image Processing,Parallel/Distributed Processing and Systems)
- Grid Resource Monitoring and Selection for Rapid Turnaround Applications(Computer Systems)
- Evaluation of Performance Prediction Method for Master/Slave Parallel Programs(Computer Systems)
- Effect of Rh and V Additions on Plastic Deformation Behaviour in Ni_3Nb Single Crystals with D0_a Structure
- Plastic Defromation by Slip on (001)[100] in Ni_3Nb Single Crystals with D0_a Structure
- THREE-DIMENSIONAL PARALLEL IMAGE PROCESSING LIBRARY(International Workshop on Advanced Image Technology 2007)
- THREE-DIMENSIONAL PARALLEL IMAGE PROCESSING LIBRARY
- Accelerating Smith-Waterman Algorithm for Biological Database Search on CUDA-Compatible GPUs
- GPU-Chariot: A Programming Framework for Stream Applications Running on Multi-GPU Systems