Performance and Power-Aware Modeling of MPI Applications for Cluster Computing - Publication - Bridge of Knowledge

Your account

login

Search

Performance and Power-Aware Modeling of MPI Applications for Cluster Computing

Abstract

The paper presents modeling of performance and power consumption when running parallel applications on modern cluster-based systems. The model includes basic so-called blocks representing either computations or communication. The latter includes both point-to-point and collective communication. Real measurements were performed using MPI applications and routines run on three different clusters with both Infiniband and Gigabit Ethernet interconnects. Regression allowed to obtain specific coefficients for particular systems, all modeled with the same formulas. The model has been incorporated into the MERPSYS environment for modeling parallel applications and simulation of execution on large-scale cluster and volunteer based systems. Using specific application and system models, MERPSYS allows to predict application execution time, reliability and power consumption of resources used during computations. Consequently, the proposed models for computational and communication blocks are of utmost importance for the environment.

Citations

  • 2

    CrossRef

  • 0

    Web of Science

  • 8

    Scopus

Authors (2)

Cite as

Full text

download paper
downloaded 30 times
Publication version
Accepted or Published Version
License
Copyright (2016 Springer International Publishing Switzerland)

Keywords

Details

Category:
Monographic publication
Type:
rozdział, artykuł w książce - dziele zbiorowym /podręczniku w języku o zasięgu międzynarodowym
Title of issue:
Parallel Processing and Applied Mathematics, Part II strony 199 - 209
ISSN:
0302-9743
Language:
English
Publication year:
2016
Bibliographic description:
Proficz J., Czarnul P.: Performance and Power-Aware Modeling of MPI Applications for Cluster Computing// Parallel Processing and Applied Mathematics. Part 2/ : Springer, 2016, s.199-209
DOI:
Digital Object Identifier (open in new tab) 10.1007/978-3-319-32152-3_19
Verified by:
Gdańsk University of Technology

seen 128 times

Recommended for you

Energy Consumption Modeling in SPMD and DAC Applications

2016

Optimization of hybrid parallel application execution in heterogeneous high performance computing systems considering execution time and power consumption

2018

Modeling energy consumption of parallel applications

2016

KernelHive: a new workflow-based framework for multilevel high performance computing using clusters and workstations with CPUs and GPUs

2016
Meta Tags