Malleable Model Coupling with Prediction

Authors:
Daihee Kim;J. Walter Larson;Kenneth Chiu
Affiliations:
-;-;-
Venue:
CCGRID '12 Proceedings of the 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)
Year:
2012

Citing 10
Cited 0

Towards Convergence in Job Schedulers for Parallel Supercomputers

IPPS '96 Proceedings of the Workshop on Job Scheduling Strategies for Parallel Processing
Implementing Malleability on MPI Jobs

Proceedings of the 13th International Conference on Parallel Architectures and Compilation Techniques
The Model Coupling Toolkit: A New Fortran90 Toolkit for Building Multiphysics Parallel Coupled Models

International Journal of High Performance Computing Applications
M X N Communication and Parallel Interpolation in Community Climate System Model Version 3 Using the Model Coupling Toolkit

International Journal of High Performance Computing Applications
CPL6: The New Extensible, High Performance Parallel Coupler for the Community Climate System Model

International Journal of High Performance Computing Applications
Data redistribution and remote method invocation for coupled components

Journal of Parallel and Distributed Computing - 19th International parallel and distributed processing symposium
Dynamic Malleability in Iterative MPI Applications

CCGRID '07 Proceedings of the Seventh IEEE International Symposium on Cluster Computing and the Grid
ReSHAPE: A Framework for Dynamic Resizing and Scheduling of Homogeneous Applications in a Parallel Environment

ICPP '07 Proceedings of the 2007 International Conference on Parallel Processing
Efficient Runtime Environment for Coupled Multi-physics Simulations: Dynamic Resource Allocation and Load-Balancing

CCGRID '10 Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing
An architecture for reconfigurable iterative MPI applications in dynamic environments

PPAM'05 Proceedings of the 6th international conference on Parallel Processing and Applied Mathematics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Achieving ultra scalability in coupled multiphysics and multiscale models requires dynamic load balancing both within and between their constituent subsystems. Interconstituent dynamic load balance requires runtime resizing -- or malleability -- of subsystem processing element (PE) cohorts. We enhance the Malleable Model Coupling Toolkit's Load Balance Manager (LBM) to incorporate prediction of a coupled system's constituent computation times and coupled model global iteration time. The prediction system employs piecewise linear and cubic spline interpolation of timing measurements to guide constituent cohort resizing. Performance studies of the new LBM using a simplified coupled model test bed similar to a coupled climate model show dramatic improvement ( 77%) in the LBM's convergence rate.