Exploring dynamic load imbalance solutions with the CoMD proxy application

Pearce, Olga; Ahmed, Hadia; Larsen, Rasmus W.; Pirkelbauer, Peter; Richards, David F.

doi:10.1016/j.future.2017.12.010

Title: Exploring dynamic load imbalance solutions with the CoMD proxy application

Abstract

Proxy applications are developed to simplify studying parallel performance of scientific simulations and to test potential solutions for performance problems. However, proxy applications are typically too simple to allow work migration or to represent the load imbalance of their parent applications. To study the ability of load balancing solutions to balance work effectively, we enable work migration in one of the Exascale Co-design Center for Materials in Extreme Environments (ExMatEx) [1] applications, CoMD. We design a methodology to parameterize three key aspects necessary for studying load imbalance correction: (1) the granularity with which work can be migrated; (2) the initial load imbalance; (3) the dynamic load imbalance (how quickly the load changes over time). Finally, we present a study of the impact of flexibility in work migration in CoMD on load balance and the associated rebalancing costs for a wide range of initial and dynamic load imbalance scenarios.

Authors:

Pearce, Olga ^[1]; Ahmed, Hadia ^[2]; Larsen, Rasmus W. ^[3]; Pirkelbauer, Peter ^[2]; Richards, David F. ^[1]

Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Univ. of Alabama, Birmingham, AL (United States). Dept. of Computer and Information Sciences
Univ. of Copenhagen (Denmark). Dept. of Computer Science

Publication Date:: Wed Dec 20 00:00:00 EST 2017

Research Org.:: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Org.:: USDOE National Nuclear Security Administration (NNSA)

OSTI Identifier:: 1497267

Alternate Identifier(s):: OSTI ID: 1702551

Report Number(s):: LLNL-JRNL-725317
Journal ID: ISSN 0167-739X; 874899

Grant/Contract Number:: AC52-07NA27344; LLNL-JRNL-725317

Resource Type:: Accepted Manuscript

Journal Name:: Future Generations Computer Systems

Additional Journal Information:: Journal Volume: 92; Journal Issue: C; Journal ID: ISSN 0167-739X

Publisher:: Elsevier

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Pearce, Olga, Ahmed, Hadia, Larsen, Rasmus W., Pirkelbauer, Peter, and Richards, David F. Exploring dynamic load imbalance solutions with the CoMD proxy application.  United States: N. p., 2017. 
Web.  doi:10.1016/j.future.2017.12.010.

Copy to clipboard


                    Pearce, Olga, Ahmed, Hadia, Larsen, Rasmus W., Pirkelbauer, Peter, & Richards, David F. Exploring dynamic load imbalance solutions with the CoMD proxy application.  United States.  https://doi.org/10.1016/j.future.2017.12.010

Copy to clipboard


                    Pearce, Olga, Ahmed, Hadia, Larsen, Rasmus W., Pirkelbauer, Peter, and Richards, David F. Wed .  
"Exploring dynamic load imbalance solutions with the CoMD proxy application".  United States.  https://doi.org/10.1016/j.future.2017.12.010.  https://www.osti.gov/servlets/purl/1497267.

Copy to clipboard


                    
@article{osti_1497267,

  title        = {Exploring dynamic load imbalance solutions with the CoMD proxy application},

  author       = {Pearce, Olga and Ahmed, Hadia and Larsen, Rasmus W. and Pirkelbauer, Peter and Richards, David F.},

  abstractNote = {Proxy applications are developed to simplify studying parallel performance of scientific simulations and to test potential solutions for performance problems. However, proxy applications are typically too simple to allow work migration or to represent the load imbalance of their parent applications. To study the ability of load balancing solutions to balance work effectively, we enable work migration in one of the Exascale Co-design Center for Materials in Extreme Environments (ExMatEx) [1] applications, CoMD. We design a methodology to parameterize three key aspects necessary for studying load imbalance correction: (1) the granularity with which work can be migrated; (2) the initial load imbalance; (3) the dynamic load imbalance (how quickly the load changes over time). Finally, we present a study of the impact of flexibility in work migration in CoMD on load balance and the associated rebalancing costs for a wide range of initial and dynamic load imbalance scenarios.},

  doi          = {10.1016/j.future.2017.12.010},

  journal      = {Future Generations Computer Systems},

  number       = C,

  volume       = 92,

  place        = {United States},

  year         = {Wed Dec 20 00:00:00 EST 2017},

  month        = {Wed Dec 20 00:00:00 EST 2017}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (Publisher)

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1016/j.future.2017.12.010

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 2 works

Citation information provided by
Web of Science

Figures / Tables:

Table 1: Example Load Distributions and Their Imbalance

All figures and tables (20 total)

Save / Share:

Export Metadata

Save to My Library

Figures / Tables found in this record:

Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.

Similar Records in DOE PAGES and OSTI.GOV collections:

Scalability under a Power Bound using the GREMLINs Framework

Thesis/Dissertation Maiterth, Matthias

With the move towards exascale, system and software developers will have to deal with issues of extreme parallelism. The system properties affected most by the increase in node and core count are the shared resources on node and across the system. The increase in parallelism leads to reduced memory and bandwidth when regarding individual cores. Since power is a limiting factor for supercomputers, and power is not fully utilized in current systems, overprovisioning compute resources is a viable approach to maximized power utilization. To maximize system performance in regard to these changing conditions, it is necessary to understand how resourcemore »« less
https://doi.org/10.2172/1183550

Full Text Available
Addressing Load Imbalance in Bioinformatics and Biomedical Applications: Efficient Scheduling across Multiple GPUs

Conference Thavappiragasam, Mathialakan ; Kale, Vivek ; Hernandez, Oscar ; ...

Computational bioinformatics and biomedical applications frequently contain heterogeneously sized units of work or tasks, for instance due to variability in the sizes of biological sequences and molecules. Variable-sized workloads lead to load imbalances in parallel implementations which detract from efficiency and performance. Many modern computing resources now have multiple graphics processing units(GPUs) per computer for acceleration. These multiple GPU resources need to be used efficiently through balancing of workloads across the GPUs. OpenMP is a portable directive-based parallel programming API used ubiquitously in bioscience applications to program CPUs; recently, the use of OpenMP directives for GPU acceleration has become possible.more »« less
https://doi.org/10.1109/BIBM52615.2021.9669317

Full Text Available
Experience with automatic, dynamic load balancing and adaptive finite element computation

Conference Wheat, S R ; Devine, K D ; Maccabe, A B

Distributed memory, Massively Parallel (MP), MIMD technology has enabled the development of applications requiring computational resources previously unobtainable. Structural mechanics and fluid dynamics applications, for example, are often solved by finite element methods (FEMs) requiring, millions of degrees of freedom to accurately simulate physical phenomenon. Adaptive methods, which automatically refine or coarsen meshes and vary the order of accuracy of the numerical solution, offer greater robustness and computational efficiency than traditional FEMs by reducing the amount of computation required away from physical structures such as shock waves and boundary layers. On MP computers, FEMs frequently result in distributed processor loadmore »« less
Full Text Available
A Framework to Analyze the Performance of Load Balancing Schemes for Ensembles of Stochastic Simulations

Journal Article Ahn, Tae-Hyuk ; Sandu, Adrian ; Watson, Layne T. ; ... - International Journal of Parallel Programming

Ensembles of simulations are employed to estimate the statistics of possible future states of a system, and are widely used in important applications such as climate change and biological modeling. Ensembles of runs can naturally be executed in parallel. However, when the CPU times of individual simulations vary considerably, a simple strategy of assigning an equal number of tasks per processor can lead to serious work imbalances and low parallel efficiency. This paper presents a new probabilistic framework to analyze the performance of dynamic load balancing algorithms for ensembles of simulations where many tasks are mapped onto each processor, andmore »« less
https://doi.org/10.1007/s10766-014-0309-6
Exascale Co-design for Modeling Materials in Extreme Environments

Technical Report Germann, Timothy C.

Computational materials science has provided great insight into the response of materials under extreme conditions that are difficult to probe experimentally. For example, shock-induced plasticity and phase transformation processes in single-crystal and nanocrystalline metals have been widely studied via large-scale molecular dynamics simulations, and many of these predictions are beginning to be tested at advanced 4th generation light sources such as the Advanced Photon Source (APS) and Linac Coherent Light Source (LCLS). I will describe our simulation predictions and their recent verification at LCLS, outstanding challenges in modeling the response of materials to extreme mechanical and radiation environments, and ourmore »« less
https://doi.org/10.2172/1136467

Full Text Available

Similar Records