Dynamic load balancing of MPI+OpenMP applications

Corbalan, Julita; Durán, Alejandro; Labarta, Jesús

doi:10.1109/icpp.2004.1327921

Cited by 30 publications

(17 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Exemplar runtime systems implementing this approach are Zoltan [3], Chombo [15], and Charm++ [10]. Similar schemes have also been proposed and used in MPI applications [16,17]. This paper proposes concepts which build upon these existing frameworks in order to make decisions related to load balancing to get good performance.…”

Section: Previous Workmentioning

confidence: 99%

Automated Load Balancing Invocation Based on Application Characteristics

Menon

Jain

Zheng

et al. 2012

2012 IEEE International Conference on Cluster Computing

View full text Add to dashboard Cite

Abstract-Performance of applications executed on large parallel systems suffer due to load imbalance. Load balancing is required to scale such applications to large systems. However, performing load balancing incurs a cost which may not be known a priori. In addition, application characteristics may change due to its dynamic nature and the parallel system used for execution. As a result, deciding when to balance the load to obtain the best performance is challenging. Existing approaches put this burden on the users, who rely on educated guess and extrapolation techniques to decide on a reasonable load balancing period, which may not be feasible and efficient.In this paper, we propose the Meta-Balancer framework which relieves the application programmers of deciding when to balance load. By continuously monitoring the application characteristics and using a set of guiding principles, MetaBalancer invokes load balancing on its own without any prior application knowledge. We demonstrate that Meta-Balancer improves or matches the best performance that can be obtained by fine tuning periodic load balancing. We also show that in some cases Meta-Balancer improves performance by 18% whereas periodic load balancing gives only a 1.5% benefit.

show abstract

Section: Previous Workmentioning

confidence: 99%

Automated Load Balancing Invocation Based on Application Characteristics

Menon

Jain

Zheng

et al. 2012

2012 IEEE International Conference on Cluster Computing

View full text Add to dashboard Cite

show abstract

“…When application is well balanced (similar to the case study of this paper in section IV), pure MPI programs usually result in good application performance [53]. The problem appears when application has internal unbalance load.…”

Section: E Load Distributionmentioning

confidence: 72%

Robotic clusters: Multi-robot systems as computer clusters

Marjovi

Choobdar

Marques

2012

Robotics and Autonomous Systems

View full text Add to dashboard Cite

“…After several contributions, an open question remained: would it be possible to avoid the programmer intervention in order to obtain the most suitable thread distribution? In this paper we propose a mechanism to do it, based on the previous works of Duran et al [7,10]. Those works introduced the facility of sampling the execution time for each branch in the outermost level of parallelism.…”

Section: Versionmentioning

confidence: 99%

Automatic thread distribution for nested parallelism in OpenMP

Durán¹,

González²,

Corbalan³

2005

Proceedings of the 19th Annual International Conference on Supercomputing

View full text Add to dashboard Cite

OpenMP is becoming the standard programming model for shared-memory parallel architectures. One of its most interesting features in the language is the support for nested parallelism. Previous research and parallelization experiences have shown the benefits of using nested parallelism as an alternative to combining several programming models such as MPI and OpenMP. However, all these works rely on the manual definition of an appropriate distribution of all the available thread across the different levels of parallelism. Some proposals have been made to extend the OpenMP language to allow the programmers to specify the thread distribution. This paper proposes a mechanism to dynamically compute the most appropriate thread distribution strategy. The mechanism is based on gathering information at runtime to derive the structure of the nested parallelism. This information is used to determine how the overall computation is distributed between the parallel branches in the outermost level of parallelism, which is constant in this work. According to this, threads in the innermost level of parallelism are distributed.The proposed mechanism is evaluated in two different environments: a research environment, the Nanos OpenMP research platform, and a commercial environment, the IBM XL runtime library. The performance numbers obtained validate the mechanism in both environments and they show the importance of selecting the proper amount of parallelism in the outer level.

show abstract

Dynamic load balancing of MPI+OpenMP applications

Cited by 30 publications

References 10 publications

Automated Load Balancing Invocation Based on Application Characteristics

Automated Load Balancing Invocation Based on Application Characteristics

Robotic clusters: Multi-robot systems as computer clusters

Automatic thread distribution for nested parallelism in OpenMP

Contact Info

Product

Resources

About