ParFUM: a parallel framework for unstructured meshes for scalable dynamic physics applications

Lawlor, Orion Sky; Chakravorty, Sayantan; Wilmarth, Terry; Choudhury, Nilesh; Dooley, Isaac; Zheng, Gengbin; Kalé, Laxmikant V.

doi:10.1007/s00366-006-0039-5

Cited by 53 publications

(35 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fractographic methods are used to determine the cause of failure in engineering structures and evaluate theoretical models of crack growth behavior. Our simulation program, called Fractography3D, is written using Charm++ FEM framework [4].…”

Section: B Fractography3dmentioning

confidence: 99%

See 1 more Smart Citation

Automated Load Balancing Invocation Based on Application Characteristics

Menon

Jain

Zheng

et al. 2012

2012 IEEE International Conference on Cluster Computing

Self Cite

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: B Fractography3dmentioning

confidence: 99%

“…In a large class of scientific applications such as NAMD [1], FEM [4] and climate simulation, the problem is broken into smaller data and work units that execute on multiple processors. The computation being performed consists of a number of time steps and/or iterations with frequent interaction among data/work units via messages.…”

Section: Introductionmentioning

confidence: 99%

Automated Load Balancing Invocation Based on Application Characteristics

Menon

Jain

Zheng

et al. 2012

2012 IEEE International Conference on Cluster Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…ParFUM has been used to develop a number of parallel unstructured mesh applications [24]. These applications utilize the many features provided by Par-FUM for faster development and better performance.…”

Section: Multi-paradigm Applicationsmentioning

confidence: 99%

“…ParFUM [24] is a framework for the parallelization of unstructured mesh applications. It provides the programmer with a rich set of features such as mesh partitioning, communication between mesh partitions, mesh adaptivity, mesh locking, collision detection and data transfer.…”

Section: Parfum: An Example Of Multi-paradigm Programmingmentioning

confidence: 99%

A Case Study in Tightly Coupled Multi-paradigm Parallel Programming

Chakravorty

Becker

Wilmarth

et al. 2008

Languages and Compilers for Parallel Computing

Self Cite

View full text Add to dashboard Cite

Abstract. Programming paradigms are designed to express algorithms elegantly and efficiently. There are many parallel programming paradigms, each suited to a certain class of problems. Selecting the best parallel programming paradigm for a problem minimizes programming effort and maximizes performance. Given the increasing complexity of parallel applications, no one paradigm may be suitable for all components of an application. Today, most parallel scientific applications are programmed with a single paradigm and the challenge of multi-paradigm parallel programming remains unmet in the broader community. We believe that each component of a parallel program should be programmed using the most suitable paradigm. Furthermore, it is not sufficient to simply bolt modules together: programmers should be able to switch between paradigms easily, and resource management across paradigms should be automatic. We present a pre-existing adaptive runtime system (ARTS) and show how it can be used to meet these challenges by allowing the simultaneous use of multiple parallel programming paradigms and supporting resource management across all of them. We discuss the implementation of some common paradigms within the ARTS and demonstrate the use of multiple paradigms within our feature-rich unstructured mesh framework. We show how this approach boosts performance and productivity for an application developed using this framework.

show abstract

“…Therefore, to reduce the excessive migration of tasks, these strategies typically invoke load balancing in a "phase-based" fashion, that is, load balancing happens periodically when needed. These load balancing schemes are suitable for a class of iterative scientific applications such as NAMD [1], FEM [23] and climate simulation, where the computation typically consists of a number of time steps, a number of iterations (as in iterative linear system solvers), or a combination of both. Phase-based load balancing strategies for iterative applications are the main focus of this paper.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Load Balancing for Charm++ Applications on Large Supercomputers

Zheng

Meneses

Bhatelé

et al. 2010

2010 39th International Conference on Parallel Processing Workshops

Self Cite

View full text Add to dashboard Cite

Abstract-Large parallel machines with hundreds of thousands of processors are being built. Recent studies have shown that ensuring good load balance is critical for scaling certain classes of parallel applications on even thousands of processors. Centralized load balancing algorithms suffer from scalability problems, especially on machines with relatively small amount of memory. Fully distributed load balancing algorithms, on the other hand, tend to yield poor load balance on very large machines. In this paper, we present an automatic dynamic hierarchical load balancing method that overcomes the scalability challenges of centralized schemes and poor solutions of traditional distributed schemes. This is done by creating multiple levels of aggressive load balancing domains which form a tree. This hierarchical method is demonstrated within a measurementbased load balancing framework in Charm++. We present techniques to deal with scalability challenges of load balancing at very large scale. We show performance data of the hierarchical load balancing method on up to 16,384 cores of Ranger (at TACC) for a synthetic benchmark. We also demonstrate the successful deployment of the method in a scientific application, NAMD with results on the Blue Gene/P machine at ANL.

show abstract

ParFUM: a parallel framework for unstructured meshes for scalable dynamic physics applications

Cited by 53 publications

References 27 publications

Automated Load Balancing Invocation Based on Application Characteristics

Automated Load Balancing Invocation Based on Application Characteristics

A Case Study in Tightly Coupled Multi-paradigm Parallel Programming

Hierarchical Load Balancing for Charm++ Applications on Large Supercomputers

Contact Info

Product

Resources

About