Moving Volunteer Computing towards Knowledge-Constructed, Dynamically-Adaptive Modeling and Scheduling

Taufer, Michela; Kerstens, Andre; Estrada, Trilce; Flores, David A.; Zamudio, Richard; Teller, Patricia J.; Armen, Roger S.; Brooks, Charles L.

doi:10.1109/ipdps.2007.370668

Cited by 8 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Статья [35] основана на данных проекта добровольных вычисле-ний Docking@Home. С помощью системы имитационного моделирова-ния SimBA авторы демонстрируют, что адаптивный выбор вычисли-тельных узлов при назначении заданий может улучшить пропускную способность Desktop Grid.…”

Section: исследовательские статьиunclassified

A survey of task scheduling in Desktop Grid

Chernov¹,

Ivashko²,

Nikitina³

2017

PSTA

View full text Add to dashboard Cite

Section: исследовательские статьиunclassified

A survey of task scheduling in Desktop Grid

Chernov¹,

Ivashko²,

Nikitina³

2017

PSTA

View full text Add to dashboard Cite

“…Second, available simulators include CloudSim and GridSim [5] do not provide fine-granularity simulations of workflows [6] and do not allow workflow partitioning or controlled scheduling as we require to conduct this study. Some examples of scheduling-based performance modeling studies that have benefited from simulations appear in [7] and [8]. Figure 1 shows a diagram of our testing engine.…”

Section: A Overviewmentioning

confidence: 99%

A Testing Engine for High-Performance and Cost-Effective Workflow Execution in the Cloud

Pallipuram

Estrada

Taufer

2015

2015 44th International Conference on Parallel Processing

Self Cite

View full text Add to dashboard Cite

While pursuing high performance and cost effectiveness for directed acyclic graph (DAG)-structured scientific workflow executions in the cloud, it is critical to identify appropriate resource instances and their quantity. This paper presents a testing engine that employs a resource-selection heuristic, which statically analyzes the DAG structure to guide the selection of resource instances, how many and which ones. The testing engine combines the heuristic with two platformindependent DAG-scheduling policies, the Area-oriented DAGscheduling heuristic AO (AO) and the Locally-Optimal heuristic (L-OPT), to perform extensive validation assessments. The testing engine ensures the realism of these assessments by modeling the performance variability of the cloud platform using real traces. The testing engine also enables cost-effectiveness analysis that guides users to select a small set of instance candidates that provide performance-cost tradeoff. Our empirical results show that the pairing of the resource-selection heuristic with AO scheduling policy is a powerful method for cost-effective DAGstructured workflow execution in the cloud.

show abstract

“…At present, this idea is actively used in mainstream research. For example, our group has developed easy-toinstall web browser extension tools [2], [3], [14], [15], [17] which, in effect, enable computers to work together. The resulting networks are already being used for bioinformatics applications [13], [16].…”

Section: Global Computingmentioning

confidence: 99%

Towards Optimal Scheduling for Global Computing under Probabilistic, Interval, and Fuzzy Uncertainty, with Potential Applications to Bioinformatics

Araiza

Taufer

Leung

2007

NAFIPS 2007 - 2007 Annual Meeting of the North American Fuzzy Information Processing Society

View full text Add to dashboard Cite

In many practical situations, in particular in many bioinformatics problems, the amount of required computations is so huge that the only way to perform these computations in reasonable time is to distribute them between multiple processors.The more processors we engage, the faster the resulting computations; thus, in addition to processor exclusively dedicated to this job, systems often use idle time on other processors. The use of these otherwise engaged processors adds additional uncertainty to computations.How should we schedule the computational tasks so as to achieve the best utilization of the computational resources?Because of the presence of uncertainty, this scheduling problem is very dif cult not only to solve but even to formalize (i.e., to describe in precise terms). In this paper, we provide the rst steps towards formalizing and solving this scheduling problem. II. SUPERCOMPUTING IN THE PASTIn this paper, we will analyze scheduling in global computing. To explain the idea (and the necessity) of global computing, it is important to explain how the concept of supercomputing has evolved in the last decades.In the past, the ability to use supercomputers to simulate such things as nuclear weapons design was an important part of military confrontation. As a result, special classi ed technology was used to design supercomputers, technology that was not allowed on regular individual computers.

show abstract

Moving Volunteer Computing towards Knowledge-Constructed, Dynamically-Adaptive Modeling and Scheduling

Cited by 8 publications

References 7 publications

A survey of task scheduling in Desktop Grid

A survey of task scheduling in Desktop Grid

A Testing Engine for High-Performance and Cost-Effective Workflow Execution in the Cloud

Towards Optimal Scheduling for Global Computing under Probabilistic, Interval, and Fuzzy Uncertainty, with Potential Applications to Bioinformatics

Contact Info

Product

Resources

About