Characterization of scientific workflows

Bharathi, S.; Chervenak, Ann; Deelman, Ewa; Mehta, Gaurang; Su, Min; Vahi, Karan

doi:10.1109/works.2008.4723958

Cited by 521 publications

(358 citation statements)

References 10 publications

Supporting

Mentioning

335

Contrasting

Unclassified

Order By: Relevance

“…The computation critical path is computed by the sum of the minimum computation time of each task on CP, it is denoted as CP c and computed using (6).…”

Section: Definitionmentioning

confidence: 99%

“…The computation-intensive workflows consist of tasks which expend most of the time in computations, while the tasks in the data-intensive workflows generate enormous data and therefore involve much in exchanging data rather than computations [6]. The tasks in the memory-intensive workflows demand high physical storage requirements.…”

Section: An Overview Of Scientific Workflowsmentioning

confidence: 99%

See 1 more Smart Citation

A New Makespan Estimation Model for Scientific Workflows on Heterogeneous Processing Systems

Sirisha¹,

Vijayakumari²

2018

IJCA

View full text Add to dashboard Cite

Scientific workflows epitomizing computation-intensive applications demand heterogeneous processing resources for attaining high performance. Generally, optimal scheduling of the tasks in workflow is well-acknowledged NP-complete problem. In the present work, a new makespan estimation model is proposed to estimate the bounds on the makespan of the workflows using minimal information. The performance of the proposed estimation model is evaluated using four scientific workflows and the estimation of the makespan computed by the model is compared with the actual makespan generated by the most-cited heuristic scheduling algorithms devised for heterogeneous processing systems. The experimental results revealed that the proposed estimation model is effective and can precisely estimate the makespan of the workflows with an error of over 10% and 26% for computation-intensive and data-intensive workflows respectively.

show abstract

“…The computation critical path is computed by the sum of the minimum computation time of each task on CP, it is denoted as CP c and computed using (6).…”

Section: Definitionmentioning

confidence: 99%

Section: An Overview Of Scientific Workflowsmentioning

confidence: 99%

A New Makespan Estimation Model for Scientific Workflows on Heterogeneous Processing Systems

Sirisha¹,

Vijayakumari²

2018

IJCA

View full text Add to dashboard Cite

show abstract

“…It can be used to provide insight on the application needs and identify the different requirements in order to optimize the deployment of different workflows. Several attempts have been made to characterize scientific applications and workflows [34,35,36,37,38,39,40,41]. The work in [37] describes the characterization of a range of scientific workflows to describe both their composition and the data and computational requirements of the tasks.…”

Section: Characterizations Of Workflows and Wmssmentioning

confidence: 99%

“…Several attempts have been made to characterize scientific applications and workflows [34,35,36,37,38,39,40,41]. The work in [37] describes the characterization of a range of scientific workflows to describe both their composition and the data and computational requirements of the tasks. Approaches that provide more fine-grained profiling data can be found in [38,39,40].…”

Section: Characterizations Of Workflows and Wmssmentioning

confidence: 99%

A characterization of workflow management systems for extreme-scale applications

Silva

Filgueira

Pietri

et al. 2017

Future Generation Computer Systems

Self Cite

125

View full text Add to dashboard Cite

Automation of the execution of computational tasks is at the heart of improving scientific productivity. Over the last years, scientific workflows have been established as an important abstraction that captures data processing and computation of large and complex scientific applications. By allowing scientists to model and express entire data processing steps and their dependencies, workflow management systems relieve scientists from the details of an application and manage its execution on a computational infrastructure. As the resource requirements of today's computational and data science applications that process vast amounts of data keep increasing, there is a compelling case for a new generation of advances in high-performance computing, commonly termed as extreme-scale computing, which will bring forth multiple challenges for the design of workflow applications and management systems. This paper presents a novel characterization of workflow management systems using features commonly associated with extreme-scale computing applications. We classify 15 popular workflow management systems in terms of workflow execution models, heterogeneous computing environments, and data access methods. The paper also surveys workflow applications and identifies gaps for future research on the road to extreme-scale workflows and management systems.

show abstract

“…Overall, the execution of this workload led to the evaluation of 1, 364 billion of puzzle setups (tasks). The number of tasks is much larger for puzzle content generation than for the largest scientific workflows; the latter comprise rarely over a million of tasks [4,23,25].…”

Section: Application Characterizationmentioning

confidence: 99%

POGGI: generating puzzle instances for online games on grid infrastructures

Iosup

2010

Concurrency and Computation

View full text Add to dashboard Cite

key words: game content generation, grid computing, puzzle, MMOG, resource management. SUMMARYThe developers of Massively Multiplayer Online Games (MMOGs) rely on attractive content such as logical challenges (puzzles) to entertain and generate revenue from millions of concurrent players. While a large part of the content is currently generated by hand, the exponentially increasing number of players and their new demand for player-customized content have made manual content generation undesirable. Thus, in this work we investigate the problem of automated, player-customized game content generation at MMOG scale; to make our investigation tractable, we focus on puzzle game content generation. In this context, we design POGGI, an architecture for generating player-customized game content using on-demand, grid resources. POGGI focuses on the large-scale generation of puzzle instances that match well the solving ability of the players, and that lead to fresh playing experience. Using our reference implementation of POGGI, we show through experiments in a real resource pool of over 1,600 nodes that POGGI can generate commercial-quality content at MMOG scale. IntroductionMassively Multiplayer Online Games (MMOGs) have emerged in the past decade as a new type of large-scale distributed application: real-time virtual world simulations entertaining at the same time millions of players located around the world. In real deployments, the operation and maintenance of these applications includes two main components, one running the large-scale virtual world simulation, the other populating the virtual world with content that keeps the players engaged (and paying). So far, content has been provided exclusively by human content designers, but the growth of the player population, the lack of scalability of the production pipeline, and the increase in the price ratio between human work and computation make this situation undesirable for the future. Extending our previous work [14], here we investigate the problem of automated, player-customized content generation for MMOGs using grids. * Correspondence to: Email: a.iosup@tudelft.nl. We thank Dr. Dick Epema and Dr. Miron Livny for support. There are many types of content present in MMOGs, from 3D objects populating the virtual worlds, to abstract challenges facing the players. Since content generation is timeconsuming and costly, MMOG developers seek the content types that entertain and challenge players for the longest time. Puzzle games, that is, games in which the player is entertained by solving a logical challenge, are a much sought-after MMOG content type; for instance, players may spend hours on a chess puzzle [17,24] that enables exiting a labyrinth. Today, puzzle game content is generated by teams of human designers, which poses scalability problems to the production pipeline. While several commercial games have made use of content generation [1,5,7,29], they have all been small-scale games in terms of number of players, and did not consider the generation of puzzle game...

show abstract

Characterization of scientific workflows

Cited by 521 publications

References 10 publications

A New Makespan Estimation Model for Scientific Workflows on Heterogeneous Processing Systems

A New Makespan Estimation Model for Scientific Workflows on Heterogeneous Processing Systems

A characterization of workflow management systems for extreme-scale applications

POGGI: generating puzzle instances for online games on grid infrastructures

Contact Info

Product

Resources

About