Efficient Adaptive Scheduling of Multiprocessors with Stable Parallelism Feedback

Sun, Hongyang; Cao, Yangjie; Hsu, Wen-Jing

doi:10.1109/tpds.2010.121

Cited by 21 publications

(29 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, feedback mechanisms introduce other overheads such as too frequent communication, inconsistency (as iteration times are not always constant), and increased complexity for non-iterative malleable applications. Thus, efficient feedback mechanisms for malleable applications have been exclusively studied by many [24], [25]. Scheduling based on feedback from application on its scaling pattern is our interest for investigation in the future and is out of scope of this work.…”

Section: Communication With the Parallel Runtime Systemmentioning

confidence: 99%

A Batch System with Efficient Adaptive Scheduling for Malleable and Evolving Applications

Prabhakaran

Neumann

Rinke

et al. 2015

2015 IEEE International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

Abstract-The throughput of supercomputers depends not only on efficient job scheduling but also on the type of jobs that form the workload. Malleable jobs are most favorable for a cluster as they can dynamically adapt to a changing allocation of resources. The batch system can expand or shrink a running malleable job to improve system utilization, throughput, and response times. In the past, however, the rigid nature of commonly used programming models like MPI made writing malleable applications a daunting task, which is why it remained largely unrealized. This is now changing. To improve fault tolerance, load imbalance, and energy efficiency in emerging exascale systems, more adaptive programming paradigms such as Charm++ enter the scene. Although they offer better support for malleability, current batch systems still lack management facilities for malleable jobs and are therefore incapable of leveraging their potential. In this paper, we present an extension of the Torque/Maui batch system for malleability. We propose a novel malleable job scheduling strategy and show the first batch system capable of efficiently managing rigid, malleable, and evolving jobs together. We demonstrate that our strategy achieves consistently superior performance in comparison to every other state-of-the-art malleable job scheduling strategy under varying dynamics of the workload.

show abstract

Section: Communication With the Parallel Runtime Systemmentioning

confidence: 99%

A Batch System with Efficient Adaptive Scheduling for Malleable and Evolving Applications

Prabhakaran

Neumann

Rinke

et al. 2015

2015 IEEE International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

show abstract

“…Each feature in the rule is modeled from a Gaussian membership function. The rules used for the optimization are (Sun et al, 2011) and Norozi et al (2010) Where awt is the average waiting time, tat is the turn around time, mrt is the mean response time, mret is the mean reaction time, msl is the mean slowdown and mu is the mean utilization. The scheduling classes are Class A is the Agile Algorithm, Class B is the Flexible co scheduling, Class C is the Gang Scheduling and the Class D is the First Come First Serve scheduling.…”

Section: Scheduling Strategy Based On Genetic Based Neuro Fuzzy Technmentioning

confidence: 99%

A Genetic Based Neuro Fuzzy Technique for Process Grain Sized Scheduling of Parallel Jobs

Sudha¹

2012

Journal of Computer Science

View full text Add to dashboard Cite

Problem statement:In this study, we present the development of genetic algorithm based neuro fuzzy technique for process grain sized in scheduling of parallel jobs with the help of real lIfe workload data. Approach: The study uses the rule based scheduling strategy for the scheduling and classIfies all possible scheduling strategies. The rule bases are developed with the help of the neuro fuzzy system and with the genetic fuzzy system. From the comparison of the two classIfiers of the fuzzy systems, it is found that the neuro fuzzy system results higher error rate when compared to the genetic fuzzy system. Hence the study concentrates on reducing the error rate of the results of the neuro fuzzy system by using the genetic algorithm for improving the parameters to the neuro fuzzy system. Results: The study shows that improving parameter like weights in the layers of the neuro fuzzy system using genetic algorithm reduces the error rate and comparative results of the neuro fuzzy, genetic fuzzy and the genetic based neuro fuzzy technique are shown for the parallel job scheduling. Conclusion:The study confirmed that the Genetic Based Neuro Fuzzy Technique can be used as a better optimization tool for optimizing any scheduling algorithm and this optimization tool is used in this study for agile algorithm which is used for process grain scheduling of parallel jobs.

show abstract

“…Since the future parallelism of the job is usually unknown, the desire calculation is usually based on the execution history of the job in the previous quantum, such as measurements about the job's processor utilizations or average parallelism [7], [10]. Another aspect is for the processor controller to decide the processor allocation of each job.…”

Section: Adaptive Schedulingmentioning

confidence: 99%

“…It was shown in [10], [16] that another adaptive scheduler based on centralized work sharing, called A-Greedy [7], exhibits desire instability problem, even when the parallelism of the job is constant. Since both A-Steal and A-Greedy use multiplicative-increase multiplicative-decrease strategy to calculate processor desires, such instability problem can also be observed in A-Steal.…”

Section: Desire Stability Of Saws and A-stealmentioning

confidence: 99%

“…First, we assume that the desires of the job can be satisfied by the globallevel processor controller as much as possible. This corresponds to light to medium workloads, in which two-level adaptive schedulers tend to work better compared to nonadaptive schemes [10], [17]. Second, we assume that the ready threads of a deque can be stolen as quickly as possible by steal attempts from other processors.…”

Section: Desire Stability Of Saws and A-stealmentioning

confidence: 99%

See 1 more Smart Citation

Stable Adaptive Work-Stealing for Concurrent Many-Core Runtime Systems

Cao

Sun

Qian

et al. 2012

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThe proliferation of many-core architectures has led to the explosive development of parallel applications using programming models, such as OpenMP, TBB, and Cilk/Cilk++. With increasing number of cores, however, it becomes even harder to efficiently schedule parallel applications on these resources since current many-core runtime systems still lack effective mechanisms to support collaborative scheduling of these applications. In this paper, we study feedback-driven adaptive scheduling based on work stealing, which provides an efficient solution for concurrently executing a set of applications on many-core systems. To dynamically estimate the number of cores desired by each application, a stable feedback-driven adaptive algorithm, called SAWS, is proposed using active workers and the length of active deques, which well captures the runtime characteristics of the applications. Furthermore, a prototype system is built by extending the Cilk runtime system, and the experimental results, which are obtained on a Sun Fire server, show that SAWS has more advantages for scheduling concurrent parallel applications. Specifically, compared with existing algorithms A-Steal and WS-EQUI, SAWS improves the performances by up to 12.43% and 21.32% with respect to mean response time respectively, and 25.78% and 46.98% with respect to processor utilization, respectively.

show abstract

Efficient Adaptive Scheduling of Multiprocessors with Stable Parallelism Feedback

Cited by 21 publications

References 34 publications

A Batch System with Efficient Adaptive Scheduling for Malleable and Evolving Applications

A Batch System with Efficient Adaptive Scheduling for Malleable and Evolving Applications

A Genetic Based Neuro Fuzzy Technique for Process Grain Sized Scheduling of Parallel Jobs

Stable Adaptive Work-Stealing for Concurrent Many-Core Runtime Systems

Contact Info

Product

Resources

About