ProcSimity: an experimental tool for processor allocation and scheduling in highly parallel systems

Windisch, Kurt; Miller, J.V.; Lo, Virginia

doi:10.1109/fmpc.1995.380484

Cited by 21 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have implemented the allocation and deallocation algorithms, including the busy list routines, in the C language, and integrated the software into the ProcSimity simulation tool for processor allocation in highly parallel systems [10,18].…”

Section: Simulation Resultsmentioning

confidence: 99%

“…In FCFS scheduling strategy, the allocation request that arrived first is considered for allocation first. Allocation attempts stop when they fail for the current FIFO queue head, while in SSD scheduling strategy, the job with the shortest service demand is scheduled first [10,21,22]. Any of them can start execution if its allocation request can be satisfied.…”

Section: Job Scheduling Strategiesmentioning

confidence: 99%

“…In this paper, a Shortest-ServiceDemand (SSD) scheduling strategy is also used because it is expected to reduce performance loss due to blocking. This strategy was found to improve performance significantly [10,21,22]. Also in this paper, the performance of allocation strategies is measured in terms of usual performance parameters [4,5,6,7,20,21,22,23,24,28,29] such as the average turnaround time and mean system utilization.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Performance Comparison of the Contiguous Allocation Strategies in 3D Mesh Connected Multicomputers

Bani-Mohammad

Ould‐Khaoua

Ababneh

et al. 2007

Parallel and Distributed Processing and Applications

View full text Add to dashboard Cite

Abstract. The performance of contiguous allocation strategies can be significantly affected by the distribution of job execution times. In this paper, the performance of the existing contiguous allocation strategies for 3D mesh multicomputers is re-visited in the context of heavy-tailed distributions (e.g., a Bounded Pareto distribution). The strategies are evaluated and compared using simulation experiments for both First-Come-First-Served (FCFS) and ShortestService-Demand (SSD) scheduling strategies under a variety of system loads and system sizes. The results show that the performance of the allocation strategies degrades considerably when job execution times follow a heavytailed distribution. Moreover, SSD copes much better than FCFS scheduling strategy in the presence of heavy-tailed job execution times. The results also show that the strategies that depend on a list of allocated sub-meshes for both allocation and deallocation have lower allocation overhead and deliver good system performance in terms of average turnaround time and mean system utilization.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Section: Job Scheduling Strategiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Performance Comparison of the Contiguous Allocation Strategies in 3D Mesh Connected Multicomputers

Bani-Mohammad

Ould‐Khaoua

Ababneh

et al. 2007

Parallel and Distributed Processing and Applications

View full text Add to dashboard Cite

show abstract

“…For our simulations, we used ProcSimity [31,29], a simulator designed to compare processor scheduling and allocation algorithms. Since our focus is on allocation rather than scheduling, we scheduled using First Come, First Serve (FCFS) in all our simulations.…”

Section: Simulationmentioning

confidence: 99%

Communication patterns and allocation strategies.

Bunde

Leung

Mache

2004

View full text Add to dashboard Cite

Motivated by observations about job runtimes on the CPlant system, we use a trace-driven microsimulator to begin characterizing the performance of different classes of allocation algorithms on jobs with different communication patterns in space-shared parallel systems with mesh topology. We show that relative performance varies considerably with communication pattern. The Paging strategy using the Hilbert space-filling curve and the Best Fit heuristic performed best across several communication patterns.

show abstract

“…For our simulations, we used ProcSimity [32,30], a simulator designed to compare processor scheduling and allocation algorithms. Since our focus is on allocation rather than scheduling, we scheduled using First Come, First Serve (FCFS) in all our simulations.…”

Section: Simulationmentioning

confidence: 99%