Filters








583 Hits in 4.6 sec

Online Algorithms for Non-preemptive Speed Scaling on Power-Heterogeneous Processors [chapter]

Aeshah Alsughayyir, Thomas Erlebach
2017 Lecture Notes in Computer Science  
In this paper we consider non-preemptive online scheduling of jobs with release times and deadlines on heterogeneous processors with speed scaling.  ...  The power needed by processor i to run at speed s is assumed to be s α i , where the exponent αi is a constant that can be different for each processor.  ...  problem of non-preemptive speed-scaling on heterogeneous processors, which is the focus of this paper.  ... 
doi:10.1007/978-3-319-71147-8_32 fatcat:mq6cdyrodbbetmq6fzancuacqu

Scheduling on Power-Heterogeneous Processors [chapter]

Susanne Albers, Evripidis Bampis, Dimitrios Letsios, Giorgio Lucarelli, Richard Stotz
2016 Lecture Notes in Computer Science  
When a processor runs at speed s, then the rate with which the energy is consumed (i.e., the power) is f (s) with f a non-decreasing function of the speed.  ...  Standard Power Functions : Each processor p ∈ P satisfies the power function f p (s) = s αp , where α p > 1 is a small constant. This is the usual assumption in the speed-scaling literature.  ... 
doi:10.1007/978-3-662-49529-2_4 fatcat:b2rjmcwtardmno5arssruacz3y

Scheduling Heterogeneous Processors Isn't As Easy As You Think [chapter]

Anupam Gupta, Sungjin Im, Ravishankar Krishnaswamy, Benjamin Moseley, Kirk Pruhs
2012 Proceedings of the Twenty-Third Annual ACM-SIAM Symposium on Discrete Algorithms  
We consider preemptive online scheduling algorithms to minimize the total weighted/unweighted flow time plus energy for speed-scalable heterogeneous multiprocessors.  ...  We then show that a variation of the non-clairvoyant algorithm Late Arrival Processor Sharing coupled with a non-obvious speed scaling algorithm is scalable for the objective of unweighted flow plus energy  ...  A system that sits atop a speed-scalable processor needs not only an online scheduling policy to determine which job to run on which processor, but also a speed scaling policy for setting the speed of  ... 
doi:10.1137/1.9781611973099.98 dblp:conf/soda/GuptaIKMP12 fatcat:lsyawgruxrcnzgeoync2tl4lma

Scheduling (Dagstuhl Seminar 16081)

Nikhil Bansal, Nicole Megow, Clifford Stein, Marc Herbstritt
2016 Dagstuhl Reports  
We present a method to obtain asymptotic fully polynomial approximation schemes (AFPTAS) for the problems.  ...  We consider two related scheduling problems: resource constrained scheduling on identical parallel machines and a generalization with resource dependent processing times.  ...  On Speed Scaling with a Sleep State We consider classical deadline-based preemptive scheduling of jobs in a computing environment equipped with both dynamic speed scaling and sleep state capabilities:  ... 
doi:10.4230/dagrep.6.2.97 dblp:journals/dagstuhl-reports/BansalMS16 fatcat:7yjnnvu26vcjfa3r6nknvrpkk4

Minimizing Total Completion Time in Multiprocessor Job Systems with Energy Constraint [chapter]

Alexander Kononov, Yulia Kovalenko
2021 Lecture Notes in Computer Science  
Each multiprocessor job requires more than one processor at the same moment of time. Processors may operate at variable speeds.  ...  We propose approximation algorithms for various particular cases.  ...  Introduction We investigate the problem of non-preemptive scheduling a set of jobs J = {1, . . . , n} on m speed scalable parallel processors.  ... 
doi:10.1007/978-3-030-77876-7_18 fatcat:ug5mk52advee3jvy65s6giem4e

Energy-aware Scheduling based Tasks dynamic Priority on Homogeneous Multiprocessor Platforms

Shahira M.
2018 International Journal of Computer Applications  
Dynamic Voltage and Frequency Scaling (DVFS) technique, permits processors to dynamically change their supply voltages and execution frequencies so it can work on many power/energy levels.  ...  Multi-core processors achieve improved performance with lower power consumption.  ...  However, the maximum task utilization can be obtained when the processor run at maximum relative speed (i.e. S = 1.0). The scheduling model used is the non-preemptive technique.  ... 
doi:10.5120/ijca2018916237 fatcat:jtlnkqxqqzaxdhfpbd7wibfqau

Keynote Speech Abstracts

2009 2009 Fourth International Conference on Frontier of Computer Science and Technology  
On the one hand, in high performance computing systems, power-aware design techniques and algorithms attempt to maximize performance under certain energy consumption constraints.  ...  This talk will highlight some of the important questions related to the development of new algorithms and tools for energy-aware resource management allocation for large-scale distributed systems enabling  ...  and heterogeneous processors, continuous and discrete voltage/speed levels, overheads for voltage/speed adjustment and idle processors), and different scheduling models (preemptive and nonpreemptive scheduling  ... 
doi:10.1109/fcst.2009.7 fatcat:25kjipjipbayvbypdznbs7nzo4

Scheduling on power-heterogeneous processors

Susanne Albers, Evripidis Bampis, Dimitrios Letsios, Giorgio Lucarelli, Richard Stotz
2017 Information and Computation  
Furthermore, we develop a faster combinatorial algorithm based on flows for standard power functions and jobs whose density is lower bounded by a small constant.  ...  Finally, we extend and analyze the AVerage Rate (AVR) online algorithm in the heterogeneous setting. * A preliminary version has been presented to LATIN 2016 †  ...  Flow-based Algorithm for Standard Power Functions In this section, we first characterize the structure of an optimal solution for the heterogeneous speed-scaling problem with power functions of the form  ... 
doi:10.1016/j.ic.2017.09.013 fatcat:yzsjikhlwfcydlk2ualjttvxjy

Resource-aware allocation strategies for divisible loads on large-scale systems

Anne Benoit, Loris Marchal, Jean-Francois Pineau, Yves Robert, Frederic Vivien
2009 2009 IEEE International Symposium on Parallel & Distributed Processing  
We show how to reduce this problem to a classical preemptive scheduling problem on a single machine, thereby establishing new complexity results, and providing new approximation algorithms and heuristics  ...  In this paper, we deal with the large-scale divisible load problem studied in [12] .  ...  Acknowledgment We thank the reviewers for their comments and suggestions. This work was supported in part by the ANR StochaGrid project.  ... 
doi:10.1109/ipdps.2009.5160912 dblp:conf/ipps/BenoitMPRV09 fatcat:tmm73eq3rzejtlqqnvn6hjrv7a

Green Data Centers: A Survey, Perspectives, and Future Directions [article]

Xibo Jin, Fa Zhang, Athanasios V. Vasilakos, Zhiyong Liu
2016 arXiv   pre-print
We further discuss the key challenges for future research and highlight some future research issues for addressing the problem of building green data centers.  ...  In this paper, we provide a survey of the state-of-the-art research on green data center techniques, including energy efficiency, resource management, thermal control and green metrics.  ...  [35] studied a heterogeneous multiprocessor preemptive problem, in which it was assumed that each processor had a different speed-to-power function.  ... 
arXiv:1608.00687v1 fatcat:if2x3wmy3rhorasl3f2vyvcozy

A Survey on Scheduling Algorithms in Cloud Computing

Mrs.M. Padmavathi, Shaik Mahabbob Basha, Mr.Srinivas Pothapragada
2014 IOSR Journal of Computer Engineering  
Cloud computing services are usually backed by large-scale data centers are built to serve many users and many disparate Applications, for this we are considering Virtualization a s a perfect match.  ...  As a future enhancement a new Algorithm will develop.  ...  their vital encouragement, support and facilities providing by them achieve this task and at they would like to thank Anonymous Reviewers for their valuable suggestions and comments.  ... 
doi:10.9790/0661-16432732 fatcat:bgkni23bhjaydkw4n7rxlevq5i

AI-based methods to resolve Real time scheduling for embedded systems

2021 International Journal of Cognitive Informatics and Natural Intelligence  
aware scheduling algorithms for ES.  ...  We end this survey by a discussion putting the light on the main challenges and the future directions.  ...  Tasks can be mapped to processors in a preemptive or non-preemptive manner.  ... 
doi:10.4018/ijcini.290308 fatcat:2hax7lts4vanbin4iqxy4cthwm

Executed-time Round Robin: EtRR an online non-clairvoyant scheduling on speed bounded processor with energy management

Pawan Singh, Berhane Wolde-Gabriel
2017 Journal of King Saud University: Computer and Information Sciences  
We adopt the conventional power function P = s a , where s and a > 1 are speed of a processor and a constant, respectively.  ...  In this paper, an online non-clairvoyant scheduling problem is studied to minimize total weighted flow time plus energy and a scheduling algorithm Executed-time Round Robin (EtRR) is proposed.  ...  Kumar for the linguistic review of our research paper.  ... 
doi:10.1016/j.jksuci.2016.03.002 fatcat:y223mbih6vccvkakfnrf2n6oze

Operational analysis of processor speed scaling

Kai Shen, Alex Zhang, Terence Kelly, Christopher Stewart
2008 Proceedings of the twentieth annual symposium on Parallelism in algorithms and architectures - SPAA '08  
By predicting the application-level performance impact of processing speed adjustments in parallel processors, including traditional SMPs and now increasingly ubiquitous multicore processors, our laws  ...  This brief announcement presents a pair of performance laws that bound the change in aggregate job queueing time that results when the processor speed changes in a parallel computing system.  ...  We thank Arif Merchant for detailed feedback on our work.  ... 
doi:10.1145/1378533.1378566 dblp:conf/spaa/ShenZKS08 fatcat:eitmsgbemjcy7hs4rv4z3efspq

Survey on Dynamic Resource Allocation Strategy in Cloud Computing Environment

N. Krishnaveni
2013 International Journal of Computer Applications Technology and Research  
This is an on demand service because it offers dynamic flexible resource allocation and guaranteed services in pay as-you-use manner to public.  ...  This paper provides detailed description of the dynamic resource allocation technique in cloud for cloud users and comparative study provides the clear detail about the different techniques.  ...  The algorithm proves,  Preemptive scheduling provides the maximum profit than the non-preemptive scheduling.  ... 
doi:10.7753/ijcatr0206.1019 fatcat:ekhlsdspxbdbhlwhbkampq5t4y
« Previous Showing results 1 — 15 out of 583 results