Filters








71,352 Hits in 3.5 sec

Minimizing total absolute deviation of job completion times: extensions to position-dependent processing times and parallel identical machines

G Mosheiov
2008 Journal of the Operational Research Society  
Thus, the total number of job allocations to machines is polynomial in n, and for each allo- cation, a simple matching of jobs to Kanet’s positional weights (requiring an effort of O(n log) time) needs  ...  The number of different (monotone) allocations of the number of jobs to machines was shown in the previous section to be bounded by (2n)”/(m — 1)!, which is polynomial in the number of jobs.  ... 
doi:10.1057/palgrave.jors.2602480 fatcat:76sdm2q3incz5kwbmvfprx5bje

Bandwidth-Guaranteed Resource Allocation and Scheduling for Parallel Jobs in Cloud Data Center

Zhen Li, Bin Chen, Xiaocheng Liu, Dandan Ning, Qihang Wei, Yiping Wang, Xiaogang Qiu
2018 Symmetry  
in the cloud, which may lead to QoS violation and inefficient utilization of resources when scheduling parallel jobs in the cloud.  ...  To obtain high job responsiveness performance, a bandwidth-reserved job backfilling strategy is designed when the requested TVC for current scheduled job cannot be allocated in the cloud.  ...  Virtual Cluster Model In this paper, we deal with resource allocation and scheduling for parallel jobs in the multi-tenant cloud data center.  ... 
doi:10.3390/sym10050134 fatcat:ixeskivygrax7ou4j6aqrmg2ji

Hybrid Performance-Oriented Scheduling of Moldable Jobs with QoS Demands in Multiclusters and Grids [chapter]

Ligang He, Stephen A. Jarvis, Daniel P. Spooner, Xinuo Chen, Graham R. Nudd
2004 Lecture Notes in Computer Science  
At the multicluster level, a scheduler (which we call MUSCLE) allocates parallel jobs with high packing potential to the same cluster; MUSCLE also takes the jobs' QoS requirements into account and employs  ...  Three metrics (over-deadline, makespan and idletime) are combined with weights to evaluate the scheduling performance. Two levels of performance optimisation are applied in the multicluster.  ...  After the composition table is constructed, MUSCLE searches the table for suitable parallel jobs to allocate to the available computer space in a cluster.  ... 
doi:10.1007/978-3-540-30208-7_34 fatcat:lbe3eq3f6rdftbwn3k2mj4mkba

Random allocation of jobs with weights and precedence

Soumen Chakrabarti
1996 Theoretical Computer Science  
We analyze random allocation applied to irregular and dynamic task-parallel programs such as branch and bound.  ...  The objective is to assign jobs to processors and to schedule them to minimize makespan. We show that random allocation achieves makespan close to a natural lower bound.  ...  The total work or weight in a job set J is denoted t(J) = x,EJ tj. The number ofjobs in J is denoted 1 J 1 or n (J). The average job weight is f(J) = t(J)/IJI.  ... 
doi:10.1016/0304-3975(96)00036-9 fatcat:5fv5hxmmhbasxgj24p7l2ai3oq

Job Allocation Strategies with User Run Time Estimates for Online Scheduling in Hierarchical Grids

Juan Manuel Ramírez-Alcaraz, Andrei Tchernykh, Ramin Yahyapour, Uwe Schwiegelshohn, Ariel Quezada-Pina, José Luis González-García, Adán Hirales-Carbajal
2011 Journal of Grid Computing  
We address non-preemptive nonclairvoyant online scheduling of parallel jobs on a Grid. We consider a Grid scheduling model with two stages.  ...  At the first stage, jobs are allocated to a suitable Grid site, while at the second stage, local scheduling is independently applied to each site.  ...  average job weighted waiting time MWWT_T min i=1..m g k =i t k w ·weight k n i , where weight k = size k , p k , w k MWWT_W MST 3 Allocates job j to the site with earliest start time for this job min  ... 
doi:10.1007/s10723-011-9179-y fatcat:iy2zo7wsrjepfo4l3r4ccpgpom

heSRPT: Parallel scheduling to minimize mean slowdown

Benjamin Berg, Rein Vesilo, Mor Harchol-Balter
2020 Performance evaluation (Print)  
When a job parallelizes across multiple servers it will complete more quickly, but jobs receive diminishing returns from being allocated additional servers.  ...  to each job at every moment in time.  ...  The SPAA/parallel community has studied the problem of allocating servers to jobs which follow arbitrary speedup functions in order to minimize flow time [24, 17, 18, 3] .  ... 
doi:10.1016/j.peva.2020.102147 fatcat:2bxrxq3mzrbmxbxvgsj76i6e3m

Hybrid performance-based workload management for multiclusters and grids

L. He, S.A. Jarvis, D.P. Spooner, X. Chen, G.R. Nudd
2004 IEE Proceedings - Software  
The results show that, compared with traditional distributed workload allocation policies, the comprehensive scheduling performance (in terms of over-deadline, makespan and idle-time) of parallel jobs  ...  The paper addresses the dynamic scheduling of parallel jobs with quality-of-service demands (soft-deadlines) in multiclusters and grids.  ...  MUSCLE then searches this table for suitable parallel jobs when allocating jobs into an available resource space in a cluster.  ... 
doi:10.1049/ip-sen:20041088 fatcat:n7yjuta2njcqlluote3ylrrg4u

Shapley Value for Parallel Machine Sequencing Situation without Initial Order

Shanshan Liu, Zhaohui Liu
2015 Mathematical Problems in Engineering  
For the situation with identical job processing time, we design a cost allocation rule which gives the Shapley value of the related sequencing game in polynomial time.  ...  For the game with identical job weight, we also present a polynomial time procedure to compute the Shapley value.  ...  In this paper, we study the parallel identical machine sequencing situation without initial schedule and design cost allocation rules for the special cases in which the jobs have identical processing time  ... 
doi:10.1155/2015/437403 fatcat:lnka5jmztrg3fj5bdikjrwl5v4

Jockey

Andrew D. Ferguson, Peter Bodik, Srikanth Kandula, Eric Boutin, Rodrigo Fonseca
2012 Proceedings of the 7th ACM european conference on Computer Systems - EuroSys '12  
• tokens to tasks Tokens are de-normalized weights in the scheduler and • guarantee a fixed slice of CPU and memory The Cosmos Environment Conclusion Users of data parallel clusters now demand  ...  "Oracle" allocation: Total allocation-hours deadline How Jockey Managed a Real Job in a Production Cluster 0% 20% 40% 60% 80% 100% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% 110%  ... 
doi:10.1145/2168836.2168847 dblp:conf/eurosys/FergusonBKBF12 fatcat:ssgedn654ng63g5wf6wxbqeqty

Job Scheduling Algorithms in Cloud Computing: A Survey

Himanshu Goel, Narendra Chamoli
2014 International Journal of Computer Applications  
The scheduler should order the jobs in a way where the balance between improving the quality of services and at the same time maintaining the efficiency and fairness among the jobs.  ...  An essential requirement in cloud computing is scheduling of current jobs to be executed within some given metrics or constraints.  ...  d) Priority-Based Consolidation of Parallel Workloads in the Cloud Xiao cheng Liu et.al [12] proposed an algorithm on improving resource utilization for data centers on which jobs execute parallel, particularly  ... 
doi:10.5120/16735-6981 fatcat:szcept6tsbfbhnvkkxhqpph7ja

Resource Matching in Non-dedicated Multicluster Environments [chapter]

Josep Lluis Lérida, Francesc Solsona, Francesc Giné, Jose Ramon García, Porfidio Hernández
2008 Lecture Notes in Computer Science  
In this paper, we present a new resource-matching model for MetaLoRaS, which is aimed at mitigating the degraded turnaround time of co-allocated jobs, caused by the contention on shared inter-cluster links  ...  Our preliminary performance results indicate that the linear programming model for on-line resource matching is efficient in speed and accuracy and can be successfully applied to co-allocate jobs across  ...  Co-allocation of parallel jobs is considered in this paper, as is minimizing their execution time, this being the desired goal.  ... 
doi:10.1007/978-3-540-92859-1_16 fatcat:byuzoexrsrc65mdm3kgha4gbiu

A New Fuzzy Algorithm for Global Job Scheduling in Multiclusters and Grids

Hamed Vahdat-Nejad, Reza Monsefi, Mahmoud Naghibzadeh
2007 2007 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications  
We assume that each job is composed of several parallel tasks, which can be executed concurrently.  ...  In this paper, we propose a fuzzy algorithm for global job scheduling in multiclusters and grids on the basis of layered task scheduling model.  ...  Figure 6 shows parallel jobs completion time for scenario I. In Figure 7 parallel jobs completion time are shown for scenario II.  ... 
doi:10.1109/cimsa.2007.4362538 fatcat:czehy3fxsbccnjbbxmj4uqujp4

Multisite co-allocation algorithms for computational grid

Weizhe Zhang, A.M.K. Cheng, Mingzeng Hu
2006 Proceedings 20th IEEE International Parallel & Distributed Processing Symposium  
Efficient multisite job scheduling facilitates the cooperation of multi-domain massively parallel processor systems in a computing grid environment.  ...  However, co-allocation, heterogeneity, adaptability, and scalability emerge as tough challenges for the design of multisite job scheduling models and algorithms.  ...  Parallel Job scheduling is a complex problem, even in a single parallel computer.  ... 
doi:10.1109/ipdps.2006.1639652 dblp:conf/ipps/ZhangCH06 fatcat:rl6mnayvxve4tayhmkj3hfmtea

Memory usage in the LANL CM-5 workload [chapter]

Dror G. Feitelson
1997 Lecture Notes in Computer Science  
It is generally agreed that memory requirements should be taken into account in the scheduling of parallel jobs.  ...  To rectify this problem, we present an analysis of memory usage by a production workload on a large parallel machine, the 1024-node CM-5 installed at Los Alamos National Lab.  ...  Acknowledgement Many thanks to Curt Canada of Los Alamos National Lab for providing the raw data used in this study.  ... 
doi:10.1007/3-540-63574-2_17 fatcat:gbas7j6a6zd2jo3blliwsa4l4y

Flexible flow shop scheduling with stochastic processing times: A decomposition-based approach

S.H. Choi, K. Wang
2012 Computers & industrial engineering  
In the proposed DBA, a neighbouring K-means clustering algorithm is developed to firstly group the machines of an FFS into an appropriate number of machine clusters, based on their stochastic nature.  ...  Two optimal back propagation networks (BPN), corresponding to the scenarios of simultaneous and non-simultaneous job arrivals, are then selectively adopted to assign either SPT or GA to each machine cluster  ...  Re-allocate the parallel machines of each stage to the machine cluster centres by the machine allocation algorithm; Re-compute the new machine cluster centres; End Compute the weighted CVI of decomposing  ... 
doi:10.1016/j.cie.2012.04.001 fatcat:el6bzyuqszhz3ocbhbvsa42i2i
« Previous Showing results 1 — 15 out of 71,352 results