Filters








286 Hits in 5.5 sec

Average-Case Performance Analysis of Online Non-clairvoyant Scheduling of Parallel Tasks with Precedence Constraints

Keqin Li
2007 2007 IEEE International Parallel and Distributed Processing Symposium  
We evaluate the average-case performance of three approximation algorithms for online non-clairvoyant scheduling of parallel tasks with precedence constraints.  ...  We show that for a class of wide task graphs, when task sizes are uniformly distributed in the range [1..C], the online non-clairvoyant scheduling algorithm LL-SIMPLE has an asymptotic average-case performance  ...  In this paper, we analyze the average-case performance of algorithm LL-SIMPLE for online non-clairvoyant scheduling of parallel tasks with precedence constraints.  ... 
doi:10.1109/ipdps.2007.370579 dblp:conf/ipps/Li07a fatcat:vhpx22jzi5cqbdbmwf5gngmola

Average-Case Performance Analysis Of Online Non-Clairvoyant Scheduling Of Parallel Tasks With Precedence Constraints

K. Li
2007 Computer journal  
We evaluate the average-case performance of three approximation algorithms for online non-clairvoyant scheduling of parallel tasks with precedence constraints.  ...  We show that for a class of wide task graphs, when task sizes are uniformly distributed in the range [1..C], the online non-clairvoyant scheduling algorithm LL-SIMPLE has an asymptotic average-case performance  ...  In this paper, we analyze the average-case performance of algorithm LL-SIMPLE for online non-clairvoyant scheduling of parallel tasks with precedence constraints.  ... 
doi:10.1093/comjnl/bxm059 fatcat:ok4go7swqrhttfu2faqg7xzthq

Non-clairvoyant scheduling of independent parallel tasks on single and multiple multicore processors

Keqin Li
2018 Journal of Parallel and Distributed Computing  
For multiple multicore processors, we also derive an asymptotic average-case performance bound for a non-clairvoyant online scheduling algorithm called random task first (RTF).  ...  performance bound for online scheduling on multiple multicore processors. a b s t r a c t We investigate the problem of non-clairvoyant scheduling of independent parallel tasks on single and multiple  ...  Average-case analysis In this section, we analyze the asymptotic average-case performance of algorithm RTF for non-clairvoyant online scheduling of independent parallel tasks on multiple multicore processors  ... 
doi:10.1016/j.jpdc.2018.06.001 fatcat:rmpdmd5fzzgf7a4eacmq2ae6la

Cloud scheduling with setup cost

Yossi Azar, Naama Ben-Aroya, Nikhil R. Devanur, Navendu Jain
2013 Proceedings of the 25th ACM symposium on Parallelism in algorithms and architectures - SPAA '13  
We study both the clairvoyant case, where the duration of each task is known upon its arrival, and the more realistic non-clairvoyant case.  ...  In this paper, we investigate the problem of online task scheduling of jobs such as MapReduce jobs, Monte Carlo simulations and generating search index from web documents, on cloud computing infrastructures  ...  In [13] , Schwiegelshohn studied the case of non-clairvoyant scheduling on massively parallel identical processors.  ... 
doi:10.1145/2486159.2486195 dblp:conf/spaa/AzarBDJ13 fatcat:rfeg6o2ekjh5jkboruewv7nrhq

Efficient Coflow Scheduling Without Prior Knowledge

Mosharaf Chowdhury, Ion Stoica
2015 Computer communication review  
By performing prioritization across queues and by scheduling coflows in the FIFO order within each queue, Aalo's non-clairvoyant scheduler reduces coflow completion times while guaranteeing starvation  ...  Inter-coflow scheduling improves application-level communication performance in data-parallel clusters.  ...  Acknowledgments We thank Yuan Zhong, Ali Ghodsi, Shivaram Venkataraman, CCN members, our shepherd Hitesh Ballani, and the anonymous reviewers of NSDI'15 and SIGCOMM'15 for useful feedback, and Kay Ousterhout  ... 
doi:10.1145/2829988.2787480 fatcat:6dr2eomozfgzfcux6yc2p2j5ze

Efficient Coflow Scheduling Without Prior Knowledge

Mosharaf Chowdhury, Ion Stoica
2015 Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication - SIGCOMM '15  
By performing prioritization across queues and by scheduling coflows in the FIFO order within each queue, Aalo's non-clairvoyant scheduler reduces coflow completion times while guaranteeing starvation  ...  Inter-coflow scheduling improves application-level communication performance in data-parallel clusters.  ...  Acknowledgments We thank Yuan Zhong, Ali Ghodsi, Shivaram Venkataraman, CCN members, our shepherd Hitesh Ballani, and the anonymous reviewers of NSDI'15 and SIGCOMM'15 for useful feedback, and Kay Ousterhout  ... 
doi:10.1145/2785956.2787480 dblp:conf/sigcomm/ChowdhuryS15 fatcat:mcejrhhldzbujjwtgnskmwtvem

Competitive Two-Level Adaptive Scheduling Using Resource Augmentation [chapter]

Hongyang Sun, Yangjie Cao, Wen-Jing Hsu
2009 Lecture Notes in Computer Science  
We focus on non-clairvoyant scheduling schemes that adaptively reallocate processors based on periodic feedbacks from the individual jobs.  ...  Since it is known that no deterministic non-clairvoyant algorithm is competitive for this problem, we focus on resource augmentation analysis, and show that two adaptive algorithms, Agdeq and Abgdeq, achieve  ...  Acknowledgments The first author would like to thank Yuxiong He for many discussions and much help on two-level adaptive scheduling.  ... 
doi:10.1007/978-3-642-04633-9_12 fatcat:i6hmcc6raze2rlqgy25g563kce

Minimizing Maximum Flowtime of Jobs with Arbitrary Parallelizability [chapter]

Kirk Pruhs, Julien Robert, Nicolas Schabanel
2011 Lecture Notes in Computer Science  
We consider the problem of nonclairvoyantly scheduling jobs, which arrive over time and have varying sizes and degrees of parallelizability, with the objective of minimizing the maximum flow.  ...  More specifically we show that the competitive ratio of every deterministic nonclairvoyant algorithm is high, namely Ω( √ n).  ...  Non-clairvoyant scheduling with precedence constraints.  ... 
doi:10.1007/978-3-642-18318-8_21 fatcat:ke6lrfv5wvc2jaahgkzbav2fay

A Case for Sampling Based Learning Techniques in Coflow Scheduling [article]

Akshay Jajoo, Y. Charlie Hu, Xiaojun Lin
2022 arXiv   pre-print
State-of-the-art online coflow schedulers in essence approximate the classic Shortest-Job-First (SJF) scheduling by learning the coflow size online.  ...  Philae pre-schedules sampled flows of each coflow and uses their sizes to estimate the average flow size of the coflow.  ...  Problem statement Our goal is to develop an efficient non-clairvoyant coflow scheduler that optimizes the communication performance, in particular the average CCT, of data-intensive applications without  ... 
arXiv:2108.11255v3 fatcat:lknfxjcd7zaqpkihaiog2wrwti

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.  ...  They provided an algorithm for online clairvoyant makespan scheduling of parallel rigid jobs in a Grid with the competitive factor 2e + 1.  ... 
doi:10.1007/s10723-011-9179-y fatcat:iy2zo7wsrjepfo4l3r4ccpgpom

On-line hierarchical job scheduling on grids with admissible allocation

Andrei Tchernykh, Uwe Schwiegelshohn, Ramin Yahyapour, Nikolai Kuzjurin
2010 Journal of Scheduling  
In this paper, we address non-preemptive online scheduling of parallel jobs on a Grid. Our Grid consists of a large number of identical processors that are divided into several machines.  ...  At the first stage, jobs are allocated to a suitable machine, while at the second stage, local scheduling is independently applied to each machine.  ...  Online scheduling of parallel jobs in a grid In this section we provide a competitive analysis for two heuristics.  ... 
doi:10.1007/s10951-010-0169-x fatcat:wk5faugu6zfjnfa23wovnacsau

Permutation Predictions for Non-Clairvoyant Scheduling [article]

Alexander Lindermayr, Nicole Megow
2022 arXiv   pre-print
In non-clairvoyant scheduling, the task is to find an online strategy for scheduling jobs with a priori unknown processing requirements with the objective to minimize the total (weighted) completion time  ...  than parts of the unknown input.  ...  Identical parallel machines Consider non-clairvoyant scheduling of weighted jobs with release dates on 𝑚 identical parallel machines, P|𝑟 𝑗 , 𝑝𝑚𝑡𝑛| 𝑤 𝑗 𝐶 𝑗 .  ... 
arXiv:2202.10199v2 fatcat:kt7pctrpmreqjb7qews6tvpuhi

Mixed Criticality on Multicore / Manycore Platforms (Dagstuhl Seminar 17131)

Liliana Cucu-Grosjean, Robert Davis, Sanjoy K. Baruah, Zoë Stephenson, Marc Herbstritt
2017 Dagstuhl Reports  
This report provides an overview of the discussions, the program and the outcomes of the second Dagstuhl Seminar on Mixed Criticality on Multicore/Manycore Platforms.  ...  The ideas in this short paper were presented and discussed in an ad-hoc working group comprising Liliana Cucu-Grosjean, Adriana Gogonel, Cristian Maxim, Iain Bate, Philipa Conway, Zoe Stephenson, Alan  ...  analysis of non-preemptive tasks (or network messages as in CAN), in the literature on self-suspensions, in the analysis of multiprocessor real-time scheduling with affinity constraints, and in the worst-case  ... 
doi:10.4230/dagrep.7.3.70 dblp:journals/dagstuhl-reports/Cucu-GrosjeanDB17 fatcat:yfevcj3azre6rdce5dcdsacnz4

Scalable Hierarchical Scheduling for Malleable Parallel Jobs on Multiprocessor-based Systems [article]

Yangjie Cao, Hongyang Sun, Depei Qian, Weiguo Wu
2014 arXiv   pre-print
We propose a hierarchical scheduling algorithm, named AC-DS, that consists of a feedback-driven adaptive scheduler, a desire aggregation scheme and an efficient resource allocation policy.  ...  The proliferation of multi-core and multiprocessor-based computer systems has led to explosive development of parallel applications and hence the need for efficient schedulers.  ...  To formalize the scheduling problem in our study, we adopt the online and non-clairvoyant scheduling model, which requires the algorithm to operate in an online manner, that is, to make irrevocable scheduling  ... 
arXiv:1412.4213v1 fatcat:y34ra3wokzcztahlrjqhuxjfia

Adaptive Scheduling of Parallel Jobs on Functionally Heterogeneous Resources

Yuxiong He, Hongyang Sun, Wen-Jing Hsu
2007 Proceedings of the International Conference on Parallel Processing  
For the special case of K = 1, i.e., scheduling on homogeneous resources, the best existing mean response time bound for online non-clairvoyant algorithm is 2 + √ 3 ≈ 3.73 proved by Edmonds et al. in STOC  ...  This competitive ratio is provably the best possible for any non-clairvoyant deterministic algorithms for K-resource scheduling.  ...  For makespan, Shmoys, Wein and Williamson [32] proved lower bounds of online non-clairvoyant scheduling.  ... 
doi:10.1109/icpp.2007.12 dblp:conf/icpp/HeSH07 fatcat:he7qkdlvpndklps47w7nzbkobu
« Previous Showing results 1 — 15 out of 286 results