检索结果-内蒙古大学图书馆

International Science and Technology Conference (Modern Networking Technologies) (MoNeTeC)

作者： Yihao Zhao Xuanzhe Liu Xin Jin School of Computer Science Peking University Beijing China

ISBN: (数字)9798350369007

ISBN: (纸本)9798350369014

Recently, there is a resurgence of packet scheduling ideas in the form of communication scheduling in the application layer for distributed training. Given recent results on potentially huge improvements, it is critical to properly interpret these results and understand how far we can *** take a first-principles approach to analyzing and understanding the role of communication scheduling in distributed training. We formulate a mathematical model to represent the computation and communication pattern, and prove that the upper bound of improvements with communication scheduling is 3× for widely-used distributed training *** importantly, we establish a quantitative relationship between the benefit of communication scheduling and the computation-to-communication ratio. While the exact curve for each model varies, we demonstrate that all models have the same shape—concave. Surprisingly, contrary to the common belief, for varying models and hardware configurations, we find that communication scheduling can offer only limited improvements in addition to overlapping. Our results raise the question about the necessity of overloading parameter transmission with application-layer semantics. Additionally, we provide both theoretical analysis and empirical studies to show that most improvements can be obtained with well-understood network-layer methods without having to obtain the application-layer knowledge.

关键词： Training Knowledge engineering Tensors Upper bound Processor scheduling scheduling algorithms Computational modeling Semantics Mathematical models scheduling

来源：评论

学校读者我要写书评

暂无评论

GAIPPTSC: An Efficient Container Tasks Orchestration and scheduling Algorithm

GAIPPTSC: An Efficient Container Tasks Orchestration and Sch...

引用

Information Science, Parallel and Distributed Systems (ISPDS), International Conference on

作者： Guofeng Zheng Bo Jiang Jinhui Xie Chuxuan Shi The 32nd Research Institute of China Electronics Technology Group Corporation Shanghai China

ISBN: (数字)9798350352719

ISBN: (纸本)9798350352726

Containers are a very promising virtualization technology because of their lightweight, portable, and scalable advantages. In the case of mixed integer nolinear programming (MINP) problems such as orchestration and scheduling for container tasks, it is particularly important to combine heuristic methods to solve the problem. In order to solve the problem quickly and improve from a number of performance indicators, this paper firstly establishes a mixed integer nonlinear model for container tasks orchestration and scheduling scenarios, and then proposes a GAIPPTSC algorithm to obtain advantageous solutions in various indicators. In the experimental results, in terms of load balancing, the GAIPPTSC algorithm is 4.2% of the average of the other algorithms. Makespan also shortened by an average of 24.7%. In terms of energy consumption, it was reduced by an average of 53.6%. Overall communication overhead is also minimized. Correspondingly, the overall time cost of the algorithm is also increased by approximately 5 times, which is acceptable in the absolute time dimension. Therefore, the experiment proves the efficiency of the GAIPPTSC algorithm.

关键词： Measurement scheduling algorithms Containers Programming Approximation algorithms Load management scheduling

来源：评论

学校读者我要写书评

暂无评论

Efficient Probabilistic Workflow scheduling for IaaS Clouds

arXiv

引用

arXiv 2024年

作者： Russo, Gabriele Russo Marotta, Romolo Cordari, Flavio Quaglia, Francesco Cardellini, Valeria Di Sanzo, Pierangelo The Department of Civil and Information Engineering University of Rome Tor Vergata Italy Sapienza University of Rome Italy Roma Tre University Italy

The flexibility and the variety of computing resources offered by the cloud make it particularly attractive for executing user workloads. However, IaaS cloud environments pose non-trivial challenges in the case of workflow scheduling under deadlines and monetary cost constraints. Indeed, given the typical uncertain performance behavior of cloud resources, scheduling algorithms that assume deterministic execution times may fail, thus requiring probabilistic approaches. However, existing probabilistic algorithms are computationally expensive, mainly due to the greater complexity of the workflow scheduling problem in its probabilistic form, and they hardily scale with the size of the problem instance. In this article, we propose EPOSS, a novel workflow scheduling algorithm for IaaS cloud environments based on a probabilistic formulation. Our solution blends together the low execution latency of state-of-the-art scheduling algorithms designed for the case of deterministic execution times and the capability to enforce probabilistic constraints. Designed with computational efficiency in mind, EPOSS achieves one to two orders lower execution times in comparison with existing probabilistic schedulers. Furthermore, it ensures good scaling with respect to workflow size and number of heterogeneous virtual machine types offered by the IaaS cloud environment. We evaluated the benefits of our algorithm via an experimental comparison over a variety of workloads and characteristics of IaaS cloud environments. Copyright © 2024, The Authors. All rights reserved.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Hybrid Cloud Workflow scheduling Algorithm Based on the Improved Wild Horse Optimization Algorithm

Hybrid Cloud Workflow Scheduling Algorithm Based on the Impr...

引用

International Conference on Computer Engineering and Applications (ICCEA)

作者： Xiaobo Chen Lupeng Qiu Tianzhe Li Yingkai Fan Naqin Zhou Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China

ISBN: (数字)9798350386776

ISBN: (纸本)9798350386783

As a cloud computing model that integrates the advantages of public and private clouds, the hybrid cloud adapts to changing application requirements, allowing users to flexibly lease public cloud resources to expand computing capabilities, effectively alleviating the problem of resource scarcity in private clouds during peak periods. However, existing hybrid cloud workflow scheduling inadequately considers the data privacy and security risks associated with cross-platform data transmission while meeting deadlines and optimizing costs. Therefore, this paper proposes a hybrid cloud workflow scheduling algorithm (HCWSA-IWHO) based on an improved wild horse optimization algorithm. The algorithm combines intelligent optimization algorithms and heuristic algorithms, divided into pre-scheduling and dynamic scheduling stages. In the pre-scheduling stage, by using an adaptive pairing range and selection method for pairing objects, the algorithm ensures the diversity of initial population individuals and the convergence of search space in later stages. In the dynamic scheduling stage, tasks are classified, and tasks that need to be reallocated in the public cloud are identified. When reallocating virtual machines for each task, virtual machines that meet performance requirements and minimize costs are selected to achieve cost minimization. The HCWSA-IWHO algorithm is compared with the PSSA and FWAPS-VI algorithms. Experimental results demonstrate that the HCWSA-IWHO not only meets deadline requirements but also outperforms PSSA and FWAPS-VI in reducing workflow execution costs.

关键词： Cloud computing Data privacy Costs scheduling algorithms Heuristic algorithms Dynamic scheduling Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation and Route Optimization of Shipping Vessels Based on Intelligent scheduling Algorithm and Data Analysis

Resource Allocation and Route Optimization of Shipping Vesse...

引用

Control, Electronics and Computer Technology (ICCECT), IEEE International Conference on

作者： Yumei Zhang Department of Shipping Management Shanghai Maritime Academy Shanghai China

ISBN: (数字)9798350380958

ISBN: (纸本)9798350380965

In the current era of globalization, import and export trade is closely related to shipping, and routes across major rivers and even oceans are constantly being developed to transport the materials needed by different countries and regions. These shipping transportation not only meet the needs of various places, but also bring practitioners a lot of income, but in order to further improve the efficiency of transportation, reasonable allocation of ship resources and transportation routes are the main research direction. Therefore, in order to meet this demand, this paper proposes to use intelligent scheduling model to solve scheduling and path planning problems, and the model needs to use NSGA-II (Non-dominated Sorting Genetic Algorithm II, a multi-objective optimization algorithm) to carry out. Finally, through the comparative experiment of transportation time, the average transportation time of intelligent scheduling system is 11.89h, while the average transportation time of basic scheduling system is as high as 15.10h. By comparing with the basic scheduling system, this paper finds that the scheduling system based on intelligent scheduling algorithm can significantly reduce the transportation time and improve the transportation efficiency.

关键词： scheduling algorithms Oceans Transportation scheduling Path planning Rivers Resource management

来源：评论

学校读者我要写书评

暂无评论

Online Flexible Busy Time scheduling on Heterogeneous Machines

arXiv

引用

arXiv 2024年

作者： Calinescu, Gruia Davies, Sami Khuller, Samir Zhang, Shirley Department of Computer Science Illinois Institute of Technology Northwestern University United States Department of EECS Simons Institute for the Theory of Computing UC Berkeley United States Department of Computer Science Northwestern University United States Paulson School of Engineering and Applied Sciences Harvard University United States

We study the online busy time scheduling model on heterogeneous machines. In our setting, unit-length jobs arrive online with a deadline that is known to the algorithm at the job's arrival time. An algorithm has access to machines, each with different associated capacities and costs. The goal is to schedule jobs on machines before their deadline, so that the total cost incurred by the scheduling algorithm is minimized. Relatively little is known about online busy time scheduling when machines are heterogeneous (i.e., have different costs and capacities), despite this being the most practical model for clients using cloud computing services. We make significant progress in understanding this model by designing an 8-competitive algorithm for the problem on unit-length jobs, and providing a lower bound on the competitive ratio of 2. We further prove that our lower bound is tight in the natural setting when jobs have agreeable deadlines. © 2024, CC BY.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimizing Memory scheduling for Efficient Image Patch Inference on Resource-Constrained Devices

Optimizing Memory Scheduling for Efficient Image Patch Infer...

引用

International Conference on Information and Communication Technology Convergence (ICTC)

作者： Seungtae Hong Gunju Park Jeong-Si Kim Intelligent Device & Simulation Research Section Electronics and Telecommunications Research Institute and University of Science and Technology Daejeon Korea Intelligent Device & Simulation Research Section Electronics and Telecommunications Research Institute Daejeon Korea

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

In this paper, we propose an optimized memory scheduling technique for efficient image patch inference on resource-constrained devices. Our approach addresses the inefficiencies in the existing MCUNet v2's memory scheduling algorithm, which maintains buffer tensors longer than necessary, leading to suboptimal memory usage. We designed an algorithm to dynamically adjust memory blocks and retain tensors only for the necessary duration during patch inference. This method significantly reduces the memory footprint, particularly for the maximum input/output tensor. The results demonstrate substantial improvements in memory utilization, enabling more complex models to be deployed on resource-constrained devices. Our findings highlight the potential of this scheduling technique to enhance the feasibility and performance of deep learning applications on MCUs.

关键词： Deep learning Performance evaluation Tensors scheduling algorithms Memory management Inference algorithms Information and communication technology Resource management Kernel Optimization

来源：评论

学校读者我要写书评

暂无评论

Q-scheduler: Optimize Job scheduling in Hadoop with Reinforcement Learning

Q-scheduler: Optimize Job Scheduling in Hadoop with Reinforc...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Yiqing Liu Li Pan Shijun Liu School of Software Shandong University Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Hadoop, as an open-source implementation of the MapReduce paradigm, is increasingly being used in both industry and academia for large-scale data processing. Yarn, one of the core components of the second-generation Hadoop, manages cluster resources and job scheduling. Minimizing the total completion time of a set of MapReduce jobs is a point worth exploring in terms of Yarn’s performance. Hadoop’s default schedulers, including first-in-first-out (FIFO), Fair, and Capacity, do not consider the characteristics and preferences of job resource demand, resulting in insufficient resource utilization. Therefore, in this paper, a new job scheduler named Q-scheduler is proposed. It uses reinforcement learning (RL) to accumulate scheduling experience autonomously based on the Fair scheduler. Specifically, the proposed scheduler consists of a Classifier and a Decider. The Classifier classifies jobs through similarity measurement, and the Decider, as an agent with a Q-Table, considers the execution order of different job classes and updates the state-action values of the Q-Table to learn optimal scheduling. The experimental results show that Q-scheduler can reduce the total completion time of the job set and improve resource utilization.

关键词： Training Industries Job shop scheduling scheduling algorithms Federated learning Optimal scheduling Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hipernetch: High-Performance FPGA Network Switch

引用

ACM TRANSACTIONS ON RECONFIGURABLE TECHNOLOGY AND SYSTEMS 2022年第1期15卷 1–31页

作者： Papaphilippou, Philippos Meng, Jiuxi Gebara, Nadeen Luk, Wayne Imperial Coll Dept Comp London England

We present Hipernetch, a novel FPGA-based design for performing high-bandwidth network switching. FPGAs have recently become more popular in data centers due to their promising capabilities for a wide range of applications. With the recent surge in transceiver bandwidth, they could further benefit the implementation and refinement of network switches used in data centers. Hipernetch replaces the crossbar with a "combined parallel round-robin arbiter". Unlike a crossbar, the combined parallel round-robin arbiter is easy to pipeline, and does not require centralised iterative scheduling algorithms that try to fit too many steps in a single or a few FPGA cycles. The result is a network switch implementation on FPGAs operating at a high frequency and with a low port-to-port latency. Our proposed Hipernetch architecture additionally provides a competitive switching performance approaching output-queued crossbar switches. Our implemented Hipernetch designs exhibit a throughput that exceeds 100 Gbps per port for switches of up to 16 ports, reaching an aggregate throughput of around 1.7 Tbps.

关键词： Network switch FPGA round-robin arbiter scheduling algorithms sorting network applications stream processing

来源：评论

学校读者我要写书评

暂无评论

Energy-aware Coflow scheduling for Sustainable Workload Management 17

Energy-aware Coflow Scheduling for Sustainable Workload Mana...

引用

17th International Conference on Network and Service Management (CNSM) - Smart Management for Future Networks and Services

作者： Ahmad, Sadiya Esposito, Flavio Coronado, Estefanla St Louis Univ Dept Comp Sci St Louis MO 63103 USA I2CAT Fdn Barcelona Spain

ISBN: (纸本)9783903176362

Handling High-Performance Computing (HPC) workflows often requires the orchestration of a collection of parallel flows. Traditional techniques to optimize flow-level metrics do not perform well in optimizing such collections because the network is usually agnostic to application requirements. A Coflow is a recently proposed abstraction that created new opportunities in network scheduling for datacenter networks. However, recent work on coflow scheduling has focused on merely two objectives: decreasing communication time of data-intensive jobs and guaranteeing predictable communication time. In this paper, we take a step further and propose some initial results towards the design of heuristics that optimize also the energy consumption of a data center that hosts HPC jobs. To this aim, we built and released an energy-aware coflow scheduling simulator to the community that helps analyze the tradeoff between energy efficiency and coflow completion time. We also propose two scheduling algorithms that consider coflow completion time, CPU utilization, and energy consumption efficiency. Our initial results using the simulator clarify how each policy should be tuned to the application needs and the computational resources available.

关键词： Measurement Economics Energy consumption Data centers scheduling algorithms Turning Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：