2014 International Conference on Parallel, Distributed and Grid Computing最新文献_第7页

Algorithmic approach for applying load balancing during task migration in multi-core system 多核系统任务迁移过程中应用负载均衡的算法方法

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030710

Suchi Johari, Arvind Kumar

{"title":"Algorithmic approach for applying load balancing during task migration in multi-core system","authors":"Suchi Johari, Arvind Kumar","doi":"10.1109/PDGC.2014.7030710","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030710","url":null,"abstract":"As day by day multi core systems are increasing researchers are looking for various techniques to reduce power consumption and improve performance. In multi-core processors several cores are placed on the single grid and multiple tasks are distributed over these cores for processing [1]. Each core is responsible for the processing of the task allocated to it. This may lead to problems like load balancing on different cores, as various tasks are allocated to the single core. Now if there is a situation that a single core or a cluster of cores have large number of task to be executed while some of the cores remain free then there is a need of a technique called task migration. Task migration is not similar to load balancing in any aspect. In task migration only the migration of the task from overloaded core to other core is done but till now maintaining load balancing during task migration was an issue[2]. But if the load balancing is done at the time of the task migration then it will improve performance about 99%. This paper emphasis on various algorithms for load balancing during task migration in a multi-core system, so that number of tasks on different cores are distributed fairly. This paper also discusses the algorithms for deciding which task is to be migrated. With the help of these algorithms, performance and response time is improved to a great extent.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125199501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Performance improvement of BWA MEM algorithm using data-parallel with concurrent parallelization 基于数据并行和并发并行的BWA MEM算法性能改进

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030780

N. Kathiresan, M. Temanni, Rashid J. Al-Ali

{"title":"Performance improvement of BWA MEM algorithm using data-parallel with concurrent parallelization","authors":"N. Kathiresan, M. Temanni, Rashid J. Al-Ali","doi":"10.1109/PDGC.2014.7030780","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030780","url":null,"abstract":"Burrows-Wheeler Transform (BWT) is the widely used data compression technique in the next-generation sequencing (NGS) analysis. Due to the advancement in the NGS technology, the genome data size was increased rapidly and these higher volumes of genome data need to be processed by empirical parallelism. Generally, these NGS data will be processed by traditional parallel processing approaches like (i) thread parallelization (ii) Data parallelization and (iii) Concurrent parallelization, which are their own performance bottlenecks in, thread scalability, scattering/gathering of data and memory bandwidth limitations respectively. To eliminate these drawbacks, we introduced the hybrid parallelization approach called “data-parallel with concurrent parallelization” to process our genome alignment. We used BWA MEM algorithm for aligning human genome sequence, which are dominated by huge memory intensive operations and the performance is limited due to cache/TLB misses. To eliminate the cache/TLB miss, the genome data is partitioned into multiple pieces (i.e., reducing the read size) using data parallelization and concurrently processing these multiple pieces of genome data within the same cache/memory hierarchy. Hence, the performance of proposed data-parallel with concurrent parallelization is 45% better than traditional parallelization approaches. Additionally, we provided proof of concept to process higher volume of genome data using BWA MEM algorithm on the high-end desktop machines.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126602235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 17

Analysis of resource mapping strategies for fault tolerant scheduling on grid computing 网格计算容错调度的资源映射策略分析

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030778

Shafi Jindal, R. Bansal, S. Bansal

{"title":"Analysis of resource mapping strategies for fault tolerant scheduling on grid computing","authors":"Shafi Jindal, R. Bansal, S. Bansal","doi":"10.1109/PDGC.2014.7030778","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030778","url":null,"abstract":"Grid environment has significant challenges due to failures encountered during job execution. Grid infrastructure must have mechanisms to deal with faults while also providing efficient and reliable services to its end users. Therefore fault tolerance in such an environment could not be ignored. In this paper, two strategies such as Maximum Mapping Strategy (MMS) and Exact Mapping Strategy (EMS) are proposed for fault tolerant job scheduling in grid. Whenever the scheduler has jobs to schedule, MMS and EMS selects the resources based on the maximum suitable mapping and exact mapping of job requirement value with the resource capable value respectively. If failure occurs during execution, re-schedules the jobs using the last saved state according to the failure rate of the resources. EMS approach is effective in the sense that all resources are busy at the same time so that resources are utilized in better way and Make-span i.e. the time taken by all jobs to be finished processing is also reduced. Failure rate is reduces in EMS because failures due to speed and memory and bandwidth is less as load is distributed almost equally among resources compared to MMS.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116836655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

VM migration auction: Business oriented federation of cloud providers for scaling of application services VM迁移拍卖:面向业务的云提供商联合，用于扩展应用程序服务

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030741

S. Majhi, P. Bera

{"title":"VM migration auction: Business oriented federation of cloud providers for scaling of application services","authors":"S. Majhi, P. Bera","doi":"10.1109/PDGC.2014.7030741","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030741","url":null,"abstract":"One of the key indicators of leveraging Cloud Computing is the penetration of e-business among Cloud Service Providers(CSP). The cloud computing applications are being developed across various domains to enable easy and efficient access to the data and services remotely. There is a potential for CSPs in applying e-business technologies, especially in the migration process between virtual machines (VM) running in different hosts. It is to enable efficient computing, resource sharing and to provide a real time response. There is a need to integrate an auction (bidding) in the VM migration process by applying new business models in the cloud computing marketplace to ensure competitiveness among CSPs. This paper describes an effort to establish a novel bidding process for the VM migration process in Cloud environment for e-business. The Internet-based auction process has been developed by considering English and Dutch auction. Various components for VM auction (actors, relations, VM, and business model) are presented. The suitable architecture in the VM auction service and the required tools are described. The IDEF0 model has been used for the central functionality of the broker service. In this proposed approach, the objective is to make independent CSPs function in a co-operative manner to provide uninterrupted service to the users on their interest and preference.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128591420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

A log data analytics based scheduling in open source cloud software 开源云软件中基于调度的日志数据分析

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030777

V. Srikrishnan, E. Sivasankar, R. Pitchiah

引用次数: 1

Model driven reverse engineering of user interface — A comparative study of static and dynamic model generation tools 模型驱动的用户界面逆向工程-静态和动态模型生成工具的比较研究

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030754

Smita Agarwal, A. Aggarwal

引用次数: 2

CT image noise reduction based on adaptive wiener filtering with Wavelet packet thresholding 基于小波包阈值自适应维纳滤波的CT图像降噪

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030722

M. Diwakar, M. Kumar

引用次数: 18

Software rejuvenation in cloud systems using neural networks 使用神经网络的云系统软件复兴

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030747

Ch. Sudhakar, Ishan Shah, T. Ramesh

引用次数: 10

Parallel syntax analysis on multi-core machines 多核机器上的并行语法分析

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030743

Amit Barve, B. K. Joshi

引用次数: 1

Understanding source-to-source transformations for frequent porting of applications on changing cloud architectures 了解在不断变化的云架构上频繁移植应用程序的源到源转换

2014 International Conference on Parallel, Distributed and Grid Computing Pub Date : 2014-12-01 DOI: 10.1109/PDGC.2014.7030769

Mohsin Khan, N. Priyanka, W. Ahmed, N. Radhika, M. Pavithra, K. Parimala

{"title":"Understanding source-to-source transformations for frequent porting of applications on changing cloud architectures","authors":"Mohsin Khan, N. Priyanka, W. Ahmed, N. Radhika, M. Pavithra, K. Parimala","doi":"10.1109/PDGC.2014.7030769","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030769","url":null,"abstract":"Writing code for heterogeneous architectures with processors and accelerators from multiple vendors from scratch or translating existing serial code, a lot of effort and investment will be required from the application developer. This problem will become more prominent when HPC applications are moved into the Cloud as Cloud providers frequently update their architectures to keep with market trends. In these scenarios, automatic parallelization tools will definitely have an important role to play. An important constituent of these tools would be the ability to perform pertinent domain decomposition of the serial code to maximize utilization of the available computational elements. One of the first steps in this direction is to understand the role of the number and type of computational element in a heterogeneous architecture to the overall performance of an application. This paper presents observations made on architectures with different types and number of computational elements using two case studies on five different architectures with different types and number of computational elements. Results show that the perceived speedup and actual speedup are not related.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"240 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116253836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2