Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000最新文献

筛选
英文 中文
Parallel computing environments and methods 并行计算环境和方法
Ghassan Fadlallah, M. Lavoie, L. Dessaint
{"title":"Parallel computing environments and methods","authors":"Ghassan Fadlallah, M. Lavoie, L. Dessaint","doi":"10.1109/PCEE.2000.873591","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873591","url":null,"abstract":"Recent advances in high-speed networks, rapid improvements in microprocessor design, and availability of highly performing clustering software implementations enables cost-effective high-performance parallel computing on clustered low cost workstations and PCs. Such clusters are very attractive because they rely on availability of the shelf hardware and software technologies. To simplify programming in network environments and to realise component-based software architectures, many models have emerged as possible standards, namely, RPC: Remote Procedure Call, DCE: Distributed Computing Environment, DCOM: Distributed Component Object Model, CORBA: Common Object Request Broker Architecture, PVM: Parallel Virtual Machine and MPI: Message Passing Interface. The MPI approach is considered one of the most mature methods currently used in parallel programming. MPI implementations an emerging cluster interconnects are an important requirement for useful parallel processing on cost-effective computer clusters. This paper offers art overview of different parallel computing environments and models. Functionality and performance of MPI running on homogeneous and heterogeneous workstation clusters are compared. The project goals, laboratory environment, performance measurements, future work, and a conclusion are presented.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127880696","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
Multiprocessor parallel routing for the quality of service enabled Internet 多处理器并行路由的服务质量使互联网
Shaowen Song
{"title":"Multiprocessor parallel routing for the quality of service enabled Internet","authors":"Shaowen Song","doi":"10.1109/PCEE.2000.873621","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873621","url":null,"abstract":"This paper presents a parallel router and a packet switching mechanism by merging IPv6 and asynchronous transfer mode (ATM) as the protocol for the quality of service (QoS) enabled Internet. The hardware architecture of the parallel router consists of N-general-purpose computers each combined with a newly designed inter-node communication unit. This parallel architecture provides the necessary speed required in cell switching for real-time applications. The IPv6 packet and ATM cell co-switching mechanism implemented by the router controlling software preserves the connectionless future for non-real-time applications and provides the QoS for real-time applications, through merging the IPv6 and ATM protocols. The IPv6 packet and ATM cell co-routing/switch mechanism is developed for the current parallel router and is presented along with the parallel hardware architecture.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122164703","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
Web-based endoscopy recommender system-ERS 基于网络的内窥镜检查推荐系统
H. Krawczyk, R. Knopa, Katarzyna Lipczynska, Maciej Lipczynski
{"title":"Web-based endoscopy recommender system-ERS","authors":"H. Krawczyk, R. Knopa, Katarzyna Lipczynska, Maciej Lipczynski","doi":"10.1109/PCEE.2000.873641","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873641","url":null,"abstract":"A Web-based recommender system supporting acquisition and recognition of endoscopy images is described. Utilization of neural networks to identify some disease symptoms is proposed. Moreover, parallel realization of the learning phase of such networks by genetic algorithms is proposed. Some experiments showing advantages of this approach are also presented.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"798 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116140835","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
Cellular automata approach to scheduling problem 元胞自动机方法求解调度问题
A. Swiecicka, F. Seredyński
{"title":"Cellular automata approach to scheduling problem","authors":"A. Swiecicka, F. Seredyński","doi":"10.1109/PCEE.2000.873596","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873596","url":null,"abstract":"In the paper we propose using cellular automata (CAs) to solve a problem of scheduling tasks of a parallel program in the two processor system. We examine a hypothesis that a nonlinear structure of a program graph can be approximated by a linear CA structure. Corresponding CAs solving the scheduling problem act according to some rules which must be found. Searching effective rules is conducted with the use of a genetic algorithm (GA). We show that for any initial allocation of tasks, a CA with discovered rules is able to find optimal or near-optimal solutions. Corresponding architecture of a CA is simpler than the ones known in the literature.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134456924","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: 16
Parallel computational algorithms for the simulation of closed-loop robotic systems 闭环机器人系统仿真的并行计算算法
J. Wang, C. Gosselin
{"title":"Parallel computational algorithms for the simulation of closed-loop robotic systems","authors":"J. Wang, C. Gosselin","doi":"10.1109/PCEE.2000.873597","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873597","url":null,"abstract":"A new approach for the modelling and parallel simulation of closed-loop robotic systems is proposed in this paper. This approach uses virtual springs and dampers to include the closed-loop constraints thereby avoiding the solution of differential-algebraic equations. Moreover, it can lead to a completely decoupled dynamic model of parallel robotic manipulators which is ideal for the parallel computation of the simulation of parallel robotic manipulators. Examples illustrating the approach are given.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115492108","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: 4
IP/ATM solution for accelerating Internet services 加速互联网服务的IP/ATM解决方案
A. E. Adnani, A. A. Ouahman, H. Clausen
{"title":"IP/ATM solution for accelerating Internet services","authors":"A. E. Adnani, A. A. Ouahman, H. Clausen","doi":"10.1109/PCEE.2000.873639","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873639","url":null,"abstract":"The Internet consists of IP routers which communicate with each other by means of distributed routing protocols. Routers use the collected information in order to make appropriate decisions regarding forwarding. On the Internet, Web navigation, file downloading and e-mail use the same protocol. Indeed, as regards IP routers, all these operations use IP datagrams. Routers have two main functions: path determination and packet routing (forwarding). Path determination is a function including the collection of network data, the preliminary processing of paths and the storage in a routing local table of the information specifying the next node on the way to its destination. The network information type depends on the routing protocol that is used. Distance-vector protocols (i.e. RIP, Routing Information Protocol) compute the number of routers before reaching the destination, whereas link-state protocols (i.e. OSPF, Open Shortest Path First) set up a local topological map of the used network that is aimed at sorting out the shortest path. The routing table is a list of all the destination networks that are declared (i.e. some masked IP addresses) with their immediate adjacent matching routers. Forwarding consists of taking a packet, looking at its destination address, consulting the routing table, and sending the packet to the appropriate output port according to the routing table information.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126442984","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
Parallel efficient implementation of hierarchical algorithms for module placement of large chips 大芯片模块放置分层算法的并行高效实现
L. Yang
{"title":"Parallel efficient implementation of hierarchical algorithms for module placement of large chips","authors":"L. Yang","doi":"10.1109/PCEE.2000.873615","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873615","url":null,"abstract":"The PROUD module placement algorithm mainly uses a hierarchical decomposition technique and the solution of sparse linear systems based on a resistive network analogy. It has been shown that the PROUD algorithm can achieve a comparable design of the placement problems for very large circuits with the best placement algorithm based on simulated annealing, but with several order of magnitude faster. The modified PROUD, namely MPROUD algorithm by perturbing the coefficient matrices performs much faster that the original PROUD algorithm. Due to the instability and unguaranteed convergence of MPROUD algorithm we have proposed a new convergent and numerically stable PROUD, namely Improved PROUD algorithm, denoted as IPROUD with attractive computational costs to solve the module placement problems by making use of the MINRES method based on Lanczos process. In this paper, we subsequently propose parallel versions of the original, modified and improved PROUD algorithms that combine both fine and coarse grain parallelism to obtain another order of magnitude improvement in the runtime without loss of the quality of the layout. Experimental results using Message Passing Interface (MPI) on various multiprocessor systems are reported showing its advantages for a variety of large layout benchmark circuits.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129838953","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
Inter-process communication for parallel computations of wavelet transforms on Hitachi SR2201 supercomputer 在日立SR2201超级计算机上并行计算小波变换的进程间通信
A. Smyk, M. Tudruj
{"title":"Inter-process communication for parallel computations of wavelet transforms on Hitachi SR2201 supercomputer","authors":"A. Smyk, M. Tudruj","doi":"10.1109/PCEE.2000.873638","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873638","url":null,"abstract":"The paper presents results of experiments which studied the impact of communication control preprocessing on efficiency of parallel programs which compute two-dimensional wavelet transforms on multiprocessor computer Hitachi SR2201. The transforms are computed using the fast Mallat algorithm. Two communication models were applied in the experiments: the MPI persistent communication requests and the Remote-DMA communication based on multiple buffering areas with the reuse of the transmission control word. It has been shown that using the Remote-DMA communication with the preprocessed communication control infrastructure important speed-up of program execution can be obtained.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121899228","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
Parallelization of the boundary element method for the modelling of large electromagnetic scattering problems 大型电磁散射问题模拟的平行化边界元方法
T. Jacques, L. Nicolas, C. Vollaire
{"title":"Parallelization of the boundary element method for the modelling of large electromagnetic scattering problems","authors":"T. Jacques, L. Nicolas, C. Vollaire","doi":"10.1109/PCEE.2000.873628","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873628","url":null,"abstract":"The boundary integral method is used to solve electromagnetic scattering by perfect electric conducting or dielectric bodies. Due to the memory requirements, the size of computed problems is limited on regular scalar computers. The use of a distributed memory parallel computer allows one to remove this limitation and to solve large problems (dense matrices with more than 100000 rows). The problem assembly is performed by nodal contribution, and the BiCGStab(m) algorithm is used in its solution. This leads to very good parallel performances.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122584908","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: 1
Numerical calculation of electromagnetic problems on an SCI based PC-cluster 基于SCI的pc集群上电磁问题的数值计算
C. Trinitis, M. Eberl, Wolfgang Karl
{"title":"Numerical calculation of electromagnetic problems on an SCI based PC-cluster","authors":"C. Trinitis, M. Eberl, Wolfgang Karl","doi":"10.1109/PCEE.2000.873622","DOIUrl":"https://doi.org/10.1109/PCEE.2000.873622","url":null,"abstract":"This paper summarizes results obtained using the parallel 3D electromagnetic field simulation program POLOPT on a cluster of PCs connected via an Scalable Coherent Interface (SCI) network interface. Compared to previous measurements carried out with conventional network technologies such as Ethernet or Fast Ethernet, a significant rise in parallel efficiency can be obtained. One of the most critical aspects in the design process of high voltage devices and in electrical engineering in general is the accurate simulation of eddy-current problems in three dimensional domains. In order to calculate such problems the engineer needs a method to solve the Maxwell equations in complex, three-dimensional domains. To deal with such problems, a special solver which was implemented by the Eidgenossische Technische Hochschule Zurich, Switzerland, has been integrated into the parallel simulation software POLOPT being run at ABB Corporate Research Center Heidelberg, Germany. The software has been ported to a LINUX based PC cluster connected via the SCI. This paper gives the first results that were obtained using the parallel 3D electric field simulation program POLOPT on the LINUX cluster for eddy current problems. Due to the high performance of the CPUs and interconnection technology the results obtained on clusters of PCs can be compared to those obtained on expensive multiprocessor machines. A practical high voltage engineering problem has been calculated.","PeriodicalId":369394,"journal":{"name":"Proceedings International Conference on Parallel Computing in Electrical Engineering. PARELEC 2000","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128703475","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: 4
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信