Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region最新文献

筛选
英文 中文
An effective method to extract fingerprint singular point 一种有效的指纹奇异点提取方法
C. Hsieh, Z. Y. Lu, Tan Li, Kung Chen Mei
{"title":"An effective method to extract fingerprint singular point","authors":"C. Hsieh, Z. Y. Lu, Tan Li, Kung Chen Mei","doi":"10.1109/HPC.2000.843528","DOIUrl":"https://doi.org/10.1109/HPC.2000.843528","url":null,"abstract":"In a fingerprint recognition system, preprocessing is difficult and wasted time. We propose a method to build a direction matrix which can describe the fingerprint texture to improve the problems of obscure and broken images. Then, utilizing the direction matrix, we propose a feature extraction method to find out counts and locations from the fingerprint singular points, such as core point and delta point. We use NIST(4) as a fingerprint database and the results seem encouraging.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116790166","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: 22
Development of molecular dynamics programs for proteins with a parallelized Barnes-Hut tree code 用并行化Barnes-Hut树代码开发蛋白质分子动力学程序
K. Misoo, Y. Akiyama, Y. Shizawa, M. Saito
{"title":"Development of molecular dynamics programs for proteins with a parallelized Barnes-Hut tree code","authors":"K. Misoo, Y. Akiyama, Y. Shizawa, M. Saito","doi":"10.1109/HPC.2000.843609","DOIUrl":"https://doi.org/10.1109/HPC.2000.843609","url":null,"abstract":"We describe the design and the MPI-implementation of two parallel tree code molecular dynamics programs called MolTreC and Treecode AMBER, respectively. Both programs were developed using the parallel Barnes-Hut tree code for calculating Coulomb interactions which have been developed in earlier work. The parallel programs can rapidly calculate the Coulomb interactions of proteins in water without any cutoff approximations. They showed good speedups on distributed-memory multiprocessors and on PC clusters. MolTreC showed 111-fold speedup on SR2201 with 256 processors for the prowat benchmark of 11585 atoms. It was only 1.7-times slower than AMBER with 12A cutoff approximation.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117217261","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
Some factors of affecting performance of numerical parallel computation 影响数值并行计算性能的几个因素
Xue-bin Chi
{"title":"Some factors of affecting performance of numerical parallel computation","authors":"Xue-bin Chi","doi":"10.1109/HPC.2000.846585","DOIUrl":"https://doi.org/10.1109/HPC.2000.846585","url":null,"abstract":"In this paper some factors affecting the performance of numerical parallel computing are analyzed. For a distributed parallel computer system, it includes the effective library utilization, parallel algorithm design, and selection of message passing functions. For a shared memory multiprocessor system, the affect of the parallel compiler is discussed. From an analysis and experiment of parallel computing of linear algebra problems, the above mentioned facts are found to be very important in improving the performance of numerical parallel computation. The scalability of a parallel program is also discussed. The numerical testing is performed on Dawning 1000, Dawning 2000, SR2201, T3E and Power Challenge.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121074059","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
Digging for gold on the Web: experience with the WebGather 在网络上挖掘黄金:WebGather的经验
Jianguo Liu, Ming Lei, Jianyong Wang, Baojue Chen
{"title":"Digging for gold on the Web: experience with the WebGather","authors":"Jianguo Liu, Ming Lei, Jianyong Wang, Baojue Chen","doi":"10.1109/HPC.2000.843538","DOIUrl":"https://doi.org/10.1109/HPC.2000.843538","url":null,"abstract":"A Web search engine is a powerful tool to find useful information for users on the resourceful World Wide Web. WebGather is a search engine system with a focus on Chinese information discovery, indexing and searching. The authors briefly describe the technology used in WebGather such as heuristic resource discovery algorithm, efficient indexing algorithm, simplified vector space model, effective searching and ranking algorithm, and access interfaces with high usability. Some experience we got from designing and implementing WebGather is provided.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127119158","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: 9
A simulation model for ATM WAN ATM广域网的仿真模型
Zhenwei Yu, Han-Ru Wei
{"title":"A simulation model for ATM WAN","authors":"Zhenwei Yu, Han-Ru Wei","doi":"10.1109/HPC.2000.846520","DOIUrl":"https://doi.org/10.1109/HPC.2000.846520","url":null,"abstract":"Parallel object-oriented simulation (POOS) is becoming the choice for modeling large and complex systems. In this paper, a POOS model for an ATM WAN is presented.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116090817","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
An object-based parallel rendering system 一个基于对象的并行渲染系统
Joo-Kyoung Park, Moon-Hee Choi, W.-K. Hong, W. Park, Shin-Dug Kim
{"title":"An object-based parallel rendering system","authors":"Joo-Kyoung Park, Moon-Hee Choi, W.-K. Hong, W. Park, Shin-Dug Kim","doi":"10.1109/HPC.2000.843542","DOIUrl":"https://doi.org/10.1109/HPC.2000.843542","url":null,"abstract":"Image composition architecture for polygon rendering is the most promising candidate for high performance. It does not suffer from any disadvantage of screen subdivision architecture (i.e., load imbalance and increased clipping time). However, in this architecture, the image composition operation cannot be overlapped with the calculation operation for computing an image and the memory requirement for local frame buffer is very large. The object based parallel rendering system (OBPRS) that is based on the image composition architecture is proposed and the objective of the OBPRS is to remove the disadvantages of the image composition architecture. According to the simulation results with a 64-renderer system, the OBPRS takes only about 80% of the rendering time of the image composition architecture. Also, it requires only 85% of the memory requirement for local frame buffer of the screen subdivision architecture. Thus the OBPRS turns out to be an effective system model, providing high performance to cost ratio.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122404419","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
A high-performance memory allocator for memory intensive applications 用于内存密集型应用程序的高性能内存分配器
J.M. Chang, Y. Hasan, W. H. Lee
{"title":"A high-performance memory allocator for memory intensive applications","authors":"J.M. Chang, Y. Hasan, W. H. Lee","doi":"10.1109/HPC.2000.846507","DOIUrl":"https://doi.org/10.1109/HPC.2000.846507","url":null,"abstract":"Dynamic memory management (DMM) has been a high cost component in many software systems. In particular, the use of object orientation often results in an intensive use of dynamic memory, making the dynamic memory performance problem worse. The paper presents a profile based strategy to improve the performance of DMM. The performance improvement comes from a segregated strategy without splitting and coalescing cost. This modification is made feasible by preallocating the free-list based on the profile data of heap memory usage. In this research, the empirical study shows that the maximum number of live objects of each size is independent of the input; this data provides a profile and estimate for the amount of memory the application will need to run and can be preallocated to give great improvement in performance. Compared to the average performance of well known algorithms, the profile based approach is about 3.9 times to 6.5 times faster.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122495199","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: 7
Research on extensibility and reliability of agents in Web-based Computing Resource Publishing 基于web的计算资源发布中代理的可扩展性和可靠性研究
Zhi-Gang Wu, B. Fang
{"title":"Research on extensibility and reliability of agents in Web-based Computing Resource Publishing","authors":"Zhi-Gang Wu, B. Fang","doi":"10.1109/HPC.2000.846592","DOIUrl":"https://doi.org/10.1109/HPC.2000.846592","url":null,"abstract":"Web-based Computing Resource Publishing is a Web oriented metacomputing system. Agent publishing is its leading style. Extensibility and reliability are two crucial problems for the agent. We propose a parent-child agent framework and a primary-slave agent framework to improve the agents' performance. Several problems arise in the frameworks: how to assign tasks among agents, how to schedule slave agents to select a new primary agent under condition that the original one cannot perform its role any more, and how to keep states in primary agent and slave agents consistent. Aiming at these problems, we introduce an agent coordination strategy, a slave scheduling strategy and an agent coherence algorithm.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124627624","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
Scaling Internet services by LinuxDirector 通过LinuxDirector扩展Internet服务
Wensong Zhang, Shiyao Jin, Quanyuan Wu
{"title":"Scaling Internet services by LinuxDirector","authors":"Wensong Zhang, Shiyao Jin, Quanyuan Wu","doi":"10.1109/HPC.2000.846543","DOIUrl":"https://doi.org/10.1109/HPC.2000.846543","url":null,"abstract":"LinuxDirector is a software tool that directs network connections to multiple servers that share their workload, which can be used to build highly scalable and highly available services. LinuxDirector extends the TCP/IP stack of the Linux kernel to support three IP load balancing techniques, which can make parallel services of different kinds of server clusters to appear as a service on a single IP address. Four scheduling algorithms have been implemented to assign connections to different servers, and a simple distributed lock manager is provided for applications on different servers to access shared data consistently. Scalability is achieved by transparently adding or removing a node in the cluster and high availability is provided by detecting node or daemon failures and reconfiguring the system appropriately. This paper describes the design and implementation of LinuxDirector and presents several of its features including scalability, high availability, connection affinity and icmp handling.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124747100","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: 7
An XML-based component model for wrapping legacy codes as Java/CORBA components 基于xml的组件模型,用于将遗留代码包装为Java/CORBA组件
Maozhen Li, O. Rana, D. Walker
{"title":"An XML-based component model for wrapping legacy codes as Java/CORBA components","authors":"Maozhen Li, O. Rana, D. Walker","doi":"10.1109/HPC.2000.846606","DOIUrl":"https://doi.org/10.1109/HPC.2000.846606","url":null,"abstract":"Techniques for wrapping an MPI-based molecular dynamics (MD) simulation code as Java/CORBA components, for use within a distributed component based problem solving environment (CB-PSE), is presented. The legacy code for simulating a Lennard-Jones fluid is first wrapped as a single CORBA object, followed by division of the code into computational sub-units, where each sub-unit is wrapped as a CORBA object containing MPI calls, and run on a cluster of workstations-enabling different MPI implementations to inter-operate. Each CORBA object is a component, with its interface and constrains defined in XML, which enables a user to search for components suitable to a particular application, enables a component to be configured when instantiated, enables each component to register with an event listener and facilitates the sharing of components between repositories. The application architecture and task graph are also described in XML. Using a Java implementation, users can submit simulation tasks through a Web based interface, without needing to know implementation details of the legacy code, or the exact interaction between sub-units within the code. We provide performance comparisons of wrapping the entire MD code as a single object, verses wrapping sub-units within it.","PeriodicalId":422299,"journal":{"name":"Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123632360","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: 5
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
小红书