This paper describes a parallel implementation of a Lanczos-based method to solve generalised eigenvalue problems related to the modal computation of arbitrarily shaped waveguides. This efficient implementation is intended for execution in moderate-low cost workstations (2 to 4 processors). The problem under study has several features: the involved matrices are sparse with a certain structure, and all the eigenvalues needed are contained in a given interval. The novel parallel algorithms proposed show excellent speed-up for small number of processors
{"title":"Parallel Implementation in PC Clusters of a Lanczos-based Algorithm for an Electromagnetic Eigenvalue Problem","authors":"M. Bernabeu, M. Taroncher, V. García, A. Vidal","doi":"10.1109/ISPDC.2006.39","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.39","url":null,"abstract":"This paper describes a parallel implementation of a Lanczos-based method to solve generalised eigenvalue problems related to the modal computation of arbitrarily shaped waveguides. This efficient implementation is intended for execution in moderate-low cost workstations (2 to 4 processors). The problem under study has several features: the involved matrices are sparse with a certain structure, and all the eigenvalues needed are contained in a given interval. The novel parallel algorithms proposed show excellent speed-up for small number of processors","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115860672","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}
The resource discovery problem, where cooperating machines need to find one another in a network, was introduced by Harchol-Balter, Leighton, and Lewin (1999) in the context of Akamai Technologies with the goal of building an Internet-wide content-distribution system. In the solutions for the synchronous setting proposed so far in the papers by Harchol-Bartel et al. (1999), Kutten et al. (2001) and Law and Siu (2000), there is a possibility that during some time step many machines may contact a single machine, and this is not a realistic assumption. This work assumes a synchronous model, however at each step a machine can send and receive only a constant number of messages. It is shown that the conjectured poly-logarithmic upper bound (Harchol-Bartel et al., 1999) for such a setting is not possible. This is done by proving a lower bound on time of Omega(n), where n is the number of participating nodes. For this model a randomized algorithm is presented that solves the resource discovery problem in O(n log2 n) time, i.e., within a poly-logarithmic factor of the corresponding lower bound. The algorithm has a O(n2 log2 n) message complexity and O(n3 log3 n) communication complexity. Simulation results for the algorithm illustrate the lower and upper bounds, and lead to interesting observations
{"title":"Resource Discovery in Networks under Bandwidth Limitations","authors":"K. Konwar, Alexander A. Shvartsman","doi":"10.1109/ISPDC.2006.40","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.40","url":null,"abstract":"The resource discovery problem, where cooperating machines need to find one another in a network, was introduced by Harchol-Balter, Leighton, and Lewin (1999) in the context of Akamai Technologies with the goal of building an Internet-wide content-distribution system. In the solutions for the synchronous setting proposed so far in the papers by Harchol-Bartel et al. (1999), Kutten et al. (2001) and Law and Siu (2000), there is a possibility that during some time step many machines may contact a single machine, and this is not a realistic assumption. This work assumes a synchronous model, however at each step a machine can send and receive only a constant number of messages. It is shown that the conjectured poly-logarithmic upper bound (Harchol-Bartel et al., 1999) for such a setting is not possible. This is done by proving a lower bound on time of Omega(n), where n is the number of participating nodes. For this model a randomized algorithm is presented that solves the resource discovery problem in O(n log2 n) time, i.e., within a poly-logarithmic factor of the corresponding lower bound. The algorithm has a O(n2 log2 n) message complexity and O(n3 log3 n) communication complexity. Simulation results for the algorithm illustrate the lower and upper bounds, and lead to interesting observations","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123608733","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}
Cristian Tapus, David A. Noblet, V. Grama, J. Hickey
This paper presents MojaveFS, a distributed file system with support for sequential consistency. It provides location transparency and makes use of replication for reliability and fault tolerance. We employ a hybrid hash-based and tree-based lookup mechanism for files that, combined with an efficient caching scheme, provides fast access to files in the system. MojaveFS uses a novel data storage strategy where files are split into smaller objects to increase data availability. It also uses a group communication protocol with guarantees for a total order on messages sent within the system, enabling MojaveFS to support the traditional sequential consistency model for concurrent access
{"title":"MojaveFS: Providing Sequential Consistency in a Distributed Objects System","authors":"Cristian Tapus, David A. Noblet, V. Grama, J. Hickey","doi":"10.1109/ISPDC.2006.34","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.34","url":null,"abstract":"This paper presents MojaveFS, a distributed file system with support for sequential consistency. It provides location transparency and makes use of replication for reliability and fault tolerance. We employ a hybrid hash-based and tree-based lookup mechanism for files that, combined with an efficient caching scheme, provides fast access to files in the system. MojaveFS uses a novel data storage strategy where files are split into smaller objects to increase data availability. It also uses a group communication protocol with guarantees for a total order on messages sent within the system, enabling MojaveFS to support the traditional sequential consistency model for concurrent access","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124760864","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}
In this paper a systematic study of bisimilarities on asymmetric chine-processes is carried out. The notion of L-bisimilarities on asymmetric chine-processes is introduced. Twelve distinct L-bisimilarities are derived from all of L-bisimilarities by constructing a bisimulation lattice. For each of these twelve distinct L-bisimilarities, its open version is defined and showed to coincide with it, and then its congruence is presented. Three update laws are proposed and three tau laws are modified. Finally, sound complete equational systems are established for twelve congruences
{"title":"Bisimulation Congruence for Asymmetric chi ^ ne -Calculus","authors":"Farong Zhong, Yuxi Fu, Xiaoju Dong","doi":"10.1109/ISPDC.2006.13","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.13","url":null,"abstract":"In this paper a systematic study of bisimilarities on asymmetric chine-processes is carried out. The notion of L-bisimilarities on asymmetric chine-processes is introduced. Twelve distinct L-bisimilarities are derived from all of L-bisimilarities by constructing a bisimulation lattice. For each of these twelve distinct L-bisimilarities, its open version is defined and showed to coincide with it, and then its congruence is presented. Three update laws are proposed and three tau laws are modified. Finally, sound complete equational systems are established for twelve congruences","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125233559","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}
Recent applications for distributed mobile devices, including multimedia video/audio streaming, typically process streams of incoming data in a regular, predictable way. The behavior of these applications during runtime can be accurately predicted most of the time by analyzing the data to be processed and annotating the stream with the information collected. We introduce an annotation-based approach to power-quality trade-offs and demonstrate its application on CPU frequency scaling during video decoding, for an improved user experience on portable devices. Our experiments show that up to 50% of the power consumed by the CPU during video decoding can be saved with this approach
{"title":"Video Stream Annotations for Energy Trade-offs in Multimedia Applications","authors":"R. Cornea, A. Nicolau, N. Dutt","doi":"10.1109/ISPDC.2006.55","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.55","url":null,"abstract":"Recent applications for distributed mobile devices, including multimedia video/audio streaming, typically process streams of incoming data in a regular, predictable way. The behavior of these applications during runtime can be accurately predicted most of the time by analyzing the data to be processed and annotating the stream with the information collected. We introduce an annotation-based approach to power-quality trade-offs and demonstrate its application on CPU frequency scaling during video decoding, for an improved user experience on portable devices. Our experiments show that up to 50% of the power consumed by the CPU during video decoding can be saved with this approach","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116737743","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}
Program execution methods and respective architectural solutions for parallel embedded systems with look-ahead dynamic inter-processor connection setting are discussed in the paper. The look-ahead dynamic connection setting is a novel method, which leads to time transparency of reconfiguration control during program execution. The look-ahead dynamic reconfiguration assumes segmentation of programs into sections, which are executed in parallel with connection setting for subsequent sections. The discussed architectures for the look-ahead dynamic reconfiguration are based on redundant resources such as processor links and link connection switches. The paper compares the efficiency of Strassen matrix multiplication in the systems based on multiple link connection switches, partitioned processor link sets and anticipated link connection setting on request in a single crossbar switch
{"title":"Assessment of Dynamic Look-Ahead Inter-Processor Connection Reconfiguration for Different Control Paradigms","authors":"E. Laskowski, M. Tudruj","doi":"10.1109/ISPDC.2006.10","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.10","url":null,"abstract":"Program execution methods and respective architectural solutions for parallel embedded systems with look-ahead dynamic inter-processor connection setting are discussed in the paper. The look-ahead dynamic connection setting is a novel method, which leads to time transparency of reconfiguration control during program execution. The look-ahead dynamic reconfiguration assumes segmentation of programs into sections, which are executed in parallel with connection setting for subsequent sections. The discussed architectures for the look-ahead dynamic reconfiguration are based on redundant resources such as processor links and link connection switches. The paper compares the efficiency of Strassen matrix multiplication in the systems based on multiple link connection switches, partitioned processor link sets and anticipated link connection setting on request in a single crossbar switch","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128955668","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}
Mobile devices are characterized by low processing power, limited communication bandwidth, limited storage space and rudimentary input and output systems. Networks of such devices are mainly the medium for data exchange. Dynamic code exchange is a feature that is not supported in this environment even though communication is easily achieved. This paper proposes a flexible class loader for the Java connected limited device configuration (CLDC). Introducing a dynamic remote class loader on the CLDC is necessary in order to efficiently deploy the platform into mobile wireless networks. The proposed solution is compared with other possible solutions and is evaluated in relation to existing systems
{"title":"Dynamic Class Provisioning on Mobile Devices","authors":"L. Petrea, D. Grigoras","doi":"10.1109/ISPDC.2006.22","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.22","url":null,"abstract":"Mobile devices are characterized by low processing power, limited communication bandwidth, limited storage space and rudimentary input and output systems. Networks of such devices are mainly the medium for data exchange. Dynamic code exchange is a feature that is not supported in this environment even though communication is easily achieved. This paper proposes a flexible class loader for the Java connected limited device configuration (CLDC). Introducing a dynamic remote class loader on the CLDC is necessary in order to efficiently deploy the platform into mobile wireless networks. The proposed solution is compared with other possible solutions and is evaluated in relation to existing systems","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133343767","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}
Valérie Fiolet, R. Olejnik, Guillem Lefait, B. Toursel
Although many data mining tasks have been parallelized and can thus be executed on dedicated clusters, few solutions currently exist to solve data mining problems on a grid or a non-specialized network of workstations. The current tendency is to focus on the use of grids and/or desktop grids in order to exploit any available workstations with no considerations of their physical positions. If a grid specific algorithm has some common characteristics with a dedicated-cluster algorithm, many constraints are inherent to the use of the grid. In particular, resource volatility and communications cost reduce the parallelism effectiveness. The DisDaMin project (distributed data mining) revisits the data mining tasks and proposes new exploitable algorithms for grids. The DisDaMin mechanisms first implement a specific fragmentation of the data using clustering methods, and then realize asynchronous collaborative techniques according to the specifics of execution on grids. The use of this fragmentation method makes it possible to carry out optimal local processing on each node, with a minimum of communications. Using this, we introduce the distributed algorithm DICCoop, an adaptation of DIC by Brin et al. (1997). Simulations were performed to prove the efficiency of the proposed mechanisms and are hosted on the French national grid GRID5000 (part of the European CoreGrid). We analyse the impact of the numerous parameters on optimization of parallel efficiency
{"title":"Optimal Grid Exploitation Algorithms for Data Mining","authors":"Valérie Fiolet, R. Olejnik, Guillem Lefait, B. Toursel","doi":"10.1109/ISPDC.2006.36","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.36","url":null,"abstract":"Although many data mining tasks have been parallelized and can thus be executed on dedicated clusters, few solutions currently exist to solve data mining problems on a grid or a non-specialized network of workstations. The current tendency is to focus on the use of grids and/or desktop grids in order to exploit any available workstations with no considerations of their physical positions. If a grid specific algorithm has some common characteristics with a dedicated-cluster algorithm, many constraints are inherent to the use of the grid. In particular, resource volatility and communications cost reduce the parallelism effectiveness. The DisDaMin project (distributed data mining) revisits the data mining tasks and proposes new exploitable algorithms for grids. The DisDaMin mechanisms first implement a specific fragmentation of the data using clustering methods, and then realize asynchronous collaborative techniques according to the specifics of execution on grids. The use of this fragmentation method makes it possible to carry out optimal local processing on each node, with a minimum of communications. Using this, we introduce the distributed algorithm DICCoop, an adaptation of DIC by Brin et al. (1997). Simulations were performed to prove the efficiency of the proposed mechanisms and are hosted on the French national grid GRID5000 (part of the European CoreGrid). We analyse the impact of the numerous parameters on optimization of parallel efficiency","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133477190","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}
The World Wide Web has become pervasive in many facets of our professional and personal lives during the past 10 years. Today, another Internet revolution is emerging: grid computing. While the Web offers easy access to mostly static information via hypertext, the grid adds another fundamental layer by enabling access to and use of the underlying resources. Based on widely accepted grid and Web services standards, resources including computers, storage, scientific instruments and experiments, applications, data, and middleware services communicate with each other and deliver results back to the user. These resources are part of a single service-oriented architecture, called OGSA, the Open Grid Services Architecture. For the past several years, early adopters in research and industry have been building and operating prototypes of grids for global communities, virtual organizations, and within enterprises
{"title":"D-Grid, an E-Science Framework for German Scientists","authors":"W. Gentzsch","doi":"10.1109/ISPDC.2006.16","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.16","url":null,"abstract":"The World Wide Web has become pervasive in many facets of our professional and personal lives during the past 10 years. Today, another Internet revolution is emerging: grid computing. While the Web offers easy access to mostly static information via hypertext, the grid adds another fundamental layer by enabling access to and use of the underlying resources. Based on widely accepted grid and Web services standards, resources including computers, storage, scientific instruments and experiments, applications, data, and middleware services communicate with each other and deliver results back to the user. These resources are part of a single service-oriented architecture, called OGSA, the Open Grid Services Architecture. For the past several years, early adopters in research and industry have been building and operating prototypes of grids for global communities, virtual organizations, and within enterprises","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134029555","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}
This paper outlines how the mobile message passing interface (MMPI) may be used for parallel computation. MMPI allows parallel programming of mobile devices over a Bluetooth network. This paper gives an overview of the MMPI library, and demonstrates that mobile devices are capable of parallel computation. An example of matrix multiplication O(n3) is used to show this
{"title":"Mobile Parallel Computing","authors":"D. Doolan, S. Tabirca, L. Yang","doi":"10.1109/ISPDC.2006.33","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.33","url":null,"abstract":"This paper outlines how the mobile message passing interface (MMPI) may be used for parallel computation. MMPI allows parallel programming of mobile devices over a Bluetooth network. This paper gives an overview of the MMPI library, and demonstrates that mobile devices are capable of parallel computation. An example of matrix multiplication O(n3) is used to show this","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114211322","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：