{"title":"A new approach to distribute program workload on software DSM clusters","authors":"Tyng-Yeu Liang, Yen-Tso Liu, C. Shieh, Chun-Yi Wu","doi":"10.1109/ISPAN.2004.1300481","DOIUrl":"https://doi.org/10.1109/ISPAN.2004.1300481","url":null,"abstract":"The workload distribution approaches used by software distributed shared memory (DSM) clusters always distribute the working threads of applications according to the computational power of processors. However, in addition to computational cost, the cost of memory accesses is an important factor for determining program performance. Neglecting this cost will result in making wrong decisions in workload distribution and then degrading program performance. To address this problem, we propose a new approach with simultaneously considering the memory capability and the computational power of processors for workload distribution on software DSM clusters in this paper. We have implemented the proposed approach on a test bed. Our experimental results show that the proposed approach can provide more performance improvement for the applications compared to the others with considering only computational powers or memory capabilities.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131987673","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}
{"title":"On a region-of-interest based approach to robust wireless video transmission","authors":"A. C. Wong, Yu-Kwong Kwok","doi":"10.1109/ISPAN.2004.1300510","DOIUrl":"https://doi.org/10.1109/ISPAN.2004.1300510","url":null,"abstract":"This paper presents a scheme aiming at transmitting real-time video to wireless channel with vigorously varying quality, which is in practice the norm rather than the exception. Region of interest (ROI) is an efficient approach to making the video more adaptive to the wireless channel because ROI is the region that human eyes tend to put more attention to than the remainder region (RM). In our proposed scheme, we adopted this feature. The real-time source video stream is divided into two regions, the ROI and the RM regions. The two regions were encoded using H.263 standard codec such that the video transmission is adaptive to the current channel state, which is characterized by the effective data rate that varies from tens of kilobits per second to hundreds of kilobits per second. Channel state parameters are fed back to the source coder to adjust the compression ratio as well as the intra/inter options of the encoders. Results including frame loss probability, compression characteristics, peak signal to noise ratio (PSNR) against channel states are given, indicating that the resulting adaptive video codec can respond judiciously to time-varying channel quality. Our scheme is evaluated together with a ROI-enabled moving picture coding standard JPEG2000. Using the features provided in JPEG2000, we have made the JPEG2000 codec adaptive to the vigorously varying wireless channel and then compared it with the H.263 scheme. Our technique is suitable for a broad area of applications including real-time news reporting and video conferencing.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132081078","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}
{"title":"M-CAN: a lookup protocol for mobile peer-to-peer environment","authors":"Gang Peng, Shanping Li, Hairong Jin, Tianchi Ma","doi":"10.1109/ISPAN.2004.1300535","DOIUrl":"https://doi.org/10.1109/ISPAN.2004.1300535","url":null,"abstract":"With the development of the mobile communication technology and P2P, a combination of mobile computing and P2P, MP2P, has revealed its attractions. Compared to traditional P2P, characteristics of MP2P include unreliable connection, limited bandwidth and constrains of mobile devices. Although there have existed some classic lookup protocols for traditional P2P systems, they all fall into impropriety and inefficiency under MP2P because of their scalability limits, unreliability and requirements of bandwidth. In this paper, a new protocol, M-CAN, is proposed for implementing an efficient lookup in MP2P. By grouping and registering resources appropriately, M-CAN accelerates the lookup process in MP2P environment. Tests show that M-CAN can greatly enhance the system performance and effectivity.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132469143","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}
{"title":"Games networks play a game theoretic approach to networks","authors":"A. Rextin, Zahid Irfan, Z. Uzmi","doi":"10.1109/ISPAN.2004.1300521","DOIUrl":"https://doi.org/10.1109/ISPAN.2004.1300521","url":null,"abstract":"Traditional network protocols such as TCP/IP require cooperation between traffic sources to achieve optimal network performance. This approach does not always work, as evident by frequent congestion problems in the Internet. Recent research in protocol design using game theory removes this limitation by modeling traffic sources as competing players and results in efficient and fair distribution of resources. This paper provides theoretical background of the game theoretic approach as applied to networks, describes some previously proposed schemes for minimizing network congestion, elaborates on pricing mechanisms and discusses game-theoretic routing solutions. Pricing provides a feasible solution for congestion control but application of distributed algorithmic mechanism design (DAMD) can be adapted for congestion control.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132901848","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}
{"title":"How to parallelize cellular neural networks on cluster architectures","authors":"Thomas Weishäupl, E. Schikuta","doi":"10.1109/ISPAN.2004.1300519","DOIUrl":"https://doi.org/10.1109/ISPAN.2004.1300519","url":null,"abstract":"In this paper, we present \"rules of thumb\" for the efficient and straight-forward parallelization of cellular neural networks (CNNs) processing image data on cluster architectures. The rules result from the application and optimization of the simple but effective structural data parallel approach, which is based on the SPMD model. Digital gray-scale images were used to evaluate the optimized parallel cellular neural network program. The process of parallelizing the algorithm employs HPF to generate an MPI-based program.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131207760","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}
{"title":"A network security architectural approach for systems integrity using multi agent systems engineering","authors":"G. Torrellas","doi":"10.1109/ISPAN.2004.1300544","DOIUrl":"https://doi.org/10.1109/ISPAN.2004.1300544","url":null,"abstract":"Ideally, information systems security enables management to have confidence that their computational systems provide the information requested and expected, while denying accessibility to those who have no right to it. The analysis of incidents resulting in damage to information systems show that most losses were still due to errors or omissions by authorized users, actions of disgruntled employees, and an increase in external penetrations of systems by outsiders. Traditional controls are normally inadequate in these cases or are focused on the wrong threat, resulting in the exposure of vulnerability. Security is a critical parameter for the expansion and wide usage of agent technology. A threat model is constructed and subsequently the basic techniques to deal effectively with these threats are analyzed. This paper presents a dynamic, extensible, configurable and interoperable security architecture for mobile agent systems. It is explained how this architecture can be used to tackle a big part of security threats. All the components of the security architecture are analyzed while we also argue for the benefits they offer.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131076722","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}
{"title":"Knowledge states for the caching problem in shared memory multiprocessor systems","authors":"W. Bein, L. Larmore, R. Reischuk","doi":"10.1142/S0129054109006504","DOIUrl":"https://doi.org/10.1142/S0129054109006504","url":null,"abstract":"Multiprocessor systems with a global shared memory provide logically uniform data access. To hide latencies when accessing global memory each processor makes use of a private cache. Several copies of a data item may exist concurrently in the system. To guarantee consistency when updating an item a processor must invalidate copies of the item in other private caches. To exclude the effect of classical paging faults, one assumes that each processor knows its own data access sequence, but does not know the sequence of future invalidations requested by other processors. Performance of a processor with this restriction can be measured against the optimal behavior of a theoretical omniscient processor, using competitive analysis. A 4/3 competitive randomized online algorithm for this problem for cache size 2 is presented. This algorithm is derived with the help of a new concept we call knowledge states. We also prove a matching lower bound, thus this online algorithm is best possible. Finally, a lower bound of 3/2 on the competitiveness for larger cache sizes is shown.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122589723","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}
{"title":"Gravity routing in ad hoc networks: integrating geographical and topology-based routing","authors":"P. Hsiao, H. T. Kung","doi":"10.1109/ISPAN.2004.1300512","DOIUrl":"https://doi.org/10.1109/ISPAN.2004.1300512","url":null,"abstract":"Gravity routing is a routing protocol that uses geographical routing such as GPSR to forward packets toward regions, where topology-based routing protocol such as DSR and AODV works well. That is, packets are \"gravitated\" toward these regions. This hybrid approach has two advantages: first, it can improve the performance of geographical routing by taking into account the existence of such regions; second, topology-based routing is limited to only run in small regions with fewer nodes where it works well. This paper describes the basic concepts of gravity routing, discusses design and implementation considerations, and provides simulation results demonstrating the superiority of the hybrid approach in nonuniform ad hoc networks. In addition, we describe a region-management-free method for gravity routing that avoids the need of maintaining regions.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126006798","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}
{"title":"Adaptive fault-tolerant wormhole routing with two virtual channels in 2D meshes","authors":"Jipeng Zhou, F. Lau","doi":"10.1109/ISPAN.2004.1300472","DOIUrl":"https://doi.org/10.1109/ISPAN.2004.1300472","url":null,"abstract":"An adaptive fault-tolerant wormhole routing algorithm based on a convex fault model in 2D meshes is presented. With the algorithm, a normal routing message, when blocked by faulty processors, would detour along some special polygons around the fault region. The result is that the proposed algorithm can tolerate convex faults with only two virtual channels per physical channel regardless of the overlapping of the boundaries of different fault regions. The convex fault model used does not include any nonfaulty processors and the proposed algorithm is deadlock-free.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122035538","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}
{"title":"Cooperation of RSVP, DiffServ for frequent and fast intersubnet handoff","authors":"Bingyi Zhang, Yamin Sun","doi":"10.1109/ISPAN.2004.1300517","DOIUrl":"https://doi.org/10.1109/ISPAN.2004.1300517","url":null,"abstract":"For the problems raised by frequent and fast intersubnet handoff, some methods based on resource reservation protocol (RSVP) extensions or differentiated services (DiffServ) model have been proposed. The merit and drawbacks of these methods are described in this paper respectively. Then a new scheme is proposed which include the merit of RSVP and DiffServ. It can explicitly provide enough quality of service (QoS) guarantee using RSVP in normal case. When the mobile host moves fast and occurs frequent intersubnet handoff, it immediately uses DiffServ to provide temporary QoS guarantee and keep handoff no dropping.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129337761","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}