Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868637
D. Thain, M. Livny
Split execution is a common model for providing a friendly environment on a foreign machine. In this model, a remotely executing process sends some or all of its system calls back to a home environment for execution. Unfortunately, hand-coding split execution systems for experimentation and research is difficult and error-prone. We have built a tool, called Bypass, for quickly producing portable and correct split execution systems for unmodified legacy applications. We demonstrate Bypass by using it to transparently connect a POSIX application to a simple data staging system based on the Globus toolkit.
{"title":"Bypass: a tool for building split execution systems","authors":"D. Thain, M. Livny","doi":"10.1109/HPDC.2000.868637","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868637","url":null,"abstract":"Split execution is a common model for providing a friendly environment on a foreign machine. In this model, a remotely executing process sends some or all of its system calls back to a home environment for execution. Unfortunately, hand-coding split execution systems for experimentation and research is difficult and error-prone. We have built a tool, called Bypass, for quickly producing portable and correct split execution systems for unmodified legacy applications. We demonstrate Bypass by using it to transparently connect a POSIX application to a simple data staging system based on the Globus toolkit.","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123570578","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}
Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868657
Gabrielle Allen, W. Benger, T. Goodale, H. Hege, Gerd Lanfermann, André Merzky, T. Radke, E. Seidel, J. Shalf
Cactus is an open source problem solving environment designed for scientists and engineers. Its modular structure facilitates parallel computation across different architectures and collaborative code development between different groups. The Cactus Code originated in the academic research community, where it has been developed and used over many years by a large international collaboration of physicists and computational scientists. We discuss how the intensive computing requirements of physics applications now using the Cactus Code encourage the use of distributed and metacomputing, describe the development and experiments which have already been performed with Cactus, and detail how its design makes it an ideal application test-bed for Grid computing.
{"title":"The Cactus Code: a problem solving environment for the grid","authors":"Gabrielle Allen, W. Benger, T. Goodale, H. Hege, Gerd Lanfermann, André Merzky, T. Radke, E. Seidel, J. Shalf","doi":"10.1109/HPDC.2000.868657","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868657","url":null,"abstract":"Cactus is an open source problem solving environment designed for scientists and engineers. Its modular structure facilitates parallel computation across different architectures and collaborative code development between different groups. The Cactus Code originated in the academic research community, where it has been developed and used over many years by a large international collaboration of physicists and computational scientists. We discuss how the intensive computing requirements of physics applications now using the Cactus Code encourage the use of distributed and metacomputing, describe the development and experiments which have already been performed with Cactus, and detail how its design makes it an ideal application test-bed for Grid computing.","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130318478","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}
Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868632
J., Davison de St. Germain, J. McCorquodale, S. Parker, Christopher R. Johnson
Describes Uintah, a component-based visual problem-solving environment (PSE) that is designed to specifically address the unique problems of massively parallel computation on tera-scale computing platforms. Uintah supports the entire life-cycle of scientific applications by allowing scientific programmers to quickly and easily develop new techniques, debug new implementations and apply known algorithms to solve novel problems. Uintah is built on three principles: (1) as much as possible, the complexities of parallel execution should be handled for the scientist, (2) the software should be reusable at the component level, and (3) scientists should be able to dynamically steer and visualize their simulation results as the simulation executes. To provide this functionality, Uintah builds upon the best features of the SCIRun (Scientific Computing and Imaging Run-time) PSE and the DoE (Department of Energy) Common Component Architecture (CCA).
{"title":"Uintah: a massively parallel problem solving environment","authors":"J., Davison de St. Germain, J. McCorquodale, S. Parker, Christopher R. Johnson","doi":"10.1109/HPDC.2000.868632","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868632","url":null,"abstract":"Describes Uintah, a component-based visual problem-solving environment (PSE) that is designed to specifically address the unique problems of massively parallel computation on tera-scale computing platforms. Uintah supports the entire life-cycle of scientific applications by allowing scientific programmers to quickly and easily develop new techniques, debug new implementations and apply known algorithms to solve novel problems. Uintah is built on three principles: (1) as much as possible, the complexities of parallel execution should be handled for the scientist, (2) the software should be reusable at the component level, and (3) scientists should be able to dynamically steer and visualize their simulation results as the simulation executes. To provide this functionality, Uintah builds upon the best features of the SCIRun (Scientific Computing and Imaging Run-time) PSE and the DoE (Department of Energy) Common Component Architecture (CCA).","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129818459","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}
Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868647
B. White, A. Grimshaw, A. Nguyen-Tuong
The unprecedented scale, heterogeneity and varied usage patterns of computational grids pose significant technical challenges to any underlying file system that supports them. While grids present a host of new concerns for file access, we focus on two issues: performance and usability. We discuss the Legion I/O model and interface to address the latter area. We compare the Legion and Globus I/O models against a baseline to validate the efficiency of existent grid-based file access solutions.
{"title":"Grid-based file access: the Legion I/O model","authors":"B. White, A. Grimshaw, A. Nguyen-Tuong","doi":"10.1109/HPDC.2000.868647","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868647","url":null,"abstract":"The unprecedented scale, heterogeneity and varied usage patterns of computational grids pose significant technical challenges to any underlying file system that supports them. While grids present a host of new concerns for file access, we focus on two issues: performance and usability. We discuss the Legion I/O model and interface to address the latter area. We compare the Legion and Globus I/O models against a baseline to validate the efficiency of existent grid-based file access solutions.","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114280019","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}
Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868638
Jasmine Y. Q. Wang, J. Ong, Y. Coady, M. Feeley
The benefits of Markov-based predictive prefetching have been largely overshadowed by the overhead required to produce high-quality predictions. While both theoretical and simulation results for prediction algorithms appear promising, substantial limitations exist in practice. This outcome can be partially attributed to the fact that practical implementations ultimately make compromises in order to reduce overhead. These compromises limit the level of algorithm complexity, the variety of access patterns and the granularity of trace data that the implementation supports. This paper describes the design and implementation of GMS-3P (Global Memory System with Parallel Predictive Prefetching), an operating system kernel extension that offloads prediction overhead to idle network nodes. GMS-3P builds on the GMS global memory system, which pages to and from remote workstation memory. In GMS-3P, the target node sends an online trace of an application's page faults to an idle node that is running a Markov-based prediction algorithm. The prediction node then uses GMS to prefetch pages to the target node from the memory of other workstations in the network. Our preliminary results show that predictive prefetching can reduce the remote-memory page fault time by 60% or more and that, by offloading prediction overhead to an idle node, GMS-3P can reduce this improved latency by between 24% and 44%, depending on the Markov model order.
基于马尔可夫的预测预取的好处在很大程度上被产生高质量预测所需的开销所掩盖。虽然预测算法的理论和仿真结果都很有希望，但在实践中存在很大的局限性。这一结果可以部分归因于实际实现最终为了减少开销而做出妥协的事实。这些妥协限制了算法的复杂性、访问模式的多样性以及实现所支持的跟踪数据的粒度。本文描述了GMS-3P (Global Memory System with Parallel Predictive prefetch)的设计和实现，GMS-3P是一个操作系统内核扩展，可以将预测开销转移到空闲的网络节点上。GMS- 3p建立在GMS全局内存系统之上，该系统在远程工作站内存之间进行分页。在GMS-3P中，目标节点将应用程序页面错误的在线跟踪发送到正在运行基于markov的预测算法的空闲节点。然后，预测节点使用GMS从网络中其他工作站的内存中预取页面到目标节点。我们的初步结果表明，预测性预取可以将远程内存页面故障时间减少60%或更多，并且通过将预测开销卸载到空闲节点，GMS-3P可以将这种改进的延迟减少24%到44%，具体取决于马尔可夫模型的顺序。
{"title":"Using idle workstations to implement predictive prefetching","authors":"Jasmine Y. Q. Wang, J. Ong, Y. Coady, M. Feeley","doi":"10.1109/HPDC.2000.868638","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868638","url":null,"abstract":"The benefits of Markov-based predictive prefetching have been largely overshadowed by the overhead required to produce high-quality predictions. While both theoretical and simulation results for prediction algorithms appear promising, substantial limitations exist in practice. This outcome can be partially attributed to the fact that practical implementations ultimately make compromises in order to reduce overhead. These compromises limit the level of algorithm complexity, the variety of access patterns and the granularity of trace data that the implementation supports. This paper describes the design and implementation of GMS-3P (Global Memory System with Parallel Predictive Prefetching), an operating system kernel extension that offloads prediction overhead to idle network nodes. GMS-3P builds on the GMS global memory system, which pages to and from remote workstation memory. In GMS-3P, the target node sends an online trace of an application's page faults to an idle node that is running a Markov-based prediction algorithm. The prediction node then uses GMS to prefetch pages to the target node from the memory of other workstations in the network. Our preliminary results show that predictive prefetching can reduce the remote-memory page fault time by 60% or more and that, by offloading prediction overhead to an idle node, GMS-3P can reduce this improved latency by between 24% and 44%, depending on the Markov model order.","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"248 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117347983","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}
Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868655
L. Renambot, H. Bal, D. Germans, H. Spoelder
We present the CAVEStudy system that enables scientists to interactively steer a simulation from a virtual reality (VR) environment. No modification to the source code is necessary. CAVEStudy allows interactive and immersive analysis of a simulation running on a remote computer. Using a high-level description of the simulation, the system generates the communication layer (based on CAVERN-Soft) needed to control the execution and to gather data at runtime. We describe three case-studies implemented with CAVEStudy: soccer simulation, diode laser simulation and molecular dynamics.
{"title":"CAVEStudy: an infrastructure for computational steering in virtual reality environments","authors":"L. Renambot, H. Bal, D. Germans, H. Spoelder","doi":"10.1109/HPDC.2000.868655","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868655","url":null,"abstract":"We present the CAVEStudy system that enables scientists to interactively steer a simulation from a virtual reality (VR) environment. No modification to the source code is necessary. CAVEStudy allows interactive and immersive analysis of a simulation running on a remote computer. Using a high-level description of the simulation, the system generates the communication layer (based on CAVERN-Soft) needed to control the execution and to gather data at runtime. We describe three case-studies implemented with CAVEStudy: soccer simulation, diode laser simulation and molecular dynamics.","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123970820","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}
Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868635
R. Bianchini, E. V. Carrera
Uses analytic modeling and simulation to evaluate network servers implemented on clusters of workstations. More specifically, we model the potential benefits of locality-conscious request distribution within the cluster and evaluate the performance of a cluster-based server called L2S (Locality and Load-balancing Server) which we designed in light of our experience with the model. Our most important modeling results show that locality-conscious distribution on a 16-node cluster can increase server throughput with respect to a locality-oblivious server by up to seven-fold, depending on the average size of the files requested and on the size of the server's working set. Our simulation results demonstrate that L2S achieves throughput that is within 22% of the full potential of locality-conscious distribution on 16 nodes, outperforming and significantly outscaling the best-known locality-conscious server. Based on our results and on the fact that the files serviced by network servers are becoming larger and more numerous, we conclude that our locality-conscious network server should prove very useful for its performance, scalability and availability.
使用分析建模和仿真来评估在工作站集群上实现的网络服务器。更具体地说，我们对集群中位置感知请求分发的潜在好处进行了建模，并评估了基于集群的服务器L2S (Locality and Load-balancing server)的性能，该服务器是我们根据使用该模型的经验设计的。我们最重要的建模结果表明，相对于位置无关的服务器，16节点集群上的位置敏感分布可以将服务器吞吐量提高多达7倍，具体取决于所请求文件的平均大小和服务器工作集的大小。我们的模拟结果表明，L2S在16个节点上实现的吞吐量在位置意识分布的全部潜力的22%以内，优于并显著超过了最著名的位置意识服务器。基于我们的结果以及网络服务器服务的文件变得越来越大和越来越多的事实，我们得出结论，我们的位置感知网络服务器应该证明其性能、可伸缩性和可用性非常有用。
{"title":"Evaluating cluster-based network servers","authors":"R. Bianchini, E. V. Carrera","doi":"10.1109/HPDC.2000.868635","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868635","url":null,"abstract":"Uses analytic modeling and simulation to evaluate network servers implemented on clusters of workstations. More specifically, we model the potential benefits of locality-conscious request distribution within the cluster and evaluate the performance of a cluster-based server called L2S (Locality and Load-balancing Server) which we designed in light of our experience with the model. Our most important modeling results show that locality-conscious distribution on a 16-node cluster can increase server throughput with respect to a locality-oblivious server by up to seven-fold, depending on the average size of the files requested and on the size of the server's working set. Our simulation results demonstrate that L2S achieves throughput that is within 22% of the full potential of locality-conscious distribution on 16 nodes, outperforming and significantly outscaling the best-known locality-conscious server. Based on our results and on the fact that the files serviced by network servers are becoming larger and more numerous, we conclude that our locality-conscious network server should prove very useful for its performance, scalability and availability.","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124735269","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}
Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868642
Yoshio Tanaka, Motonori Hirano, M. Sato, H. Nakada, S. Sekiguchi
Presents a performance evaluation of a wide-area cluster system based on a firewall-enabled Globus metacomputing toolkit. In order to establish communication links beyond the firewall, we have designed and implemented a resource manager called RMF (Resource Manager beyond the Firewall) and the Nexus Proxy, which relays TCP communication links beyond the firewall. In order to extend the Globus metacomputing toolkit to become firewall-enabled, we have built the Nexus Proxy into the Globus toolkit. We have built a firewall-enabled Globus-based wide-area cluster system in Japan and run some benchmarks on it. In this paper, we report various performance results, such as the communication bandwidth and latencies obtained, as well as application performance involving a tree search problem. In a wide-area environment, the communication latency through the Nexus Proxy is approximately six times larger when compared to that of direct communications. As the message size increases, however, the communication overhead caused by the Nexus Proxy can be negligible. We have developed a tree search problem using MPICH-G. We used a self-scheduling algorithm, which is considered to be suitable for a distributed heterogeneous metacomputing environment since it performs dynamic load balancing with low overhead. The performance results indicate that the communication overhead caused by the Nexus Proxy is not a severe problem in metacomputing environments.
{"title":"Performance evaluation of a firewall-compliant Globus-based wide-area cluster system","authors":"Yoshio Tanaka, Motonori Hirano, M. Sato, H. Nakada, S. Sekiguchi","doi":"10.1109/HPDC.2000.868642","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868642","url":null,"abstract":"Presents a performance evaluation of a wide-area cluster system based on a firewall-enabled Globus metacomputing toolkit. In order to establish communication links beyond the firewall, we have designed and implemented a resource manager called RMF (Resource Manager beyond the Firewall) and the Nexus Proxy, which relays TCP communication links beyond the firewall. In order to extend the Globus metacomputing toolkit to become firewall-enabled, we have built the Nexus Proxy into the Globus toolkit. We have built a firewall-enabled Globus-based wide-area cluster system in Japan and run some benchmarks on it. In this paper, we report various performance results, such as the communication bandwidth and latencies obtained, as well as application performance involving a tree search problem. In a wide-area environment, the communication latency through the Nexus Proxy is approximately six times larger when compared to that of direct communications. As the message size increases, however, the communication overhead caused by the Nexus Proxy can be negligible. We have developed a tree search problem using MPICH-G. We used a self-scheduling algorithm, which is considered to be suitable for a distributed heterogeneous metacomputing environment since it performs dynamic load balancing with low overhead. The performance results indicate that the communication overhead caused by the Nexus Proxy is not a severe problem in metacomputing environments.","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125197449","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}
Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868650
J. Beiriger, Wilbur R. Johnson, H. Bivens, S. Humphreys, R. Rhea
The Accelerated Strategic Computing Initiative (ASCI) computational grid is being constructed to interconnect the high performance computing resources of the nuclear weapons complex. The grid will simplify access to the diverse computing, storage, network, and visualization resources, and will enable the coordinated use of shared resources regardless of location. To match existing hardware platforms, required security services, and current simulation practices, the Globus MetaComputing Toolkit was selected to provide core grid services. The ASCI grid extends Globus functionality by operating as an independent grid, incorporating Kerberos-based security, interfacing to Sandia's Cplant/sup TM/, and extending job monitoring services. To fully meet ASCI's needs, the architecture layers distributed work management and criteria-driven resource selection services on top of Globus. These services simplify the grid interface by allowing users to simply request "run code X anywhere". This paper describes the initial design and prototype of the ASCI grid.
{"title":"Constructing the ASCI computational grid","authors":"J. Beiriger, Wilbur R. Johnson, H. Bivens, S. Humphreys, R. Rhea","doi":"10.1109/HPDC.2000.868650","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868650","url":null,"abstract":"The Accelerated Strategic Computing Initiative (ASCI) computational grid is being constructed to interconnect the high performance computing resources of the nuclear weapons complex. The grid will simplify access to the diverse computing, storage, network, and visualization resources, and will enable the coordinated use of shared resources regardless of location. To match existing hardware platforms, required security services, and current simulation practices, the Globus MetaComputing Toolkit was selected to provide core grid services. The ASCI grid extends Globus functionality by operating as an independent grid, incorporating Kerberos-based security, interfacing to Sandia's Cplant/sup TM/, and extending job monitoring services. To fully meet ASCI's needs, the architecture layers distributed work management and criteria-driven resource selection services on top of Globus. These services simplify the grid interface by allowing users to simply request \"run code X anywhere\". This paper describes the initial design and prototype of the ASCI grid.","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126996112","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}
Pub Date : 2000-08-01DOI: 10.1109/HPDC.2000.868665
H. Nishi, K. Tasho, J. Yamamoto, T. Kudoh, H. Amano
The Real World Computing Partnership (RWCP) has developed a local area system network (LASN) called RHiNET-1 (RWCP High-performance NETwork, version 1) using 1.33-Gbps optical interconnections for high-performance computing using personal computers distributed in an office or laboratory environment. The network interface, RHiNET-1/NI, uses a complex programmable logic device (CPLD) based protocol controller to provide an easy evaluation platform for various protocols. It fits in a 32-bit/33-MHz PCI bus. The switch, RHiNET-1/SW, consists of a single-chip CMOS switch and external SRAM. It provides low-latency, reliable communication with a flexible topology design. We are currently evaluating protocols on RHiNET-1. RHiNET-1 will enable a new form of high-performance computing environment. We are also developing the second implementation, RHiNET-2. RHiNET-2/NI will support a 64-bit/66-MHz PCI bus. RHiNET-2/SW is an 8-Gbps/port 8/spl times/8 single-chip ASIC switch. The aggregate bandwidth of RHiNET-2/SW is 64 Gbps.
{"title":"A local area system network RHiNET-1: a network for high performance parallel computing","authors":"H. Nishi, K. Tasho, J. Yamamoto, T. Kudoh, H. Amano","doi":"10.1109/HPDC.2000.868665","DOIUrl":"https://doi.org/10.1109/HPDC.2000.868665","url":null,"abstract":"The Real World Computing Partnership (RWCP) has developed a local area system network (LASN) called RHiNET-1 (RWCP High-performance NETwork, version 1) using 1.33-Gbps optical interconnections for high-performance computing using personal computers distributed in an office or laboratory environment. The network interface, RHiNET-1/NI, uses a complex programmable logic device (CPLD) based protocol controller to provide an easy evaluation platform for various protocols. It fits in a 32-bit/33-MHz PCI bus. The switch, RHiNET-1/SW, consists of a single-chip CMOS switch and external SRAM. It provides low-latency, reliable communication with a flexible topology design. We are currently evaluating protocols on RHiNET-1. RHiNET-1 will enable a new form of high-performance computing environment. We are also developing the second implementation, RHiNET-2. RHiNET-2/NI will support a 64-bit/66-MHz PCI bus. RHiNET-2/SW is an 8-Gbps/port 8/spl times/8 single-chip ASIC switch. The aggregate bandwidth of RHiNET-2/SW is 64 Gbps.","PeriodicalId":400728,"journal":{"name":"Proceedings the Ninth International Symposium on High-Performance Distributed Computing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115933576","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：