Pub Date : 1995-03-05DOI: 10.1109/CMPCON.1995.512376
Tony M. Brewer
A highly scalable system implementing Convex's Exemplar Architecture has been designed. The system allows up to 128 Hewlett-Packard processors to efficiently cooperate together. All processors may be used together to substantially decrease the time-to-solution for large applications, or the processors may be used in smaller subsets in a time-sharing parallel environment. The system has many features which enhance the parallel usability of the system. These features include globally shared memory, interconnect caches, memory massed semaphores, and hardware messaging support.
{"title":"A highly scalable system utilizing up to 128 PA-RISC processors","authors":"Tony M. Brewer","doi":"10.1109/CMPCON.1995.512376","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512376","url":null,"abstract":"A highly scalable system implementing Convex's Exemplar Architecture has been designed. The system allows up to 128 Hewlett-Packard processors to efficiently cooperate together. All processors may be used together to substantially decrease the time-to-solution for large applications, or the processors may be used in smaller subsets in a time-sharing parallel environment. The system has many features which enhance the parallel usability of the system. These features include globally shared memory, interconnect caches, memory massed semaphores, and hardware messaging support.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116864101","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 : 1995-03-05DOI: 10.1109/CMPCON.1995.512379
J. Bartlett
In order to separate promises from practice in personal digital assistants (PDAs) and wireless communications, we decided to try to build a wireless PDA-based client to access the world wide web. Using equipment available in the winter of 1994, we were able to build a client that we call W4, the Wireless World Wide Web. In this paper we describe our initial design choices, implementation, experience with the device, and close with some thoughts about next steps in this area.
{"title":"Experience with a wireless world wide web client","authors":"J. Bartlett","doi":"10.1109/CMPCON.1995.512379","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512379","url":null,"abstract":"In order to separate promises from practice in personal digital assistants (PDAs) and wireless communications, we decided to try to build a wireless PDA-based client to access the world wide web. Using equipment available in the winter of 1994, we were able to build a client that we call W4, the Wireless World Wide Web. In this paper we describe our initial design choices, implementation, experience with the device, and close with some thoughts about next steps in this area.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115199219","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 : 1995-03-05DOI: 10.1109/CMPCON.1995.512421
D. Greenley, J. Bauman, D. Chang, Dennis Chen, R. Eltejaein, P. Ferolito, P. Fu, R. Garner, D. Greenhill, H. Grewal, K. Holdbrook, B. Kim, Leslie Kohn, H. Kwan, M. Levitt, G. Maturana, D. Mrazek, C. Narasimhaiah, K. Normoyle, N. Parveen, P. Patel, A. Prabhu, M. Tremblay, M. Wong, L. Yang, K. Yarlagadda, R. Yu, R. Yung, G. Zyner
UltraSPARC is the first microprocessor from Sun Microsystems' SPARC Technology Business to implement the new 64-bit SPARC V9 architecture. ULtraSPARC is equipped with unique multimedia capabilities and is capable of 4-way superscalar instruction dispatch, with an emphasis on maximal system efficiency and throughput in the execution of complex, memory-intensive applications. UltraSPARC maintains a strict binary compatibility with the thousands of existing 32-bit applications developed for other SPARC processors. This paper describes the feature set and operation of UItraSPARC.
{"title":"UltraSPARC: the next generation superscalar 64-bit SPARC","authors":"D. Greenley, J. Bauman, D. Chang, Dennis Chen, R. Eltejaein, P. Ferolito, P. Fu, R. Garner, D. Greenhill, H. Grewal, K. Holdbrook, B. Kim, Leslie Kohn, H. Kwan, M. Levitt, G. Maturana, D. Mrazek, C. Narasimhaiah, K. Normoyle, N. Parveen, P. Patel, A. Prabhu, M. Tremblay, M. Wong, L. Yang, K. Yarlagadda, R. Yu, R. Yung, G. Zyner","doi":"10.1109/CMPCON.1995.512421","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512421","url":null,"abstract":"UltraSPARC is the first microprocessor from Sun Microsystems' SPARC Technology Business to implement the new 64-bit SPARC V9 architecture. ULtraSPARC is equipped with unique multimedia capabilities and is capable of 4-way superscalar instruction dispatch, with an emphasis on maximal system efficiency and throughput in the execution of complex, memory-intensive applications. UltraSPARC maintains a strict binary compatibility with the thousands of existing 32-bit applications developed for other SPARC processors. This paper describes the feature set and operation of UItraSPARC.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"705 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122987556","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 : 1995-03-05DOI: 10.1109/CMPCON.1995.512392
W. Tetzlaff, R. Flynn
Large scale multimedia systems combine technologies from audio and video systems, communications systems, and computer systems. In multimedia systems compressed video files are stored digitally on a video server that is typically shared by a large number of users. The two key metrics for a video server are the amount of material that it can store and the number of video streams it can play simultaneously. A video server must be composed of multiple storage units, processing units and network connections in order to store the large amount of digital data and concurrently play the large number of streams. In this paper, we propose a taxonomy of video server organizations, compare the alternative systems and show how some of the systems which have been commercially proposed or built fit into the taxonomy.
{"title":"Elements of scalable video servers","authors":"W. Tetzlaff, R. Flynn","doi":"10.1109/CMPCON.1995.512392","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512392","url":null,"abstract":"Large scale multimedia systems combine technologies from audio and video systems, communications systems, and computer systems. In multimedia systems compressed video files are stored digitally on a video server that is typically shared by a large number of users. The two key metrics for a video server are the amount of material that it can store and the number of video streams it can play simultaneously. A video server must be composed of multiple storage units, processing units and network connections in order to store the large amount of digital data and concurrently play the large number of streams. In this paper, we propose a taxonomy of video server organizations, compare the alternative systems and show how some of the systems which have been commercially proposed or built fit into the taxonomy.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116351181","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 : 1995-03-05DOI: 10.1109/CMPCON.1995.512409
S. Lemon, Kennan Rossi
The Object-Oriented Device Driver Model (OODDM) is a new way of integrating a computer's software with its hardware. The OODDM brings the benefits of OO technology to device and I/O support. The OODDM provides new levels of hardware innovation, dynamic device and resource configuration, support for multiple host OSs, interface flexibility and extensibility, driver reuse, and ease of development for the Independent Hardware Vendor (IHV). Using object technology and collections of C++ classes called frameworks, the OODDM provides you with powerful and flexible input/output (I/O) services. Using the OODDM, you can build on Taligent designs to produce efficient, reliable, and portable I/O software quickly. This paper highlights the fundamental features and concepts of the OODDM, and provides a look at an initial implementation.
{"title":"on object oriented device driver model","authors":"S. Lemon, Kennan Rossi","doi":"10.1109/CMPCON.1995.512409","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512409","url":null,"abstract":"The Object-Oriented Device Driver Model (OODDM) is a new way of integrating a computer's software with its hardware. The OODDM brings the benefits of OO technology to device and I/O support. The OODDM provides new levels of hardware innovation, dynamic device and resource configuration, support for multiple host OSs, interface flexibility and extensibility, driver reuse, and ease of development for the Independent Hardware Vendor (IHV). Using object technology and collections of C++ classes called frameworks, the OODDM provides you with powerful and flexible input/output (I/O) services. Using the OODDM, you can build on Taligent designs to produce efficient, reliable, and portable I/O software quickly. This paper highlights the fundamental features and concepts of the OODDM, and provides a look at an initial implementation.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133615156","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 : 1995-03-05DOI: 10.1109/CMPCON.1995.512405
Gary Hoffman, Daniel Moore
The IEEE 1394 high-speed serial bus promises to revolutionize the transport of digital data for computers and for professional and consumer electronics products. By providing an inexpensive non-proprietary high-speed method of interconnecting digital devices, IEEE 1394 is a truly universal I/O connection. Its scalable architecture and flexible peer-to-peer topology make 1394 ideal for connecting devices from computers and hard drives, to digital audio and video hardware. Isochronous, just in time delivery, allows low-cost implementations of time-critical multimedia interfaces. This paper examines this IEEE 1394 bus and provides a glimpse into its future potential.
{"title":"IEEE 1394: a ubiquitous bus","authors":"Gary Hoffman, Daniel Moore","doi":"10.1109/CMPCON.1995.512405","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512405","url":null,"abstract":"The IEEE 1394 high-speed serial bus promises to revolutionize the transport of digital data for computers and for professional and consumer electronics products. By providing an inexpensive non-proprietary high-speed method of interconnecting digital devices, IEEE 1394 is a truly universal I/O connection. Its scalable architecture and flexible peer-to-peer topology make 1394 ideal for connecting devices from computers and hard drives, to digital audio and video hardware. Isochronous, just in time delivery, allows low-cost implementations of time-critical multimedia interfaces. This paper examines this IEEE 1394 bus and provides a glimpse into its future potential.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131399052","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 : 1995-03-05DOI: 10.1109/CMPCON.1995.512395
Chien Chen, Yizhi Lu, Anthong Wong
HaL's cache subsystem is designed to provide high memory bandwidth to the processor. The cache is non-blocking: the cache can service a new CPU request while four cache line refills are progressing in the background. The cache subsystem is also designed to handle speculative and out-of-order CPU requests. The cache-CPU interface protocol allows precise interrupts to be maintained under out-of-order completion. The cache design, as other parts in HaL's PM1 module pays attention to reliability and availability (RAS). The design takes advantage of SPARC V9's RED state feature, and allows the software to recover from certain hardware errors. In addition, the cache uses SECDED (Single Error Correction Double Error Detection) to protect its data store and parity to protect its tag store.
{"title":"Microarchitecture of HaL's cache subsystem","authors":"Chien Chen, Yizhi Lu, Anthong Wong","doi":"10.1109/CMPCON.1995.512395","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512395","url":null,"abstract":"HaL's cache subsystem is designed to provide high memory bandwidth to the processor. The cache is non-blocking: the cache can service a new CPU request while four cache line refills are progressing in the background. The cache subsystem is also designed to handle speculative and out-of-order CPU requests. The cache-CPU interface protocol allows precise interrupts to be maintained under out-of-order completion. The cache design, as other parts in HaL's PM1 module pays attention to reliability and availability (RAS). The design takes advantage of SPARC V9's RED state feature, and allows the software to recover from certain hardware errors. In addition, the cache uses SECDED (Single Error Correction Double Error Detection) to protect its data store and parity to protect its tag store.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133825027","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 : 1995-03-05DOI: 10.1109/CMPCON.1995.512414
A. Bell
The rapid growth of the network infrastructure combined with the continuing reduction in the cost of storage is causing a fundamental shift in the delivery of information content, from physical to electronic means. Multimedia databases ranging well into the Terabyte range are currently not unusual, and applications in the Petabyte range can be envisioned in the future. Following an overview of the distributed storage system architecture and the requirements of some example storage intensive applications, this article describes the key SW and HW components, and some of the trade-offs required to provide the optimum solution.
{"title":"Storage intensive applications in the distributed environment","authors":"A. Bell","doi":"10.1109/CMPCON.1995.512414","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512414","url":null,"abstract":"The rapid growth of the network infrastructure combined with the continuing reduction in the cost of storage is causing a fundamental shift in the delivery of information content, from physical to electronic means. Multimedia databases ranging well into the Terabyte range are currently not unusual, and applications in the Petabyte range can be envisioned in the future. Following an overview of the distributed storage system architecture and the requirements of some example storage intensive applications, this article describes the key SW and HW components, and some of the trade-offs required to provide the optimum solution.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115364538","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 : 1995-03-05DOI: 10.1109/CMPCON.1995.512360
B. C. Neuman, Gennady Medvinsky
Secure methods of payment are needed before we will see widespread commercial use of the Internet. Recently proposed and implemented payment methods follow one of three models: electronic currency, credit-debit, and secure credit card transactions. Such payment services have different strengths and weaknesses with respect to the requirements of security, reliability, scalability, anonymity, acceptability, customer base, flexibility, convertibility, efficiency, ease of integration with applications, and ease of use. NetCheque is a payment system based on the credit-debit model. NetCheque is described and its strengths with respect to these requirements are discussed.
{"title":"Requirements for network payment: the NetCheque perspective","authors":"B. C. Neuman, Gennady Medvinsky","doi":"10.1109/CMPCON.1995.512360","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512360","url":null,"abstract":"Secure methods of payment are needed before we will see widespread commercial use of the Internet. Recently proposed and implemented payment methods follow one of three models: electronic currency, credit-debit, and secure credit card transactions. Such payment services have different strengths and weaknesses with respect to the requirements of security, reliability, scalability, anonymity, acceptability, customer base, flexibility, convertibility, efficiency, ease of integration with applications, and ease of use. NetCheque is a payment system based on the credit-debit model. NetCheque is described and its strengths with respect to these requirements are discussed.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114307334","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 : 1995-03-05DOI: 10.1109/CMPCON.1995.512407
L. Roberts
The new Available Bit Rate (ABR) service with explicit rate flow control and a minimum rate guarantee (MCR) provides such a powerful service option that it may well be more effective for video and voice than the Variable Bit Rate (VBR) service currently defined for real time use. An MPEG compressed video signal can encode at any rate the network requests down to a defined minimum. If we set the Minimum Cell Rate (MCR) to the lowest rate, and adjust the coding rate dynamically to the network feedback, the resultant video is extremely high quality and the channel is used at over 95% utilization. On the other hand, if VBR service is used, the codec runs at its own rate and the network must allocate far more bandwidth than the average used due to the possibility of many such signals peaking at once. With VBR, the utilization for MPEG video is from 30-60%. Thus, ABR may be considerably less expensive for video with little or no loss in quality.
{"title":"Can ABR service replace VBR service in ATM networks","authors":"L. Roberts","doi":"10.1109/CMPCON.1995.512407","DOIUrl":"https://doi.org/10.1109/CMPCON.1995.512407","url":null,"abstract":"The new Available Bit Rate (ABR) service with explicit rate flow control and a minimum rate guarantee (MCR) provides such a powerful service option that it may well be more effective for video and voice than the Variable Bit Rate (VBR) service currently defined for real time use. An MPEG compressed video signal can encode at any rate the network requests down to a defined minimum. If we set the Minimum Cell Rate (MCR) to the lowest rate, and adjust the coding rate dynamically to the network feedback, the resultant video is extremely high quality and the channel is used at over 95% utilization. On the other hand, if VBR service is used, the codec runs at its own rate and the network must allocate far more bandwidth than the average used due to the possibility of many such signals peaking at once. With VBR, the utilization for MPEG video is from 30-60%. Thus, ABR may be considerably less expensive for video with little or no loss in quality.","PeriodicalId":415918,"journal":{"name":"Digest of Papers. COMPCON'95. Technologies for the Information Superhighway","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123920117","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：