Path: utzoo!mnetor!uunet!husc6!purdue!gatech!hubcap!Bill From: bill@gatech.edu (Bill Appelbe) Newsgroups: comp.parallel Subject: CALL FOR PAPERS Message-ID: <1463@hubcap.UUCP> Date: 21 Apr 88 13:05:54 GMT Sender: fpst@hubcap.UUCP Lines: 108 Keywords: architecture, HICSS Approved: parallel@hubcap.clemson.edu CALL FOR PAPERS HAWAII INTERNATIONAL CONFERENCE ON SYSTEM SCIENCES - 22 High Performance Architectures KAILUA-KONA, HAWAII - JANUARY 3-6, 1989 The Architecture Track of HICSS-22 will contain a series of papers focusing upon Architectures which are at the leading edge of the performance/price curve. Such systems are variously classified as: o Mini-supercomputers o Super-minicomputers o High performance workstations Examples of such systems/manufactures include, but are not limited to: o Convex, Alliant, Warp, RP-3 o Sequent, Multiflow o Ardent, Stellar, Sillicon Graphics, SUN, Apollo, MIPs Their rationale, design tradeoffs, and performance is in- tended to be a major focus in this mini-track. The majority of the information available about such architectures tends to focus upon simple performance benchmarks and metrics, such as Whetstones, Dhrystones, MIPs, MFLOPs, etc., which unfortunately muddle the issues of architecture, hardware, compilers, and applications. From a researcher's viewpoint the major issues are why the design and its associated compromises were adopted, and how well the architecture matches a spectrum of hardware, lan- guages, and applications. From a users viewpoint the major issues are what the performance of the architecture can ac- tually deliver for a given application. Papers are invited that give an analysis of high-performance architectures, from either a developer's or user's perspec- tive. For example: o How do existing high-performance architectures effec- tively exploit hardware and applications character- istics to yield high performance. o What are the rationale and design tradeoffs to bal- ance - High performance for a range of applications - Low design, manufacturing costs - Ease of evolution to match rising hardware per- formance - Architectures designed to enhance software and applications portability o How can high-performance architectures be instru- mented and meaningfully compared? o How do projected continued hardware advances affect the evolution of current high-performance architec- tures? HICSS-22 is sponsored by the University of Hawaii in coop- eration with the ACM, the Computer Society, and the Pacific Research Institute for Information Systems and Man- agement (PRIISM). INSTRUCTIONS FOR SUBMITTING PAPERS Manuscripts should be 22-26 typewritten, double-spaced pages in length. Do not send submissions that are sig- nificantly shorter or longer than this. Papers must not have been previously presented or published, nor cur- rently submitted for journal publication. Each manu- script will be put through a rigorous refereeing process. Manuscripts should have a title page that in- cludes the title of the paper, full name of its author(s), affiliation(s), complete physical and elec- tronic address(es), telephone number(s) and a 300-word abstract of the paper. DEADLINES o A 300-word abstract is due by May 10, 1988. o Feedback to author concerning abstract by May 15, 1988. o Six copies of the manuscript are due by June 6, 1988. o Notification of accepted papers by September 1, 1988. o Accepted manuscripts, camera-ready, are due by Octo- ber 3, 1988. SEND SUBMISSIONS AND QUESTIONS TO Bill Appelbe, Associate Professor School of Information and Computer Science Georgia Tech Atlanta GA 30332-0280 Phone: (404)-894-6187 INTERNET: bill@gatech.edu UUCP: ...!gatech!bill -- Bill Appelbe School of Information & Computer Science, Georgia Tech, Atlanta GA 30332 CSNet: bill @ GATech ARPA: bill%GATech.CSNet @ CSNet-Relay.ARPA uucp: ...!{akgua,allegra,hplabs,ihnp4,linus,seismo,ulysses}!gatech!bill