CANPC '97 Final Program (Texas, Feb97)

Workshop on Communication and Architectural Support for Network-based
                                                          Parallel Computing


                                                                  CANPC '97


to be held in conjunction with Third International Symposium on High
                          Performance Computer Architecture (HPCA-3)
          The Menger Hotel, San Antonio, Texas, February 1-2, 1997


                                  Sponsored by the IEEE Computer Society
------------------------------------------------------------------------
For details, please refer to http://www.cis.ohio-state.edu/~canpc97.
------------------------------------------------------------------------


      * Advance Program
      * Registration Information
      * Location and Hotel Reservation
      * Theme of the Workshop
      * Program Committee
      * Additional Information


------------------------------------------------------------------------


                                                              Advance Program


February 1 (Saturday)


8:00 - 8:30 Registration


8:25 - 8:30 Opening


8:30 - 9:30 Keynote Speech


          Clusters, Availability, and Scaling: A Golden Triangle, Greg
          Pfister, IBM Research


9:30 - 10:00 Coffee Break


Each session involves presentation by the authors as well as group
                                                      discussion.


10:00 - 11:45 Session I


          Communication Mechanisms, Session Chair: Sudhakar Yalamanchili,
          Georgia Tech


            * Efficient Communication Mechanisms for Cluster Based Parallel
                Computing, A. Davis, M. Swanson, and M. Parker, University of
                Utah
            * Stream Sockets on SHRIMP, S. N. Damianakis, C. Dubnicki, and
                E. W. Felten, Princeton University
            * A Simple and Efficient Process and Communication Abstraction
                for Network Operating Systems, D. C. DiNucci, NASA Ames
                Research Center


11:45 - 1:15 Lunch Break


1:15 - 3:00 Session II


          Efficient Communication Support, Session Chair: Henri Bal, Vrije
          University, The Netherlands


            * Arachne: A Portable Threads Library Supporting Migrant
                Threads on Heterogeneous Network Farms, B. Dimitrov and V.
                Rego, Purdue University
            * Transparent Treatment of Remote Pointers Using IPC Primitive
                in RPC Systems, S. Kim, Semyung University, M. Hyun, Daewon
                Junior College, and S. Lee, Kyungpook National University,
                Korea
            * An Operating System Support to Low-Overhead Communications in
                NOW Clusters, P. Marenzoni, G. Rimassa, M. Vignali, M.
                Bertozzi, G. Conte, and P. Rossi, Universita di Parma, Italy


3:00 - 3:30 Coffee Break


3:30 - 4:45 Session III


          Routing, Session Chair: Dhabaleswar K. Panda, Ohio State
          University


            * Efficient Adaptive Routing in Networks of Workstations with
                Irregular Topology, F. Silla, M. P. Malumbres, A. Robles, P.
                Lopez, and J. Duato, Universidad Politechnica de Valencia,
                Spain
            * A Deadlock Avoidance Method for Computer Networks, B. Abali,
                IBM T.J. Watson Research Center


4:45 - 5:00 Break


5:00 - 6:15 Session IV


          ATM Switching, Session Chair: Jose Duato, University of
          Politecnica de Valencia, Spain


            * Extending ATM Networks for Efficient Reliable Multicast, J.
                S. Turner, Washington University
            * ATLAS-I: A Single-Chip ATM Switch for NOWs, M. G. H.
                Katevenis, P. Vatsolaki, D. Serpanos, and E. Markatos,
                Institute of Computer Science, FORTH, Greece


February 2 (Sunday)


7:45 - 8:00 Registration


8:00 - 9:45 Session V


          Synchronization and Load Balancing, Session Chair: Sandhya
          Dwarkadas, Univ. of Rochester


            * Distributed Hardware Support for Process Synchronization in
                NSM Workstation Clusters, J. Bonney, R. Ramanujan, A. Ahamad,
                S. Takkella, and K. Thurber, Architecture Technology
                Corporation
            * Synchronization Support in I/O Adapter Based SCI Clusters, K.
                Omang, University of Oslo, Norway
            * Load Balancing for Regular Data-Parallel Applications on a
                Workstation Network, M. Kaddoura, Architecture Technology
                Corporation


9:45 - 10:15 Coffee Break


10:15 - 12:00 Session VI


          Performance Evaluation, Session Chair: Jehoshua Bruck, Caltech


            * A Comparison of Three High Speed Networks for Parallel
                Cluster Computing, H. Bal, R. Hofman, and K. Verstoep, Vrije
                Universiteit, The Netherlands
            * Understanding the Performance of DSM Applications, W. Meira
                Jr., T. J. LeBlanc, N. Hardavellas, University of Rochester,
                and C. Amorim, UFRJ, Rio de Janeiro, Brazil
            * Performance Metrics and Measurement Techniques of Collective
                Communication Services, N. Nupairoj and L. M. Ni, Michigan
                State University


12:00 - 1:30 Lunch Break


1:30 - 3:15 Session VII


          Communication Protocol, Session Chair: Al Davis, University of
          Utah


            * CLAM: Connection-less, Lightweight, and Multiway
                Communication Support for Distributed Computing, J. C. Gomez
                and V. Rego, Purdue University, and V. S. Sunderam, Emory
                University
            * Network-wide Cooperative Computing Architecture (NCCA), H.
                Yamashita, T. Suguri, S. Kinoshita, NTT Information and
                Communication Systems Laboratories, and Y. Okada, NTT Network
                Strategy Planning Department, Japan
            * Data Movement and Control Substrate for Parallel Scientific
                Computing, N. Chrisochoides, Univ. of Notre Dame, I.
                Kodukula, and K. Pingali, Cornell University


3:15 - 3:45 Coffee Break


3:45 - 5:30 Panel Session


          Future Interconnects for Network-based Parallel Computing: ATM vs.
          Ethernet vs. other.
          Moderator: Craig Stunkel, IBM T.J. Watson Research
          Tentative Panelists: Henri Bal, Vrije University, The Netherlands;
          Shuki Bruck, Caltech; Jose Duato, University of Politecnica de
          Valencia, Spain; Lionel Ni, Michigan State University; Jon Turner,
          Washington University; and Thorsten von Eicken, Cornell
          University.


------------------------------------------------------------------------


                                                    Registration Information


If you are planning to register for HPCA-3 conference as well as its
workshop(s) and tutorial, please refer to the HPCA-3 conference
registration information.


                                                                                              CANPC'97 Workshop


                                                                                Advance On-site


  IEEE Members $100 $120


  Non-members $125 $150


  Full-time Students $100 $120


Advance registration deadline has been extended to January 17, 1997.


The registration fee includes a copy of the workshop proceedings,
continental breakfasts, and coffee breaks.


To register using a credit card (Mastercard or Visa only), please
e-mail the completed ASCII registration form to: hpca3@cs.utsa.edu; or
fax/mail the completed form to the Registration Chair:


Raj Boppana
Division of Computer Science
Univ. of Texas at San Antonio
San Antonio, Texas 78249-0667, USA


Tel: 210-458-5692
Fax: 210-458-4437


To register using a check, please mail the completed form with a check
(payable to HPCA-3) for the correct amount to the address given above.
Checks should be in U.S. dollars drawn on U.S. banks.


                                              Workshop Registration form


Last Name:____________ First Name:____________ Middle Initial:____


Organization:_____________________________________________________


Address:__________________________________________________________


City:__________ State:______________ Zip Code:____________________


Country:___________ Telephone:_______________ Fax:________________


Email Address:____________________________________________________


IEEE Member:__ Non-member:__ Student:__ IEEE Member No:___________


            Symposium: US$______


            Tutorial: US$______


            Workshop(s): US$______ Specify choice of workshop(s)( )


            Total: US$______


Check, payable to HPCA-3, in U.S. dollars drawn on a US Bank only:


Credit Card: VISA__ or MasterCard__ Credit Card No._______________


Expiration date:__________ Signature______________________________


---------------------------------------------------------------------


                                              Location and Hotel Reservation


Conference Site


HPCA-3 and its workshops will be held in San Antonio's Menger Hotel, a
historic landmark hotel. It is next door to the Alamo, adjacent to the
Rivercenter Mall, the IMAX Theater and River Walk and two blocks to
the convention center. The hotel is located in front of the Alamo
Plaza where the Sea World shuttle and sightseeing tours depart. Please
visit http://numedia.tddc.net/sa/index.nclk or
http://rabbit.cs.utsa.edu/about_sa.html to obtain more information
about San Antonio.


American humorist and homespun philosopher Will Rogers once described
San Antonio as One of America's four unique cities. He had a natural
instinct for getting to the very essence of a subject, and his comment
about San Antonio is no exception.


San Antonio truly is unique. From its founding in 1691 by Spanish
missionaries, San Antonio has grown from a sleepy little Texas pueblo
to the 9th largest city in the United States. Along the way it has
been the birthplace of the Texas revolution with the Battle of the
Alamo in 1836. It is the new home of bioscience and hi-tech industry
now. In all, over half a dozen cultures, from Spanish and German to
Lebanese and Greek, have impacted the growth of San Antonio. And their
influence is still evident in the architecture, festivals, cuisine and
customes which all contribute to the uniqueness and charm of the city.


Hotel Reservation


A block of rooms at the Menger Hotel are reserved for HPCA-3 and other
workshops. The conference rate is $85 per night for a single/double
room. Please make reservations directly with the hotel by calling
(210) 223-4361 or (800) 345-9285 (toll-free). The fax number is: (210)
228-0022. Reservations must be received by January 10, 1997 to
guarantee the conference rate. The address of the hotel is: The Menger
Hotel, 204 Alamo Plaza, San Antonio, Texas 78205. Please visit
http://www.txdirect.net/menger/ to obtain more information about the
Menger Hotel.


----------------------------------------------------------------------


                                                  Theme of the Workshop




Clusters of workstations connected by local area networks (LANs) are
gaining popularity as a platform for cost-effective parallel
processing, establishing the paradigm of network-based parallel
computing. Hardware and software LAN technology was not initially
developed for parallel processing, and thus the communication overhead
between workstations can be quite high. Efficient parallel execution
is often dependent on a high level of synchronization between tasks,
and there is typically little support for this in the complex
multitasking, multiuser workstation environment. These weaknesses have
forced severe constraints on maximizing parallel performance in
workstation clusters. Many research groups from academia, industry,
and research labs are currently engaged in deriving novel hardware and
software solutions to alleviate these bottlenecks. The goal of this
workshop is to bring together researchers and practitioners working in
this area to discuss state-of-the-art solutions as well as future
trends for providing efficient communication and architectural support
for network-based parallel computing.


-----------------------------------------------------------------------


WORKSHOP CO-CHAIRS:


Dhabaleswar Panda (Ohio State) and Craig Stunkel (IBM T.J. Watson)


PROGRAM COMMITTEE:


      * Tilak Agerwala (IBM)
      * Henri Bal (Vrije U., The Netherlands)
      * Adam Beguelin (Carnegie Mellon)
      * Jehoshua Bruck (Caltech)
      * Al Davis (Utah)
      * David Du (Minnesota)
      * Jose Duato (U. Politecnica de Valencia)
      * Sandhya Dwarkadas (Rochester)
      * Ian Foster (Argonne National Lab)
      * Michael Foster (NSF)
      * Ching-Tien Ho (IBM Almaden)
      * Lionel Ni (Michigan St.)
      * Steve Scott (Cray Research)
      * Marc Snir (IBM T.J. Watson)
      * Per Stenstrom (Chalmers U., Sweden)
      * Vaidy Sunderam (Emory)
      * Anand Tripathi (NSF/Minnesota)
      * Thorsten von Eicken (Cornell)
      * David Wood (Wisconsin)
      * Sudhakar Yalamanchili (Georgia Tech)


----------------------------------------------------------------------


ADDITIONAL INFORMATION:


For additional information, please refer to
http://www.cis.ohio-state.edu/ ~canpc97 or send e-mail to
canpc97@cis.ohio-state.edu.


----------------------------------------------------------------------


--
Craig Stunkel IBM T.J. Watson Research Center
stunkel@watson.ibm.com P.O. Box 218
(914)945-3090 Yorktown Heights, NY 10598
--

Return to the comp.compilers page.
Search the comp.compilers archives again.