Research projects with DAS at Vrije Universiteit Amsterdam


Albatross project:

In the Albatross project we use DAS to study algorithms and applications for wide-area parallel computing. We have run a set of Orca applications on the wide-area DAS system, analyzed their performance, and hand-optimized the applications to take the wide-area structure into account. The results indicate that surprisingly high efficiencies can be obtained on a wide-area cluster, despite the high latencies and low throughput of the WAN links.

Orca project:

We have developed efficient communication software for Myrinet (the local area network of DAS), including LANai firmware, higher-level communication protocols (Panda), and programming systems (Orca and PVM). We have analyzed the performance of the Orca system on DAS in detail and we have compared it against two other distributed shared memory systems (CRL and TreadMarks). We have also done a performance comparison between Myrinet, ATM, and Fast Ethernet, using a collection of challenging applications.

Manta project:

Manta is high-performance parallel Java system with a fast implementation of RMI. Manta has been implemented on the local DAS clusters (using Myrinet) and on the wide-area DAS system.


Research papers of Vrije Universiteit Amsterdam using DAS

javagrande99.ps.Z
R. van Nieuwpoort, J. Maassen, H.E. Bal, T. Kielmann, and R. Veldema, "Wide-Area Parallel Computing in Java", ACM 1999 Java Grande Conference, Palo Alto, California, June 1999. Copyright 1999 by ACM, Inc.
aaai99.ps.gz
J.W. Romein, A. Plaat, H.E. Bal, and J. Schaeffer, "Transposition Table Driven Work Scheduling in Distributed Search", 16th National Conference on Artificial Intelligence (AAAI), July 18-22, 1999, Orlando, Florida. Copyright 1999 by AAAI
robocup99.ps.Z
Hans J.W. Spoelder, Luc Renambot, Desmond Germans, Henri E. Bal, "Interactive and Collaborative Visualization of Robot Soccer", Vrije Universiteit Amsterdam, Faculty of Science, March 1999.
ppopp99_manta.ps
J. Maassen, R. van Nieuwpoort, R. Veldema, H.E. Bal, and A. Plaat: "An Efficient Implementation of Java's Remote Method Invocation", ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP'99), May 1999, Atlanta, GA. Copyright 1999 by ACM, Inc.
ppopp99_magpie.ps
T. Kielmann, R.F.H. Hofman, H.E. Bal, A. Plaat, and R.A.F. Bhoedjang: "MagPIe: MPI's Collective Communication Operations for Clustered Wide Area Systems", ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP'99), May 1999, Atlanta, GA. Copyright 1999 by ACM, Inc.
hpca99.ps.gz
A. Plaat, H.E. Bal, and R.F.H. Hofman: "Sensitivity of Parallel Applications to Large Differences in Bandwidth and Latency in Two-Layer Interconnects", Fifth International Symposium On High Performance Computer Architecture (HPCA-5), January 1999, Orlando, FL.
toplas98.ps.Z
Ben Hassen, S., Bal, H.E., and Jacobs, C.: "A Task and Data Parallel Programming Language based on Shared Objects", ACM. Trans. on Programming Languages and Systems, 1998. Copyright 1998 by ACM, Inc.
computer98.ps.gz
Bhoedjang, R., Ruhl, T., and Bal, H.E.: "Design Issues for User-Level Network Interface Protocols on Myrinet", IEEE Computer, 1998.
multicast98.ps.gz
R.A.F. Bhoedjang, T. Ruhl, H.E. Bal: "Efficient Multicast On Myrinet Using Link-Level Flow Control", International Conference on Parallel Processing, pp. 381-390, August 1998, Minneapolis, MN, (best paper award),
transpositions98.ps.gz
R.A.F. Bhoedjang, J. Romein, and H.E. Bal: "Optimizing Distributed Data Structures Using Application-Specific Network Interface Software", International Conference on Parallel Processing, pp. 485-492, August 1998, Minneapolis, MN.
orcaperf97.ps.Z
Bal, H.E., Bhoedjang, R., Hofman, R., Jacobs, C., Langendoen, K., Ruhl, T., and Kaashoek, M.F.,: "Performance Evaluation of the Orca Shared Object System", ACM Transactions on Computer Systems, Vol. 16, No. 1, Febr. 1998.
hpca98.ps.Z
Langendoen, K., Hofman, R., and Bal, H.E.: "Challenging Applications on Fast Networks", to appear in Fourth International Symposium on High-Performance Computer Architecture (HPCA-4), IEEE CS, Las Vegas, Nevada, Feb. 1-4, 1998.
ipps98.ps.gz
Henri E. Bal, Aske Plaat, Mirjam G. Bakker, Peter Dozy, and Rutger F.H. Hofman,: Optimizing Parallel Applications for Wide-Area Clusters, to appear in 12th International Parallel Processing Symposium IPPS'98, IEEE CS, Orlando, Florida, April 1998.

Advanced School for Computing and Imaging

Back to DAS home page.

This page is maintained by Henri Bal.