Research of Jens Mache

My Ph.D. thesis was in the area of "parallel I/O and resource management of parallel and distributed systems."
I am co-chair of Grid.Edu 2004 and DPRoM '04.
I am supported by National Science Fundation grant DUE-0411237.

My publications include:

Distributed Systems

Network Security
- A. Apon, K. Landrus, J. Mache and K. Huxtable, Using Shibboleth to Manage Access Control to Remote Cluster Computing Resources, Proceedings of SC2004 - 17th ACM/ IEEE High-Performance Computing, Networking and Storage Conference, 2004 (to appear)
- T. Likarish, E. Anholt, B. Risteska, V. Grigoreanu, J. Mache and C. Stevens, How Mature are Clientless SSL VPN?, poster at the 13th USENIX Security Symposium, 2004
- J. Mache, J. Gimba and T. Lopez, Dynamic Partitioning for High-Speed Network Intrusion Detection, Proceedings of SC2003 - 16th ACM/ IEEE Conference on High-Performance Networking and Computing, 2003
Next-Generation Internet
- J. Mache, E. Anholt, V. Grigoreanu, T. Likarish and B. Risteska, Look-Ahead Routing Reduces Wrong Turns in Freenet-style Peer-to-Peer Systems Proceedings of the 38th Hawaii International Conference on System Sciences (HICSS), 2005 (to appear)
- J. Mache and J. Lesh, Look-Ahead Improves the Routing in Freenet-style Peer-to-Peer Systems, Proceedings of the International Conference on Internet Computing (IC'04), 2004
- J. Mache, D. Ely, M. Gilbert, J. Gimba, T. Lopez and M. Wilkinson, Modifying the Overlay Network of Freenet-style Peer-to-Peer Systems after Successful Request Queries, Proceedings of the 37th Hawaii International Conference on System Sciences (HICSS) (Peer-to-Peer Ecommerce Systems and Applications Minitrack), 2004
- D. Ely and J. Mache, The "Bread-Crumb" Algorithms: Improving the Performance of Freenet-style Peer-to-Peer Systems, Proceedings of the Oregon Academy of Science, 2004
- J. Mache and J. Lesh, Simulated Annealing and Request Algorithms for Freenet-style Peer-to-Peer Systems, Proceedings of the International Conference on Internet Computing (IC'03), 2003
- J. Mache, M. Gilbert, J. Guchereau, J. Lesh, F. Ramli and M. Wilkinson, Request Algorithms in Freenet-style Peer-to-Peer Systems, Proceedings of the 2nd IEEE International Conference on Peer-to-Peer Computing (P2P2002), 2002
- P. Thomas and J. Mache, Evaluating the Performance of Peer-to-Peer Systems , Proceedings of the Oregon Academy of Science, 2002
Storage and File Systems
- J. Mache and S. Garg, Peer-to-Peer Lessons for Cluster File Systems , Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA2003), 2003
- J. Mache, J. Bower-Cooley, R. Broadhurst, J. Cranfill and C. Kirkman IV, A Sensitivity Study of Parallel I/O under PVFS, In Christophe Cerin and Hai Jin, editors, Parallel I/O for Cluster Computing, chapter 3, pages 93 - 105, Special Issue of Journal Calculateurs Paralleles, Stylus Publishing, 2003
- J. Guchereau and J. Mache, Performance and Robustness of Distributed File Systems , Proceedings of the Oregon Academy of Science, 2003
- J. Mache, M. Gilbert, J. Guchereau, J. Lesh, F. Ramli, M. Wilkinson and S. Garg, What Cluster File Systems can Learn from Peer-to-Peer Systems, Proceedings of SC2002 - 15th ACM/ IEEE Conference on High-Performance Networking and Computing, 2002
- J. Mache, J. Bower-Cooley, J. Guchereau, P. Thomas and M. Wilkinson, Cost-Effective High-Performance Disk Access on PC Clusters with Commodity IDE Disks, Proceedings of the 6th International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA), 2002
- J. Mache, J. Bower-Cooley, J. Guchereau, P. Thomas and M. Wilkinson, How to achieve 1 GByte/sec I/O throughput with commodity IDE disks, Proceedings of SC2001 - 14th ACM/ IEEE Conference on High-Performance Networking and Computing, 2001
- S. Garg and J. Mache, Performance Evaluation of Parallel File Systems for PC Clusters and ASCI Red, Proceedings of the 3rd IEEE International Conference on Cluster Computing (CLUSTER'01), 2001
- J. Mache, J. Bower-Cooley, R. Broadhurst, J. Cranfill and C. Kirkman IV, Parallel I/O Performance of PC Clusters, Proceedings of the 10th SIAM Conference on Parallel Processing for Scientific Computing (PP01), 2001
- J. Mache, J. Bower-Cooley, R. Broadhurst, J. Cranfill and C. Kirkman IV, Evaluating a Parallel File System for PC Clusters, poster at the IEEE International Conference on Cluster Computing (CLUSTER2000), 2000
Cluster and Grid Computing (other)
- A. Apon, J. Mache, K. Landrus, and Y. Yara, Classroom Exercises for Grid Services, Proceedings of the 5th International Conference on Linux Clusters: The HPC Revolution, 2004
- A. Apon, J. Mache, R. Buyya, and H. Jin, Cluster Computing in the Classroom and Integration with Computing Curricula 2001, IEEE Transactions on Education, May 2004
- D. Thompson, A. Apon, Y. Yara, J. Mache and R. Deaton, Training a Grid Workforce, poster at the Oklahoma Supercomputing Symposium, 2003
- A. Apon, R. Buyya, H. Jin, and J. Mache, Cluster Computing in the Classroom: Topics, Guidelines, and Experiences, Proceedings of the First IEEE/ ACM International Symposium on Cluster Computing and the Grid (CCGrid), 2001
- J. Bower-Cooley and J. Mache, Harnessing the Power of Networked PCs to Speed-up Computer Graphics , Proceedings of the Oregon Academy of Science, 2001
- J. Mache, R. Broadhurst and J. Ely, Ray Tracing on Cluster Computers, Proceedings of the International Workshop on Cluster Computing - Technologies, Environments, and Applications, PDPTA'2000, 2000
- J. Mache, An Assessment of Gigabit Ethernet as Cluster Interconnect, Proceedings of the First IEEE International Workshop on Cluster Computing, IWCC'99, 1999
Distributed Applications
- E. Hannan and J. Mache, Web Programming: The Lewis and Clark Commuter Computer, Proceedings of the Inaugural Conference of the Consortium for Computing in Small Colleges, CCSC-NW'99, 1999

Resource Management

D. Bunde, V. Leung and J. Mache, Communication Patterns and Allocation Strategies, Proceedings of the 18th IEEE International Parallel and Distributed Processing Symposium (Workshop on Performance Modeling, Evaluation and Optimizations), 2004
V. Lo and J. Mache, Job Scheduling for Prime Time vs. Non-Prime Time, Proceedings of the 4th IEEE International Conference on Cluster Computing (CLUSTER 2002), 2002
J. Mache, V. Lo and S. Garg, Job Scheduling that Minimizes Network Contention due to both Communication and I/O, Proceedings of the 14th International Parallel and Distributed Processing Symposium, IPDPS'00 (formerly IPPS&SPDP), 2000
J. Mache, V. Lo and S. Garg, How to Schedule Parallel I/O Intensive Jobs, Proceedings of the 6th Conference on Parallel and Real-Time Systems, PART'99, 1999
J. Mache, V. Lo and S. Garg, Parallel I/O Traffic Calls for New Job Scheduling Strategies, Proceedings of SC99 - 12th ACM/ IEEE Conference on High-Performance Networking and Computing, 1999
J. Mache, V. Lo, M. Livingston and S. Garg, The Impact of Spatial Layout of Jobs on Parallel I/O Performance, Proceedings of the 6th Workshop on I/O in Parallel and Distributed Systems, FCRC'99, 1999
V. Appaya, D. Guzman, J. B. Lin, V. Lo, J. Mache and W. Zhu, An Analysis of the Production Parallel Workload on the NASA Ames IBM SP/2 and the KFA Cray T3E, Technical Report CIS-TR-98-13, University of Oregon, 1998
V. Lo, J. Mache and K. Windisch, A Comparative Study of Real Workload Traces and Synthetic Workload Models for Parallel Job Scheduling, Proceedings of the 4th Workshop on Job Scheduling Strategies for Parallel Processing, IPPS '98, also published in "Job Scheduling Strategies for Parallel Processing" edited by Dror G. Feitelson and Larry Rudolph, Springer-Verlag LNCS Vol 1459, 1998
J. Mache, V. Lo and K. Windisch, Minimizing Message-Passing Contention in Fragmentation-Free Processor Allocation, Proceedings of the 10th International Conference on Parallel and Distributed Computing Systems, p. 120-124, 1997
J. Mache, V. Lo and K. Windisch, Design and Performance Evaluation of MC, a High-Performance Processor Allocation Strategy, Technical Report CIS-TR-97-07, University of Oregon, 1997
J. Mache and V. Lo, The Effects of Dispersal on Message-Passing Contention in Processor Allocation Strategies, Proceedings of the Third Joint Conference on Information Sciences, Sessions on Parallel and Distributed Processing, Volume 3, p. 223-226, 1997
J. Mache and V. Lo, Dispersal Metrics for Non-Contiguous Processor Allocation, Technical Report CIS-TR-96-13, University of Oregon, 1996

Miscellaneous

D. Gekiere and J. Mache, Implementing Protected Task Switching and Memory Management on Intel's 32-bit Architecture, Proceedings of the Oregon Academy of Science, 2000
J. Mache and G. Stringer, Training Artificial Neural Networks to Predict the 3-5 MeV Relativistic Electron Flux at Geosynchronous Orbit, Proceedings of the Oregon Academy of Science, 1994

My areas of interest include:

Cluster computing

The availability of high-speed networks and increasingly powerful commodity microprocessors are making the use of clusters (networks of computers) an appealing vehicle for cost-effective parallel computing. We are studying different network technologies (including Gigabit Ethernet), different network topologies, and different file systems (including PVFS).

Parallel I/O

Parallel I/O has drawn increasing attention in the last few years as it has become apparent that file-I/O performance rather than CPU performance may be the limiting factor in current as well as future high-performance parallel systems. I am investigating parallel I/O traffic and network contention in a multiprogrammed environment. I am developing and evaluating new scheduling strategies that minimize network contention and thus improve parallel I/O performance.

Parallel job scheduling

The latest performance bottleneck in fragmentation-free processor allocation for high-performance parallel computers is message-passing contention. I am developing dispersal metrics that estimate contention. I am designing a new allocation strategy that minimizes contention and thus reduces job response times.

Workload characterization

We are studying workload traces and workload models of parallel supercomputers in order to ensure a meaningful basis for performance evaluation of scheduling algorithms and to guide the design of new scheduling algorithms, e.g. job scheduling that addresses I/O and network resource needs.

Internet research

Routing in the Internet is a fascinating topic. I am studying efficient multicast communication.

Some of my projects were:

Parallel I/O Performance, Research Poster, University of Oregon, 1998 (ditto in pdf format)
Minimizing Contention, Research Poster, University of Oregon, 1997
Earthquake Crisis Management for Computer Networks - A Tokyo-based Study of Current Practices, 1996
Dispersal Metrics, Research Poster, University of Oregon, 1996
Latency Avoiding by Adequate Mapping, 1994
ATM, a short survey, 1994

I was a member of the Resource Allocation research group led by my former advisor, Virginia Lo.
I also was a Research Assistant with the Paraducks group, working on TAU (Tuning and Analysis Tools) and pC++/ Sage++.

jmache@lclark.edu
Last modified: Fri Sep 10 13:14:12 PDT 2004