|
|
||
|
|
Matthew Wolf Research Scientist |
|
Dr. Matthew Wolf is a member of the Center for Experimental Research in Computer Systems (CERCS) at Georgia Tech. His position is as a Research Scientist in the School of Computer Science of the College of Computing at Georgia Institute of Technology, as well as being a joint appointment with Oak Ridge National Laboratory. His research targets high performance, real-time applications, particularly in the scientific collaboration space. Research topics include dynamic program adaptation; online program monitoring, tuning, and steering; task and message scheduling; basic mechanisms and policies for autonomic quality management; middleware; and software tools. This research is conducted on parallel, distributed, and embedded system platforms, in laboratories shared with end users and hardware developers.
List of current publications:
1. Matthew Wolf, Hasan Abbasi, Benjamin Collins, David Spain, and Karsten Schwan, “Service Augmentation for High End Interactive Data Services,” IEEE Cluster Computing Conference 2005 (Cluster ’05), September 2005.
2. Karsten Schwan, Brian F. Cooper, Greg Eisenhauer, Ada Gavrilovska, Matt Wolf, Hasan Abbasi, Sandip Agarwala, Zhongtang Cai, Vibhore Kumar, Jay Lofstead, Mohamed Mansour, Balasubramanian Seshasayee, and Patrick Widener, “Autonomic Information Flows”, CERCS Technical Report GIT-CERCS-05-22, Nov 2005.
3. Hasan Abbasi, Matthew Wolf, Karsten Schwan, Greg Eisenhauer, and Andrew Hilton, “XChange: Coupling Parallel Applications in a Dynamic Environment,” IEEE International Conference on Cluster Computing (Cluster 2004), Sept. 2004.
4. Sandip Agarwala, Christian Poellabauer, Jiantao Kong, Karsten Schwan, and Matthew Wolf, ”System-level Resource Monitoring for Distributed Applications'', Journal of Grid Computing, 1 (3): 273-289, 2004.
5. Mohamed Mansour, Matthew Wolf, and Karsten Schwan, ``Dynamic Data Access to the GT/CERCS Linux Mirror Site,'' High Performance Grid Computing Workshop, at IPDPS '04, March 2004.
6. Mohamed Mansour, Matthew Wolf, and Karsten Schwan, “A Workload Generation Tool for Distributed Information Flow Applications,” International Conference on Parallel Processing (ICPP-04), Aug. 2004.
7. Zhongtang Cai, Greg Eisenhauer, Karsten Schwan, and Matthew Wolf, ``IQ-Services: Network-Aware Middleware for Interactive Large-Data Applications'', 2nd Workshop on Middleware for Grid Computing (with Middleware 2004), Toronto, Oct. 2004
8. Sandip Agarwala, Christian Poellabauer, Jiantao Kong, Karsten Schwan, and Matthew Wolf, “Resource-Aware Stream Management with the Customizable dproc Distributed Monitoring Mechanisms”, 12th IEEE International Symposium on High Performance Distributed Computing (HPDC-12), ACM/IEEE, June 2003.
9. C. Poellabauer, K. Schwan, S. Agarwala, A. Gavrilovska, G. Eisenhauer, S. Pande, C. Pu, M. Wolf, “Service Morphing: Integrated System- and Application-Level Service Adaptation in Autonomic Systems”, 5th Annual International Workshop on Active Middleware Services (AMS 2003), IEEE, June 2003.
10. Matthew Wolf, Zhongtang Cai, Weiyun Huang, Karsten Schwan, ``SmartPointers: Personalized Scientific Data Portals in Your Hand'', Supercomputing 2002, ACM/IEEE, Nov. 2002, 8 pgs.
11. Matthew Wolf and Uzi Landman, “Genetic Algorithms for Structural Cluster Optimization”, Journal of Physical Chemistry A, 102: 6129-6137, 1998.
- The IHPC Lab -- the Interactive High Performance Computing Laboratory and project is a university-wide effort to which Intel Corporation has granted multiple high performance cluster computers, each of substantial size. These clusters provide a low-cost solution to high performance computing for parallel and distributed scientific applications. Current research may be categorized into three areas: (1) grand challenge applications, (2) interactive high performance computing, and (3) underlying network support. Grand challenge applications include, but are not limited to, large-scale optimization problems solved by members of Georgia Tech's School of Industrial and Systems Engineering, molecular dynamics modeling conducted by researchers in Georgia Tech's School of Physics, and turbulent combustion modeling investigated in the School of Aerospace Engineering. The `I' in IHPCL reflects its key goal of supporting collaboration and interaction among end users via those applications that are most meaningful to them. Our research includes dynamic program steering and monitoring, the efficient transport of large data flows across heterogeneous machines, the real-time transformation and filtering of the data needed for remote scientific visualizations, the dynamic control of such data flows via active user interfaces, and the remote manipulation of computational tools by multiple end users. An earlier project addressing related issues was the Distributed Laboratories project.
- The Infosphere and M-Ware projects -- address future systems that are composed of users, sensors, actuators, and high performance or data-intensive programs running on distributed heterogeneous hardware/software platforms. The ECho and JECho communication middleware, the MOSS/JMOSS object models, and the Active Streams approach to application-level distributed adaptation are some of the bases on which these projects are developing underlying enabling software technology, middleware, and quality management methods as well as applications that require such infrastructure. The resulting applications constructed with M-ware mechanisms and supported by its quality management policies are further enriched by (i) those elements of the Infosphere project that actively seek new information sources during execution (e.g., Continual Queries), and (ii) novel program composition and specialization technologies being developed by Infosphere researchers. Our joint vision focuses on information flow rather than computing, thereby exploring new paradigms in how to construct future, complex distributed, parallel, and real-time applications.
- IQ-ECho: Interactive Quality Management in High Performance Peer-to-Peer Applications -- this project is creating technologies that enable continuous quality management for event-based, peer-to-peer applications. High performance in communication is attained by use of efficient binary data communications. Dynamic component coupling leverages a publish/subscribe data communication model. Runtime quality management involves dynamic binary code generation, platform extension, and joint adaptation of applications, middleware, operating system kernels, and network protocols.
- The DEOS project -- is developing kernel-level abstractions for real-time, multimedia systems, and embedded systems. Current efforts include real-time task and packet schedulers using the DWCS scheduling algorithm (jointly with Richard West at Boston Univ.), the creation of an agile runtime infrastructure for dynamic quality management for embedded and distributed platforms (incl. performance monitoring), efficient methods for kernel/user interactions -- termed E-calls, and distributed file management for cluster machines. The operating system extensions developed in this project comprise the E-Linux OS kernel. New work being conducted addresses the wireless domain and handheld/portable computers interacting via such limited bandwidth links.
- Hasan Abbasi (Karsten Schwan)
- Micah Abrams (Chem – David Sherrill)
- Sandip Agarwala (Karsten Schwan)
- Zhongtang Cai (Karsten Schwan)
- Weiyun (Cherry) Huang (Leo Mark)
- Jasmina Jancic
- Vernard Martin (Karsten Schwan)
- Christian Poellabauer (Karsten Schwan)
- Doug Spearot (ME – David McDowell)
- Patrick Widener (Karsten Schwan)
|
Contact information |
Matthew Wolf
College
of Computing
Georgia Tech,
Atlanta GA 30332-0280
Office:
Klaus Advanced Computing Building (KACB) Rm. 3323
Phone:
(404) 385-1278
Fax:
(404) 385-2295
mwolf@cc.gatech.edu