Alan S. Wagner Associate Professor Department of Computer Science University of British Columbia

Research Interests

Parallel computation, cluster computing, interconnection networks, languages and APIs for parallel and distributed programming,  MPI and SCTP (current work), parallel data mining, networking, parallel computational finance (past projects).

   Administration

• Out-reach committee 2008-2009
• Sabbatical Sept 2007 – Sept. 2008
• Chair of the Graduate Admissions Committee (2001--2003).
• Member of the Teaching Committee (1990- 2007).

Courses

• CPSC521 (Graduate course outline) Parallel Algorithms and Architectures. (Spring 2007, Fall 2008, Fall 2009)
• CPSC417 Computer Networking (Spring 2002-- 2007, Summer 2005, Spring 2009)
• CPSC111 Introduction to Computation (Fall 2003, Spring 2007).

Contact Information

Address
	Alan Wagner Room 321 CICSR/CS Building Department of Computer Science University of British Columbia 2366 Main Mall Vancouver, British Columbia CANADA V6T 1Z4
Phone Numbers
	Phone: (604) 822-6450  Fax: (604) 822-5485

Selected Papers

MPI Middleware
	Alan Wagner, and Camilo Rostoker, “A Lightweight Stream-processing Library using MPI”, 14th International Workshop on High-Level Parallel Programming Models and Supportive Environments, IPDPS 2009.
	Mike Tsai, Brad Penoff, Alan Wagner, “A Hybrid MPI Design using SCTP and iWARP”,8th Communication Architectures for Clusters Workshop, CAC 2008, Int'l. Parallel and Distributed Processing Symposium (IPDPS), March, Miami 2008
	Brad Penoff, Mike Tsai, Janardhan Iyengar, and Alan Wagner, “Using CMT in SCTP-based MPI to exploit multiple interfaces in cluster nodes”', Recent Advances in Parallel Virtual Machine and Message Passing Interface, LNCS 4757, 14th European PVM/MPI Users' Group Meeting, Pg. 204-212, Sept. 2007
	Humaira Kamal, Brad Penoff, Mike Tsai, Edith Vong, and Alan Wagner. “Using SCTP to hide latency in MPI programs”. In Heterogeneous Computing Workshop (HCW): IPDPS 2006
	Kamal H., Penoff B., Wagner A., “SCTP versus TCP for MPI” ACM/IEEE Supercomputing 2005
Data Mining
	Chilson, J., Ng R., Wagner, A., and Zamar, R., “Parallel Computation of High Dimensional Correlation and Covariance Matrices'', Algorithmica, Special Issue on Coarse Grain Computation. NY, Vol. 45, No. 3, pp. 403-431, 2006
	Ng R., Wagner A. and Yin Y., "Iceberg-cube computation with PC clusters", ACM SIGMOD/PODS, May, 2001.
Debugging
	Brodsky A., Pedersen J., and Wagner A., “On the complexity of buffer allocation in message passing systems”, Journal of Parallel Distributed Computing, Vol. 65, pp. 692-713, Elsevier Press, 2005
	Pedersen J. and Wagner A., "Correcting Errors in Message Passing Systems", 6th Intl. Workshop on High Level Parallel Programming Models and Supportive Environments (HIP'01), proceedings Springer LNCS vol. 2026, pp. 122-137, 2001. (see Matt Pedersen’s website for more work in this area)
Finance
	Wang J., Rostoker C., and Wagner A., “A High Performance Pair Trading Application”, 2nd Intl. Workshop on Parallel and Distributed Computing in Finance, IPDPS 2009.
	Rostoker C., Wagner A., and Hoos, H., “A parallel workflow for real-time correlation and clustering of high-frequency stock market data”, Int'l. Parallel and Distributed Processing Symposium (IPDPS), Long Beach 2007

_ Recent Grants

NSERC Idea to Innovation : Market Miner System (PI A. Wagner, Co-PI H. Hoos), 2008-2009	The objectives of the research are to prototype and validate several financial analysis tools directly based on our MarketMiner workflow system. MarketMiner is a financial pre-analytics workflow that can form the core of sophisticated financial analysis tools. (see scalableanalytics.com)
CISCO Collaborative Research Initiative : SCTP User Level Stack	Support for work on porting the KAME SCTP stack to user-space to open up many new research opportunities for SCTP and HPC. (http://www.cisco.com/web/about/ac50/ac207/crc/examples.html).

_

Acknowledgments: Garth Wagner

updated September 1, 2009