Yeliang Zhang
High Performance Distributed Computing Laboratory
Dept. of Electrical and Computer Engineering
Tucson AZ 85721
Phone(520) 626-3727
Office: Room 317, ECE Building
Email: zhang (at) ece (dot) arizona (dot) edu
Biography
I am from Shanghai, P. R. China. In Aug. 2007, I have earned my Ph.D. degree in Dept. of Electrical and Computer Engineering. My advisor is Prof. Salim Hariri. My research interests are adaptive distributed runtime system and autonomic grid computing.
Current Projects
The overall goal of this research is to design, develop, evaluate and deploy PRAGMA, the next generation adaptive runtime infrastructure capable of reactively and proactively managing and optimizing application execution using current system and application state, predictive models for system behavior and application performance, and an agent based control network. We have successfully implemented a proof-of-concept prototype of the agent-based runtime system that we refer to CATALINA and also developed a methodology to obtain performance functions that can be used to optimize the performance of GRID applications at runtime.
According to our analysis and observation, the overall distributed application behavior can be characterized using a set of focused analysis functions such as performance analysis function (PAF), security analysis function (SAF) or reliability analysis function (RAF). These functions model the behavior of the individual hardware/software components, subsystems and their applications/services. Using the appropriate analysis functions (e.g. PAF), we can define regions of operations (acceptable, unacceptable, and uncertain) that accurately characterize and quantify the operations of these applications (services) under certain anomalies.
In order to verify our PAF analysis, a theoretical performance function processing algebra is developed to facilitate performance analysis.
The overall objective of this research is to investigate key technologies to enable the development of Autonomic Grid Applications that are context aware and are capable of self configuring, self composition, self optimizing and self adapting. Specifically, we will investigate the definition of autonomic components, the development of autonomic applications as dynamic composition of autonomic components, and the design of key services on top of the existing Grid middleware and runtime to support these applications.
Curriculum Vitae
My recent resume in [PDF] version
Publication
S. Hariri, B. Khargharia, H. Chen, Yeliang Zhang, B. Kim, H. Liu and M. Parashar. The Autonomic Computing Paradigm. to appear in the Cluster Computing Journal, 2006
Yeliang Zhang, Salim Hariri, Jianwei Xiang and Jim Yeh. PARM: Physics Aware Runtime Manager for Large-scale Scientific and Engineering Applications. Accepted as a poster at The 15th IEEE International Symposium on High Performance Distributed Computing, June 19-23 2006, Paris, France.
S. Chandra, M. Parashar, J. Yang, Yeliang. Zhang, S. Hariri. Investigating Autonomic Runtime Management Strategies for SAMR Applications. International Journal of Parallel Programming, Springer Science+Business Media B.V., 33(2-3):247-259, June 2005
Yeliang. Zhang, X. S. Li, O. Marques. Towards an Automatic and Application-Based Eigensolver Selection. LACSI Symposium 2005.
J. Nieplocha, M. Krishnan, B. Palmer, V. Tipparaju, Yeliang. Zhang. Exploiting Processor Groups to Extend Scalability of the GA Shared Memory Programming Model. Computing Frontiers 2005 Conference May 4-6, 2005, Ischia, Italy.
Yeliang Zhang, Vinod Tipparaju, Jarek Nieplocha, Salim Hariri. Parallelization of the NAS Conjugate Gradient Benchmark Using the Global Arrays Shared Memory Programming Model. Joint Workshop on High-Performance Grid Computing and High-Level Parallel Programming Models held in conjunction with IPDPS 2005.
Yeliang Zhang, Jingmei Yang, Salim Hariri, Sumir Chandra, Manish Parashar. Autonomic Proactive Runtime Partitioning Strategies for SAMR Applications. IPDPS Next Generation Software Program - NSFNGS - PI Workshop 2004
Huoping Chen, Salim Hariri, Byoung uk Kim, Yeliang Zhang, Mazin S. Yousif. Self-Deployment and Self-Configuration of Pervasive Network Services.ICPS 2004
Salim
Hariri, Huoping Chen, Ming Zhang, Byoung Kim, Yeliang Zhang ,Bithika Kharghari. An
Autonomic Application Development & Management Environment. submitted to
IEEE Communication: XML-based Management of Networks and Services, 2003.
S. Chandra, Yeliang. Zhang, S. Sinha, M. Parashar, J. Yang, S. Hariri. A Framework for Adaptive Runtime Management of AMR Applications. Accept to appear in the Proceedings of International Conference On High Performance Computing, Dec. 2002.
Salim Hariri, C.S. Raghavendra, Yonhee Kim, Muhamad Djunaedi, Rinda P. Nellipudi, Ashok Rajagopalan, Prasad Vadlamani, Yeliang Zhang. CATALINA: A Smart Application Control and Management. Active Middleware Services Conference, 2000.
Contact Information
| Address(School) |
| Rm 317 ECE Building University of Arizona |
| Tucson AZ 85719 |
| (520) 626-3727 |
Email: zhang@ece.arizona.edu
Classes
* This research is supported by the National Science Foundation via grants numbers ACI 9984357(CA-REERS), EIA 0103674(NGS) and by DOE ASCI/ASAP(Caltech) via grant number PC295251
Page last modified:
Wednesday, 26-January-06
Contact: Yeliang Zhang<zhang@ece.arizona.edu>