Selected Publications on Parallel and Distributed Computing

Green Computing in Parallel and Distributed Systems
Design for environmental sustainability and energy efficient computing/networking have gained keen attention from research community. This applies not only to mobile and wireless systems but also to parallel and distributed systems. Dr. Yu approaches this problem by way of coordinated operation comprising a set of alternative policies such as network shutdown, load unbalacing, and cooperative DVS schemes. Proactive virtualization for energy efficiency is another research direction.

Synchronization in Parallel and Distributed Systems
A clear trend in high performance computing is to utilize multiple resoruces on the Internet.  In order to fulfill the common goal, an efficient mechanism for synchronization among the resoruces is critically important.  Dr. Yu has been working on synchronization and collective communication issues in parallel or distributed computing environments.
  1. K. Cha, D. Han, C. Yu, and O. Byeon, "Two-Tree Collective Communication in Distributed Heterogeneous Systems," IASTED International Conference on Networks, Parallel and Distributed Processing, and Applications (NPDPA 2002), 2002.
  2. Smmoh Moh, Chansu Yu, Ben Lee, Hee Yong Youn, Dongsoo Han, and Dongman Lee, "4-ary Tree-Based Barrier Synchronization for 2-D Meshes without Nonmember Involvement," IEEE Transactions on Computers, Vol. 50, No. 8, August 2001.
  3. K. Fang, H. Y. Youn, H. Choo, and C. Yu, "Evaluation of Proactive Congestion Control on RED Gateway," Parallel and Distributed Computing and Systems (PDCS 2001).
  4. Smmoh Moh, Chansu Yu, Hee Yong Youn, Dongsoo Han, Ben Lee, and Dongman Lee, "A Fast Tree-Based Barrier Synchronization on Switch-Based Irregular Networks," 7th Int'l Conference on High Performance Computing (HiPC 2000) , Lecture Notes in Computer Science, Vol. 1970, pp. 273-282, 2000.
  5. S. Moh, C. Yu, H. Y. Youn, D. Han, Ben Lee, and D. Lee," A Fast Tree-Based Barrier Synchronization without Nonmember Interference on 2-D Meshes," Parallel and Distributed Computing and Systems (PDCS 2000) , Vol. II, pp. 711-716, November 2000. 
Computer Architecture Simulation
Understanding a detailed information of modern microprocessor operations is critical in designing an efficient computer systems in various environments.  Trace-driven simulation has been usually used in architecture simulation but does not reveal the impact beyond the architecture level.  SimOS is a complete simulation environment to provide a complete picture of system activities including OS interactions.  Our research focues on Linux version of the complete simulation environment to facilitate Linux-based system understanding.
  1. C. Won, B. Lee, C. Yu, S. Moh, K. Park, M.-J. Kim, "Linux/SimOS: A Complete Systems Simulation Environment for Evaluating High-speed Communication Systems," The Journal of High Speed Networks, Vol. 13 No. 3, pp. 169-182, 2004.
  2. C. Won, B. Lee, C. Yu, S. Moh, Y. Kim, and K. Park, "Linux/SimOS - A Simulation Environment for Evaluating High-Speed Communication Systems," The 2002 International Conference on Parallel Processing (ICPP), 2002.
  3. D. Ortiz-Arroyo, B. Lee, and C. Yu, "EMSim: An Extensible Simulation Environment for Studying High Performance Microarchitectures," World Multiconference on Systemics, Cyberetics and Informatics (SCI'2002), July, 2002.
Group Communication in Distributed Computing
Efficient communication and group communication schemes in distributed systems and the distributed workflow systems are the research topics.
  1. D. Lee, D. Nam, H. Y. Youn, and C. Yu, "OCI-based Group Communication Support in CORBA," IEEE Transactions on Parallel and Distributed Systems, Vol. 14, No. 11, pp. 1126-1139, Nov. 2003.
  2. D. Nam, D. Lee, and C. Yu, "The implementation and analysis of OCI-based group communication support in CORBA," 2001 Pacific Rim International Symposium on Dependable Computing (PRDC), 2001.
  3. S. Park, D. Lee, M. Lim and C. Yu, "Scalable Data Management Using User-Based Caching and Prefetching in Distributed Virtual Environments," ACM Symp on Virtual Reality Software & Technology 2001 (VRST'2001), 2001.
  4. Dukyun Nam, Dongman Lee, Hee Yong Youn and Chansu Yu, "Group Communication Support for CORBA using OCI," (a shorter version is also available here ), Parallel and Distributed Computing and Systems (PDCS 2000) , Vol. I, pp. 106-111, November 2000.
  5. D. Lee, J. Yang, H. Y. Yoon, C. Yu, and S. J. Hyun, "Entity-Centric Scalable Concurrency Control for Distributed Interactive Applications," 19th IEEE Int'l Performance, Computing, and Communications Conference (IPCCC 2000) , February 2000.
Cluster and Grid Systems
Cluster computing is regarded as the cost effective high performance systems.  Like RAID (redundant array of inexpensive disks), many inexpensive PCs interconnected by high speed network facilities such as Gigabit Ethernet or optical Myrinet can achieve high performance systems.  And recently, Grid computing extends that idea to interconnect resources over the Internet.  Dr. Yu had completed three cluster projects: Myrinet-based 8-node cluster for high performance MPI machine, 24-node Diskless cluster system for Crytography applications, and Myrinet-based network router.
  1. K. Cha, S. Na, D. Han, and C. Yu, "Implementation of Diskless Cluster System," IEEE Int'l Symposium on CLuster Computing and the Grid (CCGrid 2001, poster session).
  2. Sangog Na, Hongsoog Kim, Dongsoo Han and Chansu Yu, Implementation and Evaluation of Remote Booting and Installation for Diskless Linux Cluster System," Parallel Processing System Symposium (Korean Information Science Society), 2001.
  3. Chansu Yu, Younghee Lee, Ben Lee, "Performance Evaluation of Myrinet-based Network Router," Technical Report, ICU, 2001.
  4. S. Moh, C. Yu, H. Y. Youn, B. Lee and D. Han, "Mapping Strategy for Switch-Based Cluster Systems of Irregular Topology," (a shorter version is also available here ), International Conference on Parallel And Distributed Systems (ICPADS 2001) , pp. 733-740, 2001.
  5. D. Han, J. Shim and C. Yu, "ICU/COWS: A Distributed Transactional Workflow System Supporting Multiple Workflow Types," IEICE Transactions on Information and Systems, Vol. E83-D, No. 7, Jul. 2000.
  6. Hee Yong Youn, Chansu Yu, Dong Soo Han, and Dongman Lee, "The Approaches for High Available and Fault-Tolerant Cluster Systems," Int'l Workshop on Fault Tolerant Control and Computing (FTCC-1), pp.107-116, May 2000.
  7. S.-J. Chen, H. Y. Youn, C. Yu, and S.-M. Yoo, "Heterogeneous Computing Based On PVM With Dynamically Varying Loads," Int'l Conference on Parallel and Distributed Computing and Systems , November 1999.
Processor Allocation in Parallel Systems
Processor allocation and task scheduling in parallel systems were the main research topics of Dr. Yu.  He still actively researches on fundamental issues in parallel systems.
  1. S. Moh, C. Yu, and D. Han, "Design and Experiment of a Communication-Aware Parallel Quicksort with Weighted Partition of Processors," International Conference on Computational Science and Its Applications (ICCSA-2004), pp. 97~105, 2004. Also in Lecture Notes in Computer Science, Vol. 3046, pp. 97~105, May 2004.
  2. M. Kang, C. Yu, H. Y. Youn, B. Lee and M. Kim, "Isomorphic Strategies for Processor Allocation in k-ary n-cube Systems," IEEE Transactions on Computers, Vol. 52, No.5, pp. 645-657, May 2003.
  3. Jeong-Si Kim, Dong-Soo Han and Chansu Yu, "Parallel Loop Transformation Technique for Efficient Race Detection," International Conference on Parallel And Distributed Systems (ICPADS 2001).
  4. Seong-Moo Yoo, Hyunseung Choo, Hee Yong Youn, Chansu Yu, and Younghee Lee, "On Task Relocation in Two-Dimensional Meshes," Journal of Parallel and Distributed Computing, Vol. 60, No. 5, pp. 616-638, May 2000.
  5. M. Kang anbd C. Yu, "Isomorphic Allocation in k-ary n-cube Systems," 6th Int'l Conference on High Performance Computing (HiPC'99) (a shorter version is also available here ), Lecture Notes in Computer Science, Vol. 1745, pp. 373-380, 1999.
  6. M. Kang and C. Yu, "Job-based Queue Delay Modeling in a Space-Shared Hypercube," Int'l Workshop on Parallel Computing (IWPC'99) , September 1999.
  7. P. Mohapatra, C. Yu and C. R. Das, Allocation and Mapping Based Reliability Analysis of Multistage Interconnection Networks," IEEE Trans. Computers, pp.600-606, May 1996.
  8. P. Mohapatra, C. Yu and C. R. Das, "A Lazy Scheduling Scheme for Hypercube Computers," Journal of Parallel and Distributed Computing, Vol.27 No.1 pp.26-37, May 1995.
  9. C. Yu and C. R. Das, "Disjoint Task Allocation Algorithms for MIN Machines with Minimal Conflicts," IEEE Trans. Parallel and Distributed Systems, Vol.6 No.4 pp.373-387, April 1995.
  10. B. Yoo, C. R. Das and C. Yu, "Processor Management Techniques for Mesh-Connected Multiprocessors," Proc. Int. Conf. Parallel Processing (ICPP), pp.II-105-112, 1995.
  11. C. Yu and C. R. Das," Limit Allocation: An Efficient Processor Management Scheme for Hypercubes," Proc. Int. Conf. Parallel Processing (ICPP), pp.II-143-150, 1994.
  12. Ph.D. Thesis, Chansu Yu, "Processor Management Policies for Multiprocessors," Department of Computer Science and Engineering of The Pennsylvania State University, University Park, PA, U.S.A., May 1994.
  13. P. Mohapatra, C. Yu, C. R. Das and J. Kim, "A Lazy Scheduling Scheme for Improving Hypercube Performance," Proc. Int. Conf. Parallel Processing (ICPP), pp.I-110-117, 1993.
  14. C. Yu, P. Mohapatra and C. R. Das, "Processor Allocation using a Reservation Technique in Hypercube Computers," Proc. Int. Conf. Parallel and Distributed Computing Systems, pp.147-152, 1993.
  15. C. Yu and C. R. Das, "Multitasking in Multistage Interconnection Network Machines," Proc. Int. Conf. Distri. Comput. Sys. (ICDCS), pp.30-37, 1992.
  16. C. R. Das, P. Mohapatra and C. Yu, "Allocation-Based Subcube Dependability for MIN-Based Multiprocessors," Workshop on Fault-Tolerant Parallel and Distributed Systems, pp.124-131, 1992.
World Wide Web Pages for Mobile Computing Lab. (last update 8/6/08)