A Middleware Approach to Teaching Computer Security (2009 - )
Project Summary
Parallel disks consisting of multiple disks with high-speed switched interconnect are ideal for data-intensive applications running in high-performance computing systems. Improving the energy efficiency of parallel disks is an intrinsic requirement of next generation high-performance computing systems, because a storage subsystem can represent 27% of the energy consumed in a data center. However, it is a major challenge to conserve energy for parallel disks and energy efficiently coordinate I/Os of hundreds or thousands of concurrent disk devices to meet high-performance and energy-saving requirements. The goal of this research is to develop energy conservation techniques that will provide significant energy savings while achieving low-cost and high-performance for parallel disks.
Our Approach:
In this project we will take an organized approach to implementing energy-saving techniques for parallel disks, simulating energy-efficient parallel disk systems, and conducting a physical demonstration. The proposed project will undertake the following four tasks:
(1) design and develop a novel buffer-disk (BUD) architecture to reduce energy dissipation in parallel disk systems;
(2) develop innovative energy-saving techniques, including an energy-related reliability model, energy-aware data partitioning, disk request processing, data movement, data placement, prefetching strategies, and power management for buffer disks;
(3) implement a simulation toolkit (BUDSIM) used to develop a variety of energy-saving techniques and their integration in the BUD architecture; and
(4) validate the BUD architecture along with our innovative energy-conservation techniques using real data-intensive applications running on high-performance clusters.
BUD News
Related News
Gadgets
Presentation Slides:
Energy-Efficient Storage Systems [PPT]
People:
Department of Computer Science Faculty
Xiao Qin (PI), Assistant Professor, Auburn University
Tao Xie (Co-PI), Assistant Professor, San Diego State University
Mais Nijim, Assistant Professor, University of Southern Mississippi
LANL Scientist and Intel Technical Staff
Peter C. Lichtner (Co-PI), Hydrology, Geochemistry, and Geology Group, Los Alamos National Laboratory
Yiming Yang, Senior Software Engineer, Intel Corporation
Students
Ziliang Zong [Ph.D. Candidate | Awards Total: 12 | Publications Total: 23; Journal Papers: 7; Conference Papers: 16]
Dissertation Research: Conserving Energy in Clusters through Resource Allocation.
Minimizing power dissipation is an important requirement in developing resource management systems for clusters. In this work, we investigate resource allocation solutions that conserve energy in clusters while retaining high performance. Our resource allocation approaches will judiciously allocate resources of a cluster computing system to satisfy performance needs of parallel applications and achieve significant energy savings. Read more...
Kiranmai Bellam [Ph.D. Student | Awards Total: 3 | Publications Total: 15; Journal Papers: 5; Conference Papers: 10]
Dissertation Research: Fault Tolerance, Security, and Energy Issues in Real-Time Systems.
Fault tolerance, security, and energy issues in modern real-time systems are of critical importance. This work is intended to seamlessly integrate security services and energy conservation techniques for real-time systems while endeavoring to achieving high system reliability. Read more...
Xiaojun Ruan [Ph.D. Student | Publications Total: 11; Journal Papers: 4; Conference Papers: 7]
Thesis Research: Dynamic Voltage Scaling for Parallel Applications on Clusters.
In this study we design and implement a scheduling algorithm that makes use of dynamic voltage scaling to effectively reduce energy consumption of parallel applications running on cluster computing systems.
Adam Manzanares [Ph.D. Student | Awards: 2 | Publications Conference Papers: 1]
Dissertation Research: Energy Efficient Wireless Storage Systems.
This study addresses the issue of modeling energy-efficient wireless storage systems and wireless network interconnections. Adam's work on energy conservation for high-performance clusters appeared in the proceedings of the 8th IEEE International Conference on Cluster Computing (Cluster'06), Sept. 2006. Read more...
Gourav Tilve [M.S. Student | Publications]
Thesis Research: Energy-Aware Data Prefetching in Disk-Based Buffers.
In this study we aim at developing novel data prefetching strategies to conserve energy in large scale storage systems with buffer disks while improving usage of disk-based buffers.
Nicholas W. O'Connor [M.S. Student | Awards Total: 1 | Publications Conference Papers: 2]
Research Project: Energy Consumption Models for Disk Systems.
This study addresses the issue of modeling energy consumption in server and embedded disk systems. Read more...
Matthew E. Briggs [Undergraduate Student | Awards Total: 1 | Publications Conference Papers: 2]
Senior Research Project: Energy-Efficient Disk Buffer Disks.
The goal of this research is to develop a novel buffer-disk architecture that will provide significant energy savings while achieving low-cost and high-performance for parallel disks. In this project we will take an organized approach to implementing energy-saving techniques for parallel disks and simulating energy-efficient parallel disk systems. Read more...
Tenzin Doleck [Undergraduate Student]
Senior Research Project: Energy-Efficient Storage Systems.
Improving the energy efficiency of storage systems is an intrinsic requirement of next generation large-scale computing systems, because a storage subsystem can represent 27% of the energy consumed in a data center. The goal of this research is to investigate energy conservation techniques that will provide significant energy savings while achieving high-performance for storage systems.
Publications
Journal Papers
J3. An Energy-Delay Tunable Task Allocation Strategy for Collaborative Applications in Networked Embedded Systems. [Abstract | PDF]
T. Xie and X. Qin, IEEE Transactions on Computers, vol. 57, no. 3, pp. 329-343, March 2008.
J2. Conserving Energy in Real-Time Wireless Networks via Message Scheduling.
X. Qin, M. Alghamdi, T. Xie, M. Nijim, and Z.-L. Zong, IEEE Transactions on Wireless Communications. Submitted Jan. 2006; revised Aug. 2006 and Dec. 2006.
J1. Energy-Efficient Scheduling for Parallel Applications on Mobile Clusters.
Z.-L. Zong, M. Nijim, and X. Qin, Cluster Computing: The Journal of Networks, Software Tools and Applications. Submitted May 2006; revised Jan. 2007; accepted March 2007.
Refereed Conference Publications
C16. PASS: Power-Aware Scheduling of Mixed Applications with Deadline Constraints on Clusters.
C. Liu, X. Qin, and S. Li, , Proc. the 17th Int'l Conf. Computer Communications and Networks (ICCCN), St. Thomas, Virgin Islands, Aug. 2008.
C15. Energy Conservation for Real-Time Disk Systems with I/O Burstiness. [Abstract | PDF]
A. Roth, A. Manzanares, K. Bellam, M. Nijim, and X. Qin, Proc. IEEE Int'l Workshop Next Generation Autonomous Storage and High Performance Computing , St. Thomas, Virgin Islands, Aug. 2008.
C14. A Prefetching Scheme for Energy Conservation in Parallel Disk Systems.
A. Manzanares, K. Bellam, and X. Qin, Proc. NSF Next Generation Software Program Workshop, April 2008.
C13. Improving Reliability and Energy Efficiency of Disk Systems.
K. Bellam, A. Manzanares, and X. Qin, Proc. 46th ACM Southeast Conf., March 2008.
C12. A Simulation Framework for Energy-Efficient Data Grids.
Z.-L. Zong, K. Bellam, X.-J. Ruan, A. Manzanares, X. Qin, and Y.-M Yang, Proc. Winter Simulation Conference, Washington, D.C., Dec. 2007.
C11. Energy-Efficient Scheduling for Parallel Applications Running on Heterogeneous Clusters. [Abstract | PDF]
Z.-L. Zong, X. Qin, M. Nijim, X.-J. Ruan, K. Bellam, and M. Alghamdi, Proc. 36th International Conference on Parallel Processing (ICPP), Sept. 2007.
C10. No More Energy-Performance Trade-Off: A New Data Placement Strategy for RAID-Structured Storage Systems. [PDF]
T. Xie and Y. Sun, Proc. 14th IEEE International Conference on High Performance Computing (HiPC 2007), Goa, India, Dec. 2007
C9. SOR: A Static File Assignment Strategy Immune to Workload Characteristic Assumptions in Parallel I/O Systems. [PDF]
T. Xie, Proc. 36th International Conference on Parallel Processing (ICPP), Sept. 2007.
C8. An Energy-Efficient Scheduling Algorithm Using Dynamic Voltage Scaling for Parallel Applications on Clusters. [Abstract | PDF]
X.-J. Ruan, X. Qin, M. Nijim, Z.-L. Zong, and K. Bellam, Proc. 16th Int'l Conference on Computer Communications and Networks (ICCCN), Honolulu, Hawaii, Aug. 2007.
C7. Design and Performance Analysis of Energy-Efficient Parallel Storage Systems.
Z.-L. Zong, M.E. Briggs, N.W. O'Connor, X. Qin, M. Alghamdi, and Y.-M. Yang, the Commodity Cluster Symposium 2007 (CCS), Annapolis, Maryland, July 2007.
C6. An Energy-Efficient Framework for Large-Scale Parallel Storage Systems. [Abstract | PDF]
Z.-L.Zong, M.E. Briggs, N.W. O'Connor, and X. Qin, Proc. 21st Int'l Parallel and Distributed Processing Symp. (IPDPS), 8th IEEE Int'l Workshop Parallel and Distributed Scientific and Engineering Computing, Long Beach, CA, March 2007.
C5. Scheduling of Periodic Packets in Energy-Aware Wireless Networks. [Abstract | PDF]
X. Qin, M. Alghamdi, M. Nijim, Z.-L. Zong, and K. Bellam, Proc. the 26th IEEE Int'l Performance Computing and Communications Conf. (IPCCC'07), New Orleans, Louisiana, April 2007.
C4. HAGEES: A High Availability Guaranteed Energy-Efficient Scheduling Strategy for High-Performance Clusters.
Z.-L. Zong, M. Nijim, M. Alghamdi, and X. Qin, Proc. the 7th Symp. the Los Alamos Computer Science Institute, Santa Fe, NM, Oct. 2006.
C3. Energy-Efficient Duplication Strategies for Scheduling Precedence Constrained Parallel Tasks on Clusters. [Abstract | PDF]
Z.-L. Zong, A. Manzanares, B. Stinar, and X. Qin, Proc. 8th IEEE International Conference on Cluster Computing (Cluster'06), Sept. 2006.
C2. Solving Energy-Latency Dilemma: Task Allocation for Parallel Applications in Heterogeneous Embedded Systems. [Abstract | PDF]
T. Xie, X. Qin, and M. Nijim, Proc. 35th International Conference on Parallel Processing (ICPP), Columbus, Ohio, Aug. 2006.
C1. PARM: A Power-Aware Message Scheduling Algorithm for Real-Time Wireless Networks. [Abstract | PDF]
M. Alghamdi, T. Xie, X. Qin, ACM Int'l Symp. Modeling, Analysis and Simulation of Wireless and Mobile Sys. (MSWiM), Workshop Wireless Multimedia Networking and Performance Modeling, Oct. 2005.
Our Funding:
BUD is being funded through the Computing Processes & Artifacts (CPA) Award CCF-0742187 (CISE-CCF) from the National Science Foundation (NSF).
Contacts
Xiao Qin, Ph.D., Principle Investigator
109 Dunstan Hall
Department of Computer Science and Software Engineering
Samuel Ginn College of Engineering
Auburn University, AL 36849-5347
Office: 1-334-844-6327
Fax: 1-334-844-6329
Email: xqin@auburn.edu