 |
 |
 |
 |
Professor |
Assistant Professor |
Visiting Researcher |
Visiting Researcher |
- New Models of Grid and Ubiquitous Computing for Image Processing
- Power-Aware Instruction Scheduling for Embedded Systems
New Models of Grid and Ubiquitous Computing for Image Processing
-
The main purpose of this research is to explore new software models/toolkits,
named Ubiquitous Multi-Processor (UMP) system, to support distributed application
development over the emerging ubiquitous/pervasive computing environment,
such as ubiquitous computing, Peer-to-Peer (P2P) computing, and mobile computing
environments. In the proposed application scenario, there are many PCs
equipped with some UMPs. These PCs are distributed over different domains
(each PC belongs and only belongs to one domain). There also has a resource
router in each domain taking charge of UMP management request processing.
In the system, the behaviors of UMPs are controlled by corresponding resource router. Once it registers to the resource router successfully, a UMP will listen and accept for the task scheduled by the resource router. the UMP will also update it status information to the resource router when a task is finished.
To support mobile computing environments, the resource router should be aware of the location of mobile users and be able to locate available UMPs from the nearest domain, so as to reduce the communication cost for the request.Power-Aware Instruction Scheduling for embedded systems
-
In most of compilers, the goal of traditional instruction scheduling algorithms is
to improve performance in terms of execution time. This can be done by some wellknown
ways such as superblock scheduling, hyperblock scheduling, and treegion scheduling. These scheduling strategies focus mainly on increasing performance
through increasing the amount of instruction-level parallelism in program code.
However, in VLIW (very long instruction word) architectures, an instruction word
consists of a variable number of individual instructions. Therefore the step power
and peak power consumption vary significantly depending on the parallel schedule
generated by compiler. Power variation reduction without losing execution speed
is an important scheduling constraint for embedded VLIW architectures. In this
research, we studied some power-aware scheduling strategies for VLIW processors.
These scheduling methods include
- low power scheduling for basic blocks with integer programming
- Modulo and Software Pipelining for loops
- Register allocation and cache reuse for power reduction.
|
The laboratory mission in the broad sense is to contribute to: |
Refereed Journal Papers
| [minyi-01:2006] |
Minyi Guo, Jiannong Cao, and Laurence Tianruo Yang. Forward:
New Trends in Parallel and DistributedComputing and Networking.
Journal of Supercomputing, 36(3):199-200, 2006. |
| This is a forward for the speciel issue on New Trends inParallel and Distributed
Computing and Networking, The Journal ofSupercomputing |
|
| [minyi-02:2006] |
Jiannong Cao, Alvin Chan, Yudong Sun, and Sajal K.
Dasand Minyi Guo. A Taxonomy of Application Scheduling Tools for
High Performance Cluster Computing. Journal of Cluster Computing,
9(3):355-371, 2006. |
| Application scheduling plays an important role inhigh-performance cluster
computing. Application schedulingcan be classified as job scheduling and task
scheduling.This paper presents a survey on the software tools for thegraphbased
scheduling on cluster systems with the focus ontask scheduling. The
tasks of a parallel or distributed applicationcan be properly scheduled onto
multi-processors inorder to optimize the performance of the program (e.g.,
executiontime or resource utilization). In general, schedulingalgorithms are
designed based on the notion of task graph thatrepresents the relationship of
parallel tasks. The schedulingalgorithms map the nodes of a graph to the processors
inorder to minimize overall execution time.Although many scheduling
algorithms have been proposed in the literature |
|
| [minyi-03:2006] |
Chen Yu, Xiaohong Jiang, Susumu Horiguchi, and Minyi Guo.
Overall Blocking Behavior Analysis of General Banyan-Based Optical
Switching Networks. IEEE Transactions on Parallel and Distributed
Systems, 17(9):1037-1047, 9 2006. |
| Abstract.Banyan networks are attractive for serving as the optical switch architectures
due to their nice properties of small depth andabsolutely signal
loss uniformity. Combining the horizontal expansion and vertical stacking of
optical banyan networks is a generalscheme for constructing banyan-based optical
switching networks. The resulting horizontally expanded and vertically
stacked opticalbanyan (HVOB) networks usually take either a high hardware
cost or a large network depth to guarantee the nonblocking property.Blocking
behavior analysis is an effective approach to studying network performance
and finding a graceful compromise amonghardware cost, network depth, and
blocking probability; however, little has been done to analyze the blocking behavior of generalHVOB networks. In this paper, we study the overall blocking
behavior of general HVOB networks, where an upper bound on theblocking
probability of a HVOB network is developed with respect to the number of
planes (stacked copies) and the number of stages.The upper bound accurately
depicts the overall blocking behavior of a HVOB network as verified by an extensive simulation study, andit agrees with the strictly nonblocking condition
of the network. The derived upper bound is significant because it reveals the
inherentrelationship among blocking probability, network depth, and network
hardware cost, so that a desirable tradeoff can be made amongthem. In particular,
our bound gives network developers an effective tool to estimate the
maximum blocking probability of a HVOBnetwork, in which different routing
strategies can be applied with a guaranteed performance in terms of blocking
probability, hardwarecost and network depth. Our upper bound model predicts
some unobvious qualitative behaviors of HVOB networks, and it draws
animportant conclusion that a very low blocking probability (e.g., less than
0.001 percent) can be achieved in a HVOB network withoutintroducing either
a significantly high hardware cost or a large network depth. |
Refereed Proceeding Papers
| [minyi-04:2006] |
Weijia Jia, Tian Wang, Guojun Wang, and Minyi Guo. Hole
Avoiding in Advance Routing in Wireless Sensor Networks. In Proceedings
of the 2007 IEEE Wireless Communications & Networking
Conference (WCNC 2007), pages 3522-3526, Hong Kong, March
2007. IEEE Communications Society. |
| Energy consumption is a major issue when designing routing protocols in
wireless sensor networks. We propose a novel Hole Avoiding In advance
Routing protocol (HAIR) to address this issue. In the proposed protocol,
a data packet can avoid meeting a hholeh in advance instead of bypassing
a hole when it meets the hole as existing Hole Avoiding Re-Routing protocols
(HARR) do. We prove that the proposed protocol can always find
a routing path between a given source node and the sink if such a routing
path does exist in the network. Simulation studies show that the proposed
HAIR protocol constructs routing paths with shorter routing distance and
less energy consumption in comparison with the existing HARR protocols.
The proposed protocol can be used in large-sca1e wireless sensor networks. |
|
| [minyi-05:2006] |
Guojun Wang, Huan Wang, Jiannong Cao, and Minyi Guo. Energy-Efficient Dual Prediction-Based Data Gathering for Environmental
Monitoring Applications. In Proceedings of the 2007 IEEE
Wireless Communications & Networking Conference (WCNC 2007),
pages 3516 - 3521, Hong Kong, March 2007. IEEE Communications
Society. |
| How to prolong the lifetime of wireless sensor networks is an important
issue in designing environmental monitoring applications. In this paper, we
propose a novel energy-efficient data gathering algorithm, called EDP, which
is based on dual prediction. Both sensor nodes and the sink node use the
same prediction algorithm based on the same historical data. Each sensor
node predicts the values of the data to be sensed according to its recorded
historical information. When getting the sensory data, the node compares
it with the predicted data. Only when the difference between the predicted
and the sensed data values exceeds a pre-defined threshold, the sensor node
sends the newly sensed data to the sink node. For the sink node, during a
reporting period, if it receives data from a sensor node, the received data will
be used as the hsensed datah; otherwise, the sink node will use the prediction
algorithm to get the hpredicted valueh in the same way as the sensor node
does. Theoretical analysis and simulation studies show that EDP can greatly
reduce the amount of data transmitted in the network, leading to significant
energy saving on the sensor nodes and extension of the lifetime of the entire
network. |
|
| [minyi-07:2006] |
Eun-Ha Song, Sung-Kook Han, Laurence Tianruo Yang andMinyi
Guo, and Young-Sik Jeong. A GML-Based Mobile Device Trace
Monitoring System. In Proceedings of 2006 International Conference
on Embedded and Ubiquitous Computing (EUC-06 workshop), 4097,
pages 234-243, Seoul, Korea, August 2006. Springer. |
| Lecture Notes in Computer Science |
|
| [minyi-08:2006] |
Baoliu Ye, Minyi Guo, and Jingling Xue. A Cooperative Cache
Based Streaming Schedule Scheme for On-demand Media Services on Overlay Networks. In Proceedings of the 2006 International Conference
on Parallel Processing (ICPP 2006), pages 577-584, Columbus,
USA, August 2006. Ohio State University, IEEE CS Press. |
| [minyi-09:2006] |
Yang-Seung Jeon, Eun-Ha Song, , and Minyi Guo. Ontology-
Based Composition of Web Services for Ubiquitous Computing. In
Proceedings of the 2006 International Conference on Parallel and Distributed
Processing and Applications (ISPA 2006), Sorrento, Italy,
December 2006. Springer. |
| Lecture Notes in Computer Science |
Books
| [minyi-10:2006] |
Minyi Guo, Laurence T. Yang, Beniamino Di Martino, Hans Zima,
and Jack Dongarra. Parallel and Distributed Computing with Applications.
Number 4330 in Lecture Notes in Computer Science. Springer-
Verlag, Berlin, 2006. |
| [minyi-11:2006] |
Geyong Min, Beniamino Di Martino, Laurence T. Yangand Minyi
Guo, and Gudula Runger. Workshop of Parallel and Distributed Computing
with Applications. Number 4331 in Lecture Notes in Computer
Science. Springer-Verlag, Berlin, 2006. |
| [minyi-12:2006] |
Minyi Guo and Hai Jin. Frontier of Computer Science and Technology.
IEEE Computer Society Press, USA, 2006. |
Grants
| [minyi-13:2006] |
Minyi Guo. The Telecommunications Advancement Foundation,
2005-2006. |
Academic Activities
| [minyi-14:2006] |
Minyi Guo, 2002-. IEICE Member |
| [minyi-15:2006] |
Minyi Guo, 2000-. IEEE, IEEE Computer Society Senior member |
| [minyi-16:2006] |
Minyi Guo, 2000-. ACM Member |
| [minyi-17:2006] |
Minyi Guo, 1995-. IPSJ Member |
| [minyi-18:2006] |
Minyi Guo, December 2006. Program Committee Chair, The 2006 International Symposium on Parallel andDistributed Computing with Applications (ISPA2006). |
| [minyi-19:2006] |
Minyi Guo, August 2006. Steering Committee Chair, the 2006 International Conference on Embedded and Ubiquitous Computing |
Ph.D. and Other Theses
| [minyi-20:2006] |
Manabu Morita. Master Thesis: Design and Implementation of
Stream ProcessingSystem and Library on Cell Processors, University of
Aizu, 2006. Thesis Advisor: Minyi Guo. |
| [minyi-21:2006] |
Takamasa Ohno. Master Thesis: Context Information Processing
Model forPervasive Computing Systems, University of Aizu, 2006. Thesis Advisor: Minyi Guo. |
| [minyi-22:2006] |
Hisamitsu Sato. Graduation Thesis: COINS-Based Parallel Program
Generation forDistributed Memory Machines, University of Aizu,
2006. Thesis Advisor: Minyi Guo. |
| [minyi-23:2006] |
Zheng Geng. Graduation Thesis: Peer-to-peer network Bulletin
Board System with Web Service, University of Aizu, 2006. Thesis Advisor: Minyi Guo. |
| [minyi-24:2006] |
Shinji Watanabe. Graduation Thesis: Creating Chains of Processes
for Wireless Mobile Users, University of Aizu, 2006. Thesis Advisor: Minyi Guo. |
| [minyi-25:2006] |
Masayuki Moriguchi. Graduation Thesis: Implementation of External
Dependence System on Mobile Devices, University of Aizu, 2006. Thesis Advisor: Minyi Guo. |
| [minyi-26:2006] |
Kazunori Kojima. Graduation Thesis: Efficient Instruction
Scheduling for Multiple Branches, University of Aizu, 2006. Thesis Advisor: Minyi Guo. |
| [minyi-27:2006] |
Takahiro Machino. Graduation Thesis: Code Translator of parallelizing
loops for CELL Broadband Engine Processor, University of Aizu,
2006. Thesis Advisor: Minyi Guo. |
Others
| [minyi-28:2006] |
Minyi Guo. Editor in Chief, International Journal of Embedded Systems |
| [minyi-29:2006] |
Minyi Guo. Editor, International Journal of Web and Grid Services |
| [minyi-30:2006] |
Minyi Guo. Editor, International Journal of High Performance Computing and Networking |
| [minyi-31:2006] |
Minyi Guo. Editor, Journal of Embedded Computing |
| [minyi-32:2006] |
Minyi Guo. Editor, Journal of Pervasive Computing and Communications |
| [minyi-33:2006] |
Minyi Guo. Editor, International Journal of Computer and Applications |
