Haifang Zhou

A behavior characteristics-based reputation evaluation method for grid entities

Reputation provides an operable metric for trust establishment between unknown entities in Grid. Yet, most reputation evaluation methods rarely analyze an entitys past behaviors, which is a deviation from the definition of reputation: an expectation for future behaviors based on past behavior information. Therefore, we propose this behavior-based method for reputation evaluation. The main idea is that: according to reputation evidences from third parties, behavior characteristics such as behavior coherence, behavior inertia etc will be well abstracted, and reputation evaluation will be better guided. Experimental results show that: this method can effectively characterize an entitys behavior, and the final reputation result is reasonable and reliable.

First evaluation of parallel methods of automatic global image registration based on wavelets

With the increasing importance of multiple multiplatform remote sensing missions, fast and automatic integration of digital data from disparate sources has become critical to the success of these endeavors. Firstly, an overview of development of automatic and parallel global image registration is given. And then, based on the analyses of existing three parallel methods of wavelet-based global registration, a new parallel strategy is proposed. Moreover, towards the quantitative evaluation, first results of the intercomparision of four parallel global registration algorithms are presented in theory and in experiments.

Static Analysis for Application-Level Checkpointing of MPI Programs

Application-level checkpointing is a promising technology in the domain of large-scale scientific computing. The consistency of global checkpoint must be carefully guaranteed in order to correctly restore the computation. Usually, some complex coordinated protocols are employed to ensure the consistency of global checkpoint, which require logging orphan or in-transit messages during checkpointing. These protocols complicate the recovery of the computation and increase the checkpoint overhead due to logging message. In this paper, a new method which ensures the consistency of global checkpoint by static analysis is proposed. The method identifies the safe checkpointing regions in MPI programs, where the global checkpoint is always strongly consistent. All checkpoints are located in those safe checkpoint regions. During checkpointing, the method will not log any messages and introduce no extra overhead. The method was implemented and integrated into ALEC, which is a source-to-source precompiler for automating application-level checkpointing. The experimental results show that our method is effective.

Building Single Fault Survivable Parallel Algorithms for Matrix Operations Using Redundant Parallel Computation

As the size of todays high performance computers continue to grow, node failures in these computers are becoming frequent events. Although checkpoint is the typical technique to tolerate such failures, it often introduces a considerable overhead and has shown poor scalability on todays large scale systems. In this paper we defined a new term called fault tolerant parallel algorithm which means that the algorithm gets the correct answer despite the failure of nodes. The fault tolerance approach in which the data of failed processes is recovered by modifying applications to recompute on all surviving processes is checkpoint-free. In particular, if no failure occurs, the fault tolerant parallel algorithms are the same as the original algorithms. We show the practicality of this technique by applying it to parallel dense matrix-matrix multiplication and Gaussian elimination to tolerate single process failure. Experimental results demonstrate that a process failure can be tolerated with a good scalability for the two fault tolerant parallel algorithms and the proposed fault tolerant parallel dense matrix-matrix multiplication is able to survive process failure with a very low performance overhead. The main drawback of this approach is non-transparent and algorithm-dependent.

GPGC: a Grid-enabled parallel algorithm of geometric correction for remote-sensing applications

ChinaGrid is an important project sponsored by the China Ministry of Education, aiming to provide high‐performance services in a Grid computing environment. In this paper, one of the applications offered by ChinaGrid, parallel remote‐sensing image processing, is described. Geometric correction is a basic step during the processing of remote‐sensing imagery, which is traditionally a computation‐intensive and communication‐intensive application if in parallel mode. In order to move this application into a Grid, a new Grid‐enabled parallel algorithm of geometric correction is proposed, called GPGC. GPGC changes the frequent and fine‐grain communication mode of the existing parallel method into a delayed but concentrated exchanging mode by computing an irregular local output area. This change means no communication or synchronization happens during resampling that occupies most of the execution time. To prove its efficiency, the complexity of GPGC is analyzed in theory. Finally, performance testing of GPGC and its application in ChinaGrid are given. Experimental results show that our algorithm is more suitable for a Grid platform, excelling the old method in both performance and salability. Copyright

Research on Grid-Enabled Parallel Strategies of Automatic Wavelet-based Registration of Remote-Sensing Images and Its Application in ChinaGrid

ChinaGrid is an important project aiming to providing high performance services in a grid computing environment.One of the applications offered by ChinaGrid, image registration is described. It is an important processing step in many applications of remote sensing area, which is requires intensive computing power. Firstly, the serial and existing parallel strategies of wavelet-based automatic image registration are overviewed. And then, some grid- enabled optimization for two of them, Hybrid-Parallel (HP) and Group-Parallel (GP), is given. Thirdly, all of these parallel strategies are reevaluated for grid environment theoretically and a performance testing of these parallel algorithms is done on a simulated grid platform. Experimental results show that our optimization is effective but the basic simple parallel strategy Parameter-Parallel (PP) is the best choice for grid. The parallel algorithms proposed here have been integrated into related service system of ChinaGrid.

A parallel mutual information based image registration algorithm for applications in remote sensing

Image registration is a classical problem that addresses the problem of finding a geometric transformation that best aligns two images. Since the amount of multisensor remote sensing imagery are growing tremendously, the search for matching transformation with mutual information is very time-consuming and tedious, and fast and automatic registration of images from different sensors has become critical in the remote sensing framework. So the implementation of automatic mutual information based image registration methods on high performance machines needs to be investigated. First, this paper presents a parallel implementation of a mutual information based image registration algorithm. It takes advantage of cluster machines by partitioning of data depending on the algorithms peculiarity. Then, the evaluation of the parallel registration method has been presented in theory and in experiments and shows that the parallel algorithm has good parallel performance and scalability.

Constructing decision tree with continuous attributes for binary classification

Continuous attributes are hard to handle and require special treatment in decision tree induction algorithms. In this paper, we present a multisplitting algorithm, RCAT, for continuous attributes based on statistical information. When calculating information gain for a continuous attribute, it first splits the value range of the attribute into some initial intervals, computes the probability estimation of every class at each interval and finds the best threshold in the probability space, uses this threshold to separate the initial intervals into two sets, combines adjacent intervals in the same set, optimizes the boundary of every combined interval, and finally obtains the information gain of the continuous attribute. We also provide a pruning method to simplify the decision trees. Empirical results show that the RCAT algorithm can realise decision trees with much higher intelligibility than C4.5 while retaining their accuracy.

Optimal Placement of Application-Level Checkpoints

One of the basic problems related to the efficient application-level checkpointing is the placement of checkpoints in the source codes. In this paper we discuss two common questions with a source-to-source precompiler ALEC: 1) if there are N checkpoints in the applications source code, how to pick M checkpoints out of them minimizing the total amount of checkpoint data? 2) if there are no checkpoint in the applications source code, how to insert a set of checkpoints minimizing the amount of checkpoint data? We reveal that these two questions can both be abstracted as a mathematic model which is similar to the 0-1 integer programming model, and the model can be solved using implicit enumeration method. The solving methods proposed in the paper have been implemented and integrated into ALEC. Experimental results show that the method is efficient.

A novel fault-tolerant parallel algorithm

The mean-time-between-failure of current high-performance computer systems is much shorter than the running times of many computational applications, whereas those applications are the main workload for those systems. Currently, checkpoint/restart is the most commonly used scheme for such applications to tolerate hardware failures. But this scheme has its performance limitation when the number of processors becomes much larger. In this paper, we propose a novel fault-tolerant parallel algorithm FPAPR. First, we introduce the basic idea of FPAPR. Second, we specify the details of how to implement a FPAPR program by using two NPB kernels as examples. Third, we theoretically analyze the overhead of FPAPR, and find out that the overhead of FPAPR decreases with the increase of the number of processors. At last, the experimental results on a 512-CPU cluster show the overhead introduced by the algorithm is very small.