Hsiao-Hsi Wang

Efficient Packet Pattern Matching for Gigabit Network Intrusion Detection Using GPUs

With the rapid development of network hardware technologies and network bandwidth, the high link speeds and huge amount of threats poses challenges to network intrusion detection systems, which must handle the higher network traffic and perform more complicated packet processing. In general, pattern matching is a highly computationally intensive process part of network intrusion detection systems. In this paper, we present an efficient GPU-based pattern matching algorithm by leveraging the computational power of GPUs to accelerate the pattern matching operations to increase the over-all processing throughput. From the experiment results, the proposed algorithm achieved a maximum traffic processing throughput of 2.4 Gbit/s. The results demonstrate that GPUs can be used effectively to speed up intrusion detection systems.

Performance issues of grid computing based on different architecture cluster computing platforms

This research paper discusses performance issues of cluster and grid computing platforms, and reasons to support the implementation of these computing infrastructures. A number of benchmark programs are executed in these computing systems, in order to perform performance analysis of experimental results. We are able to show that cluster platforms are excellent alternatives to access to supercomputing, due to its cost/performance, scalability and commodity components factors. In addition, we also show that grid technology is viable by increasing total system performance at no additional cost.

An efficient parallel-network packet pattern-matching approach using GPUs

Abstract In the past few years, the increase in interest usage has been substantial. The high network bandwidth speed and the large amount of threats pose challenges to current network intrusion detection systems, which manage high amounts of network traffic and perform complicated packet processing. Pattern matching is a computationally intensive process included in network intrusion detection systems. In this paper, we present an efficient graphics processing unit (GPU)-based network packet pattern-matching algorithm by leveraging the computational power of GPUs to accelerate pattern-matching operations and subsequently increase the overall processing throughput. According to the experimental results, the proposed algorithm achieved a maximal traffic processing throughput of over 2 Gbit/s. The results demonstrate that the proposed GPU-based algorithm can effectively enhance the performance of network intrusion detection systems.

Efficient GPGPU-Based Parallel Packet Classification

With the rapid growth of network technologies, many new web services have been developed to provide various applications and computing functions. These services rely deeply on the internet. Therefore, packet classification is an important issue of network security that typically adopts a flexible packet filtering system to classify each processed packet. Traditional packet classification requires hung computing time to process large amount of internet packets. Hence, we propose a GPGPU-based parallel packet classification method to decrease the computational cost. We also evaluate the performance of the proposed method with implementation on various memory architectures of CUDA device. The experiment results demonstrate that the proposed method can achieve significant speed up over the sequential packet classification algorithms on single CPU.

Strategies toward Optimal Access to File Replicas in Data Grid Environments

Data Grid is one of key technologies to build up large-scale dataset storage system by connecting scattered storage resources dispersedly located in the Grid. One major challenge in data grids is how to provide good and timely access to huge amount of data in distributed locations, given the high latency of interconnection networks. Parallel downloading methods can improve download efficiency and performance, and for such, processes should have started from appropriate locations. In this research paper, we present the design framework of PU-DG Optimizer toolbox (also known as PU-DG Optibox) for data grid environments. The proposed toolbox is a package containing a number of high-end techniques and algorithms running as middleware on top of data grid platforms, in order to optimize file downloads, by improving its efficiency and performance. Moreover, PU-DG Optibox not only provides users and developers possibilities for setting their own priority strategies, as also different downloading modes. Furthermore, workload balancing to avoid low quality computing node to execute highly complex job is also included in this design. Experimental results of techniques packaged in the proposed toolbox demonstrate its potential and effectiveness.

On the Design and Implementation of an Effective Prefetch Strategy for DSM Systems

Distributed Shared Memory systems provide the abstraction of a shared address space among computing hosts interconnected via a private network, in a convenient and easy way to achieve high performance. However, there are several drawbacks to these systems, such as communication overhead, network latency, false sharing, coherence and page faults. By prefetching, one can overlap communication and computation though the Accumulated Waiting Phenomenon and the Waiting Synchronization Phenomenon affect overall performance. In this paper, an Effective Prefetch Strategy (EPS) is proposed, to improve the shortcomings of previous prefetching approaches and increases the prefetch page hit rate. In addition, our EPS strategy reduces the waiting time for each computing host upon barrier synchronizations and misprefetches. Experimental comparisons show that our proposed EPS strategy offers the best performance among existinrefetching strategies.

Design issues of a novel toolkit for parallel application performance monitoring and analysis in cluster and grid environments

The low-cost and availability of network of workstations have made them attractive solution for high performance computing. Striking progress of network technology in enabling high-performance global computing, with the utilization of cluster and grid technologies, in which computational and data resources in a local or wide area network are transparently employed to solve large-scale problems. In this paper, we present implementation and design rationale of Visuel toolkit for performance measurement and analysis of parallel applications, in cluster and grid environments. Most of performance visualization tools available today for high-performance platforms show solely system performance data (e.g., CPU load, memory usage, network bandwidth, server average load), and thus, being suitable for visualisation of computing platform system activities. The Visuel toolkit, is Web-based interface designed to show performance activities of all computing nodes of a cluster or grid computing platform involved in the execution of a parallel application, such as CPU load level and memory usage of each computing node. In addition, this toolkit is able to display comparative performance data visualizations generated from a number of executions of an application under investigation, analyzing the performance of different implementations. Evaluations using this toolkit show that it outperforms in easing the process of investigation and implementation of parallel applications, in effective way.

On design of agent home scheme for prefetching strategy in DSM systems

In distributed shared memory (DSM) systems, it is the common need to access data in remote nodes. Thus, it induces to remote access performance latencies, which is the major factor of overhead for DSM systems. Prefetching strategies can improve these phenomena by reducing latencies, but it adds workload to home nodes. It is proposed in this paper a method to reduce overhead of home nodes, by providing an agent home to share the workload of home nodes, by distributing these workloads to other nodes, when sending data. The performance evaluation of proposed strategy is done by performing three well-known benchmark programs: NPB/IS, 3DFFT and Red-Black SOR. The experimental results show that our proposed agent home method achieves 8%- 40% of speedup against original JIAJIA.

Visuel: a novel performance monitoring and analysis toolkit for cluster and grid environments

The computing power provided by high performance low-cost PC-based Cluster and Grid platforms are attractive, and they are equal or superior to supercomputers and mainframes widely available. In this research paper, we present the design rationale and implementation of Visuel, a toolkit for performance measurement and analysis of MPI parallel programs and real time resources monitoring in cluster and grid computing environments. The proposed toolkit is web-based interface to show performance activities of all computing nodes involved in the execution of a MPI parallel program, such as CPU and memory usage levels of each computing node, and monitors all computing nodes of a computing platform by displaying real time performance data. In addition, this toolkit is able to display comparative performance data charts of multiple executions of MPI parallel application under investigation, which facilitates the “what-if” analysis. The usage of this toolkit shows that it outperforms in easing the process of investigation of parallel applications.

Dynamic file replica location and selection strategy in data grids

In this paper, we present the design of PU-DG optimizer toolbox (also known as PU-DG Optibox), which not only finds out the best strategy according to huge amount of simulation results but also proposes the min-max balancing workload method to upgrade the efficiency of execution in data grid environments. Data grid is one of key factors to build up large-scale dataset storage system and providing high performance computing capacity, by connecting scattered computing and storage resources located dispersedly in the grid. One major challenge in data grids is how to provide good and timely access to huge amount of data in distributed locations, given the high latency of interconnection networks. In this paper, we present the design framework of PU-DG Optibox for data grid environments. The proposed toolbox is a package containing a number of high-end techniques and methods running as middleware on top of data grid platforms, in order to optimize file downloads, by improving its efficiency and performance. The PU-DG Optibox provides users and developers possibilities for setting their own priority strategies. In addition, min-max balancing workload method is proposed to avoid that one computing node with lower network bandwidth to receive a job that has high complexity of job factor. Experimental results of techniques packaged in the proposed toolbox demonstrate its effectiveness.