Chao-Tung Yang

Hybrid CUDA, OpenMP, and MPI parallel programming on multicore GPU clusters ☆

Abstract Nowadays, NVIDIAs CUDA is a general purpose scalable parallel programming model for writing highly parallel applications. It provides several key abstractions – a hierarchy of thread blocks, shared memory, and barrier synchronization. This model has proven quite successful at programming multithreaded many core GPUs and scales transparently to hundreds of cores: scientists throughout industry and academia are already using CUDA to achieve dramatic speedups on production and research codes. In this paper, we propose a parallel programming approach using hybrid CUDA OpenMP, and MPI programming, which partition loop iterations according to the number of C1060 GPU nodes in a GPU cluster which consists of one C1060 and one S1070. Loop iterations assigned to one MPI process are processed in parallel by CUDA run by the processor cores in the same computational node.

Wiki-based rapid prototyping for teaching-material design in e-Learning grids

Grid computing environments with abundant resources can support innovative e-Learning applications, and are promising platforms for e-Learning. To support individualized and adaptive learning, teachers are encouraged to develop various teaching materials according to different requirements. However, traditional methodologies for designing teaching materials are time-consuming. To speed up the development process of teaching materials, our idea is to use a rapid prototyping approach which is based on automatic draft generation and Wiki-based revision. This paper presents the approach named WARP (Wiki-based Authoring by Rapid Prototyping), which is composed of five phases: (1) requirement verification, (2) query expansion, (3) teaching-material retrieval, (4) draft generation and (5) Wiki-based revision. A prototype system was implemented in grid environments. The evaluation was conducted using a two-group t-test design. Experimental results indicate that teaching materials can be rapidly generated with the proposed approach.

Implementation of a Medical Image File Accessing System on Cloud Computing

Large scale cluster based on cloud technologies has been widely used in many areas, including the data center and cloud computing environment. The purpose of presenting the research paper in this field was to solve the challenge in Medical Image exchanging, storing and sharing issues of EMR (Electronic Medical Record). In recent years, many countries invested significant resources on the projects of EMR topics. The benefit of the EMR included: Patient-centered Care, Collaborative Teams, Evidence-based Care, Redesigned Business Processes, Relevant Data Capture and Analysis and Timely Feedback and Education. For instance, the ARRAHIT project in Untied States (2011 - 2015), Health Infoway project in Canada (2001 - 2015) and NHIP project in Taiwan, etc. Aim to the topic of EMR, we presented a system called MIFAS (Medical Image File Accessing System) to solve the exchanging, storing and sharing on Medical Images of crossing the different hospitals issues. Through this system we can enhance efficiency of sharing information between patients and their caregivers. Furthermore, the system can make the bestpossible patient-care decisions.

A Parallel Loop Self-Scheduling on Extremely Heterogeneous PC Clusters

Cluster computers are a viable and less expensive alternative to symmetric multiprocessor systems. However, a serious difficulty in concurrent programming of a cluster computer system is how to deal with scheduling and load balancing of such a system which may consist of heterogeneous computers Self-scheduling schemes suitable for parallel loops with independent iterations on heterogeneous computer clusters have been designed in the past These schemes, such as FSS, GSS and TSS, can achieve load balancing in SMP, even in a moderate heterogeneous environment, but are not suitable in extremely heterogeneous environments. In this paper, we propose a heuristic approach to solve parallel loop scheduling problems on an extremely heterogeneous PC cluster environment.

Improvements on dynamic adjustment mechanism in co-allocation data grid environments

Abstract Several co-allocation strategies have been coupled and used to exploit rate differences among various client-server links and to address dynamic rate fluctuations by dividing files into multiple blocks of equal sizes. However, a major obstacle, the idle time of faster servers having to wait for the slowest server to deliver the final block, makes it important to reduce differences in finishing time among replica servers. In this paper, we propose a dynamic co-allocation scheme, namely Recursive-Adjustment Co-Allocation scheme, to improve the performance of data transfer in Data Grids. Our approach reduces the idle time spent waiting for the slowest server and decreases data transfer completion time.

Integrating grid with intrusion detection

In recent years, distributed denial-of-service (DDoS) and denial-of-service (DoS) are the most dreadful network threats. Single-node IDS often suffers from losing its detection effectiveness and capability when processing enormous network traffic. To solve the drawbacks, we propose grid-based IDS, called grid intrusion detection system (GIDS), which uses grid computing resources to detect intrusion packets. For balancing detection load, score subtraction approach (SSA) and score addition approach (SAA) are deployed. Furthermore, to effectively detect intrusions, a two-phase packet detection process is proposed. The first phase detects logical and momentary attacks. Chronic attacks are detected in the second phase. Experiments are also performed and the results show that GIDS is truly an outstanding system in detecting attacks.

A parallel loop self-scheduling on extremely heterogeneous PC clusters

Cluster system is viable and less expensive alternative to SMP. However, the approaches to deal with scheduling and load balancing on heterogeneous cluster computer system are not mature. Self-scheduling schemes which are suitable for parallel loops with independent iterations on heterogeneous cluster computer system have been designed in the past. However, these schemes, such as FSS, GSS and TSS, can not achieve load balancing in extremely heterogeneous environment. In this paper, we propose a heuristic approach to solve parallel regular loop scheduling problem on extremely heterogeneous PC cluster environment.

Lifetime elongation for wireless sensor network using queue-based approaches

A wireless sensor network (WSN) is envisioned as a cluster of tiny power-constrained devices with functions of sensing and communications. Sensors closer to a sink node have a larger forwarding traffic burden and consume more energy than nodes further away from the sink. The whole lifetime of WSN is deteriorated because of such an uneven node power consumption patterns, leading to what is known as an energy hole problem (EHP). From open literatures, most research works have focused on how to optimally increase the probability of sleeping states using various wake-up strategies. In this article, we propose a novel power-saving scheme to alleviate the EHP based on the N-policy M/M/1 queuing theory. With little or no extra management cost, the proposed queue-based power-saving technique can be applied to prolong the lifetime of the WSN economically and effectively. A mathematical analysis on the optimal control parameter has been made in detail. Focusing on many-to-one WSN, numerical and network simulation results validate that the proposed approach indeed provides a feasibly cost-effective approach for lifetime elongation of WSN.

An Enhanced Parallel Loop Self-Scheduling Scheme for Cluster Environments

Approaches for dealing with scheduling and load-balancing in PC-based cluster systems are famous and well known. In such environments, Self-Scheduling Schemes are suitable for parallel loops with independent iterations. However, while schemes such as FSS, GSS, and TSS fit most computer systems, they cannot provide good load-balancing. Chao-Tung Yang and Shun-Chi Chang proposed a parallel loop scheduling scheme for heterogeneous PC cluster systems in Yang and Chang [13]. Though the proposed scheme allows users to choose parameters before execution initialization, weaknesses in it motivated us to develop further improvements. For instance, using fixed and monotonous parameters can easily lead to invalid scheduling due to use of previously input information. Thus, in this paper we propose a new scheme that fits most widely available computer systems and allows the scheduling parameter to be adjusted dynamically in order to provide higher overall performance.

A performance-based grid intrusion detection system

Distributed denial-of-service (DDoS) and denial-of-service (DoS) are the most dreadful network threats in recent years. In this paper, we propose a grid-based IDS, called performance-based grid intrusion detection system (PGIDS), which exploits grids abundant computing resources to detect enormous intrusion packets and improve the drawbacks of traditional IDSs which suffer from losing their detection effectiveness and capability when processing massive network traffic. For balancing detection load and accelerating the performance of allocating detection node (DN), we use exponential average to predict network traffic and then assign the collected actual traffic to the most suitable DN. In addition, score subtraction algorithm (SSA) and score addition algorithm (SAA) are deployed to update and reflect the current performance of a DN. PGIDS detects not only DoS/DDoS attacks but also logical attacks. Experimental results show that PGIDS is truly an outstanding system in detecting attacks.