检索结果-内蒙古大学图书馆

1st International Conference on Internet Multimedia computing and Service, ICIMCS 2009

作者： Zheng, Ran Jin, Hai Zhang, Qin Zhang, Liang Cluster and Grid Computing Lab. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781605588407

Silicosis is one of the most serious occupational diseases in China. Radiologist information comes from chest radiographs, in which the most important parts are lung fields and ribs. It is necessary to distinguish lung fields and ribs from other organs. The anatomical knowledge-based lung segmentation can improve the accuracy of segmentation and solve the problems of opened region and lost clavicle region. The curve model-based rib segmentation can acquire more accurate rib location information, and provide more efficient orientation for latter diagnosis. These two methods are also deployed in grid environment to get higher efficiency when processing massive and distributed medical data for silicosis diagnosis. Experiments show that the two proposed algorithms can meet the latter medical requirements for chest radiograph with higher accuracy. Copyright 2009 ACM.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

DPLM: A novel application-layer routing scheme for low delay VoIP 08

DPLM: A novel application-layer routing scheme for low delay...

引用

4th Asian Internet Engineering Conference, AINTEC 2008

作者： Liao, Xiaofei Jin, Hai Zhu, Lili Cluster and Grid Computing Lab. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781605581279

In order to achieve low delay services in VoIP, we can use application-layer routing scheme, which is to find proper relay nodes to intermediate voice packets from the source peer to the destination peer. The difficulty of the scheme is how to find the proper relay nodes, which we call relay problem. This paper presents a new application-layer routing scheme, called DPLM, to resolve relay problem. We introduced the mechanism in detail, and evaluated our mechanism in NS2 network simulation environment and got a high relay node hit ratio result, which confirms the feasibility of a real system. Also we make a comparison with traditional schemes, and the results show that DPLM scheme has good performances. Copyright 2008 ACM.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

VMckpt:lightweight and live virtual machine checkpointing

引用

science China(Information sciences) 2012年第12期55卷 2865-2880页

作者： LIU HaiKun 1,JIN Hai 1,LIAO XiaoFei 1,MA Bo 1 & XU ChengZhong 2 1 Services computing technology and System Lab,cluster and grid computing Lab,school of computer science and technology,Huazhong University of science and technology,Wuhan 430074,China 2 Department of Electrical and computer Engineering,Wayne State University,Detroit,MI 48202,USA 1. Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China2. Department of Electrical and Computer Engineering Wayne State University Detroit MI [48202 USA

Recent advance of virtualization technology provides a new approach to check-point/restart at the virtual machine(VM) *** contrast to traditional process-level checkpointing,checkpointing at the virtualization layer brings up several advantages,such as compatibility,transparence,flexibility and ***,because the virtualization layer has little semantic knowledge about the operation system and the applications running atop,VM-layer checkpointing requires saving the entire operating system state rather than a single *** overhead may render the approach *** reduce the size of VM checkpoint,in this paper we propose a page eviction scheme and an incremental checkpointing mechanism to avoid saving unnecessary VM pages in the *** keep the system online transparently,we propose a live checkpointing mechanism by saving the memory image in a copy-on-write(COW) *** implement the performance optimization mechanisms in a prototype system,called *** results with a group of representative applications show that our page eviction scheme and incremental checkpointing can significantly reduce the checkpoint file size by up to 87% and shorten the total checkpointing/restart time by a factor of up to 71%,in comparison with the Xens default checkpointing *** observed application downtimes due to checkpointing can be reduced to as small as 300 ms.

关键词： checkpoint/restart copy-on-write page eviction virtual machine

来源：评论

学校读者我要写书评

暂无评论

An efficient distributed transactional memory system

An efficient distributed transactional memory system

引用

11th IEEE International Conference on Trust, Security and Privacy in computing and Communications, TrustCom-2012

作者： Peng, Xin Liao, Xiaofei Jin, Hai Fan, Xuepeng Tu, Xuping Yu, Linchen Cluster and Grid Computing Lab. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780769547459

Transactional memory (TM) is a parallel programming concept which reduces challenges in parallel programming. Existing distributed transactional memory system consumes too much bandwidth and brings high latency. In this work, we present Transactional Memory System for cluster (Clustm), a generalized and scalable distributed transactional memory system. Our system addresses several open issues posed by this domain, including transactional memory consistency protocol, cache consistency protocol, and the distribution strategy of the metadata of shared data across the cluster. Then, we evaluate our design with several workloads, and the results demonstrate outstanding performance. © 2012 IEEE.

关键词： Parallel programming

来源：评论

学校读者我要写书评

暂无评论

Efficient multiple-reference temporal error concealment algorithm based on H.264/AVC 2nd

Efficient multiple-reference temporal error concealment algo...

引用

2nd International Conference on Human Centered computing, HCC 2016

作者： Yu, Chen Cheng, Chao Jin, Hai Zhou, Jingli Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783319318530

Temporal error concealment at the video communication receiver recovers damaged blocks using temporal information redundancy. To enhance the quality of reconstructed image, a multiple-reference temporal error concealment algorithm based on H.264/AVC was proposed. Firstly, a pre-concealment is implemented to improve video frame;then the fractional pixel boundary matching algorithm and search algorithm are used to evaluate the candidate motion vectors from a number of reference frames, and the motion vector (MV) giving the minimum boundary matching distortion (MBMD) is selected as optimal motion vector;finally it is used to recover the damaged block and the video frame quality can be improved further. For various video sequences and different macro-block loss ratio, experimental results show that the proposed algorithm is significantly better than traditional temporal error concealment algorithms such as BMA and BM from both objectively and subjectively. At the loss ratio of 10 %, improvements of the proposed algorithm are more than 0.8~3.7 dB compared to that of other algorithms. © Springer International Publishing Switzerland 2016.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Anysee2: An auto load balance P2P live streaming system with hybrid architecture (work-in-progress) 2

Anysee2: An auto load balance P2P live streaming system with...

引用

2nd International Conference on Scalable Information Systems, InfoScale 2007

作者： Huang, Qi Jin, Hai Liu, Ke Liao, Xiaofei Tu, Xuping Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781595937575

Nowadays, Peer-to-Peer technology has been widely used in live streaming applications and many related systems are proposed. However, their single overlay design and unbalanced scheduling methods lead to some inefficiency including high control overhead and bad playback experience. This paper mainly discusses how to address these certain problems. We introduce a hybrid architecture to solve the locality problem and reduce the control overhead. We also propose a scheduling method to achieve load balance. All solutions are implemented in Anysee2.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

SymS: A symmetrical scheduler to improve multi-threaded program performance on NUMA systems

SymS: A symmetrical scheduler to improve multi-threaded prog...

引用

作者： Zhu, Liang Jin, Hai Liao, Xiaofei Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Summary The nonuniform memory access (NUMA) architecture has been used extensively in data centers. Most of the previous works used single-threaded multiprogrammed workloads to study the performance of NUMA systems, which mainly focus on two classes of problems: resource contention and data locality. However, when running multi-threaded programs on NUMA systems, the critical thread of these programs significantly influences the system performance and brings new challenges that are different from those in a single-threaded situation. In particular, an additional scheduling scheme is desired to avoid the performance degradation caused by the critical thread of multi-threaded programs running on NUMA systems. This work presents a scheduler, Symmetrical Scheduler, which successfully solves the lagging problem by balancing the number of the costly remote shared data accesses for threads on NUMA systems. To the best of our knowledge, little work has been conducted to examine the performance impacted by the critical thread of multi-threaded programs on NUMA systems. By running the PARSEC benchmark on such systems, our methodology can improve the program performance by a factor of 6% on average and achieve maximally 25.3% improvement compared with Linux kernel scheduling mechanism. © 2015 John Wiley & Sons, Ltd.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Parallel bloom filter on xeon phi many-core processors 15th

Parallel bloom filter on xeon phi many-core processors

引用

15th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2015

作者： Ni, Sheng Guo, Rentong Liao, Xiaofei Jin, Hai Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783319271217

Bloom filters are widely used in databases and network areas. These filters facilitate efficient membership checking with a low false positive ratio. It is a way to improve the throughput of bloom filter by parallel processing. Common many-core processors such as Xeon Phi can provide high parallelism. Thus, we build an iterative model to analyze memory access performance. This performance suggests that the bottleneck in the traditional design is mainly caused by synchronization cost and memory latency on many-core platforms. Therefore, we propose a parallel bloom filter (PBF), which is a lockless method involving input data preprocessing. This method reduces synchronization overhead and improves cache locality. We also implement and evaluate PBF on a Xeon Phi processor. Results show that the memory access performance is three times better than that of the counting bloom filter. PBF provides improved scalability, and the speedup ratio can reach a maximum of 80.7x. © Springer International Publishing Switzerland 2015.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Secure cryptographic functions via virtualization-based outsourced computing

Secure cryptographic functions via virtualization-based outs...

引用

作者： Qiang, Weizhong Zhang, Kang Dai, Weiqi Jin, Hai Services Computing Technology and System Lab and Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Cryptographic functions, such as encryption/decryption libraries, are common and important tools for applications to enhance confidentiality of the data. However, these functions could be compromised by subtle attacks launched by untrusted operating system or other applications, and sensitive keys or cryptographic procedures could then be compromised. In this paper, based on virtualization technology, we propose a novel approach that outsources the cryptographic functions in one virtual machine (VM) into another dedicated VM, so that sensitive keys and the cryptographic procedures are only contained by this VM with specific purpose. We also propose a prototype, called cryptographic function assurance (CFA), to enhance the security of cryptographic functions. Taking OpenSSL as an example, CFA allows those applications that use OpenSSL library to transparently utilize CFA to protect the cryptographic functions. We present the detailed implementation, as well as the security analysis of CFA. We also give the performance evaluation for OpenSSL's interfaces and Apache httpd, to show the overhead caused by the integration of CFA. Copyright © 2015 John Wiley & Sons, Ltd. Copyright © 2015 John Wiley & Sons, Ltd.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

Runtime-aware adaptive scheduling in stream processing

Runtime-aware adaptive scheduling in stream processing

引用

作者： Liu, Yuan Shi, Xuanhua Jin, Hai Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Long-running stream applications usually share the same fundamental computational infrastructure. To improve the efficiency of data processing in stream processing systems, a data analysis operator could be partitioned into n parallel tasks. The partitioned tasks are usually deployed on m nodes coexisting with other application operators. Because the node performance can vary in unpredictable ways (i.e., (1) stream input rates may fluctuate and (2) computational resource availability varies as other applications are affected), the nodes have different processing steps, and the slow node determines the operator performance. Hence, the tasks should be redistributed at runtime for stream applications to meet their strict latency requirements. Our key idea is to redistribute the tasks to the best node dynamically adaptive to resource or load fluctuations. In this paper, we present a runtime-aware adaptive schedule mechanism that aims at minimizing the operator processing latency and minimizing the latency difference between different nodes' tasks. We propose a new abstraction called performance cost ratio (PCR) that evaluates the node performance. The higher the node's PCR is, the less cost the node will pay for processing one tuple, and the more tasks should be deployed on it. In a scheduling, we first sort tasks descendingly by their loads and sort nodes by their PCR. Then we reassign the amount of computation according to the node's PCR to keep the node's PCR and its input rate the same or in similar proportion in all PCRs. The PCR-based quantitative algorithm applies itself to make tasks loads quantized to the processing capacity of nodes, move the minimum amount of operator's tasks, and keep the tasks local at the same time. We have implemented a runtime-aware adaptive scheduler as an extension to Storm and evaluated this strategy. We achieve the optimization goal using less computational resources. Copyright © 2015 John Wiley & Sons, Ltd. Copyright © 2015 John Wil

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：