检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks, IJCNN 2015

作者： Li, Teng Dou, Yong Jiang, Jingfei Wang, Yueqing Lv, Qi National Laboratory for Parallel and Distributed Processing National University of Defense and Technology Changsha China

ISBN: (纸本)9781479919604

A deep belief network (DBN) is an important branch of deep learning models and has been successfully applied in many machine learning and pattern recognition fields such as computer vision and speech recognition. However, the training of billions of parameters in DBN is computationally challenging for modern central processing units (CPUs). Many studies have reported the efficient implementations of the pre-training process of DBNs for graphics processing units (GPUs), but few studies have mentioned the fine-tuning process of DBNs. In this paper, we describe an efficient DBN implementation on the GPU, including the pre-training and fine-tuning processes. Experimental results show that our proposed method on the GPU (NVIDIA Tesla K40c) achieves up to 22 speedups on the pre-training process and 33 speedups on the fine-tuning processes compared with conventional CPU (Intel Core i7-4790K) implementations. Moreover, the performance of our algorithm is superior to that of the OpenBLAS library on the CPU and the CUBLAS library on the GPU. © 2015 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Mapping OpenMP concepts to the stream programming model

Mapping OpenMP concepts to the stream programming model

引用

International Conference on Computer Science and Education

作者： Tang, Tao Lin, Yisong Ren, Xiaoguang National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (纸本)9781424460052

OpenMP is a widely used parallel programming model on traditional multi-core processors. Generally, OpenMP is used to develop fine-grained parallelism through a multithread model. Stream programming model is a new kind of parallel programming model for stream architectures. OpenMP bears a resemblance to the stream programming model at some level. The transformation between the two models has attracted much attention from the research community, since it is the foundation of porting programs between the two architectures. Most related researches focus on the efficiency of porting existing parallel programs to the new architectures such as GPUs. Very few of these studies, however, focus on the portative problem systematically, namely, what kind of parallel programs can be or should be transplanted into stream programs and mapped to run on the stream processors. In this paper, we study the mapping relationship of parallel mechanism in OpenMP to the stream programming model, and point out those parallel mechanisms in OpenMP that are infeasible or undesirable for stream programs. By analyzing two typical benchmarks, we draw the conclusion that a majority of scientific applications are suitable to be mapped to the stream programming model. Our conclusion effectively validates the idea of accelerating scientific applications with the stream processors. ©2010 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Data parallelism exploiting for H.264 encoder

Data parallelism exploiting for H.264 encoder

引用

International Conference on Multimedia and Signal processing

作者： Wen, Mei Ren, Ju Wu, Nan Su, Huayou Xun, Changqing Zhang, Chunyuan Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha China

ISBN: (纸本)9780769543567

Real-time H.264 encoding of high-definition (HD) video (up to 1080p) is a challenge workload to most existing programmable processors. Instead, the novel programmable parallel processors such as stream processor, Graphic processor unit (GPU) and DSP offer a different and very promising technology for these demands. Thus, parallel computing for H.264 encoding on these processors is becoming a hot research point. It's challenged, because most emerging parallel processors focus on supporting Data Level parallel (DLP), while the dependency inherently existing in traditional H.264 encoding algorithm significantly restricts exploiting DLP. Facing the challenge, this paper presents data parallel processing methods for key modules of H.264 encoder which can eliminate the dependency restriction. The result shows that key modules including Intra-prediction, Inter-prediction and CAVLC achieve significant speedup on stream processor by using these data parallel processing methods.© 2011 IEEE.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

DDPER: DECENTRALIZED distributed PRIORITIZED EXPERIENCE REPLAY

DDPER: DECENTRALIZED DISTRIBUTED PRIORITIZED EXPERIENCE REPL...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Liu, Sidun Qiao, Peng Dou, Yong Li, Rongchun National Laboratory for Parallel and Distributed Processing National University of Defense Technology Hunan China

ISBN: (纸本)9781665438643

In off-policy reinforcement learning, prioritized experience replay plays an important role. However, the centralized prioritized experience replay becomes the bottleneck for efficient training. We propose to approximate the centralized prioritized experience replay in a distributed and decentralized way under certain mild assumptions. To be specific, each actor stores samples in its local replay in the same way as prioritized experience replay, the learner fetches a batch of samples from these replays following a certain strategy. We implement a Deep Q-Learning off-policy algorithm upon the proposed framework. The comparison experiments are performed on a commonly used subset of the Atari-57 learning environment. The experimental results show that the proposed framework speeds up training as the number of actors increases. With the same algorithm and hyper-parameter settings, the proposed framework with 16 actors achieves superior performance that Ape-X with 32 and even more actors does. © 2021 IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Exploiting attribute redundancy in extracting open source forge websites

Exploiting attribute redundancy in extracting open source fo...

引用

4th International Conference on Cyber-Enabled distributed Computing and Knowledge Discovery, CyberC 2012

作者： Li, Xiang Zhu, Yanxu Yin, Gang Wang, Tao Wang, Huaimin National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (纸本)9780769548104

Open Source Forge (OSF) websites provide information on massive open source software projects, extracting these web data is important for open source research. Traditional extraction methods use string matching among pages to detect page template, which is time-consuming. A recent work published in VLDB exploits redundant entities among websites to detect web page coordinates of these entities. The experiment gives good results when these coordinates are used for extracting other entities of the target site. However, OSF websites have few redundant project entities. This paper proposes a modified version of that redundancy-based method tailored for OSF websites, which relies on a similar yet weaker presumption that entity attributes are redundant rather than whole entities. Like the previous work, we also construct a seed database to detect web page coordinates of the redundancies, but all at the attribute-level. In addition, we apply attribute name verification to reduce false positives during extraction. The experiment result indicates that our approach is competent in extracting OSF websites, in which scenario the previous method can not be applied. © 2012 IEEE.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Enhanced streamline texture synthesis for vector field visualization 4

Enhanced streamline texture synthesis for vector field visua...

引用

4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000

作者： Zhang, Wen Li, Xiaomei National Laboratory of Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (纸本)0769505902

The Streamline Texture Synthesis (STS) method uses a different 1D texture to texture map each streamline and streamline textures are synthesized. The Enhanced STS (ESTS) adjusts the width of a streamline based on the critical point and maps several 1D textures to a streamline in order to accelerate computing. ESTS can also simulate animations and visualize 2D unsteady or 3D surface flows. The analyzed result proves that ESTS produces substantially better visual results and ESTS is fast enough to visualize vector field interactively. © 2000 IEEE.

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

An Efficient Identity-Based Key Agreement Protocol in a Multiple PKG Environment

引用

Wuhan University Journal of Natural Sciences 2014年第5期19卷 455-460页

作者： ZHOU Huan WANG Xiaofeng SU Jinshu School of Computer National University of Defense Technology National Laboratory for Parallel and Distributed Processing National University of Defense Technology

Identity-based key agreement protocol affords a natural way to combine the participant＇s identity with its public key. However, most of them just consider the key agreement in a single private key generator （PKG） environment. In addition, the existing key agreement protocols have a great computing overhead for mobile computing which is more and more popular today. This paper proposes a new identity based key agreement protocol. With the help of mathematical tools, we make our protocol applied in multiple PKG environment. It also satisfies all the security properties which is set for key agreement protocol. Moreover, some of its time-consuming operations can be delivered to untrusted public computation resources, so its computing complexity can be greatly reduced.

关键词： key agreement identity based public computation multiple PKG environment

来源：评论

学校读者我要写书评

暂无评论

PIBUS: A network memory-based peer-to-peer IO buffering service

引用

6th International IFIP-TC6 Networking Conference, NETWORKING 2007

作者： Zhang, Yiming Li, Dongsheng Chu, Rui Xiao, Nong Lu, Xicheng National Laboratory for Parallel and Distributed Processing NUDT Changsha Hunan410073 China

ISBN: (纸本)9783540726050

This paper proposes a network memory-based P2P IO BUffering Service (PIBUS), which buffers blocks for IO-intensive applications in P2P network memory like a 2-level disk cache. PIBUS reduces the IO overhead when local cache is missed due to speed advantage of network memory over disks, and improves hit ratio based on accurate classification of IO behaviors. © IFIP International Federation for Information processing 2007.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Iaso： an autonomous fault-tolerant management system for supercomputers

引用

Frontiers of Computer Science 2014年第3期8卷 378-390页

作者： Kai LU Xiaoping WANG Gen LI Ruibo WANG Wanqing CHI Yongpeng LIU Hongwei TANG Hua FENG Yinghui GAO Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha 410073 China College of Computer National University of Defense Technology Changsha 410073 China ATR Laboratory National University of Defense Technology Changsha 410073 China

With the increase of system scale, the inherent reliability of supercomputers becomes lower and lower. The cost of fault handling and task recovery increases so rapidly that the reliability issue will soon harm the usability of supercomputers. This issue is referred to as the ＂reliability wall＂, which is regarded as a critical problem for current and future supercomputers. To address this problem, we propose an autonomous fault-tolerant system, named Iaso, in MilkyWay- 2 system. Iaso introduces the concept of autonomous management in supercomputers. By autonomous management, the computer itself, rather than manpower, takes charge of the fault management work. Iaso automatically manage the whole lifecycle of faults, including fault detection, fault diagnosis, fault isolation, and task recovery. Iaso endows the autonomous features with MilkyWay-2 system, such as self-awareness, self-diagnosis, self-healing, and self-protection. With the help of Iaso, the cost of fault handling in supercomputers reduces from several hours to a few seconds. Iaso greatly improves the usability and reliability of MilkyWay-2 system.

关键词： supercomputer autonomous management fault tolerant fault management MilkyWay-2 system

来源：评论

学校读者我要写书评

暂无评论

Investigating social media in GitHub's pull-requests: A case study on ruby on rails 1

Investigating social media in GitHub's pull-requests: A case...

引用

1st International Workshop on Crowd-Based Software Development Methods and Technologies, CrowdSoft 2014

作者： Zhang, Yang Yin, Gang Yu, Yue Wang, Huaimin National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha410073 China

ISBN: (纸本)9781450332248

In GitHub, pull-request mechanism is an outstanding social development method by integrating with many social media. Many studies have explored that social media has an important effect on software development. @-mention as a typical social media, is a useful tool in social platform. In this paper, we made a quantitative analysis of @-mention in pull-requests of the project Ruby on Rails. First, we make a convictive statistics of the popularity of pull-request mechanism in GitHub. Then we investigate the current situation of @-mention in the Ruby on Rails. Our empirical analysis results find some insights of @-mention. Copyright 2014 ACM.

关键词： Software design

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：