检索结果-内蒙古大学图书馆

8th International Conference on Computer and Communication Systems, ICCCS 2023

作者： Li, Runhua Liu, Jie National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory Changsha China

ISBN: (纸本)9781665456128

Innovations in powerful high-performance computing (HPC) architecture are enabling high-fidelity whole-core neutron transport simulations at reasonable time. Especially, the currently fashionable heterogeneous architectures make the cost of such simulations at very low level. Neutron distribution of a reactor core is governed by the Boltzmann neutron transport equation (BTE), first viable solutions of which need tremendous computer resources. Among of the high-fidelity numerical methods, the discrete ordinates method (SN) is becoming popular in the reaction design community by taking a good balance between computational cost and accuracy. Recently, MT-3000, which is a multizone heterogeneous architecture with a peak double precision performance of 11.6 TFLOPS, is proposed. In this work, the BTE is solved by the SN with heterogenous Koch-Baker-Alcouffe (KBA) parallel algorithms based on the MT-3000 architecture. A communication mechanism has been established to efficiently transmit data among the acceleration cores and the CPU cores. The kernel computation procedure is largely accelerated by the vectorization and instruction pipelining techniques. Numerical experiments show that our formulation could achieve 1.37 TFLOPs with single MT-3000, that is 11.8% of its peak performance. © 2023 IEEE.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

DIPP—An LLC replacement policy for on-chip dynamic heterogeneous multi-core architecture

DIPP—An LLC replacement policy for on-chip dynamic heteroge...

引用

International Conference of Young Computer Scientists, Engineers and Educators, ICYCSEE 2015

作者： Yang, Zhang Zuocheng, Xing Xiao, Ma Science and technology on Parallel and distributed processing laboratory National University of Defense Technology ChangSha China

ISBN: (纸本)9783662462478

As the big data era is coming, it brings new challenges to the massive data processing. A combination of GPU and CPU on chip is the trend to release the pressure of large scale computing. We found that there are different memory access characteristics between GPU and CPU. The most important one is that the programs of GPU include a large number of threads, which lead to higher access frequency in cache than the CPU programs. Although the LRU policy favors the programs with high memory access frequency, the programs of GPU can’t get the corresponding performance boost even more cache resources are provided. So LRU policy is not suitable for heterogeneous multi-core processor. Based on the different characteristics of GPU and CPU programs on memory access, this paper proposes an LLC dynamic replacement policy--DIPP (Dynamic Insertion/ Promotion Policy) for heterogeneous multi-core processors. The core idea of the replacement policy is to reduce the miss rate of the program and enhance the overall system performance by limiting the cache resources that GPU can acquire and reducing the thread interferences between programs. Experiments compare the DIPP replacement policy with LRU and we conduct a classified discussion according to the program results of GPU. Friendly programs enhance 23.29% on the average performance (using arithmetic mean). Large working sets programs can improve 13.95%, compute-intensive programs enhance 9.66% and stream class programs improve 3.8%. © Springer-Verlag Berlin Heidelberg 2015.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Optimizing the efficiency and openness of the Kubernetes based code evaluation platform 8

Optimizing the efficiency and openness of the Kubernetes bas...

引用

2018 8th International Workshop on Computer Science and Engineering, WCSE 2018

作者： Zhang, Zhixiong Yin, Gang Wang, Tao Wang, Wei National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha410073 China

ISBN: (纸本)9789811178610

With the popularity of programming learning, there are more and more online programming platforms and learners can learn programming skills online. That's good news for users who was bothered by configuring a development environment or some other annoying little things. We have built a multi-purpose code evaluation platform which provides many different kinds of coding training courses. This code evaluation platform is based on Kubernetes and provides unique containers for every submission of users' code so that it's not a problem that many different types of code are running at the same time. Furthermore, it allows experts share their programming skills or other computer technical abilities by creating training courses on the platform, and they can even customize the evaluation methods and the evaluation process of their own training courses by producing new evaluation script. To obtain better user experience for both learners and training contributors, some useful auxiliary systems, such as the evaluating queuing system and the script management system have been introduced. © Proceedings of 2018 the 8th International Workshop on Computer Science and Engineering, WCSE 2018. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Transfer learning for deep neural network-based partial differential equations solving

引用

Advances in Aerodynamics 2021年第1期3卷 635-648页

作者： Xinhai Chen Chunye Gong Qian Wan Liang Deng Yunbo Wan Yang Liu Bo Chen Jie Liu Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangshaChina China Aerodynamics Research and Development Center MianyangChina.

Deep neural networks(DNNs)have recently shown great potential in solving partial differential equations(PDEs).The success of neural network-based surrogate models is attributed to their ability to learn a rich set of solution-related ***,learning DNNs usually involves tedious training iterations to converge and requires a very large number of training data,which hinders the application of these models to complex physical *** address this problem,we propose to apply the transfer learning approach to DNN-based PDE solving *** our work,we create pairs of transfer experiments on Helmholtz and Navier-Stokes equations by constructing subtasks with different source terms and Reynolds *** also conduct a series of experiments to investigate the degree of generality of the features between different *** results demonstrate that despite differences in underlying PDE systems,the transfer methodology can lead to a significant improvement in the accuracy of the predicted solutions and achieve a maximum performance boost of 97.3%on widely used surrogate models.

关键词： Deep neural network Partial differential equation Surrogate model Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Runtime monitoring for cyber-physical systems: A case study of cooperative adaptive cruise control

Runtime monitoring for cyber-physical systems: A case study ...

引用

2nd International Conference on Intelligent Systems Design and Engineering Applications, ISDEA 2012

作者： Mao, Jianhui Chen, Liqian National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China

ISBN: (纸本)9780769546087

Cyber-Physical Systems (CPS) involve deep interactions between computation cores, communication networks, and physical environments. These systems are inherently complex and highly nondeterministic. This makes the traditional formal verification technology impractical to verify the complete system behavior, and testing alone is insufficient to guarantee correctness. Runtime monitoring, known as a lightweight verification technique, provides a practical way to monitor and verify such systems at runtime. In this paper, we present a case study for runtime monitoring of the Cooperative Adaptive Cruise Control systems (CACC) in automobile CPS systems. We build a hybrid automaton-based model for the CACC system using the CHARON modeling language and construct an event-based runtime monitoring framework. The synthesized monitor observes the running of CACC and checks whether it works correctly against the temporal logic safety specification. Experimental results obtained through this case study provide evidence for the efficacy of runtime monitoring of CPS systems. © 2012 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

A peer-to-peer media streaming system based on the iVCE platform

A peer-to-peer media streaming system based on the iVCE plat...

引用

15th International Conference on parallel and distributed Systems, ICPADS '09

作者： Wu, Jiqing Peng, Yuxing Shen, Rui National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China

ISBN: (纸本)9780769539003

With the advancement of peer-to-peer technology, media streaming applications become more and more popular in the Internet. However, the traditional development methods for this kind of applications need developers not only to consider the application logic but also to manage the dynamics of Internet resources, thus increasing the difficulty of development and limiting the deployment of personal video distribution applications. In this paper, we design and implement a peer-to-peer streaming system in a much easier way. In this way we can concentrate on the application itself without distraction from the dynamics of Internet resources. Such simplification owes to the Internet-based Virtual Computing Environment (iVCE), which provides programming abstractions and runtime utilities that can encapsulate the complexity of managing transient resources into the platform, thus facilitating the construction of Internet applications. When we build our streaming application based on the iVCE, we only need to define the interaction protocols among distributed nodes with the Owlet programming language. Also, we implement a JavaBean, which can be used by the Owlet program, to assist the transfering and rendering of the content. Our implementation shows that peer-to-peer applications such as media streaming, can be elegantly built using the iVCE platform, and it can serve as a reference implementation for developing similar applications. © 2009 IEEE.

关键词： Media streaming

来源：评论

学校读者我要写书评

暂无评论

Dynamic program Behavior Identification for high performance CMPs with private LLCs

Dynamic program Behavior Identification for high performance...

引用

作者： Jia, Xiaomin Lu, Pingjing Sun, Caixia Zhang, Minxuan National Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology China

Chip Multi-Processors (CMPs) emerge as a mainstream architectural design alternative for high performance parallel and distributed computing. Last Level Cache (LLC) management is critical to CMPs because off-chip accesses often require a long latency. Due to its short access latency, well performance isolation and easy scalability, private cache is an attractive design alternative for LLC of CMPs. This paper proposes program Behavior Identification-based Cache Sharing (BICS) for LLC management. BICS is based on a private cache organization for the shorter access latency. Meanwhile, BICS tries to simulate a shared cache organization by allowing evicted blocks of one private LLC to be saved at peer LLCs. This technique is called spilling. BICS identifies cache behavior types of applications at runtime. When a cache block is evicted from a private LLC, cache behavior characteristics of the local application are evaluated so as to determine whether the block is to be spilled. Spilled blocks are allowed to replace some valid blocks of the peer LLCs as long as the interference is within a reasonable level. Experimental results using a full system CMP simulator show that BICS improves the overall throughput by as much as 14.5%, 12.6%, 11.0% and 11.7% (on average 8.8%, 4.8%, 4.0% and 6.8%) over private cache, shared cache, Utility-based Cache Partitioning (UCP) scheme and the baseline spilling-based organization Cooperative Caching (CC) respectively on a 4-core CMP for SPEC CPU2006 benchmarks. Copyright© 2010.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

A Novel Interactive Recurrent Attention Network for Emotion-Cause Pair Extraction 3

A Novel Interactive Recurrent Attention Network for Emotion-...

引用

3rd International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2020

作者： Jia, Xiangyu Chen, Xinhai Wan, Qian Liu, Jie Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha China

ISBN: (纸本)9781450388115

Unlike Emotion Cause Extraction (ECE) task which consists of pre-annotate emotions and passage, emotion-cause pair extraction (ECPE) aims at extracting potential emotions and corresponding causes in the document without the need for pre-annotations. Traditional ECPE solutions divide the extracting emotions and causes operation into two separate parts. However, separating the bidirectional dependence between emotion and cause may lose a lot of potentially useful information. In this paper, we propose a novel interactive recurrent attention network (IRAN). Our approach focuses on the bidirectional impact between emotions and causes, and extracts emotions and causes simultaneously. The information in the document can be fully exploited through multiple modeling and information extraction. Our emotion-specific transformation and distance fusion correlation can adaptively focus on the emotions and the distance, gracefully incorporate them into a distinguishable neural network attention framework. The experimental results show that our proposed model achieves better performance than other widely-used models on the ECPE corpus. © 2020 ACM.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A scalable architecture for supporting interactive games on the internet 16

A scalable architecture for supporting interactive games on ...

引用

16th Workshop on parallel and distributed Simulation, PADS 2002

作者： Cai, Wentong Xavier, P. Turner, S.J. Lee, Bu-Sung Parallel and Distributed Processing Laboratory School of Computer Engineering Nanyang Technological University Singapore Singapore

ISBN: (纸本)0769516084

This paper presents a scalable architecture for supporting large-scale interactive Internet games. In order to support a large number of participants and to divide the workload, the virtual world is divided into partitions. Each partition is then assigned to a server. A client (i.e., a player or a participant) will join a server according to the position of the avatar it controls. Compared to a centralized architecture, this distributed client-server architecture is more scalable. In addition, compared to a fully distributed, peer-to-peer architecture, it also provides a means for detecting cheating in distributed games. Since interactions and accounting information must be forwarded directly to one of the servers for qualification and verification, cheating amongst distributed players of the game will be minimized. To support secured communication for interactions and accounting information as well as to speedup periodic update messages (e.g., position updates), a hybrid communication scheme using both TCP and IP multicast is used between clients and the associated server. The communication among servers is enabled by the Run-Time Infrastructure (RTI) services. The High Level Architecture (HLA) Data Distribution Management (DDM) is employed to limit the amount of communication between the servers. In addition, the Ownership Management (OM) is also employed to implement the need for transferring the avatars between servers. In this paper, the design detail of the architecture will be presented. An experimental interactive Internet game realized using the architecture will be also described in the paper. © 2002 IEEE.

关键词： distributed Client-Server Architecture High Level Architecture (HLA) Large-scale Interactiv eGames Ownership and Data Distribution Management Run-Time Infrastructure (RTI) Scalability

来源：评论

学校读者我要写书评

暂无评论

Adaptive Linearized Alternating Direction Method of Multipliers for Non-Convex Compositely Regularized Optimization Problems

引用

Tsinghua Science and Technology 2017年第3期22卷 328-341页

作者： Linbo Qiao Bofeng Zhang Xicheng Lu Jinshu Su College of Computer National University of Defense Technologyand National Laboratory for Parallel and Distributed ProcessingNational University of Defense TechnologyChangsha 410073China College of Computer National University of Defense TechnologyChangsha 410073China

We consider a wide range of non-convex regularized minimization problems, where the non-convex regularization term is composite with a linear function engaged in sparse learning. Recent theoretical investigations have demonstrated their superiority over their convex counterparts. The computational challenge lies in the fact that the proximal mapping associated with non-convex regularization is not easily obtained due to the imposed linear composition. Fortunately, the problem structure allows one to introduce an auxiliary variable and reformulate it as an optimization problem with linear constraints, which can be solved using the Linearized Alternating Direction Method of Multipliers （LADMM）. Despite the success of LADMM in practice, it remains unknown whether LADMM is convergent in solving such non-convex compositely regularized optimizations. In this research, we first present a detailed convergence analysis of the LADMM algorithm for solving a non-convex compositely regularized optimization problem with a large class of non-convex penalties. Furthermore, we propose an Adaptive LADMM （AdaLADMM） algorithm with a line-search criterion. Experimental results on different genres of datasets validate the efficacy of the proposed algorithm.

关键词： adaptive linearized alternating direction method of multipliers non-convex compositely regularizedoptimization cappled-ll regularized logistic regression

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：