检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Lin Chen Kang He Hao Jiang Roberto Barrio Jie Liu Tiejun Li Science and Technology on Parallel and Distributed Processing Laboratory Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China College of Computer Science and Technology National University of Defense Technology Changsha China University of Zaragoza Zaragoza Spain

Quantization is an effective method for compressing Deep Neural Networks. Now, it is considered to accelerate the traditional HPC applications. In this article, we present a quantization method (q8gemm) using integer 8-bits(INT8) for matrix multiplication, which is implemented by block techniques to overcome the overflow problem. We choose different scales for one matrix’s each row and those for the other matrix’s each column to keep the numbers in range. With the intel advanced matrix extension cblas_gemm_s8u8s32, our q8gemm can accelerate panel-matrix multiplication in LU factorization. Furthermore, we propose a new mixed-precision solver (q8gesv 1 ) for the linear equations. Using q8gemm in INT8, q8gesv modifies LU factorization in FP32 and then utilizes GMRES iterative refinement in FP64 to bring the solution back to 64 bits accuracy. Numerical tests show that on two Intel CPU platforms with avx2 and avx512, q8gemm achieves a speedup of 1.313-1.621 over cblas_sgemm of MKL. The execution time of cblas_gemm_s8u8s32 makes up 86.78%-90.85% of the q8gemm. By means of q8gemm, our q8gesv can achieve a speedup of 1.176-1.493 over the optimized Higham’s mixed-precision algorithm utilized in the HPL-AI benchmark and a speedup of 1.1-1.459 over the LAPACKE_dsgesv function from MKL LAPACK. Meanwhile, q8gesv runs up to 2.859X faster on Intel(R) Core(TM) i5-10600KF and to 2.224X faster on Intel(R) Xeon(R) Gold 6130 than the LAPACKE_dgesv function from MKL LAPACK.

关键词： Deep learning Gold Quantization (signal) Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Memory Access Analysis of Many-core System with Abundant Bandwidth

Memory Access Analysis of Many-core System with Abundant Ban...

引用

IEEE International Symposium on Embedded Multicore Socs (MCSoC)

作者： Chuan Tang Dan Liu Zuocheng Xing Peng Yang Zhe Wang Jiang Xu Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong China

ISBN: (纸本)9781479986712

Many-core system is main architecture trend currently. One of the dominating challenges for on-chip manycore system is the memory wall. However traditional research primarily focus on the limited bandwidth. To solve this problem, many-core system is aided with large cache, and a lot of complex approaches about memory and cache are adopted aiming at relaxing the pressure of bandwidth and improving the efficiency of cache. All these methods generate much cost of area and power. In this paper, we are motivated by the feature of abundant bandwidth and low latency of optical interconnect. We analyze the characteristics of memory access on 64 cores system under the case of high bandwidth which can be assumed to benefit from optical interconnect, considering the sensibility with bandwidth and cache for different benchmarks. Finally, we discuss about promising basic frameworks suitable for manycore system with optical interconnect.

关键词： Bandwidth Benchmark testing Optical interconnections Random access memory Delays Hidden Markov models Computers

来源：评论

学校读者我要写书评

暂无评论

An Irregular cutting based distributed mapping algorithm for DVE systems

An Irregular cutting based distributed mapping algorithm for...

引用

Pacific-Asia Workshop on Computational Intelligence and Industrial Application, PACIIA

作者： Wei Zhang Hangjun Zhou Yuxing Peng Sikun Li Min Xi National Laboratory of Parallel and Distributed Processing School of Computer Science National University of Defense Technology Changsha China Department of Computer Science Xi'an Jiaotong University Xi'an China

distributed Virtual Environment (DVE) systems have become more and more important both in academic communities and the industries. To guarantee the load constrain, the physical world integrity and the virtual world integrity, the virtual environment should be divided into several parts and mapped to multiple servers, which are located in geographically different places. Many centralized algorithms based on regular cutting method are proposed to solve this problem. However, the dynamic property of clients and distributed property of the system make the existing algorithms unable to undertake it. In this paper, we propose a metric to measure the cutting quality and design a distributed mapping algorithm based on an irregular cutting. Simulation results show that our algorithm greatly decreases the costs of DVE systems for migration of clients and effectively improves the satisfaction degree of users.

关键词： Defense industry Virtual environment Computer industry Computer science Algorithm design and analysis Delay Partitioning algorithms Industrial training Computational intelligence Application software

来源：评论

学校读者我要写书评

暂无评论

Blocking LU Decomposition for FPGAs

Blocking LU Decomposition for FPGAs

引用

Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM)

作者： Guiming Wu Yong Dou Gregory D. Peterson National Laboratory for Parallel & Distributed Processing National University of Defense Technology Changsha China Electrical Engineering and Computer Science University of Tennessee Knoxville TN USA

To efficiently perform large matrix LU decomposition on FPGAs with limited local memory, the original algorithm needs to be blocked. In this paper, we propose a block LU decomposition algorithm for FPGAs, which is applicable for matrices of arbitrary size. We introduce a high performance hardware design, which mainly consists of a linear array of processing elements (PEs), to implement our block LU decomposition algorithm. A total of 36 PEs can be integrated into a Xilinx Virtex-5 xc5vlx330 FPGA on our self-designed PCI-Express card, reaching a sustained performance of 8.50 GFLOPS at 133 MHz, which outperforms previous work.

关键词： Field programmable gate arrays Matrix decomposition Hardware Power engineering computing Algorithm design and analysis Linear algebra Computer applications Concurrent computing distributed computing Laboratories

来源：评论

学校读者我要写书评

暂无评论

Optimizing Reference Gene Set for Inter-Chip Normalization Using Genetic Algorithm

Optimizing Reference Gene Set for Inter-Chip Normalization U...

引用

International Conference on BioMedical Engineering and Informatics (BMEI)

作者： Fei Li Wenjian Xu Peng Li XiaoChen Bo Yuxing Peng Department of Computer Science National Laboratory of Parallel & Distributed Processing National University of Defense Technology Changsha China Beijing Institute of Radiation Medicine Beijing China

Due to the existence of systematic bias in the measurements, inter-chip normalization is required before integrated data analysis of multiple microarray datasets. Current inter-chip normalization methods rely on some assumptions, which can rarely be verified by experiments, such as the invariant expression level of housekeeping genes or the stability of statistical data distribution. In this paper, we present a highly verifiable inter-chip normalization method using genetic optimization algorithm, which depends only on a small number of housekeeping genes, and therefore facilitates experimental validation without any accuracy lost.

关键词： Genetic algorithms Gene expression Laboratories Data analysis Optimization methods Genomics Bioinformatics Statistical distributions Probes Computer science

来源：评论

学校读者我要写书评

暂无评论

HybridSwap: A scalable and synthetic framework for guest swapping on virtualization platform

HybridSwap: A scalable and synthetic framework for guest swa...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Pengfei Zhang Xi Li Rui Chu Huaimin Wang National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China School of Information Science and Engineering Central South University Changsha China

In IaaS cloud environments, peak memory demand caused by hotspot applications in Virtual Machine (VM) often results in performance degradation within and outside of this VM. Some solutions such as host swapping and ballooning for memory consolidation and overcommitment have been proposed. These solutions, however, have no help for addressing guest swapping issues inside VM. Even though host holds sufficient memory pages, guest OS is unable to utilize free pages in host directly due to the semantic gap between VMM and it. Our goal is to alleviate the performance degradation by decreasing disk I/O operations generated by guest swapping. Based on the insight analysis of behavioral features of guest swapping, we design HybridSwap, a distributed scalable framework which organize surplus memory in all hosts within data center into virtual pools for swapping. This framework builds up a synthetic swapping mechanism in a peer-to-peer way, which VM can adaptively choose suitable pools for swapping. We implement the prototype of HybridSwap and evaluate it with different benchmarks. The results demonstrate that our solution has the ability to promote the guest swapping efficiency indeed. Even in some cases, it shows 2-5 times of performance promotion compared with the baseline setup.

关键词： Benchmark testing Virtualization Semantics Servers Operating systems Degradation Instruction sets

来源：评论

学校读者我要写书评

暂无评论

Enhancing Temporal Alignment with Autoencoder Regularization

Enhancing Temporal Alignment with Autoencoder Regularization

引用

International Joint Conference on Neural Networks

作者： Liquan Nie Yuanyuan Wang Xiang Zhang Xuhui Huang Zhigang Luo Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Department of Basic Courses Army Officer Academy Department of Computer Science and Technology College of Computer National University of Defense Technology

ISBN: (纸本)9781509006212

Temporal alignment aligns two temporal sequences and is quite challenging due to drastic differences among temporal sequences and source data from different views. Canonical time warping (CTW) has shown great potential in temporal alignment tasks because it can reduce data redundancy by transforming high-dimensional data to a lower-dimensional subspace via canonical correlation analysis (CCA). However, CTW cannot uncover the underlying nonlinear structure embedded in the dataset. In this paper, we propose an autoencoder regularized canonical time warping method (AECTW) to overcome this drawback. Specifically, AECTW enhances lower-dimensional representation of each sequence by incorporating an autoencoder regularization, meanwhile reveals the nonlinear structure of features by explicit nonlinear transformation. By these strategies, AECTW significantly boosts CTW in temporal alignment tasks. Experiments on both synthetic data and two practical human action datasets demonstrate that AECTW outperforms the representative DTW-based methods.

关键词： NONLINEAR STRUCTURES data redundancy Dataset synthetic data Alignment Warping Structural properties Canonical Religious Missions Data sources

来源：评论

学校读者我要写书评

暂无评论

Translation Non-negative Matrix Factorization with Fast Optimization

Translation Non-negative Matrix Factorization with Fast Opti...

引用

IEEE International Conference on Systems, Man, and Cybernetics

作者： Yuanyuan Wang Naiyang Guan Bin Mao Xuhui Huang Zhigang Luo Department of Basic Courses Army Officer Academy Science and Technology on Parallel and Distributed Processing Laboratory College of Computer Science National University of Defense Technology College of Science National University of Defense Technology College of Computer Science National University of Defense Technology

ISBN: (纸本)9781479938414

Non-negative matrix factorization (NMF) reconstructs the original samples in a lower dimensional space and has been widely used in pattern recognition and data mining because it usually yields sparse representation. Since NMF leads to unsatisfactory reconstruction for the datasets that contain translations of large magnitude, it is required to develop translation NMF (TNMF) to first remove the translation and then conduct a decomposition. However, existing multiplicative update rule based algorithm for TNMF is not efficient enough. In this paper, we reformulate TNMF and show that it can be efficiently solved by using the state-of-the-art solvers such as NeNMF. Experimental results on face image datasets confirm both efficiency and effectiveness of the reformulated TNMF.

关键词： Non-negative matrix factorization (NMF) Translation transformation NeNMF

来源：评论

学校读者我要写书评

暂无评论

Maximizing Uniform Multicast Throughput in Multi-Channel Dense Wireless Sensor Networks 12

Maximizing Uniform Multicast Throughput in Multi-Channel Den...

引用

12th International Conference on Mobile Ad-Hoc and Sensor Networks, MSN 2016

作者： Jiao, Xianlong Chen, Guirong Wang, Xiaodong Chen, Yuli Yang, Li Information and Navigation College Air Force Engineering University Xi'an710077 China College of Information System and Management National University of Defense Technology Changsha410073 China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China Chongqing Guanyinqiao Elementary School Chongqing400020 China Chongqing Liangjiangxinqu Renhe Experimental School Chongqing400021 China

ISBN: (纸本)9781509056965

This paper investigates the problem of maximizing uniform multicast throughput (MUMT) for multi-channel dense wireless sensor networks, where all nodes locate within one-hop transmission range and can communicate with each other on multiple orthogonal channels. This kind of networks show wide application in the real world, and maximizing uniform multicast throughput for these networks is worth deep studying. Previous researches have proved MUMT problem is NP-hard. However, previous researches are either hard to implement, or use too many relay nodes to complete the multicast task, and thus incur high overhead or poor performance. To efficiently solve MUMT problem, we adopt the concept of the maximum independent set with the size constraint, and present one novel Single-Broadcast based Multicast algorithm called SBM based on the concept. We prove that SBM algorithm achieves a constant ratio to the theoretical throughput upper bound. Extensive experimental results demonstrate that, SBM performs better than existing work in terms of both the uniform multicast throughput and the total number of transmissions. © 2016 IEEE.

关键词： Throughput

来源：评论

学校读者我要写书评

暂无评论

The dynamic allocation model for the resources of cloud services delivery networks

引用

Jisuanji Xuebao/Chinese Journal of Computers 2011年第12期34卷 2305-2318页

作者： Shi, Pei-Chang Wang, Huai-Min Yin, Gang Liu, Xue-Ning Yuan, Xiao-Qun Shi, Dian-Xi National Laboratory for Parallel and Distributed Processing School of Computer and Science National University of Defense Technology Changsha 410073 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China Department of Electronics and Information Engineering Huazhong Univ. of Sci. and Technol. Wuhan 430074 China

Cloud Services Delivery Networks (CSDN) constructs a layer distributed server overlay over the Internet, which uses the way to the nearest and on-demand approach providing services to end users. Facing the scale and diversification of the resource demand characteristics of the Internet cloud services, CSDN forms different logical sub-server overlay for different kinds of cloud services. However, most servers and bandwidth resources of CSDN are used to deliver the streaming and downloading kind of cloud services, and the dynamic allocation of their delivery resource is the main research emphasis in this paper. This paper first models the problem to be a multi-dimensional facility location problem, according to the two characteristics: the memory resource and bandwidth resource of this kind of application are the bottleneck resource;the hot contents of this kind of application can be delivered using the Peer-to-Peer mechanisms. After the model analyzed and its NP-Complete proved, we then propose a heuristic algorithm. Finally, using the service delivery cost savings as the performance metrics, while the actual system's operation trace is as the input, the effectiveness of the algorithm are comprehensively assessed.

关键词： Heuristic algorithms

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：