检索结果-内蒙古大学图书馆

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Kun Li Liang Yuan Yunquan Zhang Yue Yue Hang Cao State Key Laboratory of Computer Architecture Chinese Academy of Sciences Institute of Computing Technology Beijing School of Computer Science and Technology University of Chinese Academy of Sciences Beijing

Stencil computation is one of the most important kernels in various scientific and engineering applications. A variety of work has focused on vectorization and tiling techniques, aiming at exploiting the in-core data parallelism and data locality respectively. In this paper, the downsides of existing vectorization schemes are analyzed. Briefly, they either incur data alignment conflicts or hurt the data locality when integrated with tiling. Then we propose a novel transpose layout to preserve the data locality for tiling and reduce the data reorganization overhead for vectorization simultaneously. To further improve the data reuse at the register level, a time loop unroll-and-jam strategy is designed to perform multistep stencil computation along the time dimension. Experimental results on the AVX2 and AVX-S12 CPUs show that our approach obtains a competitive performance with the classic vectorization methods (Auto Vectorization and Data Reorganization), state-of-the-art compilers (Pluto and SDSL), and highly-optimized work (DLT and Tessellation).

关键词： Concurrent computing Distributed processing Layout Parallel processing Registers Computational efficiency Kernel

来源：评论

学校读者我要写书评

暂无评论

Dynamic inference in probabilistic graphical models 12

Dynamic inference in probabilistic graphical models

引用

12th Innovations in Theoretical computer Science Conference, ITCS 2021

作者： Feng, Weiming He, Kun Sun, Xiaoming Yin, Yitong State Key Laboratory for Novel Software Technology Nanjing University China Shenzhen University China Shenzhen Institute of Computing Sciences China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783959771771

Probabilistic graphical models, such as Markov random fields (MRFs), are useful for describing high-dimensional distributions in terms of local dependence structures. The probabilistic inference is a fundamental problem related to graphical models, and sampling is a main approach for the problem. In this paper, we study probabilistic inference problems when the graphical model itself is changing dynamically with time. Such dynamic inference problems arise naturally in today’s application, e.g. multivariate time-series data analysis and practical learning procedures. We give a dynamic algorithm for sampling-based probabilistic inferences in MRFs, where each dynamic update can change the underlying graph and all parameters of the MRF simultaneously, as long as the total amount of changes is bounded. More precisely, suppose that the MRF has n variables and polylogarithmic-bounded maximum degree, and N(n) independent samples are sufficient for the inference for a polynomial function N(·). Our algorithm dynamically maintains an answer to the inference problem using Oe(nN(n)) space cost, and Oe(N(n) + n) incremental time cost upon each update to the MRF, as long as the Dobrushin-Shlosman condition is satisfied by the MRFs. This well-known condition has long been used for guaranteeing the efficiency of Markov chain Monte Carlo (MCMC) sampling in the traditional static setting. Compared to the static case, which requires Ω(nN(n)) time cost for redrawing all N(n) samples whenever the MRF changes, our dynamic algorithm gives a Ω(min e {n, N(n)})-factor speedup. Our approach relies on a novel dynamic sampling technique, which transforms local Markov chains (a.k.a. single-site dynamics) to dynamic sampling algorithms, and an "algorithmic Lipschitz" condition that we establish for sampling from graphical models, namely, when the MRF changes by a small difference, samples can be modified to reflect the new distribution, with cost proportional to the difference on MRF. © Weiming F

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient NTT Design with One-bank SRAM and 2-D PE Array

Energy-efficient NTT Design with One-bank SRAM and 2-D PE Ar...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Jianan Mu Huajie Tan Jiawen Wu Haotian Lu Chip-Hong Chang Shuai Chen Shengwen Liang Jing Ye Huawei Li Xiaowei Li State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences CASTEST Tianjin University Nanyang Technological University Rock-Solid Security Lab Fiberhome

In Number Theoretic Transform (NTT) operation, more than half of the active energy consumption stems from memory accesses. Here, we propose a generalized design method to improve the energy efficiency of NTT operation by considering the effect of processing element (PE) geometry and memory organization on the data flow between PEs and memory. To decrease the number of data bits that are required to be accessed from the memory, a two-dimensional (2-D) PE array architecture is used. A pair of ping-pong buffers are proposed to transposed swap the coefficients to enable a single bank of memory to be used with the 2-D PE array to reduce the average memory bit access energy without compromising the throughput. Our experimental results show that this design method can produce NTT accelerators with up to 69.8% saving in average energy consumption compared with the existing designs based on multi-bank SRAM and one-bank SRAM with one-dimensional PE array with the same number of PEs and total memory size.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Many-Objective Evolutionary Algorithm Based on Indicator Selection and Adaptive Angle Estimation

SSRN

引用

SSRN 2024年

作者： Wang, Qian Gu, Qinghua Zhou, Qing Xiong, Neal Naixue Liu, Di School of Management Xi’an University of Architecture and Technology Shaanxi Xi’an China School of Resources Engineering Xi’an University of Architecture and Technology Shaanxi Xi’an China Xi’an Key Laboratory for Intelligent Industrial Perception Calculation and Decision Xi’an University of Architecture and Technology Xi’an710055 China Department of Mathematics and Computer Science Northeastern State University TahlequahOK74464 United States

Currently, real-world complex engineering problems often have more than three objectives that need to be optimized simultaneously. Existing algorithms for solving them mostly rely on the shape of the Pareto front to maintain diversity, which makes it difficult to effectively balance the convergence and diversity of the solutions. To address the above problems, a many-objective evolutionary algorithm based on indicator selection and adaptive angle estimation (MaOEA-ISAE) is proposed in this paper. Firstly, a unit vector metric selection strategy is presented, which uses the favorable physical properties of the metric to identify dominant individuals, thus striking a balance between convergence and diversity. Then, to preserve the diversity of the population, an adaptive angle estimation strategy based on Pareto front curvature prediction is developed. The angular distances of individuals are adaptively measured according to the predicted curvature, thereby selecting individuals with good diversity in the dominant region. Besides, the algorithm has a simple evolutionary process, and no additional parameters are involved. Finally, the proposed MaOEA-ISAE is compared with five other representative many-objective evolutionary algorithms on test instances of 3-20 objectives with different Pareto front shapes. The experimental results show the strong competitiveness of the proposed algorithm on different Pareto front problems. © 2024, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Latency-aware Partial Task Offloading in Collaborative Edge Computing

Latency-aware Partial Task Offloading in Collaborative Edge ...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yingmeng Gao Jie Zhu Haiping Huang Chen Chen Nanjing University of Posts & Telecommunications Nanjing China State Key Laboratory Chinese of Computer Architecture Institute of Computing Technology Academy of Sciences Beijing China Jiangsu High Technology Reasearch Key Laboratory of Wireless Sensor Networks Nanjing China Nanjing University of Aeronautics and Astronautics Nanjing China

When it comes to the fifth generation, collaborative edge computing is preferred for offloading computation-intensive tasks of low-latency applications in Internet of Things. In this paper, we consider the partial task offloading problem where tasks can be divided into subtasks and offloaded to nearby devices. The flow scheduling problem is integrated in the offloading process, i.e., multiple and conflicting route paths are considered. We propose the latency-aware partial task offloading framework (LaPTOF) for the considered problem. LaPTOF integrates a weighted priority ranking strategy (WPRS) which generates multiple solutions with different weights on task arrival time and the task processing time. A feasible solution generation method (FSGM) is designed where the best offloaded proportion of tasks are computed, and the appropriate offloaded devices and offload paths are determined. The proposed LaPTOF has an advantage in providing a scheduling plan that minimizes total completion time of task offloading in a shorter duration. The experimental results show that the proposal is suitable for the considered problem compared with JPOFH and its variants on both effectiveness and efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

TAPEMAN: Towards an Optimal Data Gathering Mechanism in Wireless Sensor Networks

引用

Chinese Journal of Electronics 2023年第4期19卷 594-598页

作者： Yu Gu Yusheng Ji Hongyang Chen Baohua Zhao Department of Computer Science University of Science and Technology of China Hefei China State Key Laboratory of Networking and Switching Technology Beijing China Information Systems Architecture Science Research Division NII Tokyo Japan Institute of Industrial Science University of Tokyo Tokyo Japan

In this paper, we study the lifetime optimization problem using a mobile sink node in a storage-constrained wireless sensor network, and propose an optimal data gathering mechanism named (TAPEMAN) which runs in three steps: first a tight upper bound of the network lifetime is derived through analysis of energy consumption, then we generate a Traveling salesman problem (TSP) solution based on a 2-approximation $O(n^{2})$ algorithm. A judgment will be made about whether this solution is optimal. If the answer is yes, TAPEMAN terminates. If not, a novel data diffusion scheme is used to distribute data to neighboring nodes, in order to avoid data leaking. We prove that under some reasonable assumptions, our algorithm can achieve this upperbound. Simulation results demonstrate the efficiency of our proposed solution and substantiate the importance of using sink mobility for energy-constrained sensor networks.

关键词： Wireless communication Wireless sensor networks Energy consumption Upper bound Simulation Traveling salesman problems Delays

来源：评论

学校读者我要写书评

暂无评论

A Case for Adaptive Resource Management in Alibaba Datacenter Using Neural Networks

引用

Journal of computer Science & Technology 2020年第1期35卷 209-220页

作者： Sa Wang Yan-Hai Zhu Shan-Pei Chen Tian-Ze Wu Wen-Jie Li Xu-Sheng Zhan Hai-Yang Ding Wei-Song Shi Yun-Gang Bao State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190China University of Chinese Academy of Sciences Beijing 100049China Peng Cheng Laboratory Shenzhen 518055China Alibaba Inc. Hangzhou 311121China Department of Computer Science Wayne State UniversityMichiganMI 48202U.S.A

Both resource efficiency and application QoS have been big concerns of datacenter operators for a long time,but remain to be *** resource utilization increases the risk of resource contention between co-located workload,which makes latency-critical(LC)applications suffer unpredictable,and even unacceptable *** of prior work devotes the effort on exploiting effective mechanisms to protect the QoS of LC applications while improving resource *** this paper,we propose MAGI,a resource management runtime that leverages neural networks to monitor and further pinpoint the root cause of performance interference,and adjusts resource shares of corresponding applications to ensure the QoS of LC *** is a practice in Alibaba datacenter to provide on-demand resource adjustment for applications using neural *** experimental results show that MAGI could reduce up to 87.3%performance degradation of LC application when co-located with other antagonist applications.

关键词： resource management neural network resource efficiency tail latency

来源：评论

学校读者我要写书评

暂无评论

Using Mobile Sinks in WSN: Computational Complexity and a Theoretical Bound

引用

Chinese Journal of Electronics 2023年第1期20卷 147-150页

In this paper, we study the lifetime optimization problem in wireless sensor networks using mobile sink nodes. This problem is inherently difficult since we need to consider both sink scheduling and data routing. Through a simple case study we develop a novel notation named the Placement pattern (PP) to bound traffic patterns with candidate locations. This significantly decreases the number of elements needed to be scheduled. Based on the PP, we mathematically formulate this optimization problem as a Mixed-integer non-linear programming (MINLP), which is very tough and time consuming to solve. By proving that the problem is NP-complete, we point out that instead of seeking an optimal algorithm, heuristic algorithms, especially those with performance guarantee, would be much more desirable to develop. Furthermore, in order to help identify performance gains of heuristic algorithms proposed in the future, we develop a Linear programming (LP) formulation which serves as an upper bound by adopting a reformulation and relaxation technique.

关键词： Wireless sensor networks Upper bound Heuristic algorithms Traffic control Programming Performance gain Routing

来源：评论

学校读者我要写书评

暂无评论

A differential public PUF design for lightweight authentication 16

A differential public PUF design for lightweight authenticat...

引用

2021 International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design, SMACD 2021 and 16th Conference on PhD Research in Microelectronics and Electronics, PRIME 2021

作者： Duan, Shengyu Sai, Gaole School of Computer Engineering and Science Shanghai University Shanghai200444 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China

ISBN: (纸本)9783800755899

Physical Unclonable Functions (PUFs) have emerged as a promising primitive to provide a hardware keyless security mechanism for integrated circuit applications. Public PUFs (PPUFs) address the crucial PUF vulnerability of requiring databases to store the secrete reference information. This paper investigates one of the PPUF families, differential PPUF (dPPUF), which exploits complexly interacted logic to create time gap between actual execution and simulation, and to prevent simulation attacks. Conventional dPPUFs have high costs. We observe the repressers have large impact on simulation time, but take a great proportion in current dPPUF structure. We thereby present a represser network with specially designed interconnection and shared logic, to maintain a high circuit complexity and to reduce the area cost. We show the proposed dPPUF has similar resilience over simulation attacks as the conventional design. Area cost can be reduced by up to 44%, and thus the proposed design can be used for lightweight authentication. © VDE VERLAG GMBH.

关键词： Authentication

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：