检索结果-内蒙古大学图书馆

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Xiaowen Chen Ta Tan Chen Li Jianzhuang Lu Qijin Zhu School of Computer National University of Defense Technology Changsha China Key Laboratory of Advanced Microprocessor Chips and Systems Changsha China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Network-on-Chip (NoC), known for its high bandwidth and scalability, is extensively utilized in chip multiprocessors. However, as technology advances to the nanometer scale, NoC is becoming increasingly vulnerable to errors caused by crosstalk, radiation, electromagnetic interference, and other factors. In addition to ensuring network reliability, designers must consider the overhead instead of blindly pursuing fault-tolerance capabilities in NoC design. In this paper, we analyze the characteristics of conventional End-to-End (E2E) and Switch-to-Switch (S2S) designs and propose AFTP, an adaptive high cost-effectiveness fault-tolerant NoC design based on prediction. Our design prioritizes stronger protection for head flits and relaxed protection for body and tail flits, and it is capable of dynamically adjusting the decoding times for flits in response to changes in error rate, aiming to achieve a balance between the overhead and the reliability of NoC. Our design demonstrates a significant improvement in cost-effectiveness compared to conventional E2E and S2S designs, achieving a 5.9x and 8.9x improvement, respectively, under common synthetic traffic and PARSEC benchmarks.

关键词： Fault tolerance Error analysis Fault tolerant systems Tail Switches Benchmark testing Reliability engineering Decoding Topology Protection

来源：评论

学校读者我要写书评

暂无评论

Area-Oriented Resubstitution For Networks of Look-Up Tables

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年

作者： Costamagna, Andrea Calvino, Alessandro Tempia Mishchenko, Alan Micheli, Giovanni De Swiss Federal Institute of Technology Lausanne Integrated Systems Laboratory Lausanne1015 Switzerland University of California Department of Electrical Engineering and Computer Sciences Berkeley United States

This paper addresses the challenge of reducing the number of nodes in Look-Up Table (LUT) networks with two significant applications. First, Field-Programmable Gate Arrays (FPGAs) can be modelled as networks of LUTs, and minimizing the node count is imperative to meet resource constraints. Second, in area-oriented design space exploration for standard-cell designs, collapsing a circuit into a LUT network, restructuring it, and later remapping to the original representation helps escape local minima. Thus, the development of algorithms for optimizing and restructuring LUT networks holds considerable promise for area-oriented optimization. Substitution (also called resubstitution) is a powerful logic minimization method that can identify non-local logic dependencies and exploit them for logic minimization. State-of-the-art substitution algorithms for LUT networks rely heavily on SAT solving, limiting the number of optimization attempts and the size of the substitution sub-networks to one node mishchenko2011scalable. Conversely, our method relies on circuit simulation to increase the number of substitution candidates and enables substitutions with more than one node. The experimental results show that the proposed method identifies optimization opportunities overlooked by other methods, improving 11 out of 23 best-known results in the EPFL synthesis competition and yielding a 3.46% area reduction compared to the state-of-the-art. © 1982-2012 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

BitShare: An Efficient Precision-Scalable Accelerator with Combining-Like-Terms GEMM

BitShare: An Efficient Precision-Scalable Accelerator with C...

引用

International Conference on Application Specific systems (ASAP), Architectures and Processors

作者： Yasong Cao Mei Wen Junzhong Shen Zhongxing Li College of Computer National University of Defense Technology Changsha China The Key Laboratory of Advanced Microprocessor Chips and Systems Changsha China

ISBN: (数字)9798350349634

ISBN: (纸本)9798350349641

Narrow-precision fixed-point (INT) computation is a significant approach for reducing memory requirements and enhancing the performance of accelerators for Deep Neural Networks (DNNs). Different DNNs, as well as different layers within the DNNs, may exhibit varying numerical distributions, necessitating INT formats with different minimum bit-widths. Therefore, DNN accelerators need to support multi-precision INT computations to strike a better balance between DNN inference accuracy and performance. However, existing precision-scalable accelerators face challenges such as low bandwidth utilization, insufficient utilization of computing resources across different precision modes, and complex circuit structures with associated overhead. In this paper, we propose (1) a hardware-friendly Combining-Like-Terms GEMM (CLT-GEMM) scheme that supports multiple computing modes of 2/4/8 bits and their combinations to align with the various bit-width settings of DNNs; (2) and subsequently design an efficient systolic accelerator with scalable precision, named BitShare, which features DataMap module and Multi-mode adder-tree-based accumulators. Compared to the state-of-the-art precision-scalable design, BitBlade, our accelerator achieves a 57.25% reduction in bandwidth requirement and exhibits an improvement of $1.14\times$ and $1.12\times$ in area and power efficiency $(2\mathbf{b}\times 2\mathbf{b})$ , respectively.

关键词： Training Program processors Art Accuracy Design methodology Memory management systems architecture

来源：评论

学校读者我要写书评

暂无评论

Learning good state and action representations for Markov decision process via tensor decomposition

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 5157-5209页

作者： Chengzhuo Ni Yaqi Duan Munther Dahleh Mengdi Wang Anru R. Zhang Department of Electrical & Computer Engineering Princeton University Laboratory for Information & Decision Systems Massachusetts Institute of Technology Electrical Engineering & Computer Science Department Massachusetts Institute of Technology Department of Biostatistics & Bioinformatics Duke University

The transition kernel of a continuous-state-action Markov decision process (MDP) admits a natural tensor structure. This paper proposes a tensor-inspired unsupervised learning method to identify meaningful low-dimensional state and action representations from empirical trajectories. The method exploits the MDP's tensor structure by kernelization, importance sampling and low-Tucker-rank approximation. This method can be further used to cluster states and actions respectively and find the best discrete MDP abstraction. We provide sharp statistical error bounds for tensor concentration and the preservation of diffusion distance after embedding. We further prove that the learned state/action abstractions provide accurate approximations to latent block structures if they exist, enabling function approximation in downstream tasks such as policy evaluation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques with Digital Twin for Fault Diagnosis in Interconnected systems: A Review

引用

IEEE Access 2025年 13卷 91860-91874页

作者： Nakti, Imen Mansouri, Majdi Al-Hmouz, Rami Khedher, Atef University of Sousse ENISO Laboratory of Advanced Technology and Intelligent systems Sousse4002 Tunisia Sultan Qaboos University College of Engineering Department of Electrical and Computer Engineering Muscat123 Oman

As industrial systems become more complex and interconnected, diagnosing faults accurately and in real time has become increasingly challenging. This paper explores how combining artificial intelligence with digital twin technology can address these challenges. We focus on developing hybrid Artificial intelligence models that leverage diverse data sources to enhance fault detection and diagnosis, enabling secure and distributed diagnostics. Digital twins, virtual models of physical systems, are shown to enhance predictive maintenance and decision-making by providing real-time system insights. What sets our work apart is the way we integrate these technologies to create scalable, adaptive, and context-aware diagnostic solutions. We demonstrate the potential of this approach across applications such as smart grids, manufacturing, and autonomous systems. Our goal is to provide researchers and practitioners with a practical and forward-looking framework for developing intelligent, reliable fault diagnosis systems in today’s data-rich industrial environments. © 2013 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Load balancing-oriented fault-tolerant NoC design

Load balancing-oriented fault-tolerant NoC design

引用

International Test Conference in Asia (ITC-Asia)

作者： Ta Tan Xiaowen Chen Chen Li Jianzhuang Lu School of Computer National University of Defense Technology Changsha China Key Laboratory of Advanced Microprocessor Chips and Systems Changsha China

ISBN: (数字)9798331540333

ISBN: (纸本)9798331540340

Network-on-Chip (NoC) has been widely applied in modern chip multiprocessors due to its high bandwidth and scalability. However, as technology advances to the nanometer scale, NoC is increasingly vulnerable to errors caused by crosstalk, radiation, electromagnetic interference, etc. Conventional Switch-to-Switch (S2S) fault-tolerant designs based on ECC have overlooked the characteristic of the distribution of traffic load. This oversight not only increases area overhead significantly but also leads to low average utilization of ECC decoder modules. In this paper, we analyze the distribution of traffic load in mesh network and propose a load balancing-oriented fault-tolerant NoC design. The core idea is to allocate different numbers of ECC decoder modules to each router based on the distribution of traffic load, aiming to improve the average utilization of ECC decoder modules and reduce the area overhead without compromising fault-tolerant capability of NoC. The experiment under 6 common synthetic traffic patterns shows that compared to the baseline, our design exhibits an average delay performance loss of less than 0.88%. Additionally, the maximum reduction in the number of ECC decoder modules is 160, the maximum reduction in the area overhead of NoC is 15.06%, and the maximum improvement in the average utilization of ECC decoder modules is 1.21x. Furthermore, the experiment under PARSEC benchmarks shows that compared to the baseline, our design exhibits an average delay performance loss of less than 0.08%. Additionally, the maximum reduction in the number of ECC decoder modules is 156, the maximum reduction in total NoC area overhead is 14.69%, and the maximum improvement in the average utilization of ECC decoder modules is 1.13x.

关键词： Fault tolerance Scalability Fault tolerant systems Telecommunication traffic Switches Network-on-chip Traffic control

来源：评论

学校读者我要写书评

暂无评论

Satisfiability threshold of the random regular(s,c,k)-SAT problem

引用

Frontiers of computer Science 2022年第3期16卷 227-229页

作者： Xiaoling MO Daoyun XU Kai YAN Zaijun ZHANG College of Computer Science and Technology Guizhou UniversityGuiyang 550025China Agricultural Development Bank of China Beijing 100045China Key Laboratory of Complex Systems and Intelligent Computing and School of Mathematics and Statistics Qiannan Normal University for NationalitiesDuyun 558000China

1Introduction The satisfiability(SAT)problem is always a core problem in the field of computer *** theoretical and applied research have long been the common attention of many scholars in the field of artificial intelligence and mathematical *** the real world,all issues related to combinatorial optimization and coordination verification are closely related to SAT problem.

关键词： problem. problem combinatorial

来源：评论

学校读者我要写书评

暂无评论

Risk-Aware Neural Navigation From BEV Input for Interactive Driving

Risk-Aware Neural Navigation From BEV Input for Interactive ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Suzanna Jiwani Xiao Li Sertac Karaman Daniela Rus Computer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Laboratory for Information and Decision Systems Massachusetts Institute of Technology

Safety has been a key goal for autonomous driving since its inception, and we believe recognizing and responding to risk is a key component of safety. In this work, we aim to answer the question, “How can explainable risk representations be generated and used to produce risk-averse trajectories?” To answer this question, previous work uses risk metrics to formulate an optimization problem. In contrast, our work is based on research showing the usefulness of grids as a representation to generate image-based risk maps through a trained neural network. We propose a method of determining risk from a bird's eye view (BEV) of an autonomous vehicle's surroundings. Our method consists of (1) a risk map generator, which is trained to recognize risk associated with nearby agents and the map, (2) differentiable value iteration using the risk map to learn a policy, and (3) a trajectory sampler, which samples from this policy to generate a trajectory. We evaluate our planner in a close-loop manner and find improvements in its overall ability to mimic human driving while maintaining comparable safety statistics. Self-ablation also reveals the potential for fine-tuning the behavior of the planner given a designer's needs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Matters: A New Dataset and Empirical Study for Multimodal Hyperbole Detection

arXiv

引用

arXiv 2023年

作者： Zhang, Huixuan Wan, Xiaojun Wangxuan Institute of Computer Technology Peking University State Key Laboratory of Media Convergence Production Technology and Systems China

Hyperbole, or exaggeration, is a common linguistic phenomenon. The detection of hyperbole is an important part of understanding human expression. There have been several studies on hyperbole detection, but most of which focus on text modality only. However, with the development of social media, people can create hyperbolic expressions with various modalities, including text, images, videos, etc. In this paper, we focus on multimodal hyperbole detection. We create a multimodal detection dataset from Weibo (a Chinese social media) and carry out some studies on it. We treat the text and image from a piece of weibo as two modalities and explore the role of text and image for hyperbole detection. Different pre-trained multimodal encoders are also evaluated on this downstream task to show their performance. Besides, since this dataset is constructed from five different keywords, we also evaluate the cross-domain performance of different models. These studies can serve as a benchmark and point out the direction of further study on multimodal hyperbole detection. © 2023, CC BY-SA.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

FDCPNet: Feature Discrimination and Context Propagation Network for 3D Shape Representation

SSRN

引用

SSRN 2024年

作者： Shi, Weimin Xiong, Yuan Wang, Qianwen Jiang, Han Zhou, Zhong State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Zhongguancun Laboratory Beijing China

3D shape representation using mesh data is essential in various applications, such as virtual reality and simulation technologies. Current methods extracting features from mesh edges or faces struggle with complex 3D models due to edge-based approaches missing global context and face-based methods overlooking variations in adjacent areas, which affects overall precision. To address these issues, we propose the Feature Discrimination and Context Propagation Network (FDCPNet), a novel approach that synergistically integrates local and global features in mesh datasets. FDCPNet is composed of two modules: 1) Feature Discrimination Module (FDM), which employs an attention mechanism to enhance the identification of key local features, 2) Context Propagation Module (CPM) enriches key local features by integrating global contextual information, facilitating a more detailed and comprehensive representation of crucial areas within the mesh model. Experiments on the Manifold40 dataset validate FDCPNet's effectiveness, showing a 1.9% improvement in classification accuracy over the baseline MeshNet, achieving 90.3%. Furthermore, even with reduced mesh face numbers and limited training data, FDCPNet achieves promising results, showing its robustness in variable complexity scenarios. © 2024, The Authors. All rights reserved.

关键词： Complex networks

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：