检索结果-内蒙古大学图书馆

ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA)

作者： Xiao, Qingcheng Zheng, Size Wu, Bingzhe Xu, Pengcheng Qian, Xuehai Liang, Yun Peking Univ Sch EECS Beijing Peoples R China Univ Southern Calif Los Angeles CA 90089 USA

ISBN: (纸本)9781665433334

Tensor computations overwhelm traditional general-purpose computing devices due to the large amounts of data and operations of the computations. They call for a holistic solution composed of both hardware acceleration and software mapping. Hardware/software (HW/SW) co-design optimizes the hardware and software in concert and produces high-quality solutions. There are two main challenges in the co-design flow. First, multiple methods exist to partition tensor computation and have different impacts on performance and energy efficiency. Besides, the hardware part must be implemented by the intrinsic functions of spatial accelerators. It is hard for programmers to identify and analyze the partitioning methods manually. Second, the overall design space composed of HW/SW partitioning, hardware optimization, and software optimization is huge. The design space needs to be efficiently explored. To this end, we propose an agile co-design approach HASCO that provides an efficient HW/SW solution to dense tensor computation. We use tensor syntax trees as the unified Ut, based on which we develop a two-step approach to identify partitioning methods. For each method, HASCO explores the hardware and software design spaces. We propose different algorithms for the explorations, as they have distinct objectives and evaluation costs. Concretely, we develop a multi-objective Bayesian optimization algorithm to explore hardware optimization. For software optimization, we use heuristic and Q.-learning algorithms. Experiments demonstrate that HASCO achieves a 1.25X to 1.44X latency reduction through HW/SW co-design compared with developing the hardware and software separately.

关键词： Tensors Heuristic algorithms software algorithms Syntactics Hardware software Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Type-2 fuzzy neural network using grey wolf optimizer learning algorithm for nonlinear system identification

引用

MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOSYSTEMS-INFORMATION STORAGE AND PROCESSING SYSTEMS 2018年第10期24卷 4075-4088页

作者： Mao, Wei-Lung Suprapto Hung, Chung-Wen Natl Yunlin Univ Sci & Technol Grad Sch Engn Sci & Technol Dept Elect Engn 123 Univ RdSect 3 Touliu 64002 Yunlin Taiwan

Real systems with nonlinearity and valuable information always have unpredictable meaning and chaos properties in nature. It is often difficult to obtain the system model based on set of stimulus and response samples due to its complexity. This paper proposes the type-2 fuzzy neural network (T2FNN) and its learning method using grey wolf optimizer (GWO) for system identification. The structure of T2FNN is a combination between a type-2 fuzzy logic system with human-like IF-THEN rule thinking properties and neural networks (NN) with learning and optimization capability. The GWO is a meta-heuristic algorithm inspired from the social hunting behavior of grey wolves as search agents. This method is investigated by strategy, which maintains a proper balance between exploration and exploitation processes and gives more importance to the fittest to find the new position of search agent during the iterations. The GWO algorithm is considered for learning method due to its advantages, including high accuracy, very effective and more competitive. To evaluate the proposed system, the T2FNN with GWO learning method is employed by several nonlinear problems, including single-input single-output systems and multi-input multi-output (MIMO) systems. They are Mackey-Glass chaotic data series, nonlinear plant, nonlinear dynamical time-varying plant, and two MIMO systems. The merits of the proposed learning algorithm can be defined through experiments of the model and compared with existing learning PSO and GA algorithms and previous studies in literature. Based on the experimental results and performance comparisons, the proposed GWO algorithm indeed obtains the enhanced performance and capability in terms of the root mean squared error for nonlinear system identification applications.

关键词： ROOT-MEAN-SQUARE ERRORS output system learning algorithms System identification Fuzzy neural networks multiple input multiple output systems Learning methods search agent data sequence nonlinearity

来源：评论

学校读者我要写书评

暂无评论

Research on warping optimization of automobile mesh based on artificial intelligence algorithm

Research on warping optimization of automobile mesh based on...

引用

2023 International conference on Materials Science and Intelligent Manufacturing, MSIM 2023

作者： Shan, Zhi School of Advanced Manufacturing Technology Gaungdong Mechanical and Electrical Polytechnic Gaungzhou510515 China

Automobile mesh is a typical large plastic part prone to warping deformation in the manufacturing process, which seriously affects the quality of products. The traditional method is to find the optimal combination parameters to reduce warping deformation in the forming process through repeated trial or mold flow analysis with high cost. In this study, An optimization method based on an artificial intelligence algorithm is proposed to optimize the warping deformation of the automobile mesh. In the optimization method, artificial intelligence regression algorithm-support vector machine regression was used to establish the nonlinear function relationship (prediction function) between the molding process parameters and the warpage of automobile mesh, and the performance of the prediction function was optimized by a genetic algorithm. The optimized prediction function was taken as the fitness function, the warping value was regarded as the fitness value, and genetic algorithm is used again to obtain a set of optimal process parameters and minimum warpage values. Finally, the reliability of the optimization method is verified by the modal flow analysis software. © Published under licence by IOP Publishing Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Soft-constraint Based Satisfactory Fault-tolerant Control for Discrete-time Systems 4

Soft-constraint Based Satisfactory Fault-tolerant Control fo...

引用

The Fourth International conference On Control, Automation and Information Sciences

作者： Zhang, Dengfeng Han, Yu Zhao, Chao Zhang, Wei Nanjing Univ Sci & Technol Sch Mech Engn Nanjing 210094 Jiangsu Peoples R China Fouzhou Univ Sch Chem Engn Fouzhou 350116 Peoples R China

ISBN: (纸本)9781479998920

The active fault-tolerant control (FTC) with multiple performance constraints is investigated for a class of discrete-time systems subject to sensor faults. A satisfactory FTC strategy by way of the online moving horizon control mode is proposed to guarantee the closed-loop stability of the faulty system. The corresponding soft-constraint based FTC controller design method is developed from the predictive control theory to handle the multiobjective requirements including the constraints on relative stability, control input and system output, and the optimized quadratic performance as well. Its main advantage is to avoid the infeasibility of the online FTC controller reconfiguration due to the inconsistent constraints by relaxing soft constraints. The optimization calculation in the design can be executed by various nonlinear programming algorithms to solve the intrinsic nonlinear and non-convex constraints, which is an obstacle for conventional linear-and convex-based algorithms. Finally, an example is presented to verify the effectiveness of the proposed satisfactory FTC method.

关键词： fault-tolerant control multiple constraints nonlinear optimization consistency feasibility

来源：评论

学校读者我要写书评

暂无评论

Optimized Password Recovery for Encrypted RAR on GPUs 17

Optimized Password Recovery for Encrypted RAR on GPUs

引用

2015 IEEE 17th International conference on high performance Computing and Communications (HPCC)

作者： An, Xiaojing Jia, Haipeng Zhang, Yunquan Chinese Acad Sci Inst Comp Technol Beijing Peoples R China

ISBN: (纸本)9781479989379

Files are often compressed for efficiency. RAR is a common archive file format that supports data compression, error recovery and file spanning. RAR uses classic symmetric encryption algorithm SHA-1 hashing and AES algorithm for encryption. These two algorithms cannot be cracked, so the only method of password recovery is brute force, which is very time-consuming. In this paper, we present an approach using GPUs to speed up the password recovery process. However, because the major calculation and time-consuming part, SHA-1 hashing, is hard to be parallelized, so this paper adopts coarse granularity parallel. That is, one GPU thread is responsible for the validation of one password. We mainly use four optimization methods to optimize this parallel version: asynchronous parallel between CPU and GPU, redundant calculations and conditional statements reduction, data locality by using LDS, and the usage of registers optimization. Experiment result shows that the final version reaches 43 similar to 57 times speedup on an AMD FirePro W8000 GPU, compared to a well-optimized serial version on Intel Core i5 CPU. Meanwhile, linear performance acceleration is achieved when using multi-GPUs.

关键词： RAR password recovery GPGPU OpenCL performance optimization

来源：评论

学校读者我要写书评

暂无评论

A high-Order Finite Element Parallel MatLab software

A High-Order Finite Element Parallel MatLab Software

引用

7th International conference on Engineering Computational Technology

作者： Bargos, F. F. Augusto, R. A. Bittencourt, M. L. Univ Estadual Campinas Fac Mech Engn Dept Mech Design Campinas SP Brazil

ISBN: (纸本)9781905088416

This work presents a high-order finite element solver developed in the MatLab environment with procedures for high performance computing based on a very simple domain decomposition technique. The code has been developed with the goal of testing news procedures for the solution of finite elements problems using distributed computing. The code has been tested in many different problems including Poisson operator, Plane Stress, Plane Strain, Linear and nonlinear Elasticity, optimization, Contact and Reynolds Equation. This paper aims to present features of the developed software, mainly the aspects of domain decomposition and distributed computing.

关键词： finite element method distributed computation MatLab parallel high-performance computing

来源：评论

学校读者我要写书评

暂无评论

Quantum-behaved Particle Swarm optimization clustering algorithm

引用

2nd International conference on Advanced Data Mining and Applications

作者： Sun, Jun Xu, Wenbo Ye, Bin So Yangtze Univ Ctr Intelligent & High Performance Comp Sch Informat Technol Wuxi 214122 Jiangsu Peoples R China

ISBN: (纸本)3540370250

Quantum-behaved Particle Swarm optimization (QPSO) is a novel optimization algorithm proposed in the previous work. Compared to the original Particle Swarm optimization (PSO), QPSO is global convergent, while the PSO is not. This paper focuses on exploring the applicability of the QPSO to data clustering. Firstly, we introduce the K-means clustering algorithm and the concepts of PSO and QPSO. Then we present how to use the QPSO to cluster data vectors. After that, experiments are implemented to compare the performance of various clustering algorithms. The results show that the QPSO can generate good results in clustering data vectors with tolerable time consumption.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Designing Building Automation Systems Using Evolutionary algorithms with Semi-Directed Variations

Designing Building Automation Systems Using Evolutionary Alg...

引用

IEEE International conference on Systems, Man and Cybernetics

作者： Oezluek, A. Cemal Ploennigs, Joern Kabitzsch, Klaus Tech Univ Dresden Inst Appl Comp Sci D-8027 Dresden Germany

ISBN: (纸本)9781424465880

In the building automation domain, many prefabricated devices from different manufacturers available in the market realize building automation functions by preprogrammed software components. For given design requirements, the existence of a high number of devices that realize the required functions leads to a combinatorial explosion of design alternatives at different price and quality levels. Finding optimal design alternatives is a hard problem to which we approach with a multi-objective evolutionary algorithm. By integrating problem-specific knowledge into variation operations, a promisingly high optimization performance can be achieved. To realize this, diverse variation operations related to goals are defined upon a classification for the exploration and convergence behavior, and applied in different strategies.

关键词： building automation system building management systems evolutionary algorithm evolutionary computation hard problem optimal design optimisation optimization preprogrammed software components

来源：评论

学校读者我要写书评

暂无评论

Research on Task Allocation optimization Algorithm based on Edge Computing 24

Research on Task Allocation Optimization Algorithm based on ...

引用

International conference on algorithms, software Engineering, and Network Security (ASENS)

作者： Wang, Dian Li, Xiaoxiao Warsaw Univ Technol Fac Elect & Informat Technol Warsaw Poland

ISBN: (纸本)9798400709784

At present, mobile computing devices had led a variety of downstream applications, which will require the low response time of servers. However, the performance of smart devices is often very limited, and it is difficult to meet the high requirements of users for service quality. Therefore, edge computing is considered an effective way to solve this dilemma. In this work, we proposed a task scheduling algorithm for resource allocation to optimize the comprehensive cost of task execution. In order to reduce the complexity of the allocation framework, we divide the optimization problem into two sub-problems including resource allocation and task scheduling. As for allocation, we utilize the Lagrangian multiplier method to dispose the resource allocation sub-problem under a specific task scheduling strategy, and develop a task scheduling algorithm for joint resource allocation based on above results to minimize the total loss of user equipment task processing. From our extensive simulations, we can observe that our proposed model can achieve the allocation optimization in edge computing system with minimization costs through comparing with traditional methods.

关键词： Task Allocation Lagrange multipliers optimization Edge Computing

来源：评论

学校读者我要写书评

暂无评论

Increasing Efficiency in Data Flow Oriented Model Driven software Development for Softcore Processors 42

Increasing Efficiency in Data Flow Oriented Model Driven Sof...

引用

42nd Annual IEEE-Computer-Society Computers, software and Applications (COMPSAC) conference - Staying Smarter in a Smartening World

作者： Kirchhoff, Michael Weisensee, Joern Streitferdt, Detlef Fengler, Wolfgang Rozova, Elena Tech Univ Ilmenau Grp Comp Architecture & Embedded Syst Ilmenau Germany Tech Univ Ilmenau Grp Software Architectures & Prod Lines Ilmenau Germany

ISBN: (纸本)9781538626672

Faster development of new algorithms is crucial in modern projects. highly abstracted, data flow and modular oriented model-driven development methods and tools are used for this purpose. But with higher abstraction levels, there is always an increase in runtime overhead and a reduction in performance. Especially in real-time and cost-sensitive applications, this becomes a big issue that has to be dealt with. In this paper, we present a data flow and model-driven Matlab/Simulink plugin for generating efficient assembly code for a specialized hard real-time softcore processor. In this context, different optimization approaches will be introduced that are minimizing the overhead that comes with the used abstraction level. It will be shown that with the developed mechanisms, it is possible to generate assembly code nearly without any abstraction overhead and reducing the development time of any new algorithm by re-using pre-constructed modular parts.

关键词： data flow modeling optimization high-efficiency software engineering software performance software tools

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：