检索结果-内蒙古大学图书馆

ACM International Conference on Computing Frontiers

作者： Gajinov, Vladimir Stipic, Srdjan Eric, Igor Unsal, Osman S. Ayguade, Eduard Cristal, Adrian Barcelona Supercomp Ctr Barcelona Spain Univ Politecn Cataluna E-08028 Barcelona Spain Univ Belgrade Belgrade 11001 Serbia Artificial Intelligence Res Inst Barcelona Spain Spanish Natl Res Council Madrid Spain

ISBN: (纸本)9781450328708

The current trend in development of parallel programming models is to combine different well established models into a single programming, model in order to support efficient implementation of a wide range of real world applications. The dataflow model has particularly managed to recapture the interest of the research community due to its ability to express parallelism efficiently. Thus, a number of recently proposed hybrid parallel programming models combine dataflow and traditional shared memory models. Their findings have influenced the introduction of task dependency in the OpenMP 4.0 standard. This article presents DaSH - the first comprehensive benchmark suite for hybrid dataflow and shared memory programming models. DaSH features 11 benchmarks, each representing one of the Berkeley dwarfs that capture patterns of communication and computation common to a wide range of emerging applications. DaSH also includes sequential and shared-memory implementations based on OpenMP and Intel TBB to facilitate easy comparison between hybrid dataflow implementations and traditional shared memory implementations based on work-sharing and/or tasks. Finally, we use DaSH to evaluate three different hybrid dataflow models, identify their advantages and shortcomings, and motivate further research on their characteristics. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Benchmark suite Dataflow Shared memory Transactional memory programming model

来源：评论

学校读者我要写书评

暂无评论

A high-performance tensor computing unit for deep learning acceleration

引用

Chip 2025年第2期4卷

作者： Qiang Zhou Tieli Sun Taoran Shen York Xue State Key Laboratory of Integrated Chips and Systems School of Microelectronics Fudan University Shanghai 201203 China Frontier Institute of Chip and System Fudan University Shanghai 200438 China TRANSCPUTING Technology LTD Shanghai 201203 China

The increasing complexity of neural network applications has led to a demand for higher computational parallelism and more efficient synchronization in artificial intelligence (AI) chips. To achieve higher performance and lower power, a comprehensive and efficient approach is required to compile neural networks for implementation on dedicated hardware. Our first-generation deep learning accelerator, tensor computing unit, was presented with hardware and software solutions. It offered dedicated very long instruction words (VLIWs) instructions and multi-level repeatable direct memory access (DMA). The former lowers the instruction bandwidth requirement and makes it easier to parallelize the index and vector computations. The latter reduces the communication latency between the compute core and the asynchronous DMA, and also greatly alleviates the programming complexity. For operator implementation and optimization, the compiler-based data-flow generator and the instruction macro generator first produced a set of parameterized operators. Then, the tuner-configuration generator pruned the search space and the distributed tuner framework selected the best data-flow pattern and corresponding parameters. Our tensor computing unit supports all the convolution parameters with full-shape dimensions. It can readily select proper operators to achieve 96% of the chip peak performance under certain shapes and find the best performance implementation within limited power. The evaluation of a large number of convolution shapes on our tensor computing unit chip shows the generated operators significantly outperform the hand-written ones, achieving 9% higher normalized performance than CUDA according to the silicon data.

关键词： Deep learning accelerator programming model VLIW DMA Tensor computing unit

来源：评论

学校读者我要写书评

暂无评论

OpenMC: Towards Simplifying programming for TianHe Supercomputers

引用

Journal of Computer Science & Technology 2014年第3期29卷 532-546页

作者：廖湘科杨灿群唐滔易会战王锋吴强薛京灵 School of Computer Science National University of Defense Technology School of Computer Science and Engineering University of New South Wales

Modern petascale and future exascale systems are massively heterogeneous architectures. Developing productive intra-node programming models is crucial toward addressing their programming challenge. We introduce a directive- based intra-node programming model, OpenMC, and show that this new model can achieve ease of programming, high performance, and the degree of portability desired for heterogeneous nodes, especially those in TianHe supercomputers. While existing models are geared towards oifloading computations to accelerators （typically one）, OpenMC alms to more uniformly and adequately exploit the potential offered by multiple CPUs and accelerators in a compute node. OpenMC achieves this by providing a unified abstraction of hardware resources as workers and facilitating the exploitation of asynchronous task parallelism on the workers. We present an overview of OpenMC, a prototyping implementation, and results from some initial comparisons with OpenMP and hand-written code in developing six applications on two types of nodes from TianHe supercomputers.

关键词： supercomputer programming model heterogeneous MIC

来源：评论

学校读者我要写书评

暂无评论

A Unifying Framework to Enable Artificial Intelligence in High Performance Computing Workflows

引用

Computing in Science & Engineering 2025年第01期27卷 73-78页

作者： Jens Domke Mohamed Wahib Anshu Dubey Tal Ben-Nun Erik W. Draeger RIKEN Center for Computational Science Kobe Japan Argonne National Laboratory Lemont IL USA Lawrence Livermore National Laboratory Livermore CA USA

Current trends point to a future where large-scale scientific applications are tightly-coupled HPC/AI hybrids. Hence, we urgently need to invest in creating a seamless, scalable framework where HPC and AI/ML can efficiently work together and adapt to novel hardware and vendor libraries without starting from scratch every few years. The current ecosystem and sparsely-connected community are not sufficient to tackle these challenges, and we require a breakthrough catalyst for science similar to what PyTorch enabled for AI.

关键词： High Performance Computing Ecosystems Market Research Hardware Artificial Intelligence Large Scale Integration Computational Intelligence Machine Learning High Performance Computing Research And Development Alternative models Computer Science Interoperability Application programming Interface Rapid Advances Load Data Pace Of Change Tight Coupling General Platform Hardware Development Oak Ridge National Laboratory Refactoring Drawing Board Hardware Changes End Users Data Transformation programming model Elements Of The Framework Co Design

来源：评论

学校读者我要写书评

暂无评论

New approach to multiple attribute decision making with interval numbers

引用

Journal of Systems Engineering and Electronics 2008年第2期19卷 304-310页

作者： Zhang Quan Gao Qisheng Geng Jinhua School of Information Engineering Shenyang Univ. of Technology Shenyang 110023 P. R. China Inst. of Complexity Science Qingdao Univ. Qingdao 266071 P. R. China

In an ambiguous decision domain, the evaluation values of alternatives against attributes would be interval numbers because of the inherent, uncertain property of the problems. By using a number of linear programming models, Bryson and Mobolurin propose an approach to compute attribute weights and overall values of the alternatives in the form of interval numbers. The intervals of the overall values of alternatives are then transformed into points or crisp values for comparisons among the alternatives. However, the attribute weights are different because of the use of linear programming models in Bryson and Mobolurin＇s approach. Thus, the alternatives are not comparable because different attribute weights are employed to calculate the overall values of the alternatives. A new approach is proposed to overcome the drawbacks of Bryson and Mobolurin＇s approach. By transforming the decision matrix with intervals into the one with crisp values, a new linear programming model is proposed, to calculate the attribute weights for conducting alternative ranking.

关键词： multiple attribute decision making interval number normalization programming model ranking.

来源：评论

学校读者我要写书评

暂无评论

A new procedure for hesitant multiplicative preference relations

引用

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS 2019年第5期34卷 819-857页

作者： Meng, Fanyong Tang, Jie An, Qingxian Chen, Xiaohong Cent S Univ Sch Business Changsha 410083 Hunan Peoples R China Nanjing Univ Informat Sci & Technol Sch Management Sci & Engn Nanjing Jiangsu Peoples R China Univ Technol Troyes Charles Delaunay Inst Ind Syst Optimizat Lab Troyes France Hunan Univ Commerce Sch Accounting Changsha Hunan Peoples R China

Hesitant information is powerful and flexible to denote decision maker's judgments. Hesitant multiplicative preference relations (HMPRs) own the advantages of preference relations and hesitant fuzzy sets that permit the decision makers (DMs) to compare objects by using several values. Just as other types of preference relations, how to derive the priority weight vector is a crucial step. According to the principle of the consistency concept for multiplicative preference relations, this paper first introduces a new consistency concept for HMPRs, which avoids the disadvantages of the previous ones. Using the new concept, models to judge the consistency of HMPRs are built. Then, a consistency probability-based method to derive the hesitant fuzzy priority weight vector from HMPRs is offered. Considering the incomplete case, consistency-based programming models to determine the missing values are constructed. To address group decision making with HMPRs, a distance measure is defined to determine the weights of the DMs, and a consensus index is proposed. Then, a consistency and consensus-based group decision-making algorithm is performed. Finally, two practical examples, an investment problem and a water conservancy problem are offered to illustrate the feasibility and efficiency of the new algorithm. Comparison analysis from the numerical and theoretical aspects verifies the potential application of the new procedure.

关键词： consensus consistency group decision making hesitant multiplicative preference relation programming model

来源：评论

学校读者我要写书评

暂无评论

Consensus Reaching Process for Traditional Group Decision Making in View of the Optimal Adjustment Mechanism

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第6期53卷 3748-3759页

作者： Meng, Fan-Yong Pedrycz, Witold Tang, Jie Nanjing Univ Informat Sci & Technol Sch Management Sci & Engn Nanjing 210044 Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2R3 Canada

Consensus reaching process (CRP) is a key topic in the area of group decision making (GDM). When the consensus level is not high enough, it becomes necessary to adjust the original opinions of decision makers (DMs). To offer the adjustment reference for DMs, we build the programming models to determine the minimum modification to be carried out from the individual and global perspectives. Meanwhile, all DMs are divided into two subgroups: DMs with acceptable and unacceptable consensus levels. If some DMs with unacceptable consensus level do not accept the relevant modifications, the Nash bargaining game-based programming model is built for the fairness and efficiency of modifications. When some DMs refuse to make any modifications or tend to modify the opinions in their way, with respect to different group consensus situations, we make the minimum hybrid penalty mechanism by the Nash bargaining game-based programming models. For each case, we determine the corresponding optimal modification mechanism in view of the fixed individual total modification and the maximum consensus level. Furthermore, we study the arrangements of weights of DMs according to their cardinal and ordinal consensus contributions. Based on these results, we present a new algorithm and illustrate its application by a numerical example. Moreover, we carry out the sensitivity and comparison analysis. We summarize the conclusions and future research directions in the end. The main originality of the new method includes: the fairness and efficiency of modifications, and the determination of the hybrid penalty mechanism.

关键词： Costs Decision making Linguistics Social networking (online) programming profession Analytical models Optimization Consensus reaching process (CRP) group decision making (GDM) Nash bargaining game optimal modification mechanism programming model

来源：评论

学校读者我要写书评

暂无评论

NRMI: Natural and efficient middleware

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2008年第2期19卷 174-187页

作者： Tilevich, Eli Smaragdakis, Yannis Virginia Tech Dept Comp Sci Blacksburg VA 24061 USA Univ Oregon Dept Comp & Informat Sci Eugene OR 97403 USA

We present Natural Remote Method Invocation (NRMI): a middleware mechanism that provides a fully general implementation of call-by-copy-restore semantics for arbitrary linked data structures, used as parameters in remote procedure calls. Call-by-copy-restore offers a more natural programming model for distributed systems than traditional call-by-copy middleware, enabling remote calls to behave much like local calls. We discuss in depth the effects of calling semantics for middleware, describe when and why NRMI is more convenient to use than standard middleware, and present three implementations of NRMI in distinct settings, showing the generality of the approach.

关键词： middleware RPC Java call-by-copy-restore programming model

来源：评论

学校读者我要写书评

暂无评论

Multi-attribute group decision-making using double hierarchy hesitant fuzzy linguistic preference information

引用

NEURAL COMPUTING & APPLICATIONS 2020年第17期32卷 14031-14045页

作者： Krishankumar, R. Ravichandran, K. S. Shyam, V. Sneha, S. V. Kar, Samarjit Garg, Harish SASTRA Univ Sch Comp Thanjavur 613401 Tamil Nadu India Natl Inst Technol Dept Math Durgapur W Bengal India Thapar Inst Engn & Technol Deemed Univ Sch Math Patiala 147004 Punjab India

Double hierarchy hesitant fuzzy linguistic term set (DHHFLTS) is one of the successful extensions of the hesitant fuzzy linguistic term set used for describing the uncertain information in a more prominent manner for solving the group decision-making problems. In DHHFLTS, the membership functions are represented in terms of linguistic membership degrees which are a flexible structure for preference elicitation and enrich the ability for rational decision-making with complex linguistic expressions. Driven by the flexibility of DHHFLTS, in this paper, a new decision framework is developed for solving decision-making problems, which provides scientific and rational decisions based on the preference information. For it, initially, a new aggregation operator is proposed for aggregating decision-makers' preferences. Later, the importance of the attribute weights in the problems is determined by formulating a mathematical model and the COPRAS method is extended to the DHHFLTS context for prioritizing alternatives. The applicability of the presented approach is demonstrated through a numeric example related to green supplier selection. A comparative analysis with existing studies is also administered to test the effectiveness and verify the method.

关键词： COPRAS method Double hierarchy Group decision-making Maclaurin symmetric mean programming model

来源：评论

学校读者我要写书评

暂无评论

Next generation grids and wireless communication networks: towards a novel integrated approach

引用

WIRELESS COMMUNICATIONS & MOBILE COMPUTING 2009年第4期9卷 445-467页

作者： Fantacci, Romano Vanneschi, Marco Bertolli, Carlo Mencagli, Gabriele Tarchi, Daniele Univ Florence Dept Elect & Telecommun Florence Italy Univ Pisa Dept Comp Sci I-56100 Pisa Italy

One of the most promising trends for next generation networks is to consider an integrated approach to the communication infrastructure and the processing layer. In particular, the introduction of broadband and reliable wireless networks allows the interaction of a huge number of devices all creating a single network. On the other hand, the grid paradigm is considered as one of the most promising approach for pervasive and dynamic applications. Aim of this paper is to present a novel integrated approach between grid paradigm and wireless networks by highlighting the main advantages of their cooperation. In particular, it will be shown here how a wireless heterogeneous network can be exploited for implementing a pervasive and dynamic grid (mobile grid) and, on the other hand, a mobile grid allows the optimization of the communication infrastructure. The integrated approach can be an effective method for solving applications, such its emergency management, where a huge amount of data derived from a wireless infrastructure needs to be processed efficiently and adaptively, and the traffic flow in the wide area wireless networks needs to be coordinated and optimized. Copyright (C) 2008 John Wiley & Sons, Ltd.

关键词： next generation networks mobile grid wireless networks adaptivity context-awareness programming model

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：