检索结果-内蒙古大学图书馆

Dual Domain Decomposition Method for High-Resolution 3D Simulation of Groundwater Flow and Transport

WATER 2024年第13期16卷 1864页

作者： Deng, Hao Li, Jiaxin Huang, Jixian Zou, Yanhong Liu, Yu Chen, Yuxiang Zheng, Yang Mao, Xiancheng Cent South Univ Sch Geosci & Info Phys Changsha 410083 Peoples R China Cent South Univ Key Lab Metallogen Predict Nonferrous Met & Geol E Minist Educ Changsha 410083 Peoples R China

The high-resolution 3D groundwater flow and transport simulation problem requires massive discrete linear systems to be solved, leading to significant computational time and memory requirements. The domain decomposition method is a promising technique that facilitates the parallelization of problems with minimal communication overhead by dividing the computation domain into multiple subdomains. However, directly utilizing a domain decomposition scheme to solve massive linear systems becomes impractical due to the bottleneck in algebraic operations required to coordinate the results of subdomains. In this paper, we propose a two-level domain decomposition method, named dual-domain decomposition, to efficiently solve the massive discrete linear systems in high-resolution 3D groundwater simulations. The first level of domain decomposition partitions the linear system problem into independent linear sub-problems across multiple subdomains, enabling parallel solutions with significantly reduced complexity. The second level introduces a domain decomposition preconditioner to solve the linear system, known as the Schur system, used to coordinate results from subdomains across their boundaries. This additional level of decomposition parallelizes the preconditioning of the Schur system, addressing the bottleneck of the Schur system solution while improving its convergence rates. The dual-domain decomposition method facilitates the partition and distribution of the computation to be solved into independent finely grained computational subdomains, substantially reducing both computational and memory complexity. We demonstrate the scalability of our proposed method through its application to a high-resolution 3D simulation of chromium contaminant transport in groundwater. Our results indicate that our method outperforms both the vanilla domain decomposition method and the algebraic multigrid preconditioned method in terms of runtime, achieving up to 8.617x and 5.515x speedups,

关键词： groundwater simulation domain decomposition parallel algorithm fast solution 3D numeric modeling

来源：评论

学校读者我要写书评

暂无评论

G-OPTICS: fast ordering density-based cluster objects using graphics processing units

引用

INTERNATIONAL JOURNAL OF WEB AND GRID SERVICES 2018年第3期14卷 273-287页

作者： Lee, Wookey Loh, Woong-Kee Inha Univ Dept Ind Engn Incheon 22212 South Korea Gachon Univ Dept Software Seongnam 13120 South Korea

Clustering is the process of forming groups or clusters of similar objects in the dataset and has been used as an important tool for many data mining applications including the web-based ones. While density-based clustering algorithms are widely adopted, their clustering result is highly sensitive to parameter values. The OPTICS algorithm presents a solution to this problem;it produces an ordering of objects that is equivalent to the clustering results for a wide range of thresholds E. In this paper, we propose an algorithm named G-OPTICS to significantly improve the performance of OPTICS using a graphics processing unit (GPU). The experimental results using real and synthetic datasets demonstrated that G-OPTICS outperformed the previously fastest FOPTICS algorithm by up to 118.3 times (67.7 times on the average).

关键词： ordering of objects density-based clustering GPU graphics processing unit parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

Development of phase domain frequency-dependent transmission line model on FPGA for real-time digital simulator

引用

ELECTRIC POWER SYSTEMS RESEARCH 2021年 197卷 107305-107305页

作者： Liu, Jiadai Chen, Yuan Ding, Hui Zhang, Yi RTDS Technol Inc Winnipeg MB R3T 2E1 Canada

The transmission line model is one of the most important components for the real-time digital simulator based on the electromagnetic transient (EMT) algorithm. In order to predict the behavior of power systems under both steady and transient states, the coupling and frequency dependence of the transmission line need to be precisely represented. This paper presents a frequency-dependent phase domain (FDPD) transmission line model on a field programmable gate array (FPGA) for an EMT type real-time digital simulator. The developed model has been fully pipelined and parallelized in hardware to achieve the lowest time-step. All the hardware developments for this model depicted in this paper are carried out in VHDL, and a customized 48-bits floating-point data representation is used for hardware implementation to improve the accuracy. This developed FPGA-based line model can be interfaced to the rest of the network to perform real-time simulation.

关键词： Electromagnetic transient analyses Real-time digital simulator Field programmable gate arrays Frequency-dependent transmission line parallel algorithm Pipelining

来源：评论

学校读者我要写书评

暂无评论

A 3D TLM code for the study of the ELF electromagnetic wave propagation in the Earth's atmosphere

引用

COMPUTERS & GEOSCIENCES 2024年 183卷

作者： Salinas, Alfonso Porti, Jorge Navarro, Enrique A. Toledo-Redondo, Sergio Albert, Inmaculada Castilla, Aida Univ Granada Res Ctr Informat & Commun Technol CITIC UGR Dept Electromagnetism & Matter Phys Granada Spain Univ Granada Res Ctr Informat & Commun Technol CITIC UGR Dept Appl Phys Granada Spain Univ Valencia IRTIC Inst ETSE Burjassot Spain Univ Murcia Dept Electromagnetism & Elect Murcia Spain

The interest in the study of electromagnetic propagation through planetary atmospheres is briefly discussed. Special attention is devoted to extremely-low-frequency fields in the Earth's atmosphere for its global nature and possible applications to climate monitoring studies among others. In the Earth's case, the system can be considered as a spherical electromagnetic shell resonator in which two concentric and large conducting spheres with a radius around 6300 km are separated by a very small distance of around 100 km, the atmosphere height. A numerical solution using the Transmission Line Method is proposed. The classical spherical-coordinate description is easy to use, however, the important difference in the dimensions along the three coordinate directions causes high numerical dispersion in the results. A Cartesian scheme with equal node size for all directions is used to reduce this undesired dispersion. A pre-processing stage is the key point introduced to lessen the resulting high demand of memory and time calculation and make the solution feasible. A parallelized Fortran code together with pre- and post-processing Python programs to ease the user interface are provided with this work. Details on the Fortran code and the Python modules are included both in the paper and the source codes to allow the use and modifications by other researchers interested in electromagnetic propagation through planetary atmospheres. The program allows calculation of the time evolution of the electromagnetic field at any point in the atmosphere. It includes the possibility of considering multiple time-dependent sources and different homogeneous and inhomogeneous conductivity profiles to model different situations. Profiles to study day-night asymmetries or locally perturbed profiles which have been attributed to earthquakes in the literature are implemented, for instance.

关键词： Atmosphere electrodynamics TLM method Schumann resonances Full 3D numerical model parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

THE M3 MULTIPROCESSOR LABORATORY

引用

IEEE TRANSACTIONS ON parallel AND DISTRIBUTED SYSTEMS 1993年第5期4卷 507-519页

作者： BURKHART, H EIGENMANN, R KINDLIMANN, H MOSER, M SCHOLIAN, H ERGOSOFT AG CH-8595 ALTNAU SWITZERLAND IBM CORP ZURICH RES LAB CH-8803 ZURICH SWITZERLAND SWISS FED INST TECHNOL INST ELEKTR CH-8092 ZURICH SWITZERLAND UNIV ILLINOIS CTR SUPERCOMPUTING RES & DEV URBANA IL 61801 USA

Microprocessor-based multiprocessors offer true parallelism at moderate hardware cost. Although such hardware building blocks are now available at many sites, the basic problem is still how to program such systems. We report about an integrated programming environment for the M3 multiprocessor, which has been built at ETH Zurich. Our tools support the software development cycle of a parallel program, that is the programming, configuration, and debugging/performance measurement phases. Programmer support for performance analysis has been a primary motivation for the system. We identify the sources of performance loss and describe how this information is gathered and analyzed. As a case study, we use a fast maze router algorithm and follow the usage of the different tools. Finally, we compare the M3 environment with other state-of-the-art projects.

关键词： MAN-MACHINE DIALOG MODULA-2 MULTIPROCESSOR parallel algorithm PERFORMANCE ANALYSIS PERFORMANCE MONITORING PROGRAMMING ENVIRONMENT

来源：评论

学校读者我要写书评

暂无评论

A new hybrid GPU-CPU sparse LDLT factorization algorithm with GPU and CPU factorizing concurrently

引用

JOURNAL OF COMPUTATIONAL SCIENCE 2024年 79卷

作者： Liu, Yunmou Du, Hui Li, Zhuogen Chen, Pu Peking Univ Coll Engn Dept Mech & Engn Sci Beijing 100871 Peoples R China Peking Univ State Key Lab Turbulence & Complex Syst Beijing 100871 Peoples R China Peking Univ NanChang Innovat Inst Nanchang 330008 Peoples R China

This paper proposes a new task assignment scheme for sparse LDLT factorization on a hybrid GPU-CPU platform, and correspondingly an efficient supernodal algorithm, GPU Node and CPU Pipelining (GNCP). GNCP assigns a large number of weakly coupled tasks to GPU and CPU respectively so that GPU and CPU can execute different factorization tasks concurrently without explicit synchronization, which has not been achieved by previous researches. More precisely, based on the number of CPU threads, the global memory of GPU as well the size of the matrix, we introduce the concept of the truncation level in the partition tree built by the multi-level graph partitioning. The sum of FLOP associated with decoupled nodes in the truncation level accounts for about 65% of the whole computations in tested numerical examples. GNCP assigns the factorization tasks of each node in the truncation level to GPU. The data of each node in the truncation level are copied to the global memory of GPU and factorized entirely and independently by GPU one-by-one. Once factorization of any node in the truncation level has been completed, the cross-factorizations of this node to its ancestors and the following related operations are decoupled from other GPU tasks. These tasks are assigned to CPU threads with a reentrant pipelining strategy, accounting for about 35% of the whole calculations. Using this novel design, CPU and GPU are working concurrently and a large part of factorization is performed in overlapped time. Numerical tests for matrices from SuiteSparse matrix collection show higher performance than the well-known hybrid GPU-CPU solver CHOLMOD.

关键词： Sparse LDL T factorization GPU algorithm Hybrid GPU-CPU algorithm parallel algorithm Partition tree

来源：评论

学校读者我要写书评

暂无评论

HyLAC: Hybrid linear assignment solver in CUDA

引用

JOURNAL OF parallel AND DISTRIBUTED COMPUTING 2024年 187卷

作者： Kawtikwar, Samiran Nagi, Rakesh Univ Illinois Ind & Enterprise Syst Engn Champaign IL 61820 USA Singapore Univ Technol & Design Engn Syst & Design Singapore Singapore

The Linear Assignment Problem (LAP) is a fundamental combinatorial optimization problem with a wide range of applications. Over the years, significant progress has been made in developing efficient algorithms to solve the LAP, particularly in the realm of high-performance computing, leading to remarkable reductions in computation time. In recent years, hardware improvements in General Purpose Graphics Processing Units (GPGPUs) have shown promise in meeting the ever-increasing compute bandwidth requirements. This has attracted researchers to develop GPU-accelerated algorithms to solve the LAP. Recent work in the GPU domain has uncovered parallelism available in the problem structure to achieve significant performance improvements. However, each solution presented so far targets either sparse or dense instances of the problem and has some scope for improvement. The Hungarian algorithm is one of the most famous approaches to solving the LAP in polynomial time. Hungarian algorithm has classical O(N-4) (Munkres') and tree based O(N-3) (Lawler's) implementations. It is well established that the Munkres' implementation is faster for sparse LAP instances while the Lawler's implementation is faster for dense instances. In this work, we blend the GPU implementations of Munkres' and Lawler's to develop a Hybrid GPU-accelerated solver for LAP that switches between the two implementations based on available sparsity. Also, we improve the existing GPU implementations to reduce memory contention, minimize CPU-GPU synchronizations, and coalesced memory access. The resulting solver (HyLAC) works faster than existing CPU/GPU LAP solvers for sparse as well as dense problem instances. HyLAC achieves a speedup of up to 6.14x over existing state-of-the-art GPU implementation when run on the same hardware. We also develop an implementation to solve a list of small LAPs (tiled LAP), which is particularly useful in the optimization domain. This tiled LAP solver performs 22.59x faster than t

关键词： Hungarian algorithm Linear assignment problem GPU-accelerated graph algorithms High-performance computing parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

Decentralized energy trading framework for active distribution networks with multiple microgrids under uncertainty

引用

SCIENTIA IRANICA 2019年第6期26卷 3606-3621页

作者： Doostizadeh, M. Shakarami, M. R. Bastami, H. Lorestan Univ Fac Engn 5 Km Tehran RdPOB 68151-44316 Lorestan Iran

The ever-increasing need for more reliable power supply as well as cost-effective and environmentally friendly utilization of distributed energy resources will result in the formation of Multiple Micro-Grids (MMGs) in the near future of distribution system. To reach this prospect, coordination among MMGs is necessary. Accordingly, this paper proposes a new non-hierarchical multi-level architecture for the optimal scheduling of Active Distribution Network (ADN) with MMGs. The proposed model is a decentralized decision making algorithm to optimally coordinate the mutual interaction between local optimization problems of ADN and MMGs. A non-hierarchical Analytical Target Cascading (ATC) method is presented to solve the local optimization problems in parallel. Also, the underlying risks of energy trading caused by renewable generation uncertainty are reflected in both the objective functions and the constraints of local optimization problem. The numerical results of modified IEEE 33-bus distribution test system containing two micro-grids demonstrate the effectiveness and merits of the proposed model. (C) 2019 Sharif University of Technology. All rights reserved.

关键词： Active distribution network Analytical target cascading Decentralized energy trading Multiple microgrids parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-objective genetic algorithm for multi-view feature selection

引用

APPLIED SOFT COMPUTING 2024年 167卷

作者： Imani, Vandad Sevilla-Salcedo, Carlos Moradi, Elaheh Fortino, Vittorio Tohka, Jussi Univ Eastern Finland AI Virtanen Inst Mol Sci Kuopio Finland Univ Eastern Finland Inst Biomed Kuopio Finland Aalto Univ Dept Comp Sci Espoo Finland

Multi-view datasets offer diverse forms of data that can enhance prediction models by providing complementary information. However, the use of multi-view data leads to an increase in high-dimensional data, which poses significant challenges for the prediction models that can lead to poor generalization. Therefore, relevant feature selection from multi-view datasets is important as it not only addresses the poor generalization but also enhances the interpretability of the models. Despite the success of traditional feature selection methods, they have limitations in leveraging intrinsic information across modalities, lacking generalizability, and being tailored to specific classification tasks. We propose a novel genetic algorithm strategy to overcome these limitations of traditional feature selection methods for multi-view data. Our proposed approach, called the multi-view multi-objective feature selection genetic algorithm (MMFS-GA), simultaneously selects the optimal subset of features within a view and between views under a unified framework. The MMFS-GA framework demonstrates superior performance and interpretability for feature selection on multi-view datasets in both binary and multiclass classification tasks. The results of our evaluations on nine benchmark datasets, including synthetic and real data, show improvement over the best baseline methods. This work provides a promising solution for multi-view feature selection and opens up new possibilities for further research in multi-view datasets.

关键词： parallel algorithm Feature selection NSGA-II Multimodal Multi-objective Optimization

来源：评论

学校读者我要写书评

暂无评论

OVERVIEW OF THE SUPER DATABASE COMPUTER (SDC-I)

引用

IEICE TRANSACTIONS ON ELECTRONICS 1994年第7期E77C卷 1023-1031页

作者： KITSUREGAWA, M YANG, WK HIRANO, S HARADA, M NAKAMURA, M SUZUKI, K TAMURA, T TAKAGI, M Univ of Tokyo Tokyo Japan

This paper presents an overview of the SDC-I (Super Database Computer 1) developed at the University of Tokyo, Japan. The purpose of the project was to build a high performance SQL server which emphasizes query processing over transaction processing. Recently relational database systems tend to be used for heavy decision support queries, which include many join, aggregation, and order-by operations. At present high-end mainframes are used for these applications requiring several hours in some cases. While the system architecture for high traffic transaction processing systems is well established, that for adhoc query processing has not yet adequately understood. SDC-1 proved that a parallel machine could attain significant performance improvements over a conventional sequential machine through the exploitation of the high degree of parallelism present in relational query processing. A unique bucket spreading parallel hash join algorithm is employed in SDC, which makes the system very robust in the presense of data skew and allows SDC to attain almost linear performance scalability. SDC adopts a hybrid parallel architecture, where globally it is a shared nothing architecture, that is, modules are connected through the multistage network, but each module itself is a symmetric multiprocessor system. Although most of the hardware elements use commodity microprocessors for improved performance to cost, only the interconnection network incorporates the special function to support our parallel relational algorithm. Data movement over the memory and the network, rather than computation, is heavy for 1/0 intensive database processing. A dedicated software system was carefully designed for efficient data movement. The implemented prototype consists of two modules. Its hardware and software organization is described. The performance monitoring tool was developed to visualize the system activities, which showed that SDC-1 works very efficiently.

关键词： parallel MACHINE RELATIONAL DATABASE SQL parallel algorithm

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：