检索结果-内蒙古大学图书馆

Load Balancing a Multi-Block Grids-based Application on Heterogeneous Platform

学校读者我要写书评

暂无评论

Load Balancing a Multi-Block Grids-based Application on Hete...

IEEE International Conference on Computational Science and Engineering, CSE

作者： Yonggang Che Chuanfu Xu Zhenghua Wang Institute for Quantum Information & State Key Lab. of High Performance Computing College of Computer National University of Defense Technology Changsha China Science and Technology on Parallel and Distributed Processing Lab National University of Defense Technology Changsha China

ISBN: (数字)9781665403986

ISBN: (纸本)9781665403993

This paper presents a load balancing method for a multi-block grids-based CFD (Computational Fluid Dynamics) application on heterogeneous platform. This method includes an asymmetric task scheduling scheme and a load balancing model. The idea is to balance the computing speed between the CPU and the coprocessor by adjusting the workload and the numbers of threads on both sides. Optimal load balance parameters are empirically selected, guided by a performance model. performance evaluation is conducted on a computer server consists of two Intel Xeon E5-2670 v3 CPUs and two MIC coprocessors (Xeon Phi 5110P and Xeon Phi 7120P) for the simulation of turbulent combustion in a supersonic combustor. The results show that the performance is highly sensitive to the load balance parameters. With the optimal parameters, the heterogeneous computing achieves a maximum speedup of 2.30 × for a 6-block mesh, and a maximum speedup of 2.66 × for a 8-block mesh, over the CPU-only computing.

关键词： Computational modeling Computational fluid dynamics Load management Servers Task analysis Load modeling Coprocessors

high order residual distribution conservative finite difference HWENO scheme for steady state problems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lin, Jianfang Ren, Yupeng Abgrall, Rémi Qiu, Jianxian School of Mathematical Sciences Zhejiang University Zhejiang Hangzhou310058 China School of Mathematical Sciences Xiamen University Fujian Xiamen361005 China Institute of Mathematics University of Zurich Zurich8057 Switzerland School of Mathematical Sciences Fujian Provincial Key Laboratory of Mathematical Modeling and High-Performance Scientific Computing Xiamen University Fujian Xiamen361005 China

In this paper, we develop a high order residual distribution (RD) method for solving steady state conservation laws in a novel Hermite weighted essentially non-oscillatory (HWENO) framework recently developed in [24]. In particular, we design a high order HWENO integration for the integrals of source term and fluxes based on the point value of the solution and its spatial derivatives, and the principles of residual distribution schemes are adapted to obtain steady state solutions. Two advantages of the novel HWENO framework have been shown in [24]: first, compared with the traditional HWENO framework, the proposed method does not need to introduce additional auxiliary equations to update the derivatives of the unknown variable, and just compute them from the current point value of the solution and its old spatial derivatives, which saves the computational storage and CPU time, and thereby improve the computational efficiency of the traditional HWENO framework. Second, compared with the traditional WENO method, reconstruction stencil of the HWENO methods becomes more compact, their boundary treatment is simpler, and the numerical errors are smaller at the same grid. Thus, it is also a compact scheme when we design the higher order accuracy, compared with that in [11] Chou and Shu proposed. Extensive numerical experiments for one- and two-dimensional scalar and systems problems confirm the high order accuracy and good quality of our scheme. Copyright © 2021, The Authors. All rights reserved.

关键词： Physical properties

Networked Robotic System Simulation Platform: Hardware-in-the-Loop Architecture, Enabling Technologies and Implementations

学校读者我要写书评

暂无评论

Networked Robotic System Simulation Platform: Hardware-in-th...

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Han Han Wei Gao Honglei Yan Jiajun Bai Jun Cai Xiaolei Wang Bo Zhang Jinlin Peng Xiaodong Yi Yuhua Tang National Innovation Institute of Defense Technology Beijing P.R.China Tianjin Artificial Intelligence Innovation Center Tianjin P.R.China State Key Laboratory of High Performance Computing National University of Defense Technology Changsha P.R.China

ISBN: (数字)9781728172361

ISBN: (纸本)9781728172378

The recent progress in robotic communications and networking demands novel simulation platforms for development and verification, especially for deep-coupled control and communication co-design in networked robotic systems (NRS). This paper analyzes the challenges and requirements of robotic communications and networking simulations. It is shown that the popular tools of software simulation and field test may hardly fulfil the fidelity, reproductivity and flexibility demands. Therefore, this paper proposed a novel hardware-in-the-loop (HIL) architecture for networked robotic system simulation platform (NRS-SP), which may strike a beneficial tradeoff between fidelity, reproductivity and flexibility. The enabling technologies of NRS-SP are discussed and a full-fledged prototype is implemented to illustrates its potential to support the simulation, development and verification of next generation networked robotic systems.

关键词： Robots Computational modeling Wireless communication Computer architecture Software Protocols Prototypes

An Actor-based Programming Framework for Swarm Robotic Systems

学校读者我要写书评

暂无评论

An Actor-based Programming Framework for Swarm Robotic Syste...

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Wei Yi Bin Di Ruihao Li Huadong Dai Xiaodong Yi Yanzhen Wang Xuejun Yang Artificial Intelligence Research Center (AIRC) National Innovation Institute of Defense Technology (NIIDT) Beijing China Tianjin ArtiFIcial Intelligence Innovation Center (TAIIC) Tianjin China State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changesha China

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

Programming cooperative tasks for autonomous swarm robotic systems has always been challenging. In this paper, we introduce a concept `Actor', as a virtualization for robot platforms. Every robot platform in the swarm robotic system carries out the task and interacts with others as an Actor. We designed an Actor-based framework for the management of autonomous swarm robotic systems including modules and interfaces for the Actor, the collective Actor, and task management. The Actor-based framework enables task developers to explicitly model cooperative tasks without intricacies about the detailed robotic algorithms or the specific robot brands, and eases the burden on robotic algorithm developers by providing common functionalities. The proposed framework is implemented in C++ and validated quantitatively and qualitatively with a swarm of thirty drones by simulations and a swarm of ten drones by in-field tests.

关键词： Swarm robotics C++ languages Programming Task analysis Virtualization Intelligent robots Drones

Pseudoinverse-free randomized block iterative algorithms for consistent and inconsistent linear systems

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Du, Kui Sun, Xiao-Hui School of Mathematical Sciences Fujian Provincial Key Laboratory of Mathematical Modeling and High Performance Scientific Computing Xiamen University Xiamen361005 China School of Mathematical Sciences Xiamen University Xiamen361005 China

Randomized iterative algorithms have attracted much attention in recent years because they can approximately solve large-scale linear systems of equations without accessing the entire coefficient matrix. In this paper, we propose two novel pseudoinverse-free randomized block iterative algorithms for solving consistent and inconsistent linear systems. The proposed algorithms require two user-defined random matrices: one for row sampling and the other for column sampling. We can recover the well-known doubly stochastic Gauss-Seidel, randomized Kaczmarz, randomized coordinate descent, and randomized extended Kaczmarz algorithms by choosing appropriate random matrices used in our algorithms. Because our algorithms allow for a much wider selection of these two random matrices, a number of new specific algorithms can be obtained. We prove the linear convergence in the mean square sense of our algorithms. Numerical experiments for linear systems with synthetic and real-world coefficient matrices demonstrate the efficiency of some special cases of our *** Codes 65F10, 65F20, 15A06 Copyright © 2020, The Authors. All rights reserved.

关键词： Linear systems

Randomized double and triple Kaczmarz for solving extended normal equations

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Du, Kui Sun, Xiao-Hui School of Mathematical Sciences Fujian Provincial Key Laboratory of Mathematical Modelling and High Performance Scientific Computing Xiamen University Xiamen361005 China School of Mathematical Sciences Xiamen University Xiamen361005 China

The randomized Kaczmarz algorithm has received considerable attention recently because of its simplicity, speed, and the ability to approximately solve large-scale linear systems of equations. In this paper we propose randomized double and triple Kaczmarz algorithms to solve extended normal equations of the form A>Ax = A>b − c. The proposed algorithms avoid forming A>A explicitly and work for arbitrary A ∈ Rm×n (full rank or rank deficient, m ≥ n or m Copyright © 2020, The Authors. All rights reserved.

关键词： Linear systems

Relating the total domination number and the annihilation number for quasi-trees and some composite graphs

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hua, Hongbo Hua, Xinying Klavžar, Sandi Xu, Kexiang Faculty of Mathematics and Physics Huaiyin Institute of Technology Jiangsu Huai’an223003 China College of Mathematics Nanjing University of Aeronautics & Astronautics Jiangsu Nanjing210016 China MIIT Key Laboratory of Mathematical Modelling and High Performance Computing of Air Vehicles Nanjing210016 China Faculty of Mathematics and Physics University of Ljubljana Slovenia Institute of Mathematics Physics and Mechanics Ljubljana Slovenia Faculty of Natural Sciences and Mathematics University of Maribor Slovenia

The total domination number γt(G) of a graph G is the cardinality of a smallest set D ⊆ V (G) such that each vertex of G has a neighbor in D. The annihilation number a(G) of G is the largest integer k such that there exist k different vertices in G with the degree sum at most m(G). It is conjectured that γt(G) ≤ a(G) + 1 holds for every nontrivial connected graph G. The conjecture has been proved for graphs with minimum degree at least 3, trees, certain tree-like graphs, block graphs, and cactus graphs. In the main result of this paper it is proved that the conjecture holds for quasi-trees. The conjecture is verified also for some graph constructions including bijection graphs, Mycielskians, and the newly introduced universally-identifying graphs. © 2021, CC BY-SA.

关键词： Graphic methods

Single-pass randomized QLP decomposition for low-rank approximation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ren, Huan Bai, Zheng-Jian School of Mathematical Sciences Xiamen University Xiamen360015 China School of Mathematical Sciences Fujian Provincial Key Laboratory on Mathematical Modeling & High Performance Scientific Computing Xiamen University Xiamen361005 China

The QLP decomposition is one of the effective algorithms to approximate singular value decomposition (SVD) in numerical linear algebra. In this paper, we propose some single-pass randomized QLP decomposition algorithms for computing the low-rank matrix approximation. Compared with the deterministic QLP decomposition, the complexity of the proposed algorithms does not increase significantly and the system matrix needs to be accessed only once. Therefore, our algorithms are very suitable for a large matrix stored outside of memory or generated by stream data. In the error analysis, we give the bounds of matrix approximation error and singular value approximation error. Numerical experiments also reported to verify our results. key words: QLP decomposition, randomized algorithm, single-pass, singular value, low-rank approximation Copyright © 2020, The Authors. All rights reserved.

关键词： Singular value decomposition

On pole-zero assignment of vibratory systems by multi-input feedback control

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bai, Zheng-Jian Wang, Yang School of Mathematical Sciences Fujian Provincial Key Laboratory on Mathematical Modeling & High Performance Scientific Computing Xiamen University Xiamen361005 China School of Mathematical Sciences Xiamen University Xiamen361005 China

In this paper, we consider the pole-zero assignment problem for vibratory systems via multi-input feedback control. We propose a multi-step two-stage approach for solving the multi-input pole-zero assignment problem. We first reformulate the assignment problem as a multi-step single-input pole-zero assignment problem. Then, in each step, we propose a two-stage approach for solving the single-input pole-zero assignment problem. In the first stage, based on the measured receptances, we replace the selected zeros of the prescribed open-loop point receptance to the desired locations, where we need to solve a small underdetermined linear equation for finding the corresponding columns of the feedback matrices. In the second stage, by using linear matrix inequalities, the complete closed-loop poles are assigned to the prescribed subregion of the complex left-hand plane. Finally, we give some numerical examples to demonstrate the effectiveness of our *** Codes 65F18 Copyright © 2020, The Authors. All rights reserved.

关键词： Combinatorial optimization