检索结果-内蒙古大学图书馆

Lattice Boltzmann model and its gpu acceleration for transient flow in channel and pressurized pipe combined water delivery system

引用

APPLIED WATER SCIENCE 2025年第3期15卷 1-15页

作者： Meng, Wanwan Yang, Shuqing Lu, Xuheng Peng, Yongqin Diao, Wei Zhang, Chunze Chongqing Jiaotong Univ Southwest Res Inst Hydraul & Water Transport Engn Chongqing 400016 Peoples R China Wuhan Univ State Key Lab Water Resources & Hydropower Engn Sc Wuhan 430072 Peoples R China Chongqing Hongtai Registered Safety Engineer Firm Chongqing 400000 Peoples R China Chongqing Xike Water Transport Engn Consulting Co Chongqing 400010 Peoples R China

The open channel and pressurized pipe combined water delivery systems usually have long pipelines, many overflow structures, and especially with two different flow regimes, making the transient simulations complicated and time-consuming. A graphics processing unit (gpu)-accelerated lattice Boltzmann model (LBM) is proposed to solve the above problem. The LBM model for water hammer in pipes is improved by introducing the one dimensional with two lattice velocities discrete model (D1Q2). Compared with the existing the one dimensional with three lattice velocities discrete model, the D1Q2 model has reduced the occupation of computational resources, and the boundary processing has become simple. By simulating the transient process of a pipe network system, the results are in good agreement with those of the method of characteristics (MOC), and the speedup ratio reaches 60.5. Then, the water hammer LBM model and shallow water LBM model are coupled to simulate the transient process of the open channel and pressurized pipe combined water delivery system, and its gpu parallel computing scheme is achieved. Practical application shows that the results agree well with those of MOC, and the maximum speedup ratio reaches 92.96, indicating the great application potential of the proposed model.

关键词： The open channel and pressurized pipe combined water delivery system Transient simulation LBM gpu parallel computing Speedup ratio

来源：评论

学校读者我要写书评

暂无评论

Ray tracing core accelerated high performance implementation for infrared radiation signature simulation using reverse Monte Carlo method

引用

INTERNATIONAL JOURNAL OF THERMAL SCIENCES 2025年 214卷

作者： Liu, Jiaan Eri, Qitai Kong, Bo Huang, Jifeng Zhou, Yue Beihang Univ Sch Energy & Power Engn Beijing 100191 Peoples R China Natl Key Lab Scattering & Radiat Beijing 100854 Peoples R China

Infrared radiation signature is a key characteristic of target and useful for many inverse analyses. Specially, infrared radiation signature simulation plays an increasingly important role in the field of stealth design of airvehicle and target identification. To improve the simulation efficiency while ensure accuracy, this study presents two novel implementations based on reverse Monte Carlo method. For the first time, hardware ray tracing cores (RT cores) are leveraged to accelerate infrared calculation considering heterogeneous participating media and walls, which is the key innovation compared to the conventional method that only using CUDA cores for acceleration. The first novel method, termed RT method, determines the intersections using bounding volume hierarchy tree (BVH) that implemented on RT cores throughout computational process. Whereas the other, termed CUDA-RT method, determines the intersections between rays and boundaries based on BVH tree that implemented on RT cores, other intersection calculations are done with the help of the adjacency relationships between the grids and are implemented on CUDA cores. Additionally, an improved ray-intersection method is proposed to address complex meshes. A comparison between the numerical and experimental infrared radiation signatures of a rocket-plume case showed the high accuracy of the novel methods. Moreover, a series of numerical examples indicate that both novel methods significantly improved the computational efficiency. Specifically, the CUDA-RT method has the minimum calculation time, approximately 10 % of the reference method with a small additional gpu memory overhead, facilitating improved stealth design and target identification capabilities.

关键词： Infrared radiation signature simulation Reverse Monte Carlo method gpu parallel computing Ray tracing core

来源：评论

学校读者我要写书评

暂无评论

Review on gpu accelerated methods for genome-wide SNP-SNP interactions

引用

MOLECULAR GENETICS AND GENOMICS 2025年第1期300卷 1-19页

作者： Ren, Wenlong Liang, Zhikai Nantong Univ Sch Publ Hlth Dept Epidemiol & Med Stat Nantong 226019 Peoples R China North Dakota State Univ Dept Plant Sci Fargo ND 58108 USA

Detecting genome-wide SNP-SNP interactions (epistasis) efficiently is essential to harnessing the vast data now available from modern biobanks. With millions of SNPs and genetic information from hundreds of thousands of individuals, researchers are positioned to uncover new insights into complex disease pathways. However, this data scale brings significant computational and statistical challenges. To address these, recent approaches leverage gpu-based parallel computing for high-throughput, cost-effective analysis and refine algorithms to improve time and memory efficiency. In this survey, we systematically review gpu-accelerated methods for exhaustive epistasis detection, detailing the statistical models used and the computational strategies employed to enhance performance. Our findings indicate substantial speedups with gpu implementations over traditional CPU approaches. We conclude that while gpu-based solutions hold promise for advancing genomic research, continued innovation in both algorithm design and hardware optimization is necessary to meet future data challenges in the field.

关键词： gpu parallel computing SNP-SNP interaction Epistasis Large biobank GWAS

来源：评论

学校读者我要写书评

暂无评论

SPH simulation for 3D non-isothermal injection molding filling process using gpu acceleration

引用

COMPUTATIONAL PARTICLE MECHANICS 2025年第2期12卷 1319-1333页

作者： Liu, Yunpu Ren, Mengke Gu, Junfeng Li, Zheng Ruan, Shilun Shen, Changyu Dalian Univ Technol Dept Engn Mech State Key Lab Struct Anal Optimizat & CAE Software Dalian 116024 Peoples R China Dalian Univ Technol Zhengzhou Coll Zhengzhou 450016 Peoples R China Zhengzhou Univ Sch Mat Sci & Engn Key Lab Mat Proc & Mold Minist Educ Zhengzhou 450002 Peoples R China

The nature of high viscosity and pressure in the injection molding process poses a great challenge for numerical simulation in terms of numerical stability, especially when using particle-based meshless methods. In the present work, 3D filling stage of injection molding is simulated using smoothed particle hydrodynamics (SPH) method. To counter the instability caused by high viscosity and pressure, various methods including a new non-penetration boundary treatment, modified low-dissipation Riemann solver, kernel gradient correction and particle shift technique are applied. gpu parallel computing is achieved by using Taichi language to boost computing efficiency. 3D non-isothermal injection molding process is performed for rectangular cavity, tensile test specimen and a customized transparent injection mold which we intend to perform visual injection experiment to verify our simulation in future work. The properties of flow field such as pressure and velocity are shown and compared with Moldflow simulation. The results of our simulation show good agreement with Moldflow.

关键词： Injection molding Smoothed particle hydrodynamics gpu parallel computing

来源：评论

学校读者我要写书评

暂无评论

Accelerated gpu computing Technology for parallel Management Systems

Accelerated GPU Computing Technology for Parallel Management...

引用

8th World Congress on Intelligent Control and Automation (WCICA)

作者： Cui, Feng Cheng, Changjian Wang, Feiyue Wei, Wei Li, Lefei Zou, Yumin Chinese Acad Sci Inst Automat Key Lab Complex Syst & Intelligent Sci Beijing Peoples R China Tsinghua Univ Dept Ind Engn Beijing Peoples R China Sinopec Maoming Co Maoming Guangdong Peoples R China

ISBN: (纸本)9781424467129

gpu (Graphic Processing Unit) has the feature of a strong floating-point computing capability, suitable for large-scale intensive computing. This paper applies gpu acceleration technology for the parallel management of complex production system, focusing on the computing of human behavior based on fuzzy logic and equipment safety assessment of Monte Carlo algorithm. The implementation process of the gpu parallel computing on two kinds of algorithms are discussed in detail and the optimization method is proposed. With the experimental comparison, the accelerated calculation of gpu relative to CPU achieves a 47-fold.

关键词： gpu parallel computing parallel management Complex production system Fuzzy logic Monte Carlo method

来源：评论

学校读者我要写书评

暂无评论

gpu-based cracking simulations for scratch resistance evaluation of composite coatings

引用

COMPOSITE STRUCTURES 2025年 357卷

作者： Yang, Hanming Zou, Chenqi Chen, Gong Imamura, Toshiyuki Tan, Yiyu Zang, Mengyan Chen, Shunhua South China Univ Technol Sch Mech & Automot Engn Guangzhou Peoples R China Sun Yat Sen Univ Sch Ocean Engn & Technol Zhuhai Peoples R China Southern Marine Sci & Engn Guangdong Lab Zhuhai Zhuhai Peoples R China RIKEN Ctr Computat Sci Kobe Japan Iwate Univ Dept Syst Innovat Engn Iwate Japan Fuyao Inst Adv Study Fuzhou Peoples R China

Although current simulation methods enable modeling of scratch-induced damage in coating structures to facilitate new coating designs, the widespread reliance on serial computation frequently yields low computing efficiency, thereby hindering the progress of coating development. To address this issue, this study develops a graphics processing unit (gpu)-based parallel computational framework to efficiently solve the scratch-induced cracking problem of composite coatings. This framework integrates rate-dependent constitutive and fracture models, a moving contact space-LC-Grid contact algorithm (MCS-LCCA), and the tied interface method to accurately describe the scratch-induced cracking of the polymeric coatings while enhancing computational efficiency. Through specific parallel strategies and optimization methods, the framework maximizes gpu performance while ensuring computational stability. With the aid of this computational framework, scratch- induced cracking simulations of an original-scale automotive coating model are achieved for the first time, boasting a speed-up ratio of approximately 279 compared to serial computing. The simulations successfully replicate the initiation and propagation of cracks observed in the scratch experiments. By comparing the simulation results with experimental outcomes, the mechanism of scratch cracking is investigated and revealed. Finally, a series of parametric studies are conducted to examine the impacts of key parameters, i.e., coating constitutive properties, fracture mechanics characteristics, layer thickness, and surface friction coefficient, on scratch-induced cracking. Such fundamental analysis may provide insights for advancing scratch-resistant composite coating technology.

关键词： gpu parallel computing Scratch-induced cracking Composite coatings Contact method Scratch resistance evaluation

来源：评论

学校读者我要写书评

暂无评论

Plausible mass-spring system using parallel computing on mobile devices

引用

HUMAN-CENTRIC computing AND INFORMATION SCIENCES 2016年第1期6卷 1页

作者： Hong, Min Jeon, Jae-Hong Yum, Hyo-Sub Lee, Seung-Hyun Soonchunhyang Univ Dept Comp Software Engn 22 Soonchunhyang Ro Asan South Korea EZIOT Suwon South Korea Bluecore Corp Strategy & Planning Team 4F326 Bongeunsa Ro Seoul South Korea Hongik Univ Coll Sci & Technol Sch Architectural Engn 2639 Sejong Ro Sejong South Korea

Recently the hardware performance of mobile devices have been extremely increased and advanced mobile devices provide multi-cores and high clock speed. In addition, mobile devices have advantages in mobility and portability compared with PC and Console, so many games and simulation programs have been developed under mobile environments. Physically-based simulation is a one of the key issues for deformable object modeling which is widely used to represent the realistic expression of 3D soft objects with tetrahedrons for game and 3D simulation. However, it requires high computation power to plausibly and realistically represent the physical behaviors and interactions of deformable objects. In this paper, we implemented parallel cloth and mass-spring simulation using graphics processing unit (gpu) with OpenCL and multi-threaded central processing unit ( CPU) on a mobile device. We applied CPU and gpu parallel computing technique into spring force computation and integration methods such as Euler, Midpoint, 4th-order Runge-Kutta to optimize the computational burden of dynamic simulation. The integration methods compute the next step of positions and velocities in each node. In this paper, we tested the performance analysis for the spring force calculation and integration method process using CPU only, multi-threaded CPU, and gpu on mobile device respectively. Our experimental results concluded that the calculation using proposed multi-threaded CPU and gpu multi-threaded CPU are much faster than using just the CPU only.

关键词： Mass-spring system Deformable object gpu parallel computing

来源：评论

学校读者我要写书评

暂无评论

Efficient Massive computing for Deformable Volume Data Using Revised parallel Resampling

引用

SENSORS 2022年第16期22卷 145-152页

作者： Park, Chailim Kye, Heewon Hansung Univ Div Comp Engn Seoul 02876 South Korea

In this paper, we propose an improved parallel resampling technique. parallel resampling is a deformable object generation method based on volume data applied to medical simulations. Existing parallel resampling is not suitable for massive computing, because the number of samplings is high and floating-point precision problems may occur. This study addresses these problems to obtain improved user latency when performing medical simulations. Specifically, instead of interpolating values after volume sampling, the efficiency is improved by performing volume sampling after coordinate interpolation. Next, the floating-point error in the calculation of the sampling position is described, and the advantage of barycentric interpolation using a reference point is discussed. The experimental results showed a significant improvement over the existing method. Volume data comprising more than 600 images used in clinical practice were deformed and rendered at interactive speed. In an Internet of Everything environment, medical imaging systems are an important application, and simulation image generation is also valuable in the overall system. Through the proposed method, the performance of the whole system can be improved.

关键词： massive computing for volume deformation parallel resampling gpu parallel computing low-latency image generation IoE medical simulation

来源：评论

学校读者我要写书评

暂无评论

Numerical simulation of borehole compressional wave and shear wave in 3D vug formation

引用

JOURNAL OF APPLIED GEOPHYSICS 2024年 228卷

作者： Zhang, Zhitao Wang, Zhuwen Han, Ruiyi Cui, Yitong Qi, Xinghua Guo, Yuhang Jilin Univ Coll Geoexplorat Sci & Technol 938 Ximinzhu St Changchun 130046 Peoples R China

The staggered grid finite difference method (SGFDM) of a monopole source is used to simulate a threedimensional vug reservoir model and study the effect of acoustic logging responses of different vug models on radial probing depth. The results show that the first arrival of the head wave peak of the compressional wave (Pwave) and the shear wave (S-wave) is unrelated to the radius of the vug, and the amplitude of the head wave peak of the P-wave and S-wave decreases as the vug volume increases. Compared with the volume change of the vug, the radial distance from the vug wall has little influence, while the vertical source distance has large influence on the P-wave and S-wave. When there are multiple vugs in the model, the amplitudes of the P-wave and S-wave head wave peaks change sinusoidally with the angle between the vugs. The ellipsoidal vug model with the same volume has a greater influence on the P-wave and S-wave than the spherical vug model. In the ellipsoidal vug model, the axial vug size has a greater impact on the first arrival of the head wave peak, while the radial vug size significantly influences the amplitude of the head wave peak. Finally, we validate the numerical simulation conclusions by comparing them with actual logging data responses in complex formations, demonstrating the practical value of the elastic wave response simulations for vugs.

关键词： Numerical modeling Vug-bearing formation Body waves gpu parallel computing Wave scattering and diffraction

来源：评论

学校读者我要写书评

暂无评论

A comparative study of three-dimensional discrete velocity set in LBM for turbulent flow over bluff body

引用

JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING 2021年第1期43卷 1-11页

作者： Agarwal, Alankar Gupta, Sandeep Prakash, Akshay Indian Inst Technol Dept Mech Engn Jodhpur 342037 Rajasthan India Indian Inst Technol Dept Aerosp Engn Kharagpur 721302 W Bengal India

The work presented in this paper investigates the efficiency of various (i.e., D3Q15, D3Q19, and D3Q27) three-dimensional discrete velocity models of lattice Boltzmann method (LBM) for the simulation of turbulent flow past over a bluff body. The numerical setup consists of a square cylinder confined in a rectangular duct. Large eddy simulation (LES) model has been used for the simulation of turbulent eddies. The small-scale turbulent structures were resolved by using the conventional Smagorinsky subgrid-scale (SGS) model. The computations have been carried out on a uniform Cartesian grid. The results for different turbulent statistics have presented and compared with the available experimental and previous numerical (based on finite volume approach) results for Reynolds number Red=3000. The algorithm developed for the present simulation has been parallelized to run on Graphical Processing Unit (gpu) parallel platform.

关键词： Lattice Boltzmann method Discrete velocity models Turbulent flow gpu parallel computing

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：