检索结果-内蒙古大学图书馆

High-speed TCP flow record extraction using gpus

JOURNAL OF SUPERcomputing 2015年第10期71卷 3851-3876页

作者： Roquero, Paula Ramos, Javier Moreno, Victor Gonzalez, Ivan Aracil, Javier Univ Autonoma Madrid EPS Dept Tecnol Elect & Comunicac E-28049 Madrid Spain

Traffic analysis is an essential part of capacity planning, quality of service assurance, and reinforcement of security in current telecommunication networks. Traffic volume increases with network speed and the analysis of large traffic traces is computationally intensive. The paper presents, for the first time ever, a flow extraction software that allows to obtain complex TCP-aware flow records at 4.4 millions of packets per second in a single gpu. Such TCP flow records include number of retransmissions and duplicates per flow, whose calculation is very challenging to obtain at high-speed. Our software significantly increases the processing performance of the recently proposed high-speed sniffers based on commodity hardware and demonstrates the advantages of applying massively parallel processing devices for traffic analysis.

关键词： gpu parallel computing Traffic analysis and parallel computing Commodity hardware for traffic sniffing

来源：评论

学校读者我要写书评

暂无评论

Optimized parallel implementation of face detection based on gpu component

引用

MICROPROCESSORS AND MICROSYSTEMS 2015年第6期39卷 393-404页

作者： Chouchene, Marwa Sayadi, Fatma Ezahra Bahri, Haythem Dubois, Julien Miteran, Johel Atri, Mohamed Fac Sci Monastir Lab Elect & Microelect EuE Monastir Tunisia Burgundy Univ Lab Elect Informat & Image LE2I Dijon France

Face detection is an important aspect for various domains such as: biometrics, video surveillance and human computer interaction. Generally a generic face processing system includes a face detection, or recognition step, as well as tracking and rendering phase. In this paper, we develop a real-time and robust face detection implementation based on gpu component. Face detection is performed by adapting the Viola and Jones algorithm. We have developed and designed optimized several parallel implementations of these algorithms based on graphics processors gpu using CUDA (Compute Unified Device Architecture) description. First, we implemented the Viola and Jones algorithm in the basic CPU version. The basic application is widened to gpu version using CUDA technology, and freeing CPU to perform other tasks. Then, the face detection algorithm has been optimized for the gpu using a grid topology and shared memory. These programs are compared and the results are presented. Finally, to improve the quality of face detection a second proposition was performed by the implementation of WaldBoost algorithm. (C) 2015 Elsevier B.V. All rights reserved.

关键词： gpu parallel computing Face detection Viola and Jones algorithm Ada Boost Wald Boost CUDA optimization

来源：评论

学校读者我要写书评

暂无评论

gpu parallel strategy for parameterized LSM-based topology optimization using isogeometric analysis

引用

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION 2017年第2期56卷 413-434页

作者： Xia, Zhaohui Wang, Yingjun Wang, Qifu Mei, Chao Rensselaer Polytech Inst Ctr Modeling Simulat & Imaging Med CeMSIM Troy NY 12180 USA South China Univ Technol Sch Mech & Automot Engn Guangzhou 510641 Guangdong Peoples R China Huazhong Univ Sci & Technol Natl CAD Support Software Engn Res Ctr Wuhan 430074 Hubei Peoples R China

This paper proposes a new level set-based topology optimization (TO) method using a parallel strategy of Graphics Processing Units (gpus) and the isogeometric analysis (IGA). The strategy consists of parallel implementations for initial design domain, IGA, sensitivity analysis and design variable update, and the key issues in the parallel implementation, e.g., the parallel assembly race condition, are discussed in detail. The computational complexity and parallelization of the different steps in the TO are also analyzed in this paper. To better demonstrate the advantages of the proposed strategy, we compare efficiency of serial CPU, multi-thread parallel CPU and gpu by benchmark examples, and the speedups achieve two orders of magnitude.

关键词： Isogeometric analysis Topology optimization Level set method CUDA gpu parallel computing

来源：评论

学校读者我要写书评

暂无评论

Split-bucket partition (SBP): a novel execution model for top-K and selection algorithms on gpus

引用

JOURNAL OF SUPERcomputing 2024年第11期80卷 15122-15160页

作者： Yang, Yiqing Zhang, Guoyin Wu, Yanxia Zhao, Zhixiang Fu, Yan Harbin Engn Univ Dept Comp Sci Harbin 150001 Heilongjiang Peoples R China

Top-K and selection operations are critical in data processing and analysis, and their efficient implementation on gpus is increasingly important due to the growing demands of data analysis. Existing methods, primarily relying on the bucket partition execution model, encounter challenges such as uneven bucket distribution and latency in merging processes. To address these issues, we introduce a novel Split-Bucket Partition (SBP) execution model that specifically addresses these challenges. Additionally, we propose task and control flow optimizations targeted at top-K and selection algorithms, which further contribute to performance improvements. Our optimized algorithms significantly outperform existing approaches, delivering performance gains of up to 2.3 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$2.3$$\end{document} times and 1.6 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1.6$$\end{document} times for different bucket partitioning rules. Our algorithms show robust performance improvements in non-uniform data scenarios, with gains ranging from 1.9 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1.9$$\end{document} times to 15.5 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$15.5$$\end{document} times. However, it should be noted that the SB

关键词： Bucket partition Top-K algorithms Selection algorithms gpu parallel computing

来源：评论

学校读者我要写书评

暂无评论

Large scale multi-gpu based parallel traffic simulation for accelerated traffic assignment and propagation

引用

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES 2024年 169卷

作者： Jiang, Xuan Sengupta, Raja Demmel, James Williams, Samuel Univ Calif Berkeley Dept Civil & Environm Engn Berkeley CA 94709 USA Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94709 USA Lawrence Berkeley Natl Lab Performance & Algorithms Res Grp Berkeley CA 94720 USA

Traffic simulation is a critical tool for congestion analysis, travel time estimation, and route optimization in urban planning, benefiting navigation apps, transportation network companies, and state agencies. Traditionally, traffic micro-simulation frameworks are based on road segments and can only support a limited number of main roads. Efficient traffic simulation on a regional scale remains a significant challenge due to the complexity of urban mobility and the large scale of spatiotemporal data. This paper introduces a Large Scale Multi-gpu parallel computing based Regional Scale Traffic Simulation Framework (LPSim), which leverages graphical processing unit (gpu) parallel computing to address these challenges. LPSim utilizes a multi-gpu architecture to simulate extensive and dynamic traffic networks with high fidelity and reduced computation time. Using the parallel processing capabilities of gpus, LPSim can perform tens of millions of individual vehicle dynamics simulations simultaneously, significantly outperforming traditional CPU-based approaches. The framework is designed to be scalable and can easily accommodate the increasing complexity of traffic simulations. We present the theory behind gpu-based traffic simulation, the architecture of single- and multi-gpu based simulations, and the graph partition strategies that enhance computation resource load balance. Our experimental results demonstrate the effectiveness of LPSim in simulating large-scale traffic scenarios. LPSim is capable of completing simulations of 2.82 million trips in just 6.28 min on a single gpu machine equipped with 5120 CUDA cores (Tesla V100-SXM2). Furthermore, utilizing a Google Cloud instance with two NVIDIA V100 gpus, which collectively offer 10240 CUDA cores, LPSim successfully simulates 9.01 million trips within 21.16 min. We further tested our simulator with the same demand on dual NVIDIA A100-PCIE-40GB gpus, which finished the simulation in 0.0398 h, approximately 113 times f

关键词： Regional-scale traffic simulation framework gpu parallel computing Graph partitioning Roofline model Digital virtual transport

来源：评论

学校读者我要写书评

暂无评论

Monte Carlo calibration to implied volatility surface under volatility models

引用

JAPAN JOURNAL OF INDUSTRIAL AND APPLIED MATHEMATICS 2017年第3期34卷 763-778页

作者： Han, Chuan-Hsiang Kuo, Chien-Liang Natl Tsing Hua Univ Dept Quantitat Finance 101Sect 2Kuang Fu Rd Hsinchu 300 Taiwan KGI Bank Dept Global Trading 125Sect 5Nanjing East Rd Taipei 10504 Taiwan

The calibration problem of implied volatility surface under complex financial models can be formulated as a nonlinear high-dimensional optimization problem. To resolve this problem for genuine volatility models, we develop a sequential methodology termed two-stage Monte Carlo calibration method. It consists of the first stage-dimension separation for splitting parametric set into two subsets, and the second stage-standard error reduction for efficient evaluation of option prices. The first stage dimension separation aims to reduce dimensionality of the optimization problem by estimating some volatility model parameters a priori under the historical probability measure such that the total number of model parameters under an option pricing measure is significantly reduced. The second stage standard error reduction aims simultaneously to reduce variance of option payoffs by the martingale control variate algorithm, and to increase the total number of Monte Carlo simulation by the hardware graphics processing unit (gpu) for parallel computing. This two-stage Monte Carlo calibration method is capable of solving a variety of complex volatility models, including hybrid models and multifactor stochastic volatility models. Essentially, it provides a general framework to analyze backward information from the historical spot prices and the forward information from option prices.

关键词： Implied volatility surface Multi-factor stochastic volatility model Hybrid model Fourier transform method Monte Carlo simulation Standard error reduction Martingale control variate gpu parallel computing

来源：评论

学校读者我要写书评

暂无评论

Fast Gap-Filling of Massive Data by Local-Equilibrium Conditional Simulations on gpu

引用

MATHEMATICAL GEOSCIENCES 2024年第3期56卷 573-603页

作者： Lach, M. Zukovic, M. Pavol Jozef Safarik Univ Kosice Inst Phys Fac Sci Dept Theoret Phys & Astrophys Pk Angelinum 9 Kosice Slovakia

The ever-growing size of modern space-time data sets, such as those collected by remote sensing, requires new techniques for their efficient and automated processing, including gap-filling of missing values. Compute Unified Device Architecture-based parallelization on graphics processing units (gpus) has become a popular way to dramatically increase the computational efficiency of various approaches. Recently, a computationally efficient and competitive yet simple spatial prediction approach inspired by statistical physics models, called the modified planar rotator method, was proposed. Its gpu implementation allowed additional impressive computational acceleration exceeding two orders of magnitude in comparison with central processing unit calculations. In the current study, a rather general approach to modeling spatial heterogeneity in gpu-implemented spatial prediction methods for two-dimensional gridded data is proposed by introducing spatial variability to model parameters. Predictions of unknown values are obtained from non-equilibrium conditional simulations, assuming "local" equilibrium conditions. It is demonstrated that the proposed method leads to significant improvements in both prediction performance and computational efficiency.

关键词： Spatial interpolation Local-equilibrium simulation Non-Gaussian model Heterogeneous data gpu parallel computing CUDA

来源：评论

学校读者我要写书评

暂无评论

Particle swarm optimization for Rayleigh wave frequency-velocity spectrum inversion

引用

JOURNAL OF APPLIED GEOPHYSICS 2024年 222卷

作者： Le, Zhao Song, Xianhai Zhang, Xueqiang Shen, Chao Ai, Hanbing Yuan, Shichuan Fu, Daiguang China Univ Geosci Sch Geophys & Geomat Wuhan Hubei Peoples R China China Jiliang Univ Coll Metrol & Measurement Engn Hangzhou Zhejiang Peoples R China Southern Univ Sci & Technol Dept Earth & Space Sci Shenzhen Guangdong Peoples R China Changjiang River Sci Res Inst Minist Water Resources Key Lab Geotech Mech & Engn Wuhan Hubei Peoples R China

Rayleigh wave exploration is capable of reconstructing seismic properties at high resolution. The dispersion curve inversion methods are mainly based on 1D layered -model assumptions and require picking the dispersion curves manually. The success is highly dependent on personal subjectivity. Full waveform inversion (FWI) has received particular attention in recent years due to the fact that it has no need for manual dispersion curve extraction and no restriction on medium distribution. However, there are still many challenges limiting the application of FWI in field data, e.g., cycle -skipping issues, dependence on the initial model, and difficulty in estimating the seismic source signature. We adapt a particle swarm optimization (PSO) algorithm for Rayleigh wave frequency -velocity spectrum (FVS) inversion. Compared with conventional dispersion curve inversion, we directly fit the FVS without manually extracting the dispersion curves. Compared with FWI, we avoid cycleskipping issues by transforming the observed data from the space-time domain to the frequency -velocity domain. We reduce the dependence on the initial model by adopting a global optimal inversion strategy, and improve the inversion efficiency by introducing gpu parallel computing. In addition, we find that the seismic source dependence of FVS inversion is much less than that of FWI. Both synthetic and field examples verify the effectiveness of the method, making it a valuable tool for retrieving the subsurface structure.

关键词： Rayleigh wave gpu parallel computing Particle swarm optimization Frequency-velocity spectrum inversion Low source dependence

来源：评论

学校读者我要写书评

暂无评论

Compute Unified Device Architecture Implementation of Euler/Navier-Stokes Solver on Graphics Processing Unit Desktop Platform for 2-D Compressible Flows

引用

Transactions of Nanjing University of Aeronautics and Astronautics 2016年第5期33卷 536-545页

作者： Zhang Jiale Chen Hongquan College of Aerospace Engineering Nanjing University of Aeronautics and Astronautics

Personal desktop platform with teraflops peak performance of thousands of cores is realized at the price of conventional workstations using the programmable graphics processing units(gpus).A gpu-based parallel Euler/Navier-Stokes solver is developed for 2-D compressible flows by using NVIDIA′s Compute Unified Device Architecture(CUDA)programming model in CUDA Fortran programming *** techniques of implementation of CUDA kernels,double-layered thread hierarchy and variety memory hierarchy are presented to form the gpu-based algorithm of Euler/Navier-Stokes *** resulting parallel solver is validated by a set of typical test flow *** numerical results show that dozens of times speedup relative to a serial CPU implementation can be achieved using a single gpu desktop platform,which demonstrates that a gpu desktop can serve as a costeffective parallel computing platform to accelerate computational fluid dynamics(CFD)simulations substantially.

关键词： graphics processing unit(gpu) gpu parallel computing compute unified device architecture(CUDA)Fortran finite volume method(FVM) acceleration

来源：评论

学校读者我要写书评

暂无评论

Billion degree of freedom granular dynamics simulation on commodity hardware via heterogeneous data-type representation

引用

MULTIBODY SYSTEM DYNAMICS 2020年第4期50卷 355-379页

作者： Kelly, Conlain Olsen, Nicholas Negrut, Dan Univ Wisconsin Dept Mech Engn Madison WI 53706 USA

We discuss modeling, algorithmic, and software aspects that allow a simulation tool called Chrono::Granular to run billion-degree-of-freedom dynamics problems on commodity hardware, i.e., a workstation with one gpu. The ability to scale the solution to large problem sizes is traced back to an adimensionalization process combined with the use of mixed-precision data types that reduce memory pressure and improve arithmetic intensity, judicious use of the memory ecosystem on gpu cards as exposed by CUDA on Nvidia architectures, and a software implementation that prioritizes execution speed over modeling generality. The simulation approach is demonstrated for 3D scenarios with up to 710 million bodies for the frictionless case (of relevance in emulsions), and up to 210 million bodies for scenarios with friction (of relevance in terradynamics, additive manufacturing, soft-matter physics). The frictional contact model used draws on the Discrete Element Method (DEM). A performance benchmark shows linear scaling with problem size up to gpu memory capacity. The implementation has an application programming interface that enables it to interact in a cosimulation framework with third-party dynamics engines. This interaction is anchored by a force-displacement data exchange protocol that brings in external bodies as geometries defined by triangle meshes. We demonstrate the cosimulation mechanism by interfacing to an open source, multiphysics simulation engine called Chrono. Therein, triangular meshes define moving boundary conditions for Chrono::Granular, which in turn provides forces and torques acting on the triangular meshes. Several tests are considered for validation and scaling analysis purposes. The limiting aspects of the current implementation are its exclusive support of monodisperse granular systems, and its lack of handling geometries beyond spheres. These limitations are addressed by ongoing work.

关键词： Many-body dynamics gpu parallel computing Friction and contact Discrete element method Granular material

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：