检索结果-内蒙古大学图书馆

Real-time single camera natural user interface engine development

MULTIMEDIA TOOLS AND APPLICATIONS 2017年第9期76卷 11159-11175页

作者： Song, Wei Cai, Xingquan Xi, Yulong Cho, Seoungjae Cho, Kyungeun North China Univ Technol Coll Comp 5 Jinyuanzhuang Rd Beijing 100144 Peoples R China Dongguk Univ Seoul Dept Multimedia Engn 26 Pildong 3 Ga Seoul 100715 South Korea

Natural user interfaces (NUIs) provide human computer interaction (HCI) with natural and intuitive operation interfaces, such as using human gestures and voice. We have developed a real-time NUI engine architecture using a web camera as a means of implementing NUI applications. The system captures video via the web camera, implements real-time image processing using graphic processing unit (gpu) programming. This paper describes the architecture of the engine and the real-virtual environment interaction methods, such as foreground segmentation and hand gesture recognition. These methods are implemented using gpu programming in order to realize real-time image processing for HCI. To verify the efficacy of our proposed NUI engine, we utilized it in the development and implementation of several mixed reality games and touch-less operation applications, using the developed NUI engine and the DirectX SDK. Our results confirm that the methods implemented by the engine operate in real time and the interactive operations are intuitive.

关键词： NUI gpu programming Mixed reality Foreground segmentation Motion detection

来源：评论

学校读者我要写书评

暂无评论

Accelerating l₁ l₂ deblurring using wavelet expansions of operators

引用

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS 2018年 343卷 373-396页

作者： Escande, Paul Weiss, Pierre ISAE DISC Toulouse France ITAV Inst Technol Avancees Sci Vivant USR3505 Toulouse France CNRS Inst Math Toulouse UMR5219 IMT Toulouse France Univ Toulouse Toulouse France

Image deblurring is a fundamental problem in imaging, usually solved with computationally intensive optimization procedures. The goal of this paper is to provide new efficient strategies to reduce computing times for simple deblurring models regularized using orthogonal wavelet transforms. We show that the minimization can be significantly accelerated by leveraging the fact that images and blur operators are compressible in the same orthogonal wavelet basis. The proposed methodology consists of three ingredients: (i) a sparse approximation of the blur operator in wavelet bases, (ii) a diagonal preconditioner and (iii) an implementation on massively parallel architectures. Combining the three ingredients leads to acceleration factors ranging from 4 to 250 on a typical workstation. For instance, a 1024 x 1024 image can be deblurred in 0.15 s. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Sparse wavelet expansion Preconditioning gpu programming Image deblurring Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Simulation of an inelastic dispersive phenomenon: stimulated Brillouin scattering in a single-mode fiber segment through parallelism

引用

JOURNAL OF SUPERCOMPUTING 2018年第7期74卷 3264-3277页

作者： Sanchez-Lara, R. Trejo-Sanchez, J. A. Lopez-Martinez, J. L. Alvarez-Chavez, J. A. Univ Autonoma Carmen Ciudad Del Carmen 24080 Mexico Conacyt Ctr Invest Matemat Merida Venezuela Univ Autonoma Yucatan Fac Matemat Merida Mexico Ctr Invest & Innovac Tecnol Inst Politecn Nacl Cerrada Cecati S-N Mexico City 02250 DF Mexico

Stimulated Brillouin scattering (SBS) is one of the most important nonlinear phenomena because it limits the maximum transmission power in modern optical communication systems. Unfortunately, the simulation of SBS is time-consuming, since it requires estimating the solutions for a set of complex differential equations that describe this phenomenon. In this paper, a novel high-performance computing model intended to analyze the main dispersive effects present in modern fiber communication systems is proposed. A full optical characterization of the simulation results is included and compared with the efficiency and improved speed of our parallel implementation versus a previous sequential model for SBS. Also, an evaluation of the throughput of our parallel implementation using both central processing unit multi-core and graphics processing unit is presented. Results show that parallelism increases the performance of the simulation tenfold.

关键词： Computer simulation Optical fiber communication gpu programming Parallel architectures Parallel programming Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Non-feedback technique to directly control multistability in nonlinear oscillators by dual-frequency driving

引用

NONLINEAR DYNAMICS 2018年第1期94卷 273-293页

作者： Hegedus, Ferenc Lauterborn, Werner Parlitz, Ulrich Mettin, Robert Budapest Univ Technol & Econ Fac Mech Engn Dept Hydrodynam Syst Budapest Hungary Georg August Univ Gottingen Drittes Phys Inst Cavitat Bubble Dynam Grp Gottingen Germany Max Planck Inst Dynam & Self Org Res Grp Biomed Phys Gottingen Germany Georg August Univ Gottingen Inst Nonlinear Dynam Gottingen Germany

A novel method to control multistability of nonlinear oscillators by applying dual-frequency driving is presented. The test model is the Keller-Miksis equation describing the oscillation of a bubble in a liquid. It is solved by an in-house initial-value problem solver capable to exploit the high computational resources of professional graphics cards. During the simulations, the control parameters are the two amplitudes of the acoustic driving at fixed, commensurate frequency pairs. The high-resolution bi-parametric scans in the control parameter plane show that a period-2 attractor can be continuously transformed into a period-3 one (and vice versa) by proper selection of the frequency combination and by proper tuning of the driving amplitudes. This phenomenon has opened a new way to drive the system to a desired, pre-selected attractor directly via a non-feedback control technique without the need of the annihilation of other attractors. Moreover, the residence in transient chaotic regimes can also be avoided. The results are supplemented with simulations obtained by the boundary-value problem solver AUTO, which is capable to compute periodic orbits directly regardless of their stability, and trace them as a function of a control parameter with the pseudo-arclength continuation technique.

关键词： Control of multistability Dual-frequency driving Bifurcation structure gpu programming Keller-Miksis equation Nonlinear dynamics

来源：评论

学校读者我要写书评

暂无评论

The Lattice Boltzmann Method Implemented on the gpu to Simulate the Turbulent Flow Over a Square Cylinder Confined in a Channel

引用

FLOW TURBULENCE AND COMBUSTION 2015年第3期94卷 495-512页

作者： Koda, Yusuke Lien, Fue-Sang Univ Waterloo Dept Mech & Mechatron Engn Waterloo ON N2L 3G1 Canada

The lattice Boltzmann method (LBM) is a relatively new method for fluid flow simulations, and is recently gaining popularity due to its simple algorithm and parallel scalability. Although the method has been successfully applied to a wide range of flow physics, its capabilities in simulating turbulent flow is still under-validated. Hence, in this paper, a 3D LBM code was developed to investigate the validity of the LBM for turbulent flow simulations through large eddy simulations (LES). A gpu enabled LBM code was developed, and validated against a benchmark test case involving the flow over a square cylinder in square channel. The flow results showed good agreement with literature, and speedups of over 150 times were observed when two gpus were used in parallel. Turbulent flow simulations were then conducted using LES with the Smagorinsky subgrid model. The methodology was first validated by computing the fully developed turbulent channel flow, and comparing the results against direct numerical simulation results. The results were in good agreement despite the relatively coarse grid. The code was then used to simulate the turbulent flow over a square cylinder confined in a channel. In order to emulate a realistic inflow at the channel inlet, an auxiliary simulation consisting of a fully developed turbulent channel flow was run in conjunction, and its velocity profile was used to enforce the inlet boundary condition for the cylinder flow simulation. Comparison of the results with experimental and numerical results revealed that the presence of the turbulent flow structures at the inlet can significantly influence the resulting flow field around the cylinder.

关键词： gpu programming CUDA Lattice Boltzmann method Parallel computing Grid refinement LES Turbulent flows

来源：评论

学校读者我要写书评

暂无评论

gpu Accelerated Finding of Channels and Tunnels for a Protein Molecule

引用

INTERNATIONAL JOURNAL OF PARALLEL programming 2016年第1期44卷 87-108页

作者： Kim, Byungjoo Lee, Jung Eun Kim, Young J. Kim, Ku-Jin Kyungpook Natl Univ Sch Comp Sci & Engn Daegu South Korea Samsung Elect Suwon South Korea Ewha Womans Univ Dept Comp Sci & Engn Seoul South Korea

This paper proposes a novel method for computing the cavities and channels/tunnels in a protein molecule in interactive time without significant user effort. A sphere tree structure is used to represent a protein molecule, which provides a parallel architecture to access a Graphic Processing Unit (gpu) memory. The use of CUDA programming with a gpu then allows the proposed system to work in parallel on either a sphere tree structure of a molecule or a set of voxels composing the space. A real-time performance is achieved for proximity queries on a protein molecule, and an interactive time performance is realized for finding all the cavities and channel/tunnels without user effort. The proposed system also provides a method for approximating a convex hull of a molecule in a discrete space, and then generates the shortest path from a user selected or automatically chosen cavity to the exterior of the protein molecule. Experimental results in comparison with previous methods confirm the time efficiency of the proposed system.

关键词： gpu programming Protein molecules Cavities Channels Tunnels

来源：评论

学校读者我要写书评

暂无评论

Constraint-based LN curves

引用

COMPUTER AIDED GEOMETRIC DESIGN 2012年第1期29卷 30-40页

作者： Ahn, Young Joon Hoffmann, Christoph Chosun Univ Dept Math Educ Kwangju 501759 South Korea Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA

We consider the design of parametric curves from geometric constraints such as distance from lines or points and tangency to lines or circles. We solve the Hermite problem with such additional geometric constraints. We use a family of curves with linearly varying normals, LN curves. The nonlinear equations that arise can be of algebraic degree 60. We solve them using the gpu on commodity graphics cards and achieve interactive performance. The family of curves considered has the additional property that the convolution of two curves in the family is again a curve in the family, assuming common Gauss maps, making the class more useful to applications. Further, we consider valid ranges in which the line tangency constraint can be imposed without the curve segment becoming singular. Finally, we remark on the larger class of LN curves and how it relates to Bezier curves. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Geometric constraints LN curves MCAD CAGD gpu programming Convolution

来源：评论

学校读者我要写书评

暂无评论

Sound and Partially-Complete Static Analysis of Data-Races in gpu Programs

引用

PROCEEDINGS OF THE ACM ON programming LANGUAGES-PACMPL 2024年第OOPSLA期8卷 2434-2461页

作者： Liew, Dennis Cogumbreiro, Tiago Lange, Julien Univ Massachusetts Boston Boston MA 02125 USA Royal Holloway Univ London Egham England

gpus are progressively being integrated into modern society, playing a pivotal role in Artificial Intelligence and High-Performance Computing. Programmers need a deep understanding of the gpu programming model to avoid subtle data-races in their codes. Static verification that is sound and incomplete can guarantee data-race freedom, but the alarms it raises may be spurious and need to be validated. In this paper, we establish a True Positive Theorem for a static data-race detector for gpu programs, i.e., a result that identifies a class of programs for which our technique only raises true alarms. Our work builds on the formalism of memory access protocols, that models the concurrency operations of CUDA programs. The crux of our approach is an approximation analysis that can correctly identify true alarms, and pinpoint the conditions that make an alarm imprecise. Our approximation analysis detects when the reported locations are reachable (control independence, or CI), and when the reported locations are precise (data independence, or DI), as well identify inexact values in an alarm. In addition to a True Positive result for programs that are CI and DI, we establish the root causes of spurious alarms depending on whether CI or DI are present. We apply our theory to introduce FaialAA, the first sound and partially complete data-race detector. We evaluate FaialAA in three experiments. First, in a comparative study with the state-of-the-art tools, we show that FaialAA confirms more DRF programs than others while emitting 1.9x fewer potential alarms. Importantly, the approximation analysis of FaialAA detects 10 undocumented data-races. Second, in an experiment studying 6 commits of data-race fixes in open source projects OpenMM and Nvidia's MegaTron, FaialAA confirmed the buggy and fixed versions of 5 commits, while others were only able to confirm 2. Third, we show that 59.5% of 2,770 programs are CI and DI, quantifying when the approximation analysis of FaialAA is comp

关键词： data-race detection gpu programming static analysis true positives

来源：评论

学校读者我要写书评

暂无评论

A new open-source gpu-based microscopic Monte Carlo simulation tool for the calculations of DNA damages caused by ionizing radiation --- Part I: Core algorithm and validation

引用

MEDICAL PHYSICS 2020年第4期47卷 1958-1970页

作者： Tsai, Min-Yu Tian, Zhen Qin, Nan Yan, Congchong Lai, Youfang Hung, Shih-Hao Chi, Yujie Jia, Xun Univ Texas Southwestern Med Ctr Dallas Dept Radiat Oncol Innovat Technol Radiotherapy Computat & Hardware Dallas TX 75287 USA Natl Taiwan Univ Dept Comp Sci & Informat Engn Taipei Taiwan Univ Texas Arlington Dept Phys POB 19059 Arlington TX 76019 USA

Purpose Monte Carlo (MC) simulation of radiation interactions with water medium at physical, physicochemical, and chemical stages, as well as the computation of biologically relevant quantities such as DNA damages, are of critical importance for the understanding of microscopic basis of radiation effects. Due to the large problem size and many-body simulation problem in the chemical stage, existing CPU-based computational packages encounter the problem of low computational efficiency. This paper reports our development on a gpu-based microscopic Monte Carlo simulation tool gMicroMC using advanced gpu-acceleration techniques. Methods gMicroMC simulated electron transport in the physical stage using an interaction-by-interaction scheme to calculate the initial events generating radicals in water. After the physicochemical stage, initial positions of all radicals were determined. Simulation of radicals' diffusion and reactions in the chemical stage was achieved using a step-by-step model using gpu-accelerated parallelization together with a gpu-enabled box-sorting algorithm to reduce the computations of searching for interaction pairs and therefore improve efficiency. A multi-scale DNA model of the whole lymphocyte cell nucleus containing similar to 6.2 Gbp of DNA was built. Results Accuracy of physical stage simulation was demonstrated by computing stopping power and track length. The results agreed with published data and the data produced by GEANT4-DNA (version 10.3.3) simulations with 10 -20% difference in most cases. Difference of yield values of major radiolytic species from GEANT4-DNA results was within 10%. We computed DNA damages caused by monoenergetic 662 keV photons, approximately representing Cs-137 decay. Single-strand break (SSB) and double-strand break (DSB) yields were 196 +/- 8 SSB/Gy/Gbp and 7.3 +/- 0.7 DSB/Gy/Gbp, respectively, which agreed with the result of 188 SSB/Gy/Gbp and 8.4 DSB/Gy/Gbp computed by Hsiao et al. Compared to computation using a

关键词： DNA damage simulation gpu programming Monte Carlo simulation

来源：评论

学校读者我要写书评

暂无评论

Autotuning Parallel Programs by Model Checking

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2022年第7期56卷 634-648页

作者： Garanina, N. O. Gorlatch, S. P. Russian Acad Sci Ershov Inst Informat Syst IIS Siberian Branch Novosibirsk 630090 Russia Russian Acad Sci Inst Automation & Electrometry Siberian Branch Novosibirsk 630090 Russia Univ Munster D-48149 Munster Germany

This paper presents a new approach to autotuning data-parallel programs. Autotuning is a search for optimal program settings, which maximize its performance. The novelty of the approach lies in the use of the model checking method to find the optimal tuning parameters by the method of counterexamples. In our work, we abstract from specific programs and specific processors by defining their representative abstract patterns. Our counterexample method implements the following four steps. At the first step, an execution model of an abstract program on an abstract processor is described in the language of a model checking tool. At the second step, in the language of the model checking tool, we formulate the optimality property that depends on the constructed model. At the third step, we find the optimal values of the tuning parameters by using counterexamples constructed during the verification of the optimality property. In the fourth step, we extract the information about the tuning parameters from the counterexample for the optimal parameters. We apply this approach to autotuning parallel programs written in OpenCL, a popular modern language that extends the C language for programming both standard multi-core processors (CPUs) and massively parallel graphics processing units (gpus). As a verification tool we use the SPIN verifier and its model representation language Promela, which formal semantics is good for modeling the execution of parallel programs on processors with different architectures.

关键词： Keywords optimization problem autotuning of parallel programs parallel programs gpu programming model checking counterexamples OpenCL SPIN Promela

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：