Filters








1,679 Hits in 2.0 sec

EFFICIENT TECHNIQUE FOR SIMULATING MULTIPLE LAYERS OF SOFT TISSUES USING CUDA BASED GPU

Jayasudha K, Mohan.G Kabadi
2019 International Journal of Current Engineering and Scientific Research  
The performance evaluation of the model is done using vtkPython and CUDA programming language implementations.  ...  CUDA based GPU computing is adopted to speed up the simulation performance. The parallel computation is achieved using necessary data structures and algorithms.  ...  Mafi and sirouspour [8] explains simulation of large deformations and strains for dynamic nonlinear deformation analysis using GPU based implementation of FEM equations. B.  ... 
doi:10.21276/ijcesr.2019.6.6.25 fatcat:odug5oos3nesvhex42fi5fu76a

Real-time nonlinear finite element computations on GPU – Application to neurosurgical simulation

Grand Roman Joldes, Adam Wittek, Karol Miller
2010 Computer Methods in Applied Mechanics and Engineering  
models, finite deformations and brain-skull contacts) in less than a minute on a personal computer for models having up to 50.000 degrees of freedom.  ...  In this paper we present an implementation of our algorithms on a Graphics Processing Unit (GPU) using the new NVIDIA Compute Unified Device Architecture (CUDA) which leads to more than 20 times increase  ...  The guidelines from the NVIDIA paper ''Optimizing Parallel Reduction in CUDA", which comes with the CUDA development kit, were followed when implementing the reduction algorithm.  ... 
doi:10.1016/j.cma.2010.06.037 pmid:21179562 pmcid:PMC3003932 fatcat:mpfcgke65famnggxgfksjkisra

A real-time multigrid finite hexahedra method for elasticity simulation using CUDA

Christian Dick, Joachim Georgii, Rüdiger Westermann
2011 Simulation modelling practice and theory  
For hexahedral models consisting of as many as 269,000 elements our approach achieves physics-based simulation at 11 time steps per second.  ...  We present a multigrid approach for simulating elastic deformable objects in real time on recent NVIDIA GPU architectures.  ...  CUDA Implementation The CUDA implementation of the multigrid finite hexahedra method consists of two parts: a pre-process for creating the finite element model and the real-time simulation of the deformable  ... 
doi:10.1016/j.simpat.2010.11.005 fatcat:bh7k7lcmfje7jhfeozpewiemuu

Fast geodesic shooting for landmark matching using CUDA [article]

Jiancong Wang
2019 arXiv   pre-print
For medical image applications, N maybe in the range of thousands, rendering this operation computationally expensive. In this work we ropose a CUDA implementation based on shared memory reduction.  ...  Landmark matching via geodesic shooting is a prerequisite task for numerous registration based applications in biomedicine.  ...  This is particularly problematic when single precision is used, as shown in the results section. 2.3 CUDA programming model and memory hierarchy CUDA is an extension to C/C++ for programming on the Nvidia  ... 
arXiv:1907.04839v1 fatcat:cxkox7pihnen3hdt4ipq2ntfxm

Data Structures and Transformations for Physically Based Simulation on a GPU [chapter]

Perhaad Mistry, Dana Schaa, Byunghyun Jang, David Kaeli, Albert Dvornik, Dwight Meglan
2011 Lecture Notes in Computer Science  
The technique used for deformation modeling is based on [14] and entails three main steps. 1.  ...  The SIMT model for CUDA requires well-structured access patterns across threads to coalesce memory accesses.  ... 
doi:10.1007/978-3-642-19328-6_17 fatcat:bp6z6lxv25abbic7f7fstxhu3e

GPU Acceleration of Real-Time Control Loops [article]

Mohamed A. Bamakhrama, Alejandro Arrizabalaga, Frank Overman, Jean-Paul Smeets, Kornel van der Sommen, Remko van der Vossen, John Wagensveld
2019 arXiv   pre-print
To alleviate this, we propose a firm real-time control system that uses a wafer heat feed-forward model to compensate for the wafer deformation.  ...  The model calculates the expected wafer deformation, and then, compensates for that by adjusting the light projection and/or the wafer movement.  ...  The performance needed to compute the WHFF model "on-time" to compensate for deformation is around 600 GFLOP/s for all dimensions.  ... 
arXiv:1902.08018v1 fatcat:r4nogf4llvekfopyac7pkpjysu

Coupling time-varying modal analysis and FEM for real-time cutting simulation of objects with multi-material sub-domains

Chen Yang, Shuai Li, Yu Lan, Lili Wang, Aimin Hao, Hong Qin
2016 Computer Aided Geometric Design  
During the dynamic stage, for each sub-domain, we leverage its local modal reduction in order to project complex deformations onto a low-dimensional subspace.  ...  reuse into a CUDA-enabled parallel computation framework.  ...  For FE method, displacements are computed from the original deformation space, while for modal reduction method, they are computed from the deformation subspace as 165 follows: M iüi (t) + D iui (t) +  ... 
doi:10.1016/j.cagd.2016.02.014 fatcat:vauquuycfbgxvkkqjbku7ayzeq

GPU-accelerated, gradient-free MI deformable registration for atlas-based MR brain image segmentation

Xiao Han, L.S. Hibbard, V. Willcut
2009 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
In this paper, we introduce a novel MI-based dense deformable registration method and apply it to the automatic segmentation of detailed brain structures.  ...  With GPU acceleration it takes less than 8 minutes to compile a multi-atlas segmentation for each subject even with as many as 17 atlases, which demonstrates that the use of GPUs can greatly facilitate  ...  Figure 2 . 2 CUDA programming model and memory hierarchy [10] . Figure 3 . 3 Illustration of the deformable registration and atlas-based segmentation results (see text for details).  ... 
doi:10.1109/cvpr.2009.5204043 fatcat:i2js5sbklzftxcj32mhvxoxawm

GPU-accelerated, gradient-free MI deformable registration for atlas-based MR brain image segmentation

Xiao Han, Lyndon S. Hibbard, Virgil Willcut
2009 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
In this paper, we introduce a novel MI-based dense deformable registration method and apply it to the automatic segmentation of detailed brain structures.  ...  With GPU acceleration it takes less than 8 minutes to compile a multi-atlas segmentation for each subject even with as many as 17 atlases, which demonstrates that the use of GPUs can greatly facilitate  ...  Figure 2 . 2 CUDA programming model and memory hierarchy [10] . Figure 3 . 3 Illustration of the deformable registration and atlas-based segmentation results (see text for details).  ... 
doi:10.1109/cvprw.2009.5204043 dblp:conf/cvpr/HanHW09 fatcat:ymvtwnyk4bemxlomnhrl7hzsfa

High performance computing for deformable image registration: Towards a new paradigm in adaptive radiotherapy

Sanjiv S. Samant, Junyi Xia, Pınar Muyan-Özçelik, John D. Owens
2008 Medical Physics (Lancaster)  
For GPU computing, we achieved TPMI = 0.00916 spmi with 3.7% variation, indicating optimized memory handling under CUDA.  ...  CUDA provides a C-like language programming interface, and allows for direct access to the highly parallel compute units in the GPU.  ...  Brook exposes a stream programming model while CUDA exposes a more general-purpose programming model.  ... 
doi:10.1118/1.2948318 pmid:18777915 fatcat:dy32l4n72jbojasefbmsktzqza

Ray Casting Deformable Models on the GPU

Suryakant Patidar, P.J. Narayanan
2008 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing  
We achieve real-time ray-casting of a million triangle model onto a million pixels on current Nvidia GPUs using the CUDA model.  ...  We explore the problem of real time ray casting of large deformable models (over a million triangles) on large displays (a million pixels) on an off-the-shelf GPU in this paper.  ...  [20] builds and ray traces small and medium sized deformable models on the GPU using CUDA. Wei et al.  ... 
doi:10.1109/icvgip.2008.92 dblp:conf/icvgip/PatidarN08 fatcat:euezxgtfk5gepo45vf7m2owhce

Accelerated Real-Time Reconstruction of 3D Deformable Objects from Multi-view Video Channels [chapter]

Holger Graf, Leon Hazke, Svenja Kahn, Cornelius Malerczyk
2011 Lecture Notes in Computer Science  
As a result, a significant increase of frame rates for the volumetric reconstruction of deformable objects can be achieved using an optimized CUDA-based implementation on NVIDIA's Fermi-GPUs.  ...  In this paper we present a new framework for an accelerated 3D reconstruction of deformable objects within a multi-view setup.  ...  As a result, a significant increase of frame rates for the volumetric reconstruction of deformable objects can be achieved.  ... 
doi:10.1007/978-3-642-21799-9_32 fatcat:b6zistrwk5banal2fdlsnj4vma

Fast Deformable Registration on the GPU: A CUDA Implementation of Demons

Pinar Muyan-Ozcelik, John D. Owens, Junyi Xia, Sanjiv S. Samant
2008 2008 International Conference on Computational Sciences and Its Applications  
We implemented Demons, a widely used deformable image registration algorithm, on NVIDIA's Quadro FX 5600 GPU with the Compute Unified Device Architecture (CUDA) programming environment.  ...  Hence, this study addresses the need for on-line deformable registration methods in intra-operative settings by providing the fastest and most scalable Demons implementation available to date.  ...  Kernels have a Single Program Multiple Data (SPMD) programming model, which is essentially Single Instruction Multiple Data (SIMD) programming model that allows limited divergence in execution.  ... 
doi:10.1109/iccsa.2008.22 dblp:conf/iccsa/Muyan-OzcelikOXS08 fatcat:6ehyabhzdrddjnvvikw6v72p74

Particle Swarm Optimization and Differential Evolution for model-based object detection

Roberto Ugolotti, Youssef S.G. Nashed, Pablo Mesejo, Špela Ivekovič, Luca Mussi, Stefano Cagnoni
2013 Applied Soft Computing  
The starting point for this work is a very general model-based approach to object detection.  ...  In the former, a 2D deformable model of a section of the hippocampus is fit to the corresponding region of a histological image, to accurately localize such a structure and analyze gene expression in specific  ...  Patney from University of California, Davis, for sharing his CUDA implementation of 21 the Catmull-Clark subdivision, and the anonymous referees for their valuable comments that allowed them to highly  ... 
doi:10.1016/j.asoc.2012.11.027 fatcat:mrqey22sq5fbjc63yrjr26e2ve

GPU-based ultrafast IMRT plan optimization

Chunhua Men, Xuejun Gu, Dongju Choi, Amitava Majumdar, Ziyi Zheng, Klaus Mueller, Steve B Jiang
2009 Physics in Medicine and Biology  
Our optimization algorithm has been implemented in CUDA for parallel GPU computing as well as in C for serial CPU computing for comparison purpose.  ...  We adopt a penalty-based quadratic optimization model, which is solved by using a gradient projection method with Armijo's line search rule.  ...  Acknowledgments We would like to thank NVIDIA for providing GPU cards and Hubert Pan for his constructive comments on the manuscript.  ... 
doi:10.1088/0031-9155/54/21/008 pmid:19826201 fatcat:e3gozq2adzf77nf5zl4muknxhy
« Previous Showing results 1 — 15 out of 1,679 results