检索结果-内蒙古大学图书馆

ieee International symposium on parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Alejandro López-Ortiz Alejandro Salinger Robert Suderman Cheriton School of Computer Science University of Waterloo Waterloo Canada

ISBN: (纸本)9781479913725

The increasing power and decreasing cost of Graphic Processing Units (GPUs) together with the development of programming languages for General Purpose Computing on GPUs (GPGPU) have led to the development and implementation of fast parallel algorithms for this architecture for a large spectrum of applications. Given the streaming-processing characteristics of GPUs, most practical applications so far are on highly data-parallel algorithms. Many problems, however, allow for task-parallel solutions or a combination of task and data-parallel algorithms. For these, a hybrid CPU-GPU parallel algorithm that combines the highly parallel stream-processing power of GPUs with the higher scalar power of multi-cores is likely to be superior. In this paper we describe a generic translation of any recursive sequential implementation of a divide-and-conquer algorithm into an implementation that benefits from running in parallel in both multi-cores and GPUs. This translation is generic in the sense that it requires little knowledge of the particular algorithm. We then present a schedule and work division scheme that adapts to the characteristics of each algorithm and the underlying architecture, efficiently balancing the workload between GPU and CPU. Our experiments show a 4.5x speedup over a single core recursive implementation, while demonstrating the accuracy and practicality of the approach.

关键词： graphics processing units Central Processing Unit Computer architecture Instruction sets Algorithm design and analysis Schedules parallel processing

来源：评论

学校读者我要写书评

暂无评论

Lossless compression with parallel decoder for improving performance of a GPU-based beamformer

Lossless compression with parallel decoder for improving per...

引用

ieee International Ultrasonics symposium

作者： U-Wai Lok Gang-Wei Fan Pai-Chi Li Grad. Inst. of Biomed. Electron. & Bioinf. Nat. Taiwan Univ. Taipei Taiwan|c|

ISBN: (纸本)9781467356855

A real time GPU-based beamformer suffers from large transmission bandwidth requirement to transfer massive ultrasound data from hardware front end to software back end system and the long processing time of memory copy from CPU to GPU. data compression with sequential decoder can reduce the data size of ultrasound data but the time-consuming decompression process degrades the performance of data transfer in a GPU. Therefore, a lossless compression associated with fully parallel decoding scheme on graphics processing units (GPU) is proposed in this study to mitigate the transmission bandwidth of hardware interface, and is used to reduce the overall processing time of data transfers in a GPU. In our simulations, the compression ratio reached around 3 to 4 by combining demodulation, decimation and our proposed lossless compression. Consequently, the transmission bandwidth to transfer data from hardware to software system has nearly four-folded reduction. In addition, the simulation results showed that the processing times of data transfer of compressed data with parallel decoding process in a GPU has around three-folded improvement relative to transferring the original uncompressed data. These results show that our proposed lossless compression method with parallel decoder can improve the performance of data transfer in a GPU-based beamformer.

关键词： GPU beamforming compression

来源：评论

学校读者我要写书评

暂无评论

Deploying Graph Algorithms on GPUs: An Adaptive Solution

Deploying Graph Algorithms on GPUs: An Adaptive Solution

引用

International symposium on parallel and Distributed Processing (IPDPS)

作者： Da Li Michela Becchi Department of Electrical and Computer Engineering University of Missouri-Columbia USA

ISBN: (纸本)9781467360661

Thanks to their massive computational power and their SIMT computational model, graphics Processing Units (GPUs) have been successfully used to accelerate a wide variety of regular applications (linear algebra, stencil computations, image processing and bioinformatics algorithms, among others). However, many established and emerging problems are based on irregular data structures, such as graphs. Examples can be drawn from different application domains: networking, social networking, machine learning, electrical circuit modeling, discrete event simulation, compilers, and computational sciences. It has been shown that irregular applications based on large graphs do exhibit runtime parallelism; moreover, the amount of available parallelism tends to increase with the size of the datasets. In this work, we explore an implementation space for deploying a variety of graph algorithms on GPUs. We show that the dynamic nature of the parallelism that can be extracted from graph algorithms makes it impossible to find an optimal solution. We propose a runtime system able to dynamically transition between different implementations with minimal overhead, and investigate heuristic decisions applicable across algorithms and datasets. Our evaluation is performed on two graph algorithms: breadth-first search and single-source shortest paths. We believe that our proposed mechanisms can be extended and applied to other graph algorithms that exhibit similar computational patterns.

关键词： graphics processing units parallel processing Algorithm design and analysis Runtime Heuristic algorithms Space exploration Instruction sets

来源：评论

学校读者我要写书评

暂无评论

Acceleration of Filtered Back-Projection Algorithm for 3D Cone-Beam CT Reconstruction Using parallel Computation

Acceleration of Filtered Back-Projection Algorithm for 3D Co...

引用

ieee Nuclear Science symposium

作者： Jartuwat Rajruangrabin Saowapak S. Thongvigitmanee Sorapong Aootaphao Pairash Thajchayapong Biomedical Electronics and Systems Development Unit X-Ray CT and Medical Imaging Laboratory Thailand National Science and Technology Development Agency Thailand

Filtered back-projection (FBP) is the most commonly used reconstruction method for computed tomographic image reconstruction due to its practicality in comparison with other computationally demanding methods. However, the FBP is still a very computationally expensive algorithm to implement, given that real world data obtained from CT machine are relatively large. Memory management and arithmetic computation of the FBP algorithm on conventional PC-based sequential executions still pose challenges in terms of computation time required for demanding diagnostic requirements. In this work, we propose and develop an approach for GPU-based implementation of the FBP algorithm that fully utilizes the parallel computing power of the graphic processing unit (GPU). We confirmed that the computation performance is significantly improved by applying our proposed approach with actual data obtained from our in-house dental CBCT machine called DentiiScan. The experiments show that we are able to achieve up to 80 times of computation time reduction.

关键词： graphics processing units Image reconstruction Computed tomography Biomedical imaging Three-dimensional displays parallel processing Arrays

来源：评论

学校读者我要写书评

暂无评论

A suite of domain-specific visual languages for scientific software application modelling

A suite of domain-specific visual languages for scientific s...

引用

ieee symposium on Visual Languages and Human Centric Computing (VL/HCC)

作者： Mohamed Almorsy John Grundy Richard Sadus Willem van Straten David G. Barnes Owen Kaluza Centre for Computing and Engineering Software and Systems Swinburne University of Technology Hawthorn Australia Centre for Astrophysics and Supercomputing Swinburne University of Technology Hawthorn Australia Monash Monash Biomedical Imaging and Monash e-Research Centre Monash University Clayton Australia

ISBN: (纸本)9781479903702

Many advances in science now require sophisticated scientific software applications that facilitate data and computationally intensive experiments. However, the effective utilization of existing computational power e.g., grid and cloud platforms depends on the capabilities of scientists to implement parallel, scalable code for such experiments. Currently, tools aimed at supporting scientists are either very limited to specific domains, or require significant development using low-level code. We describe our work towards a more end user-friendly scientific applications development process, notations and toolset. We introduce a scientific application designer intended for use primarily by scientists to enable them in describing workflow, processes, entities, formulae, computation and ultimately realization code for different computing platforms. This is achieved via a set of integrated, domain-specific visual and textual languages (DSVLs). A Web-based modeling tool supports definition of new DSVLs and modeling of these applications. We are currently extending our tool to support generation of multi-core and GPU implementations, and visualization of results.

关键词： Computational modeling visualization Prototypes graphics processing units Programming Mathematical model

来源：评论

学校读者我要写书评

暂无评论

WebGL-based interactive rendering of whole body anatomy for web-oriented visualisation of avatar-centered digital health data

WebGL-based interactive rendering of whole body anatomy for ...

引用

ieee symposium on Bioinformatics and Bioengineering (BIBE)

作者： Y. Zhao X. Zhao F. Dong G. J. Clapworthy N. Ersotelos E. Liu University of Bedfordshire UK senior lecturer with University of Bedfordshire UK

The visualisation of whole-body anatomy has a variety of applications in health-related analysis and simulation. However, the rendering of complex 3D human anatomy models is generally performed by standalone applications rather than via a web interface, as rendering large 3D models has always been a weak spot of traditional web browsers. Consequently, online access to, and exploration of, the human anatomy in 3D has not been feasible in the past. With the advent of WebGL and HTML5, high performance OpenGL rendering seamlessly integrated with the web interface is now within reach, and this opens the possibility of visualising avatar-centered health data via a web interface. In this paper, a WebGL-based prototype for rendering whole-body anatomy is introduced, and the technical details are presented.

关键词： Load modeling Three-dimensional displays data visualization Rendering (computer graphics) Solid modeling Browsers Memory management

来源：评论

学校读者我要写书评

暂无评论

parallel Computation of 2D Morse-Smale Complexes

引用

ieee TRANSACTIONS ON visualization AND COMPUTER graphics 2012年第10期18卷 1757-1770页

作者： Shivashankar, Nithin Senthilnathan, M. Natarajan, Vijay Indian Inst Sci Dept Comp Sci & Automat Bangalore 560012 Karnataka India Indian Inst Sci Supercomp Educ & Res Ctr Bangalore 560012 Karnataka India

The Morse-Smale complex is a useful topological data structure for the analysis and visualization of scalar data. This paper describes an algorithm that processes all mesh elements of the domain in parallel to compute the Morse-Smale complex of large 2D datasets at interactive speeds. We employ a reformulation of the Morse-Smale complex using Forman's Discrete Morse Theory and achieve scalability by computing the discrete gradient using local accesses only. We also introduce a novel approach to merge gradient paths that ensures accurate geometry of the computed complex. We demonstrate that our algorithm performs well on both multicore environments and on massively parallel architectures such as the GPU.

关键词： Topology-based methods discrete Morse theory large datasets gradient pairs multicore 2D scalar functions

来源：评论

学校读者我要写书评

暂无评论

Geometric Quantification of Features in large Flow Fields

引用

ieee COMPUTER graphics AND APPLICATIONS 2012年第4期32卷 46-54页

作者： Kendall, Wesley Huang, Jian Peterka, Tom Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN 37996 USA Argonne Natl Lab Math & Comp Sci Div Argonne IL USA

Interactive exploration of flow features in large-scale 3D unsteady-flow data is one of the most challenging visualization problems today. To comprehensively explore the complex feature spaces in these datasets, a proposed system employs a scalable framework for investigating a multitude of characteristics from traced field lines. This capability supports the examination of various neighborhood-based geometric attributes in concert with other scalar quantities. Such an analysis wasn't previously possible because of the large computational overhead and I/O requirements. The system integrates visual analytics methods by letting users procedurally and interactively describe and extract high-level flow features. An exploration of various phenomena in a large global ocean-modeling simulation demonstrates the approach's generality and expressiveness as well as its efficacy. [ABSTRACT FROM AUTHOR]

关键词： computer graphics Feature extraction geometric flow analysis Geometry large-scale data analysis large-scale systems parallel I/O particle tracing Three dimensional displays Visual analytics visualization

来源：评论

学校读者我要写书评

暂无评论

Scalable Multivariate Volume visualization and Analysis Based on Dimension Projection and parallel Coordinates

引用

ieee TRANSACTIONS ON visualization AND COMPUTER graphics 2012年第9期18卷 1397-1410页

作者： Guo, Hanqi Xiao, He Yuan, Xiaoru Peking Univ Key Lab Machine Percept Minist Educ Beijing 100871 Peoples R China Peking Univ Sch EECS Beijing 100871 Peoples R China Peking Univ Ctr Computat Sci & Engn Beijing 100871 Peoples R China

In this paper, we present an effective and scalable system for multivariate volume data visualization and analysis with a novel transfer function interface design that tightly couples parallel coordinates plots (PCP) and MDS-based dimension projection plots. In our system, the PCP visualizes the data distribution of each variate (dimension) and the MDS plots project features. They are integrated seamlessly to provide flexible feature classification without context switching between different data presentations during the user interaction. The proposed interface enables users to identify relevant correlation clusters and assign optical properties with lassos, magic wand, and other tools. Furthermore, direct sketching on the volume rendered images has been implemented to probe and edit features. With our system, users can interactively analyze multivariate volumetric data sets by navigating and exploring feature spaces in unified PCP and MDS plots. To further support large-scale multivariate volume data visualization and analysis, Scalable Pivot MDS (SPMDS), parallel adaptive continuous PCP rendering, as well as parallel rendering techniques are developed and integrated into our visualization system. Our experiments show that the system is effective in multivariate volume data visualization and its performance is highly scalable for data sets with different sizes and number of variates.

关键词： Multivariate volume transfer function parallel coordinates dimension projection user-interface design parallel visualization

来源：评论

学校读者我要写书评

暂无评论

On Graphs, GPUs, and Blind Dating: A Workload to Processor Matchmaking Quest

On Graphs, GPUs, and Blind Dating: A Workload to Processor M...

引用

International symposium on parallel and Distributed Processing (IPDPS)

作者： Abdullah Gharaibeh Lauro Beltrão Beltrão Costa Elizeu Santos-Neto Matei Ripeanu Department of Electrical and Computer Engineering University of British Columbia Canada

Graph processing has gained renewed attention. The increasing large scale and wealth of connected data, such as those accrued by social network applications, demand the design of new techniques and platforms to efficiently derive actionable information from large scale graphs. Hybrid systems that host processing units optimized for both fast sequential processing and bulk processing (e.g., GPUaccelerated systems) have the potential to cope with the heterogeneous structure of real graphs and enable high performance graph processing. Reaching this point, however, poses multiple challenges. The heterogeneity of the processing elements (e.g., GPUs implement a different parallel processing model than CPUs and have much less memory) and the inherent irregularity of graph workloads require careful graph partitioning and load assignment. In particular, the workload generated by a partitioning scheme should match the strength of the processing element the partition is allocated to. This work explores the feasibility and quantifies the performance gains of such low-cost partitioning schemes. We propose to partition the workload between the two types of processing elements based on vertex connectivity. We show that such partitioning schemes offer a simple, yet efficient way to boost the overall performance of the hybrid system. Our evaluation illustrates that processing a 4-billion edges graph on a system with one CPU socket and one GPU, while offloading as little as 25% of the edges to the GPU, achieves 2x performance improvement over state-of-the-art implementations running on a dual-socket symmetric system. Moreover, for the same graph, a hybrid system with dualsocket and dual-GPU is capable of 1.13 Billion breadth-first search traversed edge per second, a performance rate that is competitive with the latest entries in the Graph500 list, yet at a much lower price point.

关键词： graphics processing units Partitioning algorithms Computational modeling parallel processing Hardware Kernel Algorithm design and analysis

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：