检索结果-内蒙古大学图书馆

Simulation of cortex-like neural networks on a CNAPS simd neurocomputer

NEURAL PROCESSING LETTERS 1996年第2期4卷 67-74页

作者： Moller, R Paschke, P UNIV TUBINGEN LEHRSTUHL RECHNERARCHITEKTURD-72074 TUBINGENGERMANY TECH UNIV ILMENAU FACHGEBIET NEUROINFORMATIKD-98684 ILMENAUGERMANY

Neurons of the cortical tissue in a mammalian brain are connected in an extremely sparse and random fashion. The paper presents efficient methods for a parallel simulation of neural networks modeling this connection scheme on a CNAPS simd neurocomputer. Appropriate algorithms and data structures are introduced that allow for a minimal loss of parallelism during the computation of input scalar products. A 'greedy' optimization procedure applied to the neuron-processor assignment is shown to gain a further reduction of computation time getting close to the lower bound. Using these methods, a considerable speedup in comparison to sequential computation is achieved.

关键词： cortical models neurocomputer parallel simulation simd parallelism sparse random networks speed optimization

来源：评论

学校读者我要写书评

暂无评论

Recursive least-squares using a hybrid Householder algorithm on massively parallel simd systems

引用

PARALLEL COMPUTING 1999年第9期25卷 1147-1159页

作者： Kontoghiorghes, EJ Clint, M Naegeli, HH Univ Neuchatel Inst Informat CH-2007 Neuchatel Switzerland Queens Univ Belfast Dept Comp Sci Belfast BT7 1NN Antrim North Ireland

Within the context of recursive least-squares, the implementation of a Householder algorithm for block updating the QR decomposition, on massively parallel simd systems, is considered. Initially, two implementations based on different mapping strategies for distributing the data matrices over the processing elements of the parallel computer are investigated. Timing models show that neither of these implementations is superior in all cases. In order to increase computational speed, a hybrid implementation uses performance models to partition the problem into two subproblems which are then solved using the first and second implementation, respectively. (C) 1999 Elsevier Science B.V. All rights reserved.

关键词： least-squares Householder transformations QR decomposition timing models simd parallelism

来源：评论

学校读者我要写书评

暂无评论

Fast local and global illuminations through a simd z-buffer

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 1997年第7期11卷 1095-1112页

作者： Renaud, C LAB INFORMAT LITTORAL F-62228 CALAISFRANCE

The z-buffer is a well-known hidden-part removal technique commonly used by local illumination algorithms. Some global illumination approaches use this technique too, in order to approximate energy exchanges. In this paper we propose a massively parallel implementation of the z-buffer on the MP-1 machine. Efficiency is achieved by precisely studying the different stages of the algorithm, and by taking care in correctly using the simd control of the architecture. Local illumination models are then applied to the Z-buffer algorithm, by using Gouraud and Phong's interpolations. Finally the parallel Z-buffer is used in a massively parallel radiosity algorithm. The results obtained anew to provide quickly illuminated images by decreasing dramatically the computation time required for global illumination.

关键词： hidden-part removal z-buffer local illumination radiosity simd parallelism efficiency

来源：评论

学校读者我要写书评

暂无评论

simd algorithm for curved object recognition using Grimson and Lozano-Pérez matching

引用

The Visual Computer 1993年第3期10卷 160-172页

作者： Usoh, Martin Buxton, Hilary Department of Computer Science Queen Mary and Westfield College London E1 4NS Mile End Road United Kingdom

The complexity of many computer-recognition problems is such that speed of processing is an important factor that cannot be overlooked, especially when real-time applications are sought. In order to reduce the processing time of matching, our work is implemented in parallel on simd architecture. We describe an extension of the Holder and Buxton algorithm (1989) using the surface normal and axis of rotation of objects as 'edge' features to increase the object-recognition scope to objects containing developable surfaces. In addition, we implement an improved data-sorting algorithm that gives impressive speed ups compared with the earlier sorting technique. We show the method to be highly effective in the fast determination of scene interpretations with tests using artificial scenes generated efficiently by a parallel ray caster incorporating constructive solid geometry (CSG). Accuracy and robustness are further tested by application to a real-world scene. © 1993 Springer-Verlag.

关键词： Computer vision Model matching Planar curve Ray tracing simd parallelism

来源：评论

学校读者我要写书评

暂无评论

Insufficient Vectorization: A New Method to Exploit Superword Level parallelism

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2017年第1期E100D卷 91-106页

作者： Gao, Wei Han, Lin Zhao, Rongcai Li, Yingying Liu, Jian State Key Lab Math Engn & Adv Comp Zhengzhou 450000 Peoples R China Nanjing Univ Posts & Telecommun Coll Commun & Informat Engn Xinmofan Rd 66 Nanjing 210003 Peoples R China

Single-instruction multiple-data (simd) extension provides an energy-efficient platform to scale the performance of media and scientific applications while still retaining post-programmability. However, the major challenge is to translate the parallel resources of the simd hardware into real application performance. Currently, all the slots in the vector register are used when compilers exploit simd parallelism of programs, which can be called sufficient vectorization. Sufficient vectorization means all the data in the vector register is valid. Because all the slots which vector register provides must be used, the chances of vectorizing programs with low simd parallelism are abandoned by sufficient vectorization method. In addition, the speedup obtained by full use of vector register sometimes is not as great as that obtained by partial use. Specifically, the length of vector register provided by simd extension becomes longer, sufficient vectorization method cannot exploit the simd parallelism of programs completely. Therefore, insufficient vectorization method is proposed, which refer to partial use of vector register. First, the adaptation scene of insufficient vectorization is analyzed. Second, the methods of computing inter-iteration and intra-iteration simd parallelism for loops are put forward. Furthermore, according to the relationship between the parallelism and vector factor a method is established to make the choice of vectorization method, in order to vectorize programs as well as possible. Finally, code generation strategy for insufficient vectorization is presented. Benchmark test results show that insufficient vectorization method vectorized more programs than sufficient vectorization method by 107.5% and the performance achieved by insufficient vectorization method is 12.1% higher than that achieved by sufficient vectorization method.

关键词： simd extension simd parallelism vector register insufficient vectorization

来源：评论

学校读者我要写书评

暂无评论

HFPaC: GPU friendly height field parallel compression

引用

GEOINFORMATICA 2013年第1期17卷 207-233页

作者： Durdevic, Dorde M. Tartalja, Igor I. Univ Belgrade Sch Elect Engn Belgrade 11120 Serbia

In this paper, we present a novel method for fast lossy or lossless compression and decompression of regular height fields. The method is suitable for simd parallel implementation and thus inherently suitable for modern GPU architectures. Lossy compression is achieved by approximating the height field with a set of quadratic Bezier surfaces. In addition, lossless compression is achieved by superimposing the residuals over the lossy approximation. We validated the method's efficiency through a CUDA implementation of compression and decompression algorithms. The method allows independent decompression of individual data points, as well as progressive decompression. Even in the case of lossy decompression, the decompressed surface is inherently seamless. In comparison with the GPU-oriented state-of-the-art method, the proposed method, combined with a widely available lossless compression method (such as DEFLATE), achieves comparable compression ratios. The method's efficiency slightly outperforms the state-of-the-art method for very high workloads and considerably for lower workloads.

关键词： Height field Lossy and lossless compression Progressive decompression Bezier surface simd parallelism

来源：评论

学校读者我要写书评

暂无评论

Integration of GPU Computing in a Software Radio Environment

引用

JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 2012年第1期69卷 55-65页

作者： Horrein, Pierre-Henri Hennebert, Christine Petrot, Frederic Minatec Leti CEA F-38054 Grenoble 9 France CNRS Grenoble INP UJF TIMA Lab Grenoble France

This article studies the integration of Graphics Processing Units in a Software Defined Radio environment. Two main solutions are considered, based on two levels of granularity for the parallelization. First, a fine grain parallelism solution, which is an extension of the existing solutions but adapted to operations of large computational complexity, is proposed. Second, an original solution based on coarse grain approach allowing better usage of the computing resources and easier parallelism extraction is described. For both solutions, scheduling and communication design as well as implementation are given, along with integration in the environment. Both solutions have been implemented and compared on different operations types and on multi-operations sequences. It is clearly shown that using the second solution can provide performance improvement, while the first one is not adapted to SDR applications.

关键词： GPGPU OpenCL GPU SDR simd parallelism GNURadio

来源：评论

学校读者我要写书评

暂无评论

A NOVEL ARCHITECTURE FOR HANDLING PERSISTENT OBJECTS

引用

MICROPROCESSORS AND MICROSYSTEMS 1993年第3期17卷 131-138页

作者： LAVINGTON, SH Department of Computer Science University of Essex Wivenhoe Park Colchester CO4 35Q UK

The storage and processing of persistent objects presents opportunities for add-on hardware support. Particularly, there are aspects of memory management and whole-structure processing which are seen to benefit from a novel kind of simd-parallel architecture. This paper discusses the top-down requirements for handling persistent objects and then describes an active memory unit called the IFS/2 which meets these requirements. Performance figures for prototype hardware are given, and its application to an object-oriented data model is briefly described.

关键词： ASSOCIATIVE MEMORY PATTERN DIRECTED SEARCH RELATIONAL ALGEBRAIC PROCESSING simd parallelism ACTIVE MEMORY

来源：评论

学校读者我要写书评

暂无评论

Fast CUDA-based Codec for Height Fields

Fast CUDA-based Codec for Height Fields

引用

21st Telecommunications Forum (TELFOR)

作者： Durdevic, Dorde M. Tartalja, Igor I. Univ Belgrade Sch Elect Engn Belgrade 11120 Serbia

ISBN: (纸本)9781479914203

Following the advances in remote sensing technology in the last decade, the horizontal and vertical scan resolutions for digital terrains have reached the order of a meter and decimeter, respectively. At these resolutions, descriptions of real terrains require very large storage spaces. Efficient storage, transfer, retrieval, and manipulation of such large amounts of data require an efficient compression method. This paper presents a method for fast lossy and lossless compression of regular height fields, which are a commonly used solution for representing surfaces scanned at regular intervals along two axes. The method is suitable for simd parallel implementation and thus inherently suitable for modern GPU architectures, which significantly outperform modern CPUs in computation speed, and are already present in home computers. The method allows independent decompression of individual data points, as well as progressive decompression. Even in the case of lossy decompression, the decompressed surface is inherently seamless. The method's efficiency was confirmed through a CUDA implementation of compression and decompression algorithms, and application in a terrain visualization system.

关键词： height field lossy and lossless compression progressive decompression simd parallelism GPU friendly algorithm CUDA programming model terrain visualization

来源：评论

学校读者我要写书评

暂无评论

libHOG: Energy-Efficient Histogram of Oriented Gradient Computation 18

libHOG: Energy-Efficient Histogram of Oriented Gradient Comp...

引用

18th IEEE International Conference on Intelligent Transportation Systems

作者： Iandola, Forrest N. Moskewicz, Matthew W. Keutzer, Kurt Univ Calif Berkeley Berkeley CA 94720 USA DeepScale Cairo Egypt

ISBN: (纸本)9781467365963

Histogram of Oriented Gradients (HOG) features are the underlying representation in automotive computer vision applications such as collision avoidance and lane keeping. In these applications, we have observed that HOG feature computation is often a slow and energy-intensive component of the overall pipeline. In this paper, we focus on reducing both the time taken and the energy used for computing Felzenszwalb HOG features. We achieve our results though a combination of reduced precision, simd parallelism, algorithmic changes, and outer-loop parallelism. In particular, we address a bottleneck in histogram accumulation by phrasing the problem as a gather instead of the (traditional) scatter. Additionally, we explore the tradeoffs of using L1 instead of L2 norms to compute gradients, which enables smaller operands and more simd parallelism. Overall, we are able to compute multiresolution HOG pyramids at 70fps for 640x480 images on a multicore CPU. This is a 3.6x speedup over the best known HOG implementation and a 29x speedup over the popular voc-release5 HOG code. This is also a 3.6x - 22x reduction in energy per frame compared to previous HOG implementations. Our open-source implementation is available for download.

关键词： computer vision parallel processing pedestrians traffic engineering computing Felzenszwalb HOG features simd parallelism automotive computer vision applications collision avoidance energy-efficient histogram of oriented gradient computation lane keeping libHOG multicore CPU multiresolution HOG pyramids outer-loop parallelism Feature extraction Histograms Image resolution Parallel processing Table lookup Vehicles Yttrium

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：