發(fā)布時(shí)間：2018-05-02 16:29

  本文選題：GPU + CUDA��； 參考：《中南大學(xué)》2013年碩士論文

【摘要】：摘要：隨著地理信息系統(tǒng)技術(shù)、遙感技術(shù)、計(jì)算機(jī)技術(shù)以及信息技術(shù)的快速發(fā)展,以多種技術(shù)結(jié)合為手段,從海量的實(shí)時(shí)數(shù)據(jù)源中提取有用信息,用以解決資源管理配置、城市規(guī)劃管理、土地信息管理、生態(tài)環(huán)境管理、基礎(chǔ)設(shè)施建設(shè)、交通規(guī)劃等問(wèn)題。然而,對(duì)于海量數(shù)據(jù)的處理,其運(yùn)算量相對(duì)于一般的處理來(lái)說(shuō)會(huì)有幾百到幾千倍的增加,不僅嚴(yán)重考驗(yàn)著計(jì)算機(jī)的數(shù)據(jù)處理能力,而且考驗(yàn)著算法設(shè)計(jì)在處理海量數(shù)據(jù)問(wèn)題中的有效性。高性能計(jì)算技術(shù)突飛猛進(jìn)的發(fā)展,給海量數(shù)據(jù)的處理工作帶來(lái)了新的方向。多核CPU技術(shù)以及圖形處理器(GPU)日益增強(qiáng)的可編程性以及高效計(jì)算能力,促進(jìn)處理方式的巨大變化,由以往的CPU端編程處理,逐漸過(guò)渡到CPU+GPU異構(gòu)編程處理,再發(fā)展到分布式處理,以及云計(jì)算。處理方式的改變帶動(dòng)了處理效率的提高,并由以往單一的計(jì)算機(jī)到現(xiàn)今多臺(tái)計(jì)算機(jī)同時(shí)計(jì)算,同時(shí)實(shí)現(xiàn)了事務(wù)處理的均衡分配,可有效的利用各種計(jì)算機(jī)資源以提高處理效率。本文中結(jié)合GPU并行計(jì)算技術(shù),探討如何利用GPU存儲(chǔ)器特點(diǎn)完成對(duì)海量數(shù)據(jù)的處理任務(wù),以取得較好的加速效果。 本文所做的工作有如下幾個(gè)方面： 1、針對(duì)海量遙感影像數(shù)據(jù)的切分與調(diào)度問(wèn)題,提出了基于CPU+GPU異構(gòu)編程快速處理影像數(shù)據(jù)的解決方案,探討利用不同的GPU存儲(chǔ)器實(shí)現(xiàn)遙感影像數(shù)據(jù)的重采樣處理。基于GPU并行技術(shù)的影像處理,應(yīng)考慮到算法的設(shè)計(jì)和處理任務(wù)的劃分,合理的劃分線程,實(shí)現(xiàn)并行執(zhí)行優(yōu)化、存儲(chǔ)器優(yōu)化、指令使用優(yōu)化,以提高整體的處理效率。闡述了統(tǒng)一計(jì)算設(shè)備架構(gòu)(Compute Unified Device Architecture, CUDA)通用計(jì)算模型構(gòu)架及其特點(diǎn),并在此基礎(chǔ)上實(shí)現(xiàn)了對(duì)于遙感影像數(shù)據(jù)的重采樣加速。 2、提出GPU并行處理空間聚類中復(fù)雜的數(shù)值計(jì)算問(wèn)題。以二部圖空間聚類算法為例,依據(jù)聚類中數(shù)值計(jì)算的特點(diǎn),以及GPU并行結(jié)構(gòu)和硬件特點(diǎn),探討合適的并行處理方式,采用全局存儲(chǔ)器、共享存儲(chǔ)器加速技術(shù),提高了數(shù)據(jù)的處理效率。實(shí)驗(yàn)結(jié)果表明,基于GPU并行計(jì)算比CPU串行計(jì)算在效率上有顯著的提高。圖14幅,表7個(gè),參考文獻(xiàn)47篇。
[Abstract]:Abstract: with the rapid development of geographic information system technology, remote sensing technology, computer technology and information technology, useful information is extracted from massive real-time data sources to solve the problem of resource management. Urban planning management, land information management, ecological environment management, infrastructure construction, traffic planning and other issues. However, for the processing of massive data, its computation will increase hundreds to thousands times compared with the normal processing, which not only seriously tests the computer's data processing ability, It also tests the effectiveness of algorithm design in dealing with massive data problems. The rapid development of high performance computing technology has brought a new direction to the processing of massive data. The increasing programmability and high efficiency computing power of multi-core CPU technology and graphics processor (GPU) promote the great change of processing methods, and gradually transition from the former CPU side programming processing to the CPU GPU heterogeneous programming processing. And then into distributed processing, and cloud computing. The change of processing mode leads to the improvement of processing efficiency, and from the former single computer to many computers at the same time, it realizes the balanced allocation of transaction processing, which can effectively use all kinds of computer resources to improve the processing efficiency. Combined with GPU parallel computing technology, this paper discusses how to use the characteristics of GPU memory to complete the processing of massive data in order to achieve a better acceleration effect. The work done in this paper is as follows: 1. Aiming at the problem of segmentation and scheduling of massive remote sensing image data, a solution of fast processing of remote sensing image data by heterogeneous programming based on CPU GPU is proposed, and different GPU memory is used to realize resampling processing of remote sensing image data. The image processing based on GPU parallel technology should consider the design of algorithm and partition of processing tasks, reasonably partition threads, realize parallel execution optimization, memory optimization, instruction usage optimization, in order to improve the overall processing efficiency. In this paper, the general computing model architecture of computer Unified Device Architecture (CUDAA) and its characteristics are described. On this basis, the resampling acceleration of remote sensing image data is realized. 2. GPU parallel processing of complex numerical computation problem in spatial clustering is proposed. Taking the bipartite graph space clustering algorithm as an example, according to the characteristics of numerical calculation in clustering, as well as the parallel structure and hardware characteristics of GPU, the suitable parallel processing method is discussed. The global memory and shared memory acceleration technology are adopted. The efficiency of data processing is improved. Experimental results show that the efficiency of parallel computing based on GPU is significantly higher than that of serial computing based on CPU. There are 14 figures, 7 tables and 47 references.
【學(xué)位授予單位】：中南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP751;P208

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 楊靖宇;張永生;張宏蘭;紀(jì)松;;基于可編程圖形硬件的遙感影像并行處理研究[J];測(cè)繪工程;2008年03期

2 陳靜,龔健雅,朱欣焰,李清泉;海量影像數(shù)據(jù)的Web發(fā)布與實(shí)現(xiàn)[J];測(cè)繪通報(bào);2004年01期

3 鄧雪清;柵格型空間數(shù)據(jù)服務(wù)體系結(jié)構(gòu)與算法研究[J];測(cè)繪學(xué)報(bào);2003年04期

4 萬(wàn)元嵬;程承旗;宋樹(shù)華;;大數(shù)據(jù)量遙感影像快速顯示剖分組織方法研究[J];地理與地理信息科學(xué);2009年03期

5 鄭群英;周曉光;欒柱曉;;影像金字塔增量更新方法[J];地理空間信息;2009年05期

6 許雪貴;張清;;基于CUDA的高效并行遙感影像處理[J];地理空間信息;2011年06期

7 黃杰;劉仁義;劉南;沈林芳;王娜;;海量遙感影像管理與可視化系統(tǒng)的研究與實(shí)現(xiàn)[J];浙江大學(xué)學(xué)報(bào)(理學(xué)版);2008年06期

8 康俊鋒;杜震洪;劉仁義;方雷;;基于GPU加速的遙感影像金字塔創(chuàng)建算法及其在土地遙感影像管理中的應(yīng)用[J];浙江大學(xué)學(xué)報(bào)(理學(xué)版);2011年06期

9 曾志;劉仁義;李先濤;張豐;包衛(wèi)正;;一種基于分塊的遙感影像并行處理機(jī)制[J];浙江大學(xué)學(xué)報(bào)(理學(xué)版);2012年02期

10 周波;祝忠明;劉再東;;遙感影像的瓦片金字塔切割與邊界填充研究[J];計(jì)算機(jī)與信息技術(shù);2011年10期

相關(guān)博士學(xué)位論文 前1條

1 肖漢;基于CPU+GPU的影像匹配高效能異構(gòu)并行計(jì)算研究[D];武漢大學(xué);2011年

，

本文編號(hào)：1834653