【摘要】：隨著科技的發(fā)展，尤其是計(jì)算機(jī)技術(shù)的發(fā)展，各個(gè)行業(yè)中的數(shù)據(jù)量都開始呈指數(shù)型增長(zhǎng)，傳統(tǒng)的串行計(jì)算能力，已經(jīng)遠(yuǎn)遠(yuǎn)不能滿足日益增長(zhǎng)的數(shù)據(jù)處理需求。在這種背景下，并行計(jì)算技術(shù)應(yīng)運(yùn)而生，其主要目的是快速解決大型且復(fù)雜的計(jì)算問題。并行計(jì)算不僅和國(guó)家的科技和經(jīng)濟(jì)發(fā)展密切相關(guān),而且直接影響到國(guó)防能力和國(guó)家安全，如核爆炸模擬，復(fù)雜系統(tǒng)精確解算、基因研究和國(guó)家機(jī)要通信的加密與解密等等。并行計(jì)算能力是衡量國(guó)家實(shí)力的重要標(biāo)志。 雖然并行計(jì)算已發(fā)展多年，在一些具體問題的解決上也已經(jīng)有了較為實(shí)用的方案，總結(jié)了相當(dāng)多的經(jīng)驗(yàn)，但還遠(yuǎn)遠(yuǎn)不及串行算法那樣豐富，因此這門學(xué)科研究尚不成熟。并行算法與串行算法的最大不同之處在于，不僅需要考慮問題本身的解決方法，還需要考慮問題所適用的并行模型，若要達(dá)到效率最大化，還需要考慮處理器架構(gòu)、網(wǎng)絡(luò)連接等因素，這必然會(huì)增加并行算法的設(shè)計(jì)和實(shí)現(xiàn)難度。 本論文在分析了并行計(jì)算中的各種難題以及國(guó)內(nèi)外研究現(xiàn)狀的基礎(chǔ)上，針對(duì)并行計(jì)算模型的種種難題，提出了一種新的滿足多核處理器機(jī)群計(jì)算需求的分層異構(gòu)并行的通用計(jì)算模型，并對(duì)其中的關(guān)鍵技術(shù)做了初步研究,具體內(nèi)容如下: （1）提出了一種新的滿足多核處理器機(jī)群計(jì)算需求的分層異構(gòu)并行的通用計(jì)算模型，該模型將目標(biāo)問題的開發(fā)劃分為程序模型算法設(shè)計(jì)、并行程序設(shè)計(jì)、并行程序執(zhí)行三個(gè)階段。程序模型算法設(shè)計(jì)階段，開發(fā)人員面對(duì)參數(shù)化的并行機(jī)設(shè)計(jì)程序模型算法；并行程序設(shè)計(jì)階段，開發(fā)人員利用并行開發(fā)平臺(tái)開發(fā)具體的并行程序，實(shí)現(xiàn)并行任務(wù)；并行程序執(zhí)行階段，并行程序運(yùn)行在相應(yīng)的軟硬件架構(gòu)下，通過解釋系統(tǒng)優(yōu)化的計(jì)算參數(shù)優(yōu)化指令執(zhí)行效率。 （2）對(duì)模型框架進(jìn)行細(xì)化和實(shí)現(xiàn)，針對(duì)分層異構(gòu)模型的分層，在不同的層次設(shè)計(jì)相應(yīng)的方法庫、參數(shù)庫、程序復(fù)用庫等工具對(duì)模型功能以匹配，分層實(shí)現(xiàn)并行算法設(shè)計(jì)與實(shí)現(xiàn)的過程，最終實(shí)現(xiàn)并行計(jì)算模型的動(dòng)態(tài)性、自適應(yīng)性、可重構(gòu)性與通用性。 （3）在不同的層次之間，提出了語言解釋系統(tǒng)和編譯系統(tǒng)，，實(shí)現(xiàn)層次之間的鏈接，保證了系統(tǒng)模型的框架的完整性和可實(shí)現(xiàn)性。 （4）利用該異構(gòu)并行通用計(jì)算模型，實(shí)現(xiàn)了疊前偏移程序并行算法的設(shè)計(jì)。疊前偏移程序算法是石油探測(cè)中經(jīng)典算法之一，該算法的串行程序已經(jīng)較為完善，但其并行算法一直是個(gè)較為復(fù)雜的問題。應(yīng)用該模型很好地解決了其并行性。 該通用并行計(jì)算框架對(duì)應(yīng)用開發(fā)人員提供簡(jiǎn)單易用的設(shè)計(jì)語言，實(shí)現(xiàn)并行計(jì)算程序設(shè)計(jì)的高效性、正確性、普適性。因而具有廣泛的應(yīng)用前景和顯著的社會(huì)效益。分層異構(gòu)并行的通用計(jì)算模型為應(yīng)用開發(fā)人員提供獨(dú)立于硬件的可擴(kuò)展的編程接口，為具有普遍性的問題建立方法庫，為程序運(yùn)行平臺(tái)建立參數(shù)庫，綜合管理不同的計(jì)算資源，合理分配計(jì)算任務(wù)，減輕程序的開發(fā)難度以及應(yīng)用開發(fā)人員的工作量。
[Abstract]:With the development of science and technology, especially the development of computer technology, the amount of data in each industry is beginning to be exponential growth, and the traditional serial computing power is far from meeting the increasing demand of data processing. In this background, the parallel computing technology has come into being, and its main purpose is to quickly solve large and complex computing problems. Parallel computing is not only closely related to the state's science and technology and economic development, but also directly affects national defense capability and national security, such as nuclear explosion simulation, accurate solution of complex system, gene research and encryption and decryption of communication between national machine and so on. The ability of parallel computation is an important symbol to measure the national strength. Although the parallel computing has been developed for many years, a more practical solution has been made in the solution of some specific problems, and a considerable amount of experience has been summarized, but it is far less abundant than the serial algorithm, so the research of this subject is not yet feasible. The maximum difference between the parallel algorithm and the serial algorithm is not only to consider the solution of the problem itself, but also to consider the parallel model applicable to the problem. If the efficiency is maximized, the processor architecture, network connection, etc. need to be taken into account. In addition, this will increase the design and implementation of the parallel algorithm. In this paper, based on the analysis of the various problems in parallel computation and the current research situation at home and abroad, a new, multi-core processor cluster, which can meet the needs of multi-core processor cluster, is put forward in order to solve the problems of parallel computing model. In this paper, the key technology in the model is studied and the key technology in the model is studied in detail. The method is as follows: (1) A new, hierarchical and heterogeneous parallel general-purpose computing model for multi-core processor cluster computing needs is proposed, which divides the development of the target problem into a program model algorithm design, parallel program design and parallel program execution In the design stage of the program model, the developer faces the parameterized parallel machine design program model algorithm, and the developer uses the parallel development platform to develop the specific parallel program in the design phase of the parallel program, so as to realize the parallel task, in that sequence execution stage, the parallel program is run under the corresponding software and hardware structure, and the optimization of the calculation parameter of the system optimization is and (2) refining and implementing the model framework, and aiming at the layering of the hierarchical heterogeneous model, and designing the corresponding method library, the parameter library, the program multiplexing library and the like at different levels to match the model functions so as to realize the parallel algorithm in the layering manner. and finally, the dynamic and self-adaptive of the parallel computing model can be realized, (3) At different levels, the language interpretation system and the compiling system are put forward, the link between the levels is realized, and the framework of the system model is guaranteed. and (4) utilizing the heterogeneous parallel general-purpose computing model to realize the pre-stack The algorithm of pre-stack migration is one of the classical algorithms in petroleum exploration, and the serial program of the algorithm is perfect, but its parallel algorithm It's a more complex problem. Application of the model The general parallel computing framework provides a simple and easy-to-use design language for the application developer to realize the parallel computing program. The invention has the advantages of high efficiency, correctness and universality. The application developer is provided with an extensible programming interface which is independent of the hardware, a method library is established for the problem of universality, a parameter library is established for the program running platform, and the comprehensive management is different computing resources, reasonably allocating computing tasks, and reducing the development of programs
【學(xué)位授予單位】：中國(guó)海洋大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP338.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳鵬,張立昂;PRAM模型模擬RMESH模型的2種方案[J];北京大學(xué)學(xué)報(bào)(自然科學(xué)版);2005年03期

2 周浩;鐘波;羅志才;張坤;;OpenMP并行算法在衛(wèi)星重力場(chǎng)模型反演中的應(yīng)用[J];大地測(cè)量與地球動(dòng)力學(xué);2011年05期

3 劉勁松;劉福田;劉俊;郝天珧;;地震層析成像LSQR算法的并行化[J];地球物理學(xué)報(bào);2006年02期

4 于秀敏,李建中,郭風(fēng);高性能并行計(jì)算的曙光:機(jī)群系統(tǒng)[J];哈爾濱學(xué)院學(xué)報(bào);2004年02期

5 陶應(yīng)龍;王建國(guó);牛勝利;范如玉;;MCATNP蒙特卡羅粒子輸運(yùn)程序的MPI并行化[J];核電子學(xué)與探測(cè)技術(shù);2011年05期

6 沈緒榜;;MPP系統(tǒng)芯片體系結(jié)構(gòu)技術(shù)的發(fā)展[J];中國(guó)科學(xué)(E輯:信息科學(xué));2008年06期

7 張理論;葉紅;吳建平;宋君強(qiáng);;基于最大負(fù)載偏移率的并行負(fù)載平衡性能分析[J];計(jì)算機(jī)研究與發(fā)展;2010年06期

8 喬香珍,楊曄;基于LogP模型的并行計(jì)算模擬器[J];計(jì)算機(jī)研究與發(fā)展;1997年09期

9 申俊,鄭緯民;異構(gòu)并行工作站機(jī)群系統(tǒng)的性能評(píng)價(jià)指標(biāo)[J];計(jì)算機(jī)研究與發(fā)展;1998年03期

10 林智華;對(duì)陣列處理機(jī)和多處理機(jī)的深入比較[J];福建金融管理干部學(xué)院學(xué)報(bào);2004年01期

相關(guān)博士學(xué)位論文 前1條

1 胡悅;并行計(jì)算時(shí)間與存儲(chǔ)空間關(guān)系研究[D];上海大學(xué);2011年

本文編號(hào)：2370249