本文選題：RTI　切入點(diǎn)：高性能計(jì)算平臺(tái)　出處：《國(guó)防科學(xué)技術(shù)大學(xué)》2012年碩士論文

【摘要】：高層體系結(jié)構(gòu)HLA在軍事仿真領(lǐng)域得到了廣泛應(yīng)用。隨著應(yīng)用的不斷深入，仿真應(yīng)用的規(guī)模越來(lái)越大，模型復(fù)雜度越來(lái)越高，仿真實(shí)體之間的信息交互愈加頻繁，對(duì)仿真平臺(tái)通信和計(jì)算資源的需求不斷提高。傳統(tǒng)的基于PC機(jī)網(wǎng)絡(luò)的仿真平臺(tái)已經(jīng)不能滿足應(yīng)用需求。高性能計(jì)算平臺(tái)可以為大規(guī)模仿真應(yīng)用提供強(qiáng)大的計(jì)算和通信能力，然而傳統(tǒng)的HLA運(yùn)行支撐平臺(tái)RTI主要面向分布式網(wǎng)絡(luò)環(huán)境，在通信結(jié)構(gòu)、消息處理方式、系統(tǒng)數(shù)據(jù)一致性維護(hù)等方面都難以有效發(fā)揮高性能計(jì)算平臺(tái)的性能優(yōu)勢(shì)。因此，研發(fā)基于高性能計(jì)算平臺(tái)的并行RTI，對(duì)于充分發(fā)揮平臺(tái)高效的通信和計(jì)算能力，提高仿真系統(tǒng)運(yùn)行效率，促進(jìn)大規(guī)模仿真應(yīng)用的發(fā)展等都具有十分重要的意義。 論文針對(duì)傳統(tǒng)RTI難以有效發(fā)揮高性能計(jì)算平臺(tái)性能優(yōu)勢(shì)的現(xiàn)實(shí)問(wèn)題，以提高大規(guī)模HLA仿真系統(tǒng)運(yùn)行效率為根本目標(biāo)，對(duì)RTI通信結(jié)構(gòu)、消息處理技術(shù)、數(shù)據(jù)一致性維護(hù)方法等關(guān)鍵問(wèn)題進(jìn)行了深入研究，主要工作和創(chuàng)新點(diǎn)如下： （1）高性能計(jì)算平臺(tái)往往提供了共享內(nèi)存/IB/以太網(wǎng)等多種不同層次的硬件通信環(huán)境，然而，目前的RTI大多只提供TCP/IP通信支持，難以有效發(fā)揮高性能計(jì)算平臺(tái)多層次并行通信優(yōu)勢(shì)。為此，論文提出了一種支持多層次并行通信的RTI通信結(jié)構(gòu)，該通信結(jié)構(gòu)采用多線程并行處理技術(shù)，把不同硬件通信環(huán)境數(shù)據(jù)的發(fā)送和接收分配到不同的線程處理，，從而可有效支持不同層次通信環(huán)境之間的并行通信，提高系統(tǒng)的通信效率和吞吐率。 （2）RTI中消息的處理可分為接收解包和分類處理兩個(gè)階段。目前的RTI往往采用單線程消息處理方法，兩個(gè)階段只能串行進(jìn)行，消息處理效率較低。為此，論文提出了一種基于消息緩沖隊(duì)列的多線程流水處理方法，該方法通過(guò)在兩個(gè)消息處理階段中加入消息緩沖隊(duì)列，數(shù)據(jù)接收解包后放入消息緩沖隊(duì)列，再由專門(mén)的消息分類處理線程根據(jù)具體消息類型進(jìn)行相應(yīng)處理。測(cè)試結(jié)果表明：在消息交互較為頻繁的HLA仿真中，與傳統(tǒng)的單線程處理方法相比，采用該方法消息接收處理的效率可提高8%以上。 （3）數(shù)據(jù)一致性是HLA仿真正確運(yùn)行的前提。目前的RTI要么采用集中式策略，維護(hù)算法簡(jiǎn)單，但中心節(jié)點(diǎn)往往成為系統(tǒng)性能瓶頸；要么采用分布式策略，雖避免了系統(tǒng)性能瓶頸，但效率較低且算法復(fù)雜。綜合兩種維護(hù)策略的優(yōu)缺點(diǎn)，論文提出了一種分布集中相結(jié)合的數(shù)據(jù)一致性維護(hù)方法，該方法根據(jù)數(shù)據(jù)修改模式的不同，把盟員和聯(lián)盟數(shù)據(jù)分為兩類：盟員可立即修改的數(shù)據(jù)（自主修改數(shù)據(jù)）和需要多個(gè)盟員共同決定是否修改的數(shù)據(jù)（協(xié)商修改數(shù)據(jù)），對(duì)于前者采用分布式維護(hù)策略，由各局部RTI部件（LRC）自主維護(hù)；對(duì)于后者采用集中式維護(hù)策略，由中心RTI部件（CRC）集中維護(hù)。該方法能夠在保證正確性的基礎(chǔ)上，有效減小數(shù)據(jù)同步對(duì)系統(tǒng)性能的影響。 （4）在上述研究成果的基礎(chǔ)上，設(shè)計(jì)實(shí)現(xiàn)了基于高性能計(jì)算平臺(tái)的并行RTI軟件shmRTI。測(cè)試結(jié)果表明：shmRTI較完整地實(shí)現(xiàn)了IEEE1516規(guī)范的管理服務(wù)功能，在多核PC環(huán)境中，其節(jié)點(diǎn)內(nèi)數(shù)據(jù)吞吐率是pRTI1516的2.8倍以上，節(jié)點(diǎn)內(nèi)通信延遲僅為pRTI1516的40%以下；在具有IB/以太網(wǎng)的高性能計(jì)算平臺(tái)與PC機(jī)組成的混合網(wǎng)絡(luò)環(huán)境中，shmRTI的綜合時(shí)間推進(jìn)性能比pRTI1516可提高30%以上。
[Abstract]:The high level architecture of HLA has been widely applied in the field of military simulation. With the deepening of the application, the application of simulation model is larger and larger, more complex, simulation entities and the information interaction between the more frequent, the simulation platform of communication and computing resources needs to be improved. The traditional simulation platform PC network has can not meet the application requirements. Based on high performance computing platform can provide powerful computing and communication capabilities for large-scale simulation applications, however, traditional HLA running platform of RTI is mainly for the distributed network environment, the communication structure, message processing method, system data consistency maintenance are difficult to effectively play the performance advantages of high performance computing platform. Therefore, development of parallel computing based on RTI platform with high performance, to make full use of communication and computing capabilities of the platform effectively, improve the simulation system. It is of great significance to carry out efficiency and promote the development of large-scale simulation applications.
The real problem in the traditional RTI can not effectively play the high performance computing platform performance advantage, in order to improve the efficiency of large-scale HLA simulation system as the basic goal of RTI communication structure, message processing technology, the deep study of the key problem of data consistency maintenance methods, the main work and innovation are as follows:
(1) high performance computing platform often provides different levels of hardware shared memory /IB/ Ethernet communication environment, etc. However, the current RTI only provides TCP/IP communication support, difficult to effectively play high performance computing platform multi-level parallel communication. Therefore, this paper proposed a RTI communication architecture supports multi-level parallel communication the communication structure, using multi-threaded parallel processing technology, send different hardware communication environment and receiving data assigned to different threads, which can effectively support the parallel communication between different levels of communication environment, improve communication efficiency and throughput rate of the system.
(2) RTI news can be divided into receiving two stages of unpacking and classification. At present RTI often use a single thread message processing method, two stage serial only, message processing efficiency is low. Therefore, this paper proposes a multi thread pipelining method based on message queue, the method the two message processing join message queue stage, data receiving and unpacking into the message queue, then special message classification processing thread according to the specific types of messages are processed. The test results show that the simulation in HLA message exchange is more frequent, compared with the traditional single thread processing method, the efficiency of the method of message reception processing can be increased by more than 8%.
(3) the data consistency is a prerequisite for the correct operation of HLA simulation. The current RTI or centralized maintenance strategy, the algorithm is simple, but the center node often become the bottleneck of the system; or a distributed strategy, is to avoid the bottleneck of the system, but the efficiency is low and complexity. The advantages and disadvantages of two kinds of comprehensive maintenance strategy. This paper presents a data consistency maintenance method of combining centralized distribution, according to the data modification mode, the alliance and alliance data are divided into two categories: members can immediately modify data (independently modify data) and the need for multiple members to decide whether to modify the data (negotiation data). The former adopts distributed maintenance strategy, by the local RTI component (LRC) self maintenance; for the latter centralized maintenance strategy, from the center of the RTI parts (CRC) centralized maintenance. The method can ensure On the basis of correctness, the effect of data synchronization on the performance of the system is effectively reduced.
(4) on the basis of the above research, the design and implementation of parallel RTI software shmRTI. test results show that the platform based on High Performance Computing: shmRTI is a complete implementation of the IEEE1516 specification management services in the multi-core PC environment, the node throughput is 2.8 times more than the pRTI1516, the intra node communication the delay is only less than 40% of pRTI1516; in high performance computing with IB/ Ethernet hybrid network environment platform and PC machine in the shmRTI integrated time performance than pRTI1516 can be increased by more than 30%.

【學(xué)位授予單位】：國(guó)防科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：TP38;TP391.9

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 姚益平,盧錫城;HLA/RTI時(shí)間管理的一種優(yōu)化算法[J];電子學(xué)報(bào);2004年02期

2 劉步權(quán);王懷民;姚益平;;HLA時(shí)間管理中的死鎖問(wèn)題研究[J];電子學(xué)報(bào);2006年11期

3 唐見(jiàn)兵;李革;楊海剛;;KD-RTI軟件的測(cè)試研究[J];計(jì)算機(jī)工程;2007年03期

4 周忠;趙沁平;;一種基于興趣約束的新型組播地址分配方法[J];計(jì)算機(jī)學(xué)報(bào);2006年03期

5 姚益平;張穎星;陳欣;季利春;;基于索引排序的快速動(dòng)態(tài)區(qū)域匹配算法[J];計(jì)算機(jī)學(xué)報(bào);2009年07期

6 劉步權(quán),王懷民,姚益平;RTI中樂(lè)觀推進(jìn)機(jī)制的實(shí)現(xiàn)[J];軟件學(xué)報(bào);2004年03期

7 李伯虎,柴旭東,朱文海,邸彥強(qiáng),王鵬,施國(guó)強(qiáng),譚娟,殷潤(rùn)民,侯寶存;現(xiàn)代建模與仿真技術(shù)發(fā)展中的幾個(gè)焦點(diǎn)[J];系統(tǒng)仿真學(xué)報(bào);2004年09期

8 孫世霞,黃柯棣;RTI性能測(cè)試分析[J];系統(tǒng)仿真學(xué)報(bào);2005年04期

9 劉鐘書(shū);周忠;吳威;;BH RTI中容錯(cuò)機(jī)制的設(shè)計(jì)與實(shí)現(xiàn)[J];系統(tǒng)仿真學(xué)報(bào);2006年08期

10 陳春鵬;陳麗;王懷民;姚益平;;基于HPC環(huán)境的RTI及作戰(zhàn)仿真應(yīng)用[J];系統(tǒng)仿真學(xué)報(bào);2006年10期

本文編號(hào)：1679809