本文選題：數(shù)值積分 + 負(fù)載平衡�。� 參考：《天津大學(xué)》2016年碩士論文

【摘要】：太陽系外的所有宇宙天體的信息幾乎都是通過光譜計算獲得的,能夠觀察到的光譜包含了大量的重要信息,例如恒星的溫度、年齡、金屬豐度以及星系組成等。目前天文領(lǐng)域有一些經(jīng)典的光譜計算工具包,例如XSPEC,ISIS,XSTART,APEC等等,雖然這些工具包可以精確地進行光譜計算的求解,但程序結(jié)構(gòu)仍停留在傳統(tǒng)的串行模式上,目前并沒有任何一個基于并行架構(gòu)的光譜計算工具。光譜計算的核心部分是數(shù)值積分,隨著GPU通用性的不斷提高,計算性能的穩(wěn)步增長,許多經(jīng)典的數(shù)值積分算法已經(jīng)發(fā)展出來GPU加速版本。但是目前現(xiàn)有的GPU加速版本的數(shù)值積分算法都是針對大區(qū)間的高維積分,并不適用于光譜的計算,光譜計算中數(shù)值積分的特點是大量的、一維的、積分區(qū)間非常小的積分計算。因此要在多GPU-CPU的混合異構(gòu)平臺上加速光譜計算,不但需要解決光譜計算的核心算法向GPU的遷移,而且必須對GPU與CPU進行合理的動態(tài)任務(wù)調(diào)度,充分發(fā)揮GPU和CPU各自的優(yōu)勢。本文提出了一種多CPU-GPU混合異構(gòu)并行方法來加速求解光譜計算。首先將計算密集型的積分部分放到了GPU上來計算,通過合理的任務(wù)粒度劃分減少主機和設(shè)備之間頻繁的數(shù)據(jù)拷貝來提高計算的性能。其次,提出了一種基于多個CPU與多個GPU之間的動態(tài)任務(wù)調(diào)度策略,該策略基于任務(wù)隊列和共享內(nèi)存的方法,該種方法相對于傳統(tǒng)的客戶機-服務(wù)器的體系結(jié)構(gòu)可以很好地減少額外的通訊開銷。最后,綜合理論分析和實驗驗證了本文所提出的方法的有效性和準(zhǔn)確性,實驗顯示,使用24個CPU核、3個GPU設(shè)備,相對于傳統(tǒng)的串行APEC實現(xiàn)方法,可以將整體的計算加速300倍,相對于純CPU的MPI并行方法,整體的計算加速也有22倍。此外,本文提出的方法也可以適用于單個任務(wù)計算量小,但總體任務(wù)量巨大的應(yīng)用,使用本文提出的方法,在求解非電離平衡的常微分方程的計算中,相對于純MPI的并行方法提速了15倍。
[Abstract]:Almost all the information of cosmic celestial bodies outside the solar system is obtained by spectral calculation. The observable spectra contain a lot of important information, such as star temperature, age, metal abundance and galaxy composition. At present, there are some classical spectral calculation toolkits in the field of astronomy, such as XSPECO ISISI XSTARTAPEC and so on. Although these toolkits can accurately solve the spectral calculation, the program structure is still in the traditional serial mode. At present, there is no spectral computing tool based on parallel architecture. The core part of spectral computation is numerical integration. With the improvement of the universality of GPU and the steady increase of computational performance, many classical numerical integration algorithms have been developed GPU accelerated version. But the current GPU accelerated version of the numerical integration algorithm is aimed at the high-dimensional integral of large interval and is not suitable for spectral calculation. The characteristics of numerical integration in spectral calculation are a large number of one-dimensional integral calculations with very small integral interval. Therefore, in order to accelerate spectral computation on mixed heterogeneous platforms with multiple GPU-CPU, it is necessary not only to solve the migration from the core algorithm of spectral computation to GPU, but also to schedule reasonably the dynamic tasks between GPU and CPU, so as to give full play to the respective advantages of GPU and CPU. In this paper, a multi CPU-GPU hybrid heterogeneous parallel method is proposed to accelerate the spectral computation. Firstly, the computation-intensive integral is put on the GPU to improve the computing performance by reducing the frequent data copy between the host and the device by reasonable task granularity partition. Secondly, a dynamic task scheduling strategy based on multiple CPU and multiple GPU is proposed, which is based on task queue and shared memory. Compared with the traditional client-server architecture, this method can reduce the extra communication cost. Finally, the effectiveness and accuracy of the proposed method are verified by comprehensive theoretical analysis and experiments. The experimental results show that using 24 CPU cores and 3 GPU devices can speed up the whole calculation by 300 times compared with the traditional serial APEC implementation method. Compared with the pure CPU MPI parallel method, the overall computational acceleration is 22 times. In addition, the method proposed in this paper can also be used in the calculation of ordinary differential equations of non-ionization equilibrium, which has a small amount of computation but a large amount of total task. Compared with the parallel method of pure MPI, the speed of the parallel method is increased by 15 times.
【學(xué)位授予單位】：天津大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：P144.1-39

【相似文獻】

相關(guān)期刊論文 前6條

1 ;國外資料索引[J];激光與紅外;1974年11期

2 曾維楊，毛叔其，，毛延哲;“李時珍石”晶格振動光譜計算[J];光散射學(xué)報;1995年Z1期

3 湯大新;武志堅;潘守甫;;C/H_2O復(fù)合微粒子的光學(xué)截面及發(fā)射率光譜計算[J];紅外研究;1990年06期

4 張虎;戴景民;辛春鎖;;氮氣CARS理論光譜簡化計算及應(yīng)用[J];固體火箭技術(shù);2009年03期

5 曾維揚;CBrF_3晶格振動光譜計算和分析[J];光譜學(xué)與光譜分析;1996年04期

6 ;光譜與光譜理論[J];中國光學(xué)與應(yīng)用光學(xué)文摘;1997年06期

相關(guān)會議論文 前1條

1 張睿挺;張強;宋建;莊巍;;蛋白質(zhì)水溶液體系動力學(xué)光譜理論研究[A];中國化學(xué)會第28屆學(xué)術(shù)年會第13分會場摘要集[C];2012年

相關(guān)博士學(xué)位論文 前2條

1 許法強;基于光譜的多色復(fù)制技術(shù)研究及實現(xiàn)[D];武漢大學(xué);2013年

2 孟凡;基于微結(jié)構(gòu)的新型光子器件及相關(guān)性能研究[D];北京郵電大學(xué);2015年

相關(guān)碩士學(xué)位論文 前2條

1 徐星宇;多GPU-CPU混合異構(gòu)平臺下的光譜計算優(yōu)化[D];天津大學(xué);2016年

2 趙婉雪;BaBPO_5中Sm~（2+）還原與穩(wěn)定性研究[D];蘇州大學(xué);2010年

本文編號：1814166