基于CUDA的SMAC算法并行化
發(fā)布時(shí)間:2018-06-15 17:36
本文選題:計(jì)算流體力學(xué) + 統(tǒng)一計(jì)算設(shè)備架構(gòu) ; 參考:《西安郵電大學(xué)學(xué)報(bào)》2016年05期
【摘要】:改進(jìn)SMAC(Simplified Marker and Cell)算法,增強(qiáng)其對(duì)流體模擬的實(shí)時(shí)處理能力。采用點(diǎn)差分格式對(duì)求解壓力場(chǎng)和速度更新的偏微分方程進(jìn)行離散化;引入消除數(shù)據(jù)相關(guān)性的存儲(chǔ)算法以減少數(shù)據(jù)傳輸,并借助分層存儲(chǔ)機(jī)制提高訪存比,采用并行歸約增加線程并行度;在統(tǒng)一計(jì)算設(shè)備架構(gòu)平臺(tái)下,對(duì)離散化的SMAC算法進(jìn)行改進(jìn)、優(yōu)化及并行化實(shí)現(xiàn)。純粹計(jì)算及多次迭代模擬實(shí)驗(yàn)結(jié)果顯示,改進(jìn)算法提速明顯,可實(shí)現(xiàn)對(duì)一般場(chǎng)景的實(shí)時(shí)模擬。
[Abstract]:The algorithm of simplified Marker and cell is improved to enhance its real time processing ability for fluid simulation. The point difference scheme is used to discretize the partial differential equations to solve the pressure field and the velocity update, the storage algorithm to eliminate the data correlation is introduced to reduce the data transmission, and the hierarchical storage mechanism is used to improve the memory access ratio. Parallel reduction is used to increase the degree of thread parallelism, and the discrete SMAC algorithm is improved, optimized and parallelized on the platform of unified computing equipment architecture. The experimental results of pure computation and iterative simulation show that the improved algorithm increases the speed obviously and can realize the real-time simulation of general scenes.
【作者單位】: 西安郵電大學(xué)電子工程學(xué)院;西安郵電大學(xué)計(jì)算機(jī)學(xué)院;
【基金】:國(guó)家自然科學(xué)基金資助項(xiàng)目(61136002) 西安市科技發(fā)展計(jì)劃資助項(xiàng)目(CXY1440(10))
【分類號(hào)】:O35;TP338.6
【相似文獻(xiàn)】
相關(guān)期刊論文 前4條
1 張永學(xué),趙月軍,曹樹良,王國(guó)玉;解不可壓縮流動(dòng)N-S方程的隱式SMAC方法[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2004年02期
2 謝海英,吳克啟;用SMAC方法對(duì)二維非定常流動(dòng)的數(shù)值模擬[J];上海理工大學(xué)學(xué)報(bào);1999年04期
3 張永學(xué);李振林;趙洪濱;;求解非定常不可壓湍流的SMAC隱式方法[J];機(jī)械工程學(xué)報(bào);2006年11期
4 ;[J];;年期
,本文編號(hào):2022889
本文鏈接:http://sikaile.net/kejilunwen/jisuanjikexuelunwen/2022889.html
最近更新
教材專著