线程级并行计算在图形渲染引擎中的研究  

Research on graphic rendering engine with thread-level parallelism method

作　　者：赵建斌[1] 李灵巧[1] 杨辉华[1] 

机构地区：[1]桂林电子科技大学,计算机科学与工程学院,广西桂林541004

出　　处：《计算机工程与设计》2011年第12期4143-4146,共4页Computer Engineering and Design

摘　　要：针对并行计算技术在当前图形渲染系统中应用层面较浅的问题,为提高多核平台下图形应用程序CPU利用率,提出了一种新的Fork-Join多线程渲染方案。对当前流行的开源图形渲染引擎——OGRE引擎的渲染框架进行了多线程优化,用OpenMP方法对图形引擎的逻辑帧实现并行化,根据Win32线程库和DirectX11的多线程支持提出了一种渲染帧并行化方法,并将其应用于图形引擎。在多核平台上的实验结果表明,该方案能有效提高渲染速率和CPU利用率,改善CPU负载均衡。Aimed at the problems of the low level application of parallel computing technology in graphic rendering systems and to increase the CPU utilization of graphic application program in multi-core systems,a new fork-join multithreaded rendering method is presented.A multithreaded optimization is applied to a popular open sourced graphic rendering engine named OGRE.Firstly,the logical frame is parallelized by the method of OpenMP.Then,according to the Win32 library and the DirectX11 multithread support,a new method is presented to parallelize the rendering frame and then is applied to graphic engine.The test on the multi-core platform shows that the optimized engine gains a high rendering speed and CPU utilization,and also better CPU load balancing.

关 键 词：并行计算 多核平台 多线程 图形渲染 延迟执行 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]