基于Fork/Join框架的等值面快速生成并行算法

A Parallel Algorithm of Rapid Isosurface Generation Based on Fork/Join Framework

针对传统串行等值面提取算法在处理离散点数量多、网格点密度大的数据时生成效率差的问题,提出一种新的基于Fork/Join框架下的等值面快速生成并行算法。通过对传统串行算法中的关键步骤进行并行计算可行性分析,提出可以实施并行计算的四个单独步骤:离散点数据网格化处理、等值点计算、等值线追踪与光滑、等值面标记识别。通过将并行计算作用于等值面生成的这四个步骤中,减少了等值面计算的执行时间,加快了等值面的生成速度。实验结果表明,在数据计算量较大时,与传统串行算法相比,并行算法能在2秒内快速生成等值面,最大加速比高于5.0,提高了等值面的生成效率并取得了良好的绘制效果,满足了高实时性的业务需求。

In order to solve the problem of poor generating efficiency of traditional serial isosurface extraction algorithm in processing data with large number of discrete points and large density of grid points,a new parallel algorithm of rapid isosurface generation based on Fork/Join framework is proposed.By analyzing the feasibility of parallel computing for the key steps in the traditional serial algorithm,four separate steps for parallel computing are proposed:discrete point data grid processing,equivalent point calculation,contour tracing and smoothing,and isosurface marking and identification.By applying parallel computation to these four steps,the execution time of isosurface calculation is reduced and the generation speed of isosurface is accelerated.The experiment shows that compared with the traditional serial algorithm,the proposed algorithm can quickly generate the isosurface within 2 seconds with a maximum acceleration ratio higher than 5.0 when the data calculation is large,which improves the isosurface generation efficiency and achieves the great rendering effect,satisfying the business demand of high real-time.