基于GPU的B样条曲面加速计算

Rapid Evaluation of B-spline Surfaces Using GPU

图形处理器(GPU)可编程性能的不断提高使得在三维几何造型系统中出现了越来越多的基于GPU的应用。提出了一个基于GPU片元程序计算B样条曲面的加速算法。通过测试算法在GPU上计算B样条曲面的时间与基于CPU的传统算法相比较,表明提出的基于GPU的加速算法效率明显高于传统算法。同时提出的算法具有良好的易用性和可扩展性,可以应用到Bézier曲面、NURBS曲面等其他参数曲面的加速计算中。

Many GPU based applications in 3D geometric modeling system have been proposed along with the augmented programmable performance of Graphics Processing Unit (GPU). A new method of rapid evaluation of B-spline surfaces was proposed with GPU fragment program. The efficiency of the proposed GPU-based evaluating method was tested and compared with the traditional method. The results show that the efficiency of the proposed algorithm outperforms the traditional algorithm. The proposed scheme can also be applied to the evaluation of other parametric surfaces such as Bézier and NURBS surfaces, with its usability and extensibility.