论文标题
3D原语GPGPU生成3D图形系统中的体积可视化
3D Primitives Gpgpu Generation for Volume Visualization in 3D Graphics Systems
论文作者
论文摘要
本文讨论了基于通用图形处理单元（GPGPU）技术的3D图形原始计算机系统生成（3D段）的研究。它基于体积3D原始生成的一般方法和用于3D线的体素化算法，该算法先前由作者提出和研究。我们考虑了一种参数方法的计算统一设备架构师（CUDA）实现，该方法用于生成3D线段和在现代图形处理单元上发电的特征。测试工作台上的实验表明，在图形处理单元（GPU）上同时生成固定长度和任意长度的3D段的相对效率低下。与现有的最新方法相比，实验研究证明了通过我们的方法产生的解决方案的有效性和质量。
This article discusses the study of 3D graphic volume primitive computer system generation (3D segments) based on General Purpose Graphics Processing Unit (GPGPU) technology for 3D volume visualization systems. It is based on the general method of Volume 3D primitive generation and an algorithm for the voxelization of 3D lines, previously proposed and studied by the authors. We considered the Compute Unified Device Architect (CUDA) implementation of a parametric method for generating 3D line segments and characteristics of generation on modern Graphics Processing Units. Experiments on the test bench showed the relative inefficiency of generating a single 3D line segment and the efficiency of generating both fixed and arbitrary length of 3D segments on a Graphics Processing Unit (GPU). Experimental studies have proven the effectiveness and the quality of produced solutions by our method, when compared to existing state-of-the-art approaches.
