Title :
Fast mesh similarity measuring based on CUDA
Author :
Tang, Jie ; Wu, Gangshan ; Xu, Bo ; Gong, Zhongliang
Author_Institution :
Nat. Key Lab. for Novel Software Technol., Nanjing Univ., Nanjing, China
Abstract :
This paper presented a fast algorithm which could measure similarity between two meshes interactively. The algorithm was based on CUDA (Compute Unified Device Architecture) technology. In order to fully utilize the computing power of GPU, we developed parallel method to construct uniform grid for fast space indexing of triangles. Special data structure was designed on device end to overcome the disadvantage of CUDA that it does not support dynamic allocation of memory. Lots of experiments were carried out and the results verified the effectiveness and efficiency of our algorithm.
Keywords :
computational geometry; computer graphic equipment; coprocessors; data structures; image matching; net structures (mechanical); parallel processing; CUDA technology; GPU; compute unified device architecture; computing power; dynamic memory allocation; fast mesh similarity measurement; space indexing; special data structure; uniform grid construction; Computational modeling; Graphics; Instruction sets; Performance evaluation; Robots; Testing; Velocity measurement; CUDA; Hausdorff distance; Mesh;
Conference_Titel :
Progress in Informatics and Computing (PIC), 2010 IEEE International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-6788-4
DOI :
10.1109/PIC.2010.5687883
