Voxel model surface offsetting for computer-aided manufacturing using virtualized high-performance computing

Autor: Mohammad M. Hossain, Thomas R. Kurfess, Nuodi Huang, Roby Lynn, Tommy Tucker, Didier Contis
Rok vydání: 2017
Předmět:
Zdroj: Journal of Manufacturing Systems. 43:296-304
ISSN: 0278-6125
DOI: 10.1016/j.jmsy.2016.12.005
Popis: Curve and surface offsetting is a common operation performed on solid models when planning toolpaths for a machining operation. This operation is usually done in a computer-aided manufacturing (CAM) software package to define the path along which the center of a cutting tool will follow to create a given feature. The CAM software then translates the toolpath created from the offset into G-Code, which is the standard programming language of CNC machine tools. The toolpath planning process can be computationally intensive; thus, a powerful workstation is required to run the CAM software effectively. These standalone workstations can be inconvenient due to their cost and size. Many organizations have been turning to virtualization as an alternative to multiple standalone workstations; virtualization allows for many users to access desktop environments that are hosted from a single remote server. This has the benefit of isolating the user from both OS and hardware requirements for certain software, and also allows them to run the applications they need from anywhere. This research explores the emerging area of virtualized general purpose computation on graphics processing units (GPGPU); this technique is used to support the development of a voxelized CAM package that allows for rapid toolpath generation for complex parts. The surface offset performance is benchmarked on various local and virtualized platforms to evaluate the losses from virtualization. Results indicate a minor loss of performance between virtualized and local GPUs, which is to be expected due to the abstraction of hardware from a virtual machine. Additionally, the development of a GPU-sharing implementation using a server operating system is described and analyzed; results indicate that, as compared to single virtual machines, the GPU-sharing approach demonstrates higher computational efficiency with the addition of compute load to the GPU.
Databáze: OpenAIRE