.png){kind=icon}
.png){kind=icon}
Return
Mobile Cloud computing architecture for massively parallelizable geometric computation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compind.2020.103336.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A B S T R A C T Cloud Computing is one of the most disruptive technologies of this century. This technology has been widely adopted in many areas of the society. In the field of manufacturing industry, it can be used to provide advantages in the execution of the complex geometric computation algorithms involved on CAD/CAM processes. The idea proposed in this research consists in outsourcing part of the load to be com-puted in the client machines to the cloud through the Mobile Cloud Computing paradigm. This practice gives substantial benefits to both the clients and the software-provider in terms of costs, flexibility, ubiq-uity and performance. In this document, an outsourcing architecture is proposed based on this paradigm. Extensive experiments have been done using highly parallelizable computational geometry operations to show the strengths and weaknesses of the proposal in combination of specialized computing plat-forms in the cloud. The results suggest that there are some issues that affect the overall performance and the stability of the QoS: the network communication delay, and the number of simultaneous clients and multiple requests. Some solutions have been proposed to face these challenges. (c) 2020 Elsevier B.V. All rights reserved.
Keywords:
GPU computing
GPU
CUDA
Cloud offloading
Cloud computing
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.1
Papers:
2.9K
Citations:
1.1W