High-performance computing (HPC) is defined as the ability to process a massive amount of data and perform complex calculations at high speeds. Technologies such as DA and AI need the big amount of data and computing resources. Especially the deep learning (DL) and neural network development need lots of computational power which cannot be achieved using traditional CPU (Central Processing Unit) based computing. DL is a field with intense computational requirements, and the choice of GPU (Graphics Processing Unit) will fundamentally determine the deep learning experience.
The purpose of this paper is to present the performance benchmark test results both data-analytics and artificial intelligence cases in the HPC system used by JAMK University of Applied Sciences (JAMK).
Read JAMK HPC-Performance Tests White Paper (pdf)
Authors
Lassi Partamies, Joni Korpihalkola, Juha Jokinen, Mika Rantonen & Janne Alatalo
Acknowledgements
JAMK has two Data Analytics projects funded by European Regional Development Fund (ERDF): New Business Innovations from Data Analytics and Information Secure R&D-environment for Data Analytics. The focus of the Information Secure R&D environment for Data Analytics project is on implementing the needed investments in order to plan, build and deploy an integrated, information secure data analytics development, i.e. HPC environment.
