CYBELE: A Hybrid Architecture of HPC and Big Data for AI Applications in Agriculture
| Main Authors: | Naweiluo Zhou, Li Zhong, Dennis Hoppe, Branislav Pejak, Oskar Marko, Javier Cardona, Mikolaj Czerkawski, Ivan Andonovic, Craig Michie, Christos Tachtatzis, Emmanouil Alexakis, Philip Mavrepis, Dimosthenis Kyriazis, Marcin Pospieszny |
|---|---|
| Format: | Book publication-section Journal |
| Bahasa: | eng |
| Terbitan: |
CRC Press
, 2021
|
| Online Access: |
https://zenodo.org/record/5597977 |
Daftar Isi:
- Big-data analytics hosted by Cloud clusters are becoming more data-intensive and computation-intensive, mainly due to development in Artificial Intelligence (AI) applications. High Performance Computing (HPC) systems are often used to execute large-scale programs, such as programs performing engineering, scientific or financial simulations that demand low latency and high throughput. By taking advantage of HPC systems, AI applications have the potential to achieve better performance compared to that on Cloud. In general, an AI application incorporates a complex list of software and therefore its user needs flexibility to customize the working environment. However, HPC systems, supporting multi-tenant environments, typically provide complete stacks of software packages and often do not allow user customization in contrast to Cloud systems. Containerization could offer a solution for provisioning flexible execution environments for AI applications on HPC clusters.