CYBELE: A Hybrid Architecture of HPC and Big Data for AI Applications in Agriculture
Authors/Creators
- 1. High Performance Computing Center Stuttgart (HLRS), University of Stuttgart, Stuttgart, Germany
- 2. BioSense Institute Serbia
- 3. University of Strathclyde
- 4. University of Piraeus
- 5. Institute of Bioorganic Chemistry of the Polish Academy of Sciences, Poznan Supercomputing and Networking Center (PSNC), Poznan, Poland
Description
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.
Files
Restricted
The record is publicly accessible, but files are restricted. <a href="https://zenodo.org/account/settings/login?next=https://zenodo.org/records/5597977">Log in</a> to check if you have access.