Cloud services

The new IaaS capabilities offered by CSPs allow organizations interested in HPC to tailor computational resources to specific project needs, and benefit from lower costs and increased flexibility. Odycloud provides dedicated services to facilitate a smooth migration so that your organization, regardless of its size and sector, can take full advantage of public IaaS. Small and midsized businesses can greatly benefit from the new technology by circumventing expensive upfront capital investment, thus giving them access to hardware traditionally reserved for large corporations, national laboratories, and research universities. Whether your goal is to migrate current software to the cloud (lift & carry) or to develop new applications able to take advantage of new capabilities, we can help you achieve your objectives. We provide, among others, the following services:

  • Optimized Amazon Machine Images (AMI) for some common HPC apps, which can be used on AWS EC2 instances and clusters
  • Virtual Machine Images for Azure that includes optimized binaries of Numerical Weather Prediction and Air Quality Modeling apps
  • Evaluation of IaaS for your organization needs and comparison of potential solutions from different CSPs
  • Evaluation of best solution for HPC apps in the public cloud
  • Benchmarking and migration of proprietary and non-proprietary software to cloud environments
  • Assessment of Total Cost of Ownership (TCO) for HPC from different CSPs
  • Customization and administration of IaaS to meet your organization’s goals

Performing HPC computations in the cloud requires matching capabilities with computational demands. Each project is unique and can benefit from tailoring IaaS to its specific needs. The below sketch shows a  configuration of an elastic cluster using several tools offered by CSPs:

 

We also provide on-site training sessions offering instructions on the use of scientific and engineering software in cloud environments. The sessions are customized based on organizational needs and can cover from the most basic concepts to the deployment of large clusters.