Petrobras optimizes cost and capacity of HPC applications with Amazon EC2 Spot Instances
HPC Blog
Petrobras and the Federal Fluminense University developed Sim@Cloud, a framework for optimizing high-performance computing (HPC) workloads using Amazon EC2 Spot Instances, achieving significant cost savings and improved efficiency.
- Developed a hybrid system combining on-premises and cloud resources
- Used AWS ParallelCluster and EC2 Spot Instances for unlimited computing power
- Achieved cost savings ranging from 43% to 90%
- Created a framework with two main components: Launcher and Execution Manager
- Implemented machine learning to predict simulation execution times and select optimal instances
- Used checkpoint and restart capabilities to manage Spot Instance interruptions
The solution enables Petrobras to handle peak computational demands more efficiently, reducing costs and improving productivity for complex simulations in the oil and gas industry.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
2024
2026
2024
2026
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.