AWS HPC Blog

This blog post will explore the technical attributes of computationally demanding high performance computing (HPC) workloads within the financial services sector. By examining the key characteristics of your workloads, we will guide you through a decision tree approach to help determine the most suitable HPC platform for the cloud – whether it be a commercial vendor solution, open-source option, or a fully cloud-native implementation.

Running High Performance Computing workloads in AWS offers immense scale and flexibility, but many on-premises approaches to cost management don’t apply in the cloud. In this post we explore the key levers to reducing unit costs, understanding consumption, and how efficiency and effectiveness are key measures of success.

As climate change escalates, power infrastructure faces growing risks. Explore how the ClimateEarthDigitalTwin (CDT™) platform from riskthinking.AI leverages AWS HPC to assess these risks and enable resilience planning for the energy sector. Learn how this cutting-edge solution can safeguard your critical assets.

Discover how Petrobras and Universidade Federal Fluminense (Rio de Janeiro — Brazil) developed an innovative HPC solution on AWS, leveraging Spot Instances to optimize costs. Explore the automations in place to avoid interruptions and use the lowest-cost instances available.

Autonomous robots are increasingly used across industries, from warehouses to space exploration. While developing these robots requires complex simulation and reinforcement learning (RL), setting up training environments can be challenging and time-consuming. AWS Batch multi-node parallel (MNP) infrastructure, combined with NVIDIA Isaac Lab, offers a solution by providing scalable, cost-effective robot training capabilities for sophisticated behaviors and complex tasks.

Discover how to coordinate multiple applications in separate containers within a single AWS Batch job definition. Learn the benefits of this approach and how to share resources between containers for more efficient, scalable deployments.

Developing robust investment strategies requires thorough testing, but relying solely on historical data can introduce biases and limit your insights. Learn how synthetic data from agent-based models can provide an unbiased testbed to systematically evaluate your strategies and prepare for future market scenarios. Part 2 covers implementation details and results.

Developing robust investment strategies requires thorough testing, but relying solely on historical data can introduce biases and limit your insights. Learn how synthetic data from agent-based models can provide an unbiased testbed to systematically evaluate your strategies and prepare for future market scenarios. Part 1 of 2 covers the theoretical foundations of the approach.

Struggling with bottlenecks in your batch processing? AWS Batch’s new resource aware scheduling capability could be the solution your business needs. This feature allows you to define and manage consumable resources, helping maximize the use of your compute power. Check out our blog to learn more.

Quantum mechanics meets drug discovery: QSimulate’s latest advancements in QM-based FEP simulation are poised to transform the industry. Our blog post takes you on a journey through the groundbreaking science and innovative software that are redefining the future of drug design.