HPC on AWS: Innovation Without Infrastructure Constraints

on YouTube ↗33m

" summary

The talk explains how to run high-performance computing (HPC) workloads on AWS using Amazon EC2 (new instance types), Amazon FSx for Lustre, Elastic Fabric Adapter, AWS ParallelCluster and AWS Batch to remove infrastructure limits. It covers applying these services to demanding use cases—reservoir simulation, computational fluid dynamics and drug discovery—to scale and optimize large, complex simulations.

AI-written summary · about

" chapters (7)

1. 0:00Introduction
2. 0:49HPC challenges locally
3. 5:51HPC advantages on AWS
4. 10:11Key HPC services on AWS
5. 27:36Schedulers and use cases
6. 29:44Customer HPC examples
7. 32:35Conclusion

" related talks

• 38mHigh Performance Computing on AWS (HPC): Innovation Without LimitsJosé Lorenzo Cuéncar Garza (El) · AWS Summit Mexico City 2022
• 34mHPC on AWS: Innovation without infrastructure constraintsArun Subramaniyan · AWS AMER Summit May 2021
• 46mHPC to Accelerate Innovation in IndustryRayan Chikhi, Arthur Petitpierre, Patrick Lamplé · AWS Summit Paris 2024
• 10mLightning Talk: Does Cloud Elasticity Pay off for HPC Workloads?Joris Cramwinckel · Kubernetes Batch + HPC Day Europe 2023
• 39mWhat would you do with 10^6 cores? High Performance Computing in the AWS CloudFrank Munz · Voxxed Days Ticino 2019
• 48mAccelerate science, research, and innovation with AWSJason Duffe, Sanaz Vafaei, Arthur Krughkov · AWS Public Sector Symposium Ottawa 2023
• 16mA novel Cloud High Performance Computing infrastructure for userGiuseppa Muscianisi, Andrea Vanni · OpenInfra Summit Berlin 2022
• 43mWhat’s new in Amazon EC2Art Baudo · AWS Summit San Francisco 2022