Keynote: Cloud Optimization: Gurobi & Cloud Foundry
summary
Gap runs a pricing optimizer using Gurobi for linear solves, queuing 6,000 independent problems and completing them within about four hours by spinning up ephemeral EC2 instances, typically using 90 c4.4xlarge EC2s. Cloud Foundry runs on-prem to host a Java Spring Boot stack with Spring Cloud Config and RabbitMQ for work distribution while Gurobi runs in AWS, with orchestration creating and tearing down compute instances in ~2 minutes. Data virtualization fronts DB2/Oracle sources and teams wrestle with Java vs Python and agile vs science tradeoffs.
AI-written summary · about
chapters (7)
- 0:00Introduction and background
- 1:04What is optimization
- 2:48Why move to the cloud
- 3:55Cloud Foundry benefits
- 4:57Technical integration overview
- 7:26Process control and scaling
- 8:53Organizational challenges
related talks
18mKeynote: Mind the Gap: Bridging Cloud Native Innovation with Real-World Use
13mKeynote: Leveraging Cloud Foundry for Development Efficiencies
41mIntegrating optimization into your cloud journey
36mQuantum & High-Performance Computing in The Cloud
05mSponsored Keynote: The Cloud (And Your $$$) is Not Infinite: Dynamic Scheduling at Every Layer
56mKeynote on Building the Cloud for You
21mKeynote: CERN Experiences - Ricardo Rocha & Clenimar Filemon
10mLightning Talk: Does Cloud Elasticity Pay off for HPC Workloads?