Keynote: Reperforming a Nobel Prize Discovery on Kubernetes
summary
Recreates the 2012 Higgs discovery analysis on Kubernetes using a 70 TB CMS open dataset split into 25,000 files, submitted from a Jupyter notebook into a private cluster and replicated to GKE with GCS and Google Memorystore (Redis). The system runs 25,000 jobs in parallel, pulls data at nearly 200 GB/s, produces the invariant-mass histogram with the 125 GeV bump, and completes the rediscovery in minutes, demonstrating containerized reproducibility and multicloud placement.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 0:48CERN
- 1:05Fundamental Research
- 1:52World Wide Web
- 3:06Web 30th Anniversary
- 3:22Large Hadron Collider
- 5:47CMS
- 6:57Capacity
- 7:28Nobel Prize Discovery
- 8:21The Higgs
- 9:33Demo
- 11:27Data
- 12:10Limitations
related talks
47mCloud Native and Sustainable, Reproducible Scientific Computing
36mAn almost perfect match: cloud native and scientific computing
19mKeynote: Building Bridges: Cloud Native and High Performance Computing
41mBuilding & Operating a Large-scale HPC AI Cluster on Kubernetes
07mKeynote: High Performance Computing on Google Kubernetes Engine
44mEmpowering Data Science with Kubernetes | Samuele Chiocca and Andrea Rota
05mMaking the Impossible Possible with Kubernetes
18mKeynote: Adapting Kubernetes for Machine Learning Workflows