Supporting Data Intensive Science on HPC
Improvements in instruments and computing had led to a massive increase in data and simulation across many fields of science. Turning that data into knowledge requires high-performance applications, processing, networking and storage services. In this presentation I will discuss how we have approached these problems at the Flatiron Institute, which is a multidisciplinary institute that specializes in data intensive science analysis. I will talk about the choices we have made and the challenges we have faced in services, architectures, and support models as we have ramped up. I will cover some of the innovative development activities we have been exploring in data distribution and enabling access.
About the Speaker
Ian Fisk, Co-Director of the Scientific Computing Core, Flatiron Institute
Ian Fisk came to the Simons Foundation in 2014 after working in the computing division at the Fermi National Accelerator Laboratory in Illinois since 2003. Fisk was the Compact Muon Solenoid (CMS) experiment’s computing coordinator at CERN from 2010 to 2013, overseeing operations and improvements for the global CMS computing infrastructure. Before that, Fisk served in several roles to prepare the experiment for the first run. He oversaw service integration, facility development and operations, and project management. He is currently one of the Co-Directors of the Scientific Computing Core of the Flatiron Institute. Fisk holds an M.S. and a Ph.D. in physics from the University of California, San Diego.
Omnia: Open Source Converged Software for HPC & AI Workloads
Omnia is a new open source community project started in the Dell Technologies HPC & AI Innovation Lab to automate the deployment of mixed-workload HPC clusters for simulation, HTC, ML/DL, and data analytics. Omnia automates the deployment of open source or publicly available accelerator drivers (GPU and FPGA), workload management software (Slurm and Kubernetes), libraries, frameworks, operators, services, platforms, and applications. We will discuss Omnia’s current capabilities, working with the Dell Technologies HPC Community to develop new capabilities, and future plans for the project.
About the Speakers
John Lockman, HPC & AI Specialist, Dell Technologies
Programmer, developer and evangelist for containerization and orchestration with Kubernetes, John Lockman works in the Dell Technologies HPC & AI Innovation Lab. He specializes in nature-inspired programming, deep learning, and artificial intelligence. John brings a passion for building tools to make advanced computing accessible to a broader audience.
Luke Wilson, Chief Data Scientist, Dell Technologies
Luke Wilson is Chief Data Scientist of the HPC & AI Innovation lab at Dell Technologies. Luke leads the engineering and design of Dell Technology’s AI Solutions, works with customers and partners to develop state-of-the-art AI models and new techniques for reducing time-to-value of AI projects, and publishes peer-reviewed research in international conferences and journals.
(Valid NDA with Dell Technologies required to attend this presentation)
Check out future events scheduled for the Dell Technologies HPC Community.