SC20 Meeting (Session 1): Storage for AI

The Spectrum Scale user group meets annually at the SC conference. For 2020 the user group will be split into two 90 minute digital sessions. The second session will be on Wednesday Nov 18th, 11 am EST
>> Session 2: What is new in Spectrum Scale 5.1? <<

This session will focus on Storage for AI including a customer case study and a deep dive in new Spectrum Scale features which optimize the analysis of datasets stored in a data lake. Live Q&A will be available.
The session will be hosted by IBM and moderated by the user group.
>> Please register here to join the session. <<

Continental: Deep Thought – An AI Project for Autonomous Driving Development

Continental, a tier-1 automotive supplier, runs a new high-performance cluster based on NVIDIA DGX, IBM Spectrum Scale and IBM ESS to boost autonomous driving development performance. Continental uses this system for deep learning, simulation, virtual data generation and related workloads. The new cluster reduces development time from weeks to hours. Speakers from Continental and the business partner SVA will present business requirements and derived workloads, the Spectrum and ESS implementation, and first operational experience.

https://www.continental.com/en-us/press-/press-releases/continental-supercomputer-nvidia-228624

Data Accelerator for AI and Analytics (DAAA)

This talk focuses on the need of data orchestration in enterprise data pipelines. It provides details about data orchestration and how to address typical challenges that customers face when dealing with large and ever-growing amounts of data for data analytics. While the amount of data increases steadily, AI workloads need to speed up in order to be able to deliver insights and business value in a timely manner. IBM addresses these requirements with the Data Accelerator for AI and Analytics (DAAA), an expertly engineered solution based on new features delivered with Spectrum Scale 5.1. The session will include a demo of a complex proof-of-concept and present the key learnings and results.