Paper Title: If "Data is the new Oil", Data Management is the Combustion Engine

Paper Abstract: "Information (data) is the oil of the 21st century, and analytics is the combustion engine" (Peter Sondergaard, EVP Gartner Group). Like oil, data is only valuable if it is in a usable form. In practice real-world data suffers from flaws such as inconsistent, inaccurate, missing, information, as well as latency issues impacting timely analysis. Modern Artificial Intelligence (deep learning) applications require vast amounts of quality data. Just as oil requires infrastructure for storage and transportation, data requires infrastructure in the form of software and hardware. DeepSpace is open-source software (client/catalog/data store) that can hydrate/rehydrate files or entire filesystems to/from storage tiers (object, tape, cloud), as well as replicate a file system to another client in seconds. RPI offers an ultra-fast data store infrastructure that provides "fast everything" including high IOPs SQL server, Open-Source Catalog, Policy-based data management and provisioning.

Paper Author: Robert Plaster, President & CTO, RPI-CS

Author Bio: Robert Plaster is President and CTO of RPI, a Systems Integrator and consulting company focused on HPC, data lifecycle management, and large data system integrations. Clients include the Navy, National Institutes of Health, General Dynamics, Warner Brothers, USC Shoah Foundation. Projects vary from large SAN infrastructures (4000+ ports) for real-time data capture, Data center consolidation (100 racks into 10 racks), while maintaining performance levels for over 1000 VDI clients, large scale (1000+ ports) FCoE system for several data centers, Hierarchical Storage Management (HSM) Archival Systems, multi-petabyte data migrations (e.g., Oracle's SAM to Quantum StorNext file system), and high definition (9.6GB/s +) signal capture infrastructure for land, sea, and air tactical environments.