How Computational Storage works

Scott Shadley, VP of Marketing (July 19, 2018) – In many respects, a Computational Storage device looks just like a normal SSD. It has a large number of NAND flash devices that actually store the data, a controller that manages writing the data to the flash devices, and some amount of RAM to act as a read/write buffer. What is unique about Computational storage devices is the inclusion of one or more multi-core processors. These processors can be utilized to perform many functions, from indexing data as it enters the storage device to searching the contents for specific entries. By embedding intelligence in flash storage, NGD Systems provides a means to scale compute resources with storage capacity while eliminating the need to move large datasets back and forth. To see it being implemented, check out our keynote presentation with Microsoft Research to see how our partner is changing the face of their storage solution.

This capability is valuable not only for datacenters and the cloud, but also for the Internet of Things, Edge Computing, smart cities, and autonomous vehicles (#Datacenter, #Fog, #Cloud, #Edge, #SmartCities, #AutonomousVehicles). In our next blog of this series, we will examine the performance and cost impacts that Computational Storage can have on petabyte-scale real-time analytics.