UPDATED 15:00 EDT / JANUARY 10 2019

INFRA

Nonvolatile memory turns up AI, edge power of flash storage

For all the performance gains of flash over disk storage, it was traditionally designed for low cost-per-bit. A brand new breed of flash that prioritizes performance is coming. Its low latency and high capacity might provide the jolt of immediate processing that edge applications demand.

High-density flash storage that packs and compacts data into small spaces makes many modern-tech wonders possible. Smartphones that put the internet in everyone’s pocket are an example. “That wouldn’t be without the flash technology that … gives us all of the high-density storage that we see,” said Scott Nelson (pictured, left), senior vice president of the GM Memory Business Unit at Toshiba Memory America Inc.

Nelson and Doug Wong (pictured, right), member of the technical staff at Toshiba Memory America, spoke with Peter Burris (@plburris), host of theCUBE, SiliconANGLE Media’s mobile livestreaming studio, at theCUBE’s studio in Palo Alto, California. They discussed the next generation of flash storage and potential uses in AI and autonomous vehicles. (* Disclosure below.)

New storage-memory Frankenstein for AI

Flash has been subdividing to meet demands of different markets. There is a class of applications emerging that require extremely high density and low latency for on-the-spot inferencing.

“I think that new types of flash will be necessary for new emerging applications, such as AI or instant recognition of images,” Wong said.

New nonvolatile memory technologies are called storage class memories. They include things like optimized flash, phase-change memories, or resistance memories. What’s interesting about them is that they are technically slower than volatile memories like dynamic random-access memory. However, since they are nonvolatile, they can learn and can store data for future use.

These memory features will become more important for the learning systems in AI, according to Wong. After all, you can’t learn what you can’t remember.

Toshiba is working on these performance-optimized technologies and believes they will change the flash landscape. They hold promise for autonomous cars, virtual reality, and augmented reality, according to Wong.

“A lot of applications to come will be utilizing the high density and low latency that flash offers for storage,” Wong concluded.

Watch the entire video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s CUBE Conversations(* Disclosure: Toshiba Memory America Inc. sponsored this segment of theCUBE. Neither Toshiba Memory America nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE

A message from John Furrier, co-founder of SiliconANGLE:

Your vote of support is important to us and it helps us keep the content FREE.

One click below supports our mission to provide free, deep, and relevant content.  

Join our community on YouTube

Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.

“TheCUBE is an important partner to the industry. You guys really are a part of our events and we really appreciate you coming and I know people appreciate the content you create as well” – Andy Jassy

THANK YOU