Crossbar Inc. is
the leader in RRAM technology, widely accepted as the front-runner to replace
traditional Flash technology in future storage systems. Delivering terabyte
storage on a postage stamp-sized chip, with power low enough for massive
adoption throughout the Internet of Things, Crossbar RRAM is easy to tailor for
a broad range of applications. From embedded memory on SOCs for wearables, to
very high density SSDs for cloud data centers, Crossbar is ushering in a new era
of storage innovation. For more information, visit www.crossbar-inc.com|
memory channel SSDs
storage interface glue chips and
sudden power loss
Memory Defined Software
who's who in SSD? - Crossbar
by Zsolt Kerekes,
first appeared as a company of interest to the SSD market in
August 2013 when
it emerged from stealth mode and unveiled the prototype of a new 3D stackable
non volatile RAM like technology called RRAM which it claimed "would
deliver 20x faster write performance, 20x lower power consumption, and 10x the
endurance at half the die size, compared to today's best-in-class NAND Flash
I had heard similar claims to replace flash from
many other companies in the alternative nvm market and listed them in an
article - storage media
contenders which threatened flash SSDs in the past decade. So I considered
Crossbar to be just another company in that category. Some of these
technologies have in fact been used in applications in which storage density
is less important than some other attribute - such as environmental ruggedness -
for example - and the ability to implement a fast non volatile memory in a
small physical space - but they were a long way off being viable and able to
replace most of the flash in any SSD at that time.
2 years later - in
the summer of 2015 - Micron
and Intel started
preannouncing a new 3D ReRAM technology called Optane which they promised might
ship in the next few years aimed at the
So then many people in the industry started looking
around and re-posing the fundamental question - how real is this stuff? And what
percentage of these kinds of claims might be true?
That scepticism -
remember - had been conditioned by 12 years of the alternative nvm market crying
wolf and claiming in would replace flash real soon.
Well we're still
a long way off flash being replaced everywhere. But the potential rewards of
gambling in the enlarged SSD ecosystem with new risky memory technologies are
much greater than they have been in the past. Because even the smaller niches
in the enterprise SSD universe are big enough to satisfy investors.
in my opening article for 2015
- I said "All the systems in the market today are implementations of
transient architectures which are pragmatically adapting legacy installations
and infrastructure. And ...there are still many surprises ahead from SSD market
in 2015 - which promises to be another momentous year for the SSD market."
August 2015 in a paper -
RRAM Technology and Applications (pdf) delivered at the
Flash Memory Summit -
Crossbar's cofounder Hagop Nazarian
said that not only is his company's technology accessible to the fabless
manufacturing model (as it uses standard CMOS processing) but - intriguingly -
the discrimination window between the on and off states would improve as cell
geometries were scaled to be smaller.
That's the opposite case to nand
flash where the demand for stronger
ECC to maintain
data integrity increases as cells get smaller. The suggestion is that RRAM will
be easy to manufacture - and (if it proves to be a reliable memory technology)
might scale to similar densities (or beyond) to flash.
So in September
2015 - when Crossbar announced it had secured a $35 million Series D funding
round - in a way that was similar to all those earlier nvm funding stories and
acquisitions I'd read about before. But maybe - just maybe - the story will end
differently this time.
flash and other nvms,
VCs in SSDs,
storage market research
In September 2015 -
Crossbar announced it
has completed a $35 million Series D funding round bringing total investment to
$85 million to date. Crossbar plans to use the funds to continue the commercial
ramp of its game-changing non-volatile (NVM) memory technology.
In January 2017
- Crossbar announced
it was sampling 8Mb ReRAM based on 40nm CMOS friendly technology.
demonstrates ReRAM AI accelerator chip|
| Editor:- May 14, 2018 - Crossbar today
that it will demonstrate a test chip showing the capabilities of its ReRAM
technology for AI in the form of a facial recognition accelerator at the
Embedded Vision Summit
next week in Santa Clara, California.|
VP Marketing at Crossbar said - "The biggest challenge facing engineers
for AI today is overcoming the memory speed and power bottleneck in the current
architecture to get faster data access while lowering the energy cost. By
enabling a new, memory-centric non-volatile architecture like ReRAM, the entire
trained model or knowledge base can be on-chip, connected directly to the neural
network with the potential to achieve massive energy savings and performance
improvements, resulting in a greatly improved battery life and a better user
Editor's comments:- It's a great idea for Crossbar to
integrate the capabilities of their SoC compatible ReRAM technhologies into a
demonstration accelerator like this as it cuts out a lot of guesses and the
requirement to imagine what can be done with the new architectures so enabled.
an example of this powerful business development idea from
all know (or have heard of)
They're the company(founded in December 2005) which transformed the enterprise
server market from SSD deniers into born again
PCIe SSD acceleration
evangelists. Fusion-io was acquired for $1.1 billion in
might be surprised to know that despite its huge market impact Fusion-io's
original business plan wasn't the one which they later followed.
they became successful the founders told me their original idea had been to
operate as a software and IP licensing company.
And they said that
their prototype PCIe SSD cards - the ioDrives - had been intended simply to
demonstrate the concept of what Fusion's software and architecture could do.
The founders had expected that server makers would license the technology but
build their own cards. However, when server customers saw what this acceleration
technology could do for their own server sales (or those of competitors if they
adopted it) they chose to buy cards instead. And that's how the PCIe SSD market
It's possible that with the AI memory accelerator market
we're going to see application specific products born out of demonstrators which
are too good to stay in the labs. And that's a proposition which I also
mentioned in my recently completed blog -
are we ready
for infinitely faster RAM?