The Wall Street Journal
August 5, 2013
Crossbar Enters Race to Change Memory Chips
Several kinds of chips are used to store data, all of them good at some parts of that job but not others. A company called Crossbar has been quietly planning to disrupt a big chunk of that memory market.
The Silicon Valley startup on Monday becomes the latest to unveil plans for an alternative to flash memory, the mainstay storage technology for products like smartphones, tablets and digital cameras.
NAND flash, the most widely used variety, is less expensive than some competing technologies per bit of data stored. But NAND chips are slower at writing data than retrieving it. Moreover, chip makers fear that continuing to shrink NAND circuitry to boost storage capacity will soon become difficult or impossible.
Crossbar says it has developed a variant of a technology called RRAM that is 20 times faster than NAND, consumes one-twentieth the power, stores data 10 times longer on chips that could be half the size.
A single chip based on its technology could store a trillion bites of data, or a terabyte, Crossbar says. By comparison, the highest-capacity NAND chips now on the market store 128 gigabits of data, or 16 gigabytes; storing a terabyte would require 64 of those chips, notes Jim Handy, a market researcher with Objective Analysis.
There are benefits beyond simply increasing how much data mobile devices and other gadgets might store, says George Minassian, Crossbar’s chief executive officer.
For one thing, the slow data-writing speed of NAND flash means that many devices also have to have another kind of faster chips–DRAMs, or dynamic random-access memories. They are used for purposes such as temporarily storing images from digital cameras to minimize big delays when shooting photos, Minassian says.
Those DRAMS won’t be necessary if Crossbar’s technology takes hold, he says, further reducing the cost and size of consumer products. “You can take photos as fast as you want,” he says.
Some of this may sound familiar. The list of companies pursuing new memory alternatives is long. Some of the new devices have reached the market, but others remain largely an unfulfilled promise after years of investment.
Crossbar’s technology is based largely on inventions credited to Wei Lu, an associate professor of electrical engineering at the University of Michigan. The venture capital firm Kleiner Perkins Caufield and Byers put up money to fund research on the concept, and later backed Crossbar–the exclusive licensee of the underlying patents.
Where conventional memory chips use electrons to store data, Crossbar’s technology is based on tiny filaments that are formed by applying electricity from electrodes to a layer of amorphous silicon, a non-crystalline cousin to the silicon used in conventional chips. These act like on or off switches to record the presence or absence of a bit of data.
Crossbar claims that its variant of RRAM, or resistive random-access memory, is simpler than others and can largely be fabricated on production lines now used to churn out conventional chips. It can also be used to create multiple three-dimensional layers of memory more easily than the widely used approach of creating separate chips and subsequently stacking them, Minassian says.
The company is announcing its plans after developing working prototypes based on the technology. While Crossbar may make and sell some chips of its own, it plans mainly to license its technology to others–first to store data in specialized products known as SoCs, for systems on a chip, and eventually to makers of standalone memory chips, Minassian says.
Handy says Crossbar’s approach has some advantages. But he argues that its inventions and other alternatives don’t really deserve much consideration until they prove that they can beat incumbents on cost once mass production begins.
“The guys who do NAND flash and DRAM have been pulling any number of rabbits out of their hats for years,” Handy says. “I’m expecting them to continue to do that.”
Another analyst briefed on the technology, Greg Wong of Forward Insights, echoed the challenges but said Crossbar definitely made an impression. “It definitely looked interesting,” he said.
The company has raised $25 million and reached the prototype stage with just 20 employees. Minassian estimates that commercial products based on the technology are about two years away.
They can’t come too soon for Lu, who says the fundamental idea for the technology came from an accidental discovery in 2004 during a stint at Harvard University before he joined the Michigan faculty. Applying extra voltage to a tiny wire that contained amorphous silicon had some surprising effects, he recalls.
“This is like a child of mine,” says Lu of Crossbar. “We are so close.”
© Wall Street Journal