Intel’s 3D XPoint non-volatile RAM has sucked up most of the attention in the NVRAM space, but Nantero’s NRAM has taken a giant step forward. So far forward that Intel may get ARM’d again if they aren’t careful.
nantero-logo_web

NRAM?
Nantero is the 15 year old startup pioneering carbon nano-tube RAM, or NRAM. 15 years is a lot of pioneering, but NRAM’s promise is immense:

  • DRAM speed
  • Lower cost in volume
  • Endurance that rivals – or equals – DRAM
  • Higher density
  • Plus, of course, lower power

StorageMojo has followed Nantero for a while, but has seen enough great lab demos that fizzled in the marketplace that I’ve remained skeptical. But Fujitsu announced last week that they are productizing NRAM – the first Nantero licensee to go public – and since Fujitsu is also the world’s largest vendor of FRAM – ferromagnetic RAM – their announcement is a weighty endorsement.

Fujitsu plans to start with a 256mbit part and scale up and down from there – plus offering embedded NRAM in their fab. Given their FRAM customer base of people who have already stepped outside the DRAM/NAND box, they are well-positioned for NRAM design wins.

Also, Nantero is one of the few companies whose product specs have improved as they got closer to production. The product is better than expected. How often does that happen?

Can NRAM replace DRAM?
Maybe. The biggest uncertainty today is NRAM’s endurance. Nantero says they haven’t found a wear mechanism and have tested to 10^12 writes. But to reach DRAM’s 10^15 writes will take a couple of years to certify.

Wrinkles
Achieving DRAM density requires vertical NRAM – multiple layers of processing. Nantero says that’s not a problem because DRAM capacitors have such a high aspect ratio that they takes as many processing steps and mask layers as 8 layers of NRAM.

Achieving lower-than-DRAM pricing requires volume, and that’s where NRAM has a competitive advantage over, say, 3D XPoint. Processing can be done on today’s flash, DRAM or logic lines. NRAM processing only needs spin coating and patterning – as well as carbon nanotubes – which modern fabs all support.

The StorageMojo take
The Intel/Micron 3D XPoint announcement last year seemed rushed. At the time it seemed due to a possible Micron takeover. But I think now that the rush was because of Nantero’s NRAM.

While Fujitsu is the first public reference, Nantero, who wouldn’t reveal any names, says they have a dozen other licensees, including, I’ll wager, Apple, Samsung, HP, Lenovo, Dell/EMC, TSMC, and other major players. Since Nantero, like ARM, licenses their technology, Intel wanted to take up as many development resources for 3D XPoint as possible, leaving fewer for NRAM.

But NRAM’s advantages are many. And ARM has shown that having dozens of companies working with your technology can beat one, not matter how large and wealthy.

Courteous comments welcome, of course.