Is ReRAM the end of NAND flash?

Is ReRAM the end of NAND flash?

Summary: Toshiba continues to push their Resistance RAM (ReRAM) plans. Sampling starts next year with commercial devices in 2015. Is this the beginning of the end for NAND flash?

SHARE:
TOPICS: Storage
10

Get ready for a new primary storage technology: ReRAM.

NAND flash stores data in a little cloud of electrons in a quantum well. The presence or absence of charge - or the strength of the charge - tells us what bits are stored.

ReRAM stores data through changes in the resistance of a cell. There are a variety of ReRAM technologies in development, including phase-change memory (PCM) and HP's memristors, based on at least a half-dozen competing materials.

Expect healthy competition as the industry and buyers sort out the details.

Advantages

While different implementations have different specs, all ReRAM has key advantages over today's common NAND flash.

  • Speed. ReRAM can be written much faster - in nanoseconds rather than milliseconds - making it better for high-performance applications.
  • Endurance. MLC flash - the most common - can only handle about 10,000 writes. ReRAM can handle millions.
  • Power. Researchers have demonstrated micro-Amp write power and expect to get in the nano-Amp range soon, which makes ReRAM much more power efficient than NAND flash, which requires voltage pumps to achieve the 20 volts required for writes.

The Storage Bits take

NAND flash will retain advantages in cost and density for the foreseeable future, meaning that it will be here for decades to come. So where will ReRAM fit in the storage hierarchy?

  • Data integrity. Losing a snapshot is no big deal. Losing your checking account deposit is. Mission critical applications will prefer ReRAM devices - and can afford them.
  • Performance. Today's SSDs go through many contortions to give good performance - and don't succeed all that well. A fast medium removes complexity as well as increasing performance.
  • Mobility. Depending on how the never-ending tug-of-war between network bandwidth and memory capacity develops, consumers may come to prefer large capacity storage on their mobile devices. If so, ReRAM's power-sipping ways will be an asset on high-end products.

Toshiba is well-positioned to enter these high-end markets with SSDs analogous to today's 15k disks. It may not be a huge market, but the margins will make it worthwhile.

Other vendors, including Panasonic, Micron and Samsung, are also working on ReRAM products. Another interesting question: to what extent will fast ReRAM replace DRAM in systems?

Comments welcome, of course. Here's http://techon.nikkeibp.co.jp/english/NEWS_EN/20120713/228338/ more detail on Toshiba's plans from Tech-On.

Topic: Storage

About

Robin Harris has been a computer buff for over 35 years and selling and marketing data storage for over 30 years in companies large and small.

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.

Talkback

10 comments
Log in or register to join the discussion
  • Very interesting article

    Looks promising.

    An ampere has nothing to do with a volt though. You may want to clarify the power demand comparison.
    LarsDennert
    • You're correct

      that volts & nanoamps have little to do with each other - at least until some other terms of the equations are defined. You'll notice if you search the web that the flash industry is not very open about the programming power required for flash.

      But given Ohm's Law: V/I*R, and the expected nanoamps write power, we know that the resistance (R) would would have to many megaOhms to get V (voltage) to ≈20 volts.
      R Harris
  • Looking at HP's memristors. Not buying that flash will be here for decades

    to come. I'd be surprised if its near more than a single decade from now. Do you have any references for your density point? Id very much like to read about that. I dont see manufacturing disadvantages that would keep memristor cost higher long term (>5yr) other than density.
    Johnny Vegas
    • PS very PISSED OFF about hps artifical delay of memristors just because

      Hynix sucks at basic business management. WTF? They've already had more than enough time to sort that out. Lead, follow, or get out of the way. Hynix is now in the way. HP I know youve really lost your way but seriously, find a leader or become one again.
      Johnny Vegas
    • It's all in the applications

      ReRAM will cost more than NAND flash for some time to come. Therefore there will be many applications that won't support the cost of ReRAM.

      A major reason for the cost differential is data density. Flash is commercializing 3bits per cell and may go to 4bpc. Haven't seen any suggestion that ReRAM can equal that.
      R Harris
  • Power is measured in watts. Amps measure current.

    Voltage measures electric potential. How about re-writing your article using the terms correctly when making your product comparisons.
    baggins_z
    • It is correct.

      Power (watts) is current * voltage (I*R). The writer wasn't calling volts power. He was merely pointing out that the voltage potential required to write NAND is 20Volts. In all current RAM technologies write operations consume more power (and time) than reads. Assuming a write current requirement is minimally equal to a read, pumping 20 volts absolutely factors into the power equation.

      The article is correct.
      predmond
  • milliseconds

    flash can do less the 1 millisecond. I have seen .5 to .01 milliseconds

    Also, if companies made SLC cheap, then speeds would not be an issue.
    MLC only gives 2x capacity advantage at 1/2-1/5 speed, so what is the point in MLC, and 1/10000 as much write cycles. So why bother with MLC or TLC. MLC should be killed off and SLC would become common place and be cheap due to mass production. I am not sure why MLC exists at all. Would be different if MLC gave 5x the capacity advantage but it doesn't. The only reason why MLC exists is to justify the crazy prices for SLC.
    ShqTth
  • ReRam: Great concept but it's too early to be considered a viable option...

    The end of NAND Flash is a hot topic of debate right now. We understand the end of NAND is inevitable, as all good things must come to an end, but not for a very, very long time. ReRAM certainly has some advantages over today’s NAND flash, including the elimination of P/E cycles, but practically speaking, ReRAM has a long road ahead. As a storage industry veteran and leader, the evolution to a new storage takes quite a bit of time. You have to take into consideration the transition to new architectures and applications that can take advantage of this new storage technology. The cost of building a new architecture alone is enough to delay the storage manufacturers from making a whole-hearted switch to another storage media. The concept of ReRAM is great, but it just may be too early to really consider the storage as a viable option in today’s market.

    Plus, both the cost and capacity points of ReRAM are not currently at NAND levels, so those will also need to be overcome before ReRam can be considered a feasible storage option.

    -John Scaramuzzo, President, SMART Storage Systems
    John Scaramuzzo
  • Help me please

    Reram is my seminar topic
    if any one know more about this kindly send details to my email
    riyas.pappinippara@gmail.com
    riyasudheenkk