Non-volatile DIMMs: immortal DRAM?

Non-volatile DIMMs: immortal DRAM?

Summary: DRAM's speed. Flash's data preservation. The NVDIMM has both. Too good to be true? It isn't.

TOPICS: Hardware, Processors

DRAM's speed. Flash's data preservation. The NVDIMM has both. Too good to be true? It isn't.

Lots of cool flash apps at the Flash Memory Summit last week. One of the best was the NVDIMM from San Diego-area Agiga Tech, a Cypress Semiconductor company.

Nothing beats synchronous DRAM's combination of price, performance and durability for main memory. But lose power and DRAM's data is gone. Critical apps have long used battery-back up (BBU) to guard against wonky power.

But BBUs have problems. Heavy. Slow charging. 2-3 year life. Costly. Compared to solid state devices, a pain.

The NVDIMM backs up data without a battery. Their NVDIMM integrates standard DDR3 SDRAM with NAND flash, a system controller and an ultracapacitor power source.

Ultracapacitors are cool. In a demo at the conference, Agiga Tech showed how the UCs would fully charge in less than 10 seconds and run a power-hungry toy over a minute.

Orchestrating the DRAM off-load onto the flash when there is a power outage is the problem. The system has to:

  1. Sense power failure.
  2. Initiate DRAM-to-flash offload.
  3. Restore DRAM contents while the ultracapacitors recharge.
  4. Inform system when process is complete.

The NVDIMM includes a simple host-controlled protocol that let's the system call the shots. Only the system knows if a power-down is accidental or not, while only the NVDIMM knows if the ultracapacitors are charged or not.

The Storage Bits take Will NVDIMMs replace standard DIMMs on PCs and notebooks? No. Consumers won't pay the extra cost for the occasional benefit.

But for embedded systems that already use batteries to ensure data protection - RAID controllers for example - NVDIMMs should prove popular. Even if they cost more, they are lighter, faster to recharge, smaller and have longer data retention than battery backed DRAM.

What NVDIMMs don't do is condition power like many whole system BBUs. But data centers already condition their power even if few consumers do.

The bigger issue is that system designers need prodding to take advantage of non-volatile DIMMs. Not only do they need to code to Agiga's protocol, they need to think about how, for example, an NVDIMM RAMdisk could benefit their application.

Despite these issues, ultracapacitor-based flash backup promises to extend non-volatility to smaller and lower-cost devices. That is a welcome improvement.

Comments welcome, of course.

Topics: Hardware, Processors

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


Log in or register to join the discussion
  • Nothing really new

    Memories like this have been available for years for use in the embedded world. Using NAND is new but also has it's draw backs. Speed being #1 among them. Competing tech has ms save and micro second restore times.
    • RE: Non-volatile DIMMs: immortal DRAM?

      speed isn't an issue if the only write is during a power failure. As long as the write can take place in a few seconds, or 10 seconds, and the data is safe, it meets the need.
  • Robin, thanks

    Thank you for the good article (seriously). And thanks for not mentioning Blu-Ray! ;-)
  • Cool

    but can you imagine trying to reset that flakey router and it refuses to clear memory because it's NV? LOL
  • RE: Non-volatile DIMMs: immortal DRAM?

    I disagree with your statement "The bigger issue is that system designers need prodding to take advantage of non-volatile DIMMs." Electrical Engineers in general enjoy designing with the latest and greatest and hardly have to be "prodded" to design with something new that meets a need. The issue is one of economics. Can a product support the additional cost of the components plus the additional engineering necessary to produce the new software? Adding something that an engineer thinks is cool does not help when the consumers refuse to pay a penny more for something that is more reliable. Consumers in general consider the purchase price first and all other issues second. Just my 2 cents from a engineer that has been designing microprocessor and microcontroller based circuitry for the last 30 years.
    • RE: Non-volatile DIMMs: immortal DRAM?

      30 years is impressive. I have only been in the industry for less than 10 years, but have witnessed innovation from both young and old blood. I don't disagree with your statement though, a new technology invariably comes at a higher price (SSDs anyone?). It's whether or not the customer is willing to pay for the value that the new tech or product can create for their end customers. In this case, I don't think the play is to replace standard DIMMs, it's probably to improve the system performance and remove the headaches of batteries. I think we can all agree those are good things.

    Ultracaps have been around for over 25 years and have never been improved enough to use in today's market. They leak and have a short life span of 2 or 3 years max. This "new" concept is actually another attempt at an old idea from the early 1980s. A smarter move would be using lithium batteries that charge while powered up, since their life is closer to 10 years.
    • RE: BAD IDEA! <is a bad idea!>

      @dave@... <br>Hmmmm. I don't know about you, but even though lithium ion batts contain hazardous material and must be disposed of properly, the majority probably still ends up in the land fill. I know it's just a small step, but I am all for going "green".

      @dave@...<br>I think your information is very dated. I won't argue that there are *some* ultracaps that do wear out quickly, but there are many that do not. Take a look at Lane Hauck's presentation from the flash memory summit ( entitled "Reliable Flash-Backed Cache Using Ultracaps". Yes, Lane is from AgigA Tech, but you'll notice that the presentation is less of a commercial and more of a tutorial on the reliability of ultracaps. This is new data taken over the last few years on the latest and greatest. Even the ultracap vendors themselves do not have this level of reliability information. Bottom line - not only are the *right* ultracaps reliable, but they are superior to batteries (especially Li Ion) in many ways.
  • Ever since the Palm, I've wondered...

    ... What would computers become if RAM were fast, cheap, and non-volatile?

    Would mass-storage become irrelevant, and disappear altogether, along with all its many reliability contrivances?