This Sunday (Sept. 20, 2015) I will be presenting my company’s findings on the 3D XPoint memory that was introduced by Intel and Micron in July. I will be speaking at the Storage Networking Industry Association (SNIA) Storage Developer Conference (SDC) Pre-Conference Primer. You can click the name to be taken to the agenda.
This won’t be the only talk about persistent memory technology at the conference. Prior to my presentation storage consultants Tom Coughlin and Ed Grochowski will give an overview of advances in nonvolatile memories, and following my presentation will be two Intel talks.
Intel will be covering this new technology a lot during the conference. Of a total of 120 presentations at the conference and pre-conference primer, Intel will be presenting nine, seven of which directly name persistent memory or nonvolatile memory in the title. Other firms will also be talking about NVM: AgigA, Calypso, HP, Pure Storage, and SMART Modular. Even Microsoft alludes to it in a couple of its presentation titles. Persistent memory is a hot issue.
So, the question for readers of The SSD Guy blog is: “Will this do away with SSDs?”
This is a question that was pretty exhaustively reviewed in our 3D XPoint memory report. We find that server DRAM is the technology most threatened by the new 3D XPoint memory, and with good reason. 3D XPoint should provide users the ability to beat DRAM performance at a lower price. Who wouldn’t ike that?
Over a longer time period the new memory’s persistence will come into use, but it still won’t compete against SSDs, but will rather complement them.
The reason that there’s so much talk about persistent memory is that it presents a new way to manage data. Sensitive data that once was safely stored in magnetic storage can now be left in memory, as long as the memory is persistent. This opens up a lot of opportunities, and SNIA is making a big effort to develop standards to support this new architecture. With these standards application program developers can produce code that takes advantage of this new high-speed way to store hot data.
It’s an exciting field. Readers may want to look through the SDC agenda to see what this conference has in store.
Those who want a thorough understanding of the new 3D XPoint memory should consider the new Objective Analysis report: A Close Look at the Micron/Intel 3D XPoint Memory which can be purchased for immediate download on the Objective Analysis website.
You raised this question for your readers: Will 3D XPoint do away with SSDs?
I must be missing the point. If 3D XPoint is a replacement for NAND, wouldn’t it just be an evolution for SSDs? I don’t see any scenario where this does away with SSDs. I do see the scenario where is replaces DRAM, however. Please clarify.
Tim,
Thanks for the comment.
My point is that persistent memory will complement SSDs, rather than compete against them.
A number of folks see 3D XPoint as a NAND replacement since they are both nonvolatile/persistent. I am trying to help them move beyond this mindset.
The role of 3D XPoint is to fit between DRAM and NAND flash SSDs. There’s no reason it should reduce the amount of NAND in a system, but it could cause systems to use less DRAM, just as savvy system administrators already use SSDs to reduce their systems’ DRAM requirements.
3D XPoint is too slow to actually replace all of the DRAM in the system, but after a certain minimum DRAM size is reached, applications will get a bigger performance boost by adding a dollar’s worth of 3D XPoint than by adding a dollar’s worth of DRAM.