Introduction

Originally published on LinkedIn, October 12, 2022.

If you’ve followed me for any length of time, you know I have a strong opinion on Intel’s Optane business.

First, I believe 3D XPoint, developed by Intel and Micron, was one of the most disruptive technologies to hit the market.

Second, I believe persistent memory was the real breakthrough, not SSD packaging.

Third, I believe the way Optane was packaged and positioned ultimately confused the market. Had Intel focused on persistent memory and walked away from SSD positioning entirely, it would have had a much better chance of reshaping the memory landscape.

This article I am posting, “Understand the Intel Optane Shutdown” from August of 2022, was sent to me by an industry colleague who asked me for my thoughts and opinion.  I’ll not share my entire response, but here is a summary.

Where do we go from here?

The article ends with “What comes next?” Where does it leave companies that developed their solutions based on Optane?  I’m less concerned about those companies and more concerned about the customers who were sold solutions containing Optane SSDs.

What happens to those customers?  Think about it, if you were one of those customers who were sold a “10 year endurance” model storage solution, where do you go in 3 years or 5 years when you potentially need a replacement Optane SSD?  Will it be available?  Doubtful, but maybe on eBay.

It is a shame when companies place bets with their customer’s money on perceivably risky technology.

The article goes on to talk about CXL saying, “Optane does leave behind a positive legacy. The industry learned a lot from its introduction. The Compute Express Link (CXL) interconnect may have been designed with Optane in mind, and the Storage Networking Industry Association developed a Nonvolatile Memory Programming Model that promises to speed up many other forms of storage.”

May have been designed with Optane in mind?  Hmm…

If you recall, Micron’s statement back in March of 2021 about its exit from the 3D XPoint business said the “3D XPoint development was being shelved, with a strategic move to technologies that support the CXL interface.”  Micron was going to focus on technologies that support the CXL interface.  Although the standard was primarily developed by Intel, Micron said it wanted to focus on tech that supports CXL.

This statement confused me because Intel had a technology that could support CXL.  It was its NVDIMM product called Optane Persistent Memory, based on 3D XPoint – the same tech that Micron was shelving.  I would have thought Intel would be the first to market, announcing that it would look at how the technologies in its portfolio, specifically Optane PMEM, would benefit from this new standard it primarily developed.  Especially if it truly was developed with Optane in mind.

Yet five months after the Micron exit announcement this Blocks and Files article came out that, oddly enough, was published exactly 1 year before the TechTarget article I shared earlier, where Chris Mellor opens with, “Intel foresees the CXL bus enabling rack-level disaggregation of compute, memory, accelerators storage and network processors, with persistent memory on the CXL bus as well.”  This was based on comments by Intel Fellow and Director of I/O Technology and Standards, Dr. Debendra Das Sharma.

Chris ends this article with a series of comments, one of which states, “The only SCM made by Intel is Optane. Das Sharma is talking about having Optane NVDIMMs hooked up to the CXL interconnect and have that capacity accessed by servers across the CXL link. He says persistent memory would then be cacheable, multi-headed for failover, and hot-pluggable.”  Yes, 100% and that kind of implementation would, or could have really changed the game going forward.

In closing…

Now, I will say that Optane had its own set of challenges and things to deal with, such as direct mode and application mode to programmatically take full advantage of what 3D XPoint could offer, but CXL could have potentially covered those complexities up and made it more broadly accessible to a mass market, becoming what I would call “a market maker.”

I believe what we may have witnessed was one of the most incredible inventions in 3D XPoint, perhaps a bit of a misguided GTM strategy and packaging, that may have been misaligned on the roadmaps between Optane and CXL, and perhaps the need for more customer sentiment studies to help Intel with how it should view the market needs as it related to its Optane brand.

Or it could simply have been that the new regime at Intel did not share the previous one’s vision, and for that reason, it was canceled and kicked to the curb. I really don’t know; this is all just my opinion.

Either way, I’m sad the market never felt the full potential of Optane persistent memory. I feel we as an industry missed a major opportunity.