It seems the end is in sight for Intel’s beleaguered Optane memory business. Tucked away in a stark Q2 2022 earnings release for the company (more on that later today) is a very curious statement in a section dealing with non-GAAP adjustments: In the second quarter of 2022, we began winding down our Intel Optane memory business. Additionally, Intel’s earnings report also notes that the company is taking a $559 million charge for “Optane inventory impairment” this quarter.
Beyond these two items, there is no further information about Optane in Intel’s earnings release or associated presentation. We have contacted company representatives for more information and are awaiting a response.
Taking these elements at face value, it therefore seems that Intel is preparing to stop its Optane memory business and the development of the associated 3D XPoint technology. Admittedly, there is a high degree of nuance around the Optane name and product lines here – which is why we are seeking clarification from Intel – as Intel offers several Optane products including “Optane memory” “Optane persistent memory” and “SSD Optane”. Nonetheless, in previous Intel earnings releases and other financial documents, Optane’s full business unit has traditionally been referred to as their “Optane memory business”, so it would appear that Intel is indeed shrinking the business unit. of Optane, not just the Optane Memory product.
Update: 6:40pm ET
Further to our request, Intel has sent a short statement on the Optane phase-down. While not offering many additional details on Intel’s exit, it does confirm that Intel is indeed exiting the entire Optane business.
We continue to streamline our portfolio to support our IDM 2.0 strategy. This includes evaluating divestment activities that are not sufficiently profitable or that are not essential to our strategic objectives. After careful consideration, Intel plans to discontinue future product development within its Optane business. We are committed to supporting Optane customers through the transition.
Intel, in turn, used 3D XPoint as the basis for two product lines. For its data center customers, it offered Optane Persistent Memory, which integrated 3D XPoint into DIMMs as a partial replacement for traditional DRAMs. Optane DIMMs offered greater bit density than DRAM and, combined with their persistent and non-volatile nature, were an attractive offering for systems that required massive sets of working memory and could benefit from its non-volatile nature, such as database servers. During this time, Intel also used 3D XPoint as the basis for several storage products, including high-performance SSDs for the server and client market, and as a smaller high-speed cache for use with slower NAND SSDs.
However, 3D XPoint’s unique attributes have also been a challenge for Intel since the technology’s launch. Although it was designed for scalability via layer stacking, 3D XPoint’s manufacturing costs remained higher than NAND per bit, making the technology significantly more expensive than SSDs even more. efficient. Meanwhile, Optane DIMMs, while occupying a unique niche, were just as expensive and offered slower transfer rates than DRAM. So despite Intel’s efforts to come up with a product that could cross both product spaces, for workloads that don’t benefit from the technology’s unique capabilities, 3D XPoint ended up being neither as good as DRAM. or NAND in their respective tasks – making Optane products a tough sell.
As a result, Intel has been losing money on its Optane business for most (if not all) of its life, including hundreds of millions of dollars in 2020. Optane, but all at once. -excluding the occasions when they have published these figures, they have been well in the red on an operating profit basis. Additionally, reports from Blocks & Files have claimed that Intel is sitting on a significant oversupply of 3D XPoint chips – on the order of two years of inventory at the start of this year. All of this underscores the difficulty Intel has had in selling Optane products and adds to the cost of a write-down/write-off, which Intel is doing today with its $559 million Optane write-down charge.
Therefore, a potential slowdown for Optane/3D XPoint has been in the tea leaves for some time now, and Intel has taken steps to modify or reduce the activity. Most notably, the dissolution of the Intel/Micron IMFT joint venture left Micron in possession of the sole production plant for 3D XPoint, while Micron abandoned its own 3D XPoint plans. And after producing 3D XPoint memory until 2021, Micron finally sold the fab to Texas Instruments for other uses. Since then, Intel hasn’t had access to a high-volume factory for 3D XPoint – although if the inventory reports are true, they haven’t needed to produce more memory for some time.
Meanwhile, on the product side, the shutdown of the Optane business follows Intel’s earlier exit from the client storage market. Although the company released two generations of Optane products for the data center market, it never released a second generation of consumer products (e.g. Optane 905P). And, after selling its NAND business to SK Hynix (which now operates as Solidigm), Intel no longer produces other types of client storage. Retiring the remaining data center products is therefore the logical, if unfortunate, next step.
Intel’s Old Optane Persistent Memory Roadmap: What Will Never Be
Overall, Intel chose to end the Optane/3D XPoint business at a critical time for the business. With the launch of their Sapphire Rapids Xeon processors this year, Intel was previously expected to release a third generation of Optane products, most notably their “Crow Pass” 3rd Generation Persistent DIMMs, which among other things would update Optane DIMM technology to use a DDR5 interface. While development of Crow Pass is likely complete or nearly complete at this point (given Intel’s development schedule and Sapphire Rapids delays), launching and supporting the product would still incur up-front and long-term costs. important long-term, forcing Intel to support the technology. for another generation.
Instead of Optane persistent memory, Intel’s official strategy is to turn to CXL memory technology (CXL.mem), which allows volatile and non-volatile memory to be attached to a processor via a compatible PCIe bus. CXL. This would accomplish many of the same goals as Optane (non-volatile memory, large capacities) without the development costs of an entirely separate memory technology. Sapphire Rapids, in turn, will be Intel’s first processor to support CXL, and the overall technology has much wider industry support.
AsteraLabs: CXL Memory Topology
Still, Intel’s withdrawal of Optane/3D XPoint marks the unfortunate end of an interesting product line. 3D XPoint DIMMs were a novel idea even if they didn’t quite work, and 3D XPoint was designed for ridiculously fast SSDs thanks to its massive random I/O advantage – and that’s a feature unlike any other SSD vendor. going to be able to fully replicate anytime soon. So for the solid state storage market, it marks the end of an era.