SK hynix and SanDisk announce new High Bandwidth Flash — speedy HBF standard is targeted at inference AI servers

Data storage — (Image credit: Getty Images)

Typical NAND chips present in SSDs have steadily evolved in speed and capacity over time, with contemporary server-grade units capable of reaching 28 GB/s per unit. Somehow, that's still not enough for the AI world. In turn, SK Hynix and SanDisk have jointly announced HBF, or High Bandwidth Flash, for the inference servers of tomorrow.

Go deeper with TH Premium: AI and data centers

Microsoft data center in Mount Pleasant, Wisconsin — (Image credit: Microsoft)

The official press release is exceedingly light on details, but it mentions that HBF is specifically poised to act as a layer between HBM DRAM and flash SSDs. Given that a stack of current-gen HBM3E is good for around 1.2 TB/s, we can hypothesize that HCF chips could be gunning for speeds of at least 10 GB/s each, if not more, for combined speeds in the hundreds of GB/s. After all, going to the trouble of creating an entirely new standard wouldn't make much sense otherwise.

Power efficiency is apparently a concern for the standard-bearers, a pretty understandable notion in this day and age, where datacenters have massive wattage needs. A high-end Micron 9650 SSD pulls 25 W at full tilt, a figure that gets really ugly really fast when you think in exabyte-scale deployments with tens of thousands of drives.

There are no specifics on how this new HBF is meant to interact with systems, but the vague wording of "supporting layer" could mean it would be analogous to an on-SSD cache, but much bigger. It could also be a really fast block storage device a la Optane that applications and/or operating systems would have to be tweaked to use efficiently.

The announcement offers no target date, but it mentions that "demand of complex memory solutions, including HBF, will pick up around 2030", so that's as a good estimate as any for a production release date. The standard will be under the purview of the Open Compute Project. The companies are targeting HBF at inference servers, given that the outputs that bots users produce needs to be stored somewhere, and that storage need is projected to grow exponentially.

Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds.

TOPICS

Bruno Ferreira is a contributing writer for Tom's Hardware. He has decades of experience with PC hardware and assorted sundries, alongside a career as a developer. He's obsessed with detail and has a tendency to ramble on the topics he loves. When not doing that, he's usually playing games, or at live music shows and festivals.

3 Comments Comment from the forums

Jame5

Typical NAND chips present in SSDs have steadily evolved in speed and capacity over time, with contemporary server-grade units capable of reaching 28 GB/s per unit.

This sentence is incorrect. the SSDs have evolved to reach 28GB/s per unit. Not the NAND chips present in them.

It takes many chips in parallel and good controller design to reach those speeds. The NAND is part of it, but the individual chips are not running at 28GB/s per unit.

It's like by the time they finished the sentence they forgot how they started it.
Reply
Scott_Tx

"It's like by the time they finished the sentence they forgot how they started it." Like they ran out of the context window you could say.
Reply
edzieba

Bet Intel and Micron wished they still had their Chalcogenide plant running for 3DXpoint. It fills that exact niche, and the absurd margins and the anything-you-can-fab demands of the AI bubble would have gotten them over the initial production hump.
Reply