Never-never chip tech Memristor shuffles closer to death row

Execution warrant close to being signed for Fink's folly


Comment Martin Fink’s HPE Labs has been dangling the Memristor in front of us for years. With Fink retiring and HPE Labs losing its independence, becoming part of Antonio Neri’s Enterprise Group, inventing far out blue sky stuff will likely shift to devising technologies that can be realistically productised. The Memristor cannot.

The Memristor always was a rich company's technology toy, but Meg Whitman wants HPE to be lean and mean, not fat and wasteful, with HPE Labs producing blue sky tech that rarely becomes a product success.

Memristor was first reported by HPE Labs eight years ago, as a form of persistent memory. At the time HP Labs Fellow R. Stanley Williams compared it to flash: "It holds its memory longer. It's simpler. It's easier to make - which means it's cheaper - and it can be switched a lot faster, with less energy."

Unfortunately it isn’t simpler to make and still isn’t here. NVMe SSDs have boosted flash’s data access speed, reducing the memory-storage gap, and Intel/Micron’s 3D XPoint SSDs will arrive later this year as the first viable productised technology to fill that gap.

WDC’s SanDisk unit is working on ReRAM technology for its entry into storage-class memory hardware, and HPE has a partnership with SanDisk over its use.

SanDisk foundry partner Toshiba has a ReRAM interest.

WDC’s HGST unit has been involved with Phase Change Memory.

IBM has demonstrated a 3bits/cell Phase Change Memory (PCM) technology.

Samsung has no public storage-class memory initiative, although it has been involved in STT-RAM .

The problem for HPE with Memristor is that it would need volume manufacturing to get the cost down. Unless it can sell the potential chips to other server OEMs, it would be the only consumer of Memristor chips and have its servers compete with the XPoint-using OEMs that Intel and Micron are lining up.

That sounds like a re-run of the Itanium scenario, with proprietary tech vs commercial, off-the-shelf (COTS) commodity tech, and, let's face it, COTS generally prevails over proprietary tech.

SK Hynix, which has been working with HPE on Memristor chip-making technology, has so far failed to come up with affordable, reliable chips.

The only large-scale chip fabricator that could take on Memristor production would appear to be Samsung. Unless it, or another large-scale fab operator, takes Memristor on board, providing the productising, fab capacity and potential OEM channels needed, then Memristor is dead - edged off the table by XPoint. ®

Similar topics


Other stories you might like

  • DuckDuckGo tries to explain why its browsers won't block some Microsoft web trackers
    Meanwhile, Tails 5.0 users told to stop what they're doing over Firefox flaw

    DuckDuckGo promises privacy to users of its Android, iOS browsers, and macOS browsers – yet it allows certain data to flow from third-party websites to Microsoft-owned services.

    Security researcher Zach Edwards recently conducted an audit of DuckDuckGo's mobile browsers and found that, contrary to expectations, they do not block Meta's Workplace domain, for example, from sending information to Microsoft's Bing and LinkedIn domains.

    Specifically, DuckDuckGo's software didn't stop Microsoft's trackers on the Workplace page from blabbing information about the user to Bing and LinkedIn for tailored advertising purposes. Other trackers, such as Google's, are blocked.

    Continue reading
  • Despite 'key' partnership with AWS, Meta taps up Microsoft Azure for AI work
    Someone got Zuck'd

    Meta’s AI business unit set up shop in Microsoft Azure this week and announced a strategic partnership it says will advance PyTorch development on the public cloud.

    The deal [PDF] will see Mark Zuckerberg’s umbrella company deploy machine-learning workloads on thousands of Nvidia GPUs running in Azure. While a win for Microsoft, the partnership calls in to question just how strong Meta’s commitment to Amazon Web Services (AWS) really is.

    Back in those long-gone days of December, Meta named AWS as its “key long-term strategic cloud provider." As part of that, Meta promised that if it bought any companies that used AWS, it would continue to support their use of Amazon's cloud, rather than force them off into its own private datacenters. The pact also included a vow to expand Meta’s consumption of Amazon’s cloud-based compute, storage, database, and security services.

    Continue reading
  • Atos pushes out HPC cloud services based on Nimbix tech
    Moore's Law got you down? Throw everything at the problem! Quantum, AI, cloud...

    IT services biz Atos has introduced a suite of cloud-based high-performance computing (HPC) services, based around technology gained from its purchase of cloud provider Nimbix last year.

    The Nimbix Supercomputing Suite is described by Atos as a set of flexible and secure HPC solutions available as a service. It includes access to HPC, AI, and quantum computing resources, according to the services company.

    In addition to the existing Nimbix HPC products, the updated portfolio includes a new federated supercomputing-as-a-service platform and a dedicated bare-metal service based on Atos BullSequana supercomputer hardware.

    Continue reading

Biting the hand that feeds IT © 1998–2022