More like this

Data Center

Arrow

Storage

Never-never chip tech Memristor shuffles closer to death row

Execution warrant close to being signed for Fink's folly

Memristor_wafer
Memristor wafer

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. ®

Sponsored: Customer Identity and Access Management