HGST sets hearts aflutter with second sexy PCM demo

Plenty of sizzle so far, but no product steak to speak of yet


HGST is being a sexy beast and strutting its Phase Change Memory stuff once again, at the Flash Memory Summit.

Sex sells in the flash biz and HGST thinks it has a hot little number – again – with its Phase Change Memory technology. A year on from its 3 million IOPS/1.5 microsecs latency demo of a PCIe-connected PCM SSD, it is showing an RDMA over InfiniBand connected PCM SSD with less than two microseconds round-trip access latency for 512B reads, and throughput exceeding 3.5 GB/s for 2KB block sizes.

The background pitch is that volatile DRAM is hugely expensive in its electrical use, while HGST’s non-volatile PCM card is electrically anorexic, while providing DRAM-like speed.

The InfiniBand came from Mellanox, and its marketing VP Kevin Deierling had a canned quote saying: “In the future, our goal is to support PCM access using both InfiniBand and RDMA over Converged Ethernet (RoCE) to increase the scalability and lower the cost of in-memory applications.”

HGST is calling its set-up a persistent memory fabric, describing it as a PCM-based, RDMA-enabled in-memory compute cluster architecture. It says the host servers don’t need either BIOS changes or app software mods.

The demo at the Flash Memory Summit shows that RDMA-connected PCM storage is faster than NAND would be, but you can’t buy it.

HGST_PCM_RDMA

What is HGST up to here? Last year its PCM chips came from Micron. Let’s assume they’re Micron ones again and HGST’s interest is in selling PCM storage cards. They’re obviously not ready for prime-time, because HGST isn’t selling PCM-based storage cards.

It appears to be aiming to develop an RDMA-enabled, InfiniBand or fast Ethernet-linked PCM box that can be added to several servers’ memory address spaces and so help propel in-memory compute to the foreground.

Memory mapping of remote PCM using the Remote Direct Memory Access (RDMA) protocol over networking infrastructures, such as Ethernet or InfiniBand, enables a seamless, wide-scale deployment of in-memory computing. This network-based approach allows applications to harness the non-volatile PCM across multiple computers to scale out as needed.

HGST CTO Steve Campbell’s canned quote said: “Our work with Mellanox proves that non-volatile main memory can be mapped across a network with latencies that fit inside the performance envelope of in-memory compute applications.”

Diablo Technologies’ Memory1 is in-server DIMM-connected NAND acting as a DRAM substitute and expander. HGST’s persistent memory fabric is a networked and presumably more scalable DRAM substitute and expander. Is it faster in access than Memory1? We don’t yet know.

Intel and Micron’s 3D XPoint memory is faster than NAND but not as fast as DRAM, and will be/should be/could be ready in 2016. How it will compare price and performance-wise to PCM will be fascinating to understand.

For now, HGST’s demo is a PCM tease. If you like being teased, then hop along to HGST’s booth #645-647 at the 2015 Flash Memory Summit in the Santa Clara Convention Centre, Santa Clara, CA, on August 11-13, 2015 and take a look at its sexy phase-changing beast. ®

Similar topics


Other stories you might like

  • NASA delays SLS rollback due to concerns over rocky path to launchpad
    The road to the Moon is paved with... river rock?

    NASA's Moon rocket is to trundle back into its shed today after a delay caused by concerns over the crawlerway.

    The massive transporter used to move the Space Launch System between Vehicle Assembly Building (VAB) and launchpad requires a level pathway and teams have been working on the inclined pathway leading to the launchpad where the rocket currently resides to ensure there is an even distribution of rocks to support the mobile launcher and rocket.

    The latest wet dress rehearsal was completed on June 20 after engineers "masked" data from sensors that would have called a halt to proceedings. Once back in the VAB, engineers plan to replace a seal on the quick disconnect of the tail service mast umbilical. The stack will then roll back to the launchpad for what NASA fervently hopes is the last time before a long hoped-for launch in late August.

    Continue reading
  • Datacenter operator Switch hit with claims it misled investors over $11b buyout
    Complainants say financial projections were not disclosed, rendering SEC filing false and misleading

    Datacenter operator Switch Inc is being sued by investors over claims that it did not disclose key financial details when pursuing an $11 billion deal with DigitalBridge Group and IFM Investors that will see the company taken into private ownership if it goes ahead.

    Two separate cases have been filed this week by shareholders Marc Waterman and Denise Redfield in the Federal Court in New York. The filings contain very similar claims that a proxy statement filed by Switch with the US Securities and Exchange Commission (SEC) in regard to the proposed deal omitted material information regarding Switch's financial projections.

    Both Redfield and Waterman have asked the Federal Court to put the deal on hold, or to undo it in the event that Switch manages in the meantime to close the transaction, and to order Switch to issue a new proxy statement that sets out all the relevant material information.

    Continue reading
  • Google to pay $90m to settle lawsuit over anti-competitive behavior on the Play Store
    US developers that qualify could receive more than $200,000

    Google is to pay $90 million to settle a class-action lawsuit with US developers over alleged anti-competitive behavior regarding the Google Play Store.

    Eligible for a share in the $90 million fund are US developers who earned two million dollars or less in annual revenue through Google Play between 2016 and 2021. "A vast majority of US developers who earned revenue through Google Play will be eligible to receive money from this fund," said Google.

    Law firm Hagens Berman announced the settlement this morning, having been one of the first to file a class case. The legal firm was one of four that secured a $100 million settlement from Apple in 2021 for US iOS developers.

    Continue reading
  • Devops tool Jenkins now requires Java 11: This might sting a bit
    Final shift set for version 2.357 of developer automation platform

    It has taken a while, but the Jenkins project confirmed this week that Java 11 will be required from this week's Jenkins 2.357 and for the upcoming September LTS release.

    Jenkins, originally authored by Kohsuke Kawaguchi, recently passed its 10th anniversary. Originally known as Hudson, before the Oracle / Sun deal resulted in a fork, the platform is a veteran of the continuous integration and continuous delivery world. It is also written in Java.

    It's going to be a bit of a wrench. Java 11 itself was released in 2018 as a long-term support version, and the Jenkins LTS core has been Java 11-capable for a while now. The June LTS also supports Java 17 (the latest LTS of Java SE.)

    Continue reading

Biting the hand that feeds IT © 1998–2022