SK Hynix today announced that they’ve begun sampling of its first ever PCIe 4.0 enterprise SSDs in the form of the new 96-layer 3D-NAND U.2/U.3 form-factor PE8010 and PE8030 eSSDs, as well as announcing plans to sample the new PE81111 EDSFF E1.L SSDs based on their 128-layer “4D NAND” flash modules later in the year.

We had expected the new PE8111 eSSD for some time know as we reported about SK Hynix’s plans to introduce such a product last November. The biggest change here is the company’s use of new 128-layer 3D NAND modules that the company dubs as “4D-NAND” because of a new denser cell structure design and higher per-die I/O speeds.


16TB Enterprise EDSFF E1.L SSD

The PE8111 still retains as PCIe 3.0 interface and its corresponding performance characteristics plateau at 3400MB/s sequential reads and 3000MB/s sequential writes – whilst supporting random reads and writes up to respectively 700K and 100K IOPs. Because it’s a long-factor EDSFF E1.L form-factor, storage capacity for the unit falls in at 16TB, and SK Hynix is reporting that they’re working on a 32TB solution in the future.

The new PE8010 and PE8030 come in an U.2/U.3 form-factor and are the company’s first SSDs support PCIe 4.0. The SSDs here still rely on 96-layer NAND modules from the company – but are using an in-house controller chip. Bandwidth here is naturally higher, reaching up to 6500MB/s reads and 3700MB/s write sequentially, with random IOPs falling in at respectively 1100K for reads and 320K for writes.

Power consumption for the new U.2/U.3 drives is actually extremely competitive given their jump to PCIe 4.0 – rising only up to 17W as opposed to their previous generation PCIe 3.0 products which fell in at 14W. This is likely to be attributed to the new generation custom controller, which might be more optimised for low-power compared some or the early third-party 4.0 controllers out there.

The PE8010 and PE8030 are sampling right now with customers – with the PE8111 planned to be sampled in the second half of the year.

Related Reading:

Source: SK Hynix

Comments Locked

40 Comments

View All Comments

  • azfacea - Wednesday, April 8, 2020 - link

    and oh i dont know there are two big consoles coming this year that made that exact point. very little generational jump in memory size compared to previous generations, but they made the point that reading disk at approx 5GB (xbox) and 9GB (ps) per second changes what you can do with it.
  • schujj07 - Wednesday, April 8, 2020 - link

    Rather than making snide comments to me, why don't you make valid counter arguments. When I said that even the fastest SSDs are orders of magnitude slower than DRAM, I made a factual statement that refuted your "if SSD performance keeps improving like this, it can provide competitive pressure to DRAM..." Even Optane Memory acts as nothing more than a large cache between the DRAM and storage on SAP HANA hosts.

    I have heard of this thing called a "network," however, your assessment of a home network is quite wrong. Even a slow 5400 RPM USB powered drive is fast enough on sequential reads and writes to take the full bandwidth of a 1GbE connection. Most homes don't have more than GbE for their home network. With that speed networking having SSD on it is a waste as you will be network limited pretty bad.

    Yes SSD is getting faster and that is a good thing, but it has a VERY long way to go before it can ever be a competitor to DRAM.
  • azfacea - Thursday, April 9, 2020 - link

    you don't know what u r talking about. Cobble together some anecdotes and generalize about the whole market. I said competitive pressure. that means any application not every application. and I already gave u an example that increased its Oct investment in disk at the expense of ram.

    your statement was no such thing as fact that refuted my statement. again its like saying no other node from the past can compete with tsmc 5nm, and that it exclusively sets the price of transistors.

    the rest of it was nonsense about home networks and what not that I could never respond too. its like me saying more supply prices go down, and u talk about most Pol can't buy meat because apple are cheaper.
  • azfacea - Thursday, April 9, 2020 - link

    pct investment*
    not "Oct investment"
  • GreenReaper - Thursday, April 9, 2020 - link

    Much of the benefit of an SSD comes from access times, and while a network does add significant latency, it is still at least an order of magnitude faster (perhaps two) than a hard disk's access time. This is why network-based SSD block storage is a viable thing.
  • schujj07 - Thursday, April 9, 2020 - link

    I know that SSD based block storage is a very viable thing. I run a DC that uses NVMe based SDS on a dual port 25GbE iSCSI connection. The difference in performance between that and our old 8Gb Fibre Channel 10k array is night and day. However, asfacea's comment seemed to be more home network related than storage network related.
  • close - Thursday, April 9, 2020 - link

    @schujj07, don't worry about @azfacea. Valid counter arguments are a foreign concept to them. For the past few years tt's always some immature comment about how SSDs already replaced all HDD, HDD aren't used by anyone because SSDs already do everything, better capacity, better price. Now that the recording got old they switched to "OMG GBps, will be better than RAM".

    Keep in mind that they appear to have the understanding of a child, looking at the flashy numbers and peak performance. Like someone bulging their eyes at phone camera MP count and immediately concluding that DSLRs or dedicated cameras will be dead by the end of the month.
  • rpg1966 - Wednesday, April 8, 2020 - link

    Ignore him, he has this price-fixing conspiracy theory in his brain, and can't help but comment on it every time there's a slightly-relevant article.
  • azfacea - Thursday, April 9, 2020 - link

    its not a conspiracy theory if several govt are investigating it. lets also forget how so many ppl have felt about dram in the last few years. those are all my alt accounts.

    but let's focus on the real issue here which is that I have posted too many comments. but i have a soln for your problem. piss off. don't read them if u don't like comments. u r in the wrong place not me.
  • deil - Thursday, April 9, 2020 - link

    ~100x slower, sata is 1000x slower than DRAM.

Log in

Don't have an account? Sign up now