Looking To The Future: NAND Flash Scales Up to 64 TB SSDs in 2030

Over the past few years, the NAND Flash industry has gone through two major shifts in technology: the movement from 1 to 2 to 3 bits per cell, which directly increases bit density and capacity, and also moving from planar flash to variants of 3D stacking. Stacking can refer to individual NAND dies, as well as stacking those dies into a single package: both of these features are being extensively investigated to increase density also. There are two main drivers for this: reduction in cost, and capacity. However, despite this, the predictions in the ITRS report for NAND flash are primarily looking at improvements to numbers of layers rather than lithography changes or moving to more bits per cell.

As we can see, TLC (according to the report) is here to stay. QLC, or whatever you want to call it, is not mentioned. The two changes are the number of memory layers, moving from 32 today to 128 around 2022 and then 256/512 by 2030, and the number of word-lines in one 3D NAND string. This gives a product density projection of 256 Gbit packages today to 1 Tbit packages in 2022 and 4 Tbit packages in 2030.

If we apply this to consumer drives available today, we can extrapolate potential SSD sizes for the future. The current Samsung 850 EVO 4 TB uses Samsung’s 48-layer third generation V-NAND to provide 256 Gbit TLC parts. Alongside the 4 TB of memory, the controller requires 4 GB of DRAM, which is another concern to remember. So despite the report stating 256 Gbit in 32-layer, we have 256 Gbit in 48-layer, which is a difference primarily in die-size predictions for the report. Still, if we go off of the product density we should see 12 TB SSDs by 2020, 16 TB in 2022, 48 TB in 2028 and 64 TB drives in 2030. It’s worth noting that the ITRS report doesn’t mention power consumption in this table, nor controller developments which may be a substantial source of performance and/or capacity implementations.

Looking To The Future: 450mm Wafers in 2021, and Down to ‘2nm’ Looking To The Future: Mobile with 32 CPU Cores and 8K Displays
Comments Locked

158 Comments

View All Comments

  • Jon Tseng - Wednesday, July 27, 2016 - link

    Great chip. Only just upgraded from my QX6850 last month. Paired with a GTX 970 it was doing just fine running all new games maxed out at 1080p. Amazing for something nearly a decade old!!
  • Negative Decibel - Wednesday, July 27, 2016 - link

    my E6600 is still kicking.
  • tarqsharq - Wednesday, July 27, 2016 - link

    My dad still uses my old E8400 for his main PC. He's getting my old i7-875k soon though.
  • jjj - Wednesday, July 27, 2016 - link

    You can't do DRAM in glasses, not in a real way. Since that's what mobile is by 2025.
    On-package DRAM is next year or soon not 2025.
    You can't have big cores either and you need ridiculous GPUs and extreme efficiency. Parallelism and accelerators, that's where computing needs to go, from mobile to server.
    We need 10-20 mm3 chips not 100cm2 boards. New NV memories not DRAM and so on.
    Will be interesting to see who goes 3D first with logic on logic and then who goes 3D first as the default in the most advanced process.

    At the end of the day, even if the shrinking doesn't stop, 2D just can't offer enough for the next form factor. Much higher efficiency is needed and the size of a planar chip would be far too big to fit in the device while the costs would be mad.Much more is needed. For robots too.The costs and efficiency need to scale and with planar it's at best little.
  • wumpus - Thursday, August 4, 2016 - link

    On package DRAM seems to be a "forever coming" tech. AMD Fury-X basically shipped it, and it went nowhere. I'm guessing it will be used whenever Intel or IBM feel it can be used for serious advantage on some high-core server chip, or possibly when Intel want to build a high-speed DRAM cache (with high-speed-bus) and use 3dXpoint for "main memory".

    The slow rollout is shocking. I'm guessing nvidia eventually gave up with it and went with tiling (see the Kanter demo on left, but ignore the thread: nothing but fanboys beating their chests).
  • willis936 - Wednesday, July 27, 2016 - link

    I'm certainly no silicon R&D expert but I'm very skeptical of those projections.
  • Mr.Goodcat - Wednesday, July 27, 2016 - link

    Typo:
    "On the later, we get the prediction that 450nm wafers should be in play at around 2021 for DRAM"
    450nm wafers would be truly interesting ;-)
  • wumpus - Thursday, August 4, 2016 - link

    I like the rapidly falling static safety. Don't breathe on a 2030 chip.
  • faizoff - Wednesday, July 27, 2016 - link

    My first Core 2 Duo was an E4400 that I bought in 2007 I believe, thing lasted me up to 2011 when I upgraded to an i5 2500k. I should've kept that C2D just for nostalgia's sake, I used it intermittently as a plex server and that thing worked great on FreeNAS. The only issue was it was really noisy and would get hot.
  • Notmyusualid - Thursday, July 28, 2016 - link

    I've got a few old servers kicking around, all with valid Win server licenses, but due to UK electricity costs, just can't bring myself to have them running at home 24/7 just to serve a backup, or yet another Breaking Bad viewing session... :) which we can do locally now.

Log in

Don't have an account? Sign up now