One of the key drivers to increase capacity in next generation storage has been to increase the number of bits that can be stored per cell. The easy jump of one to two bits-per-cell gives a straight 100% increase, in exchange for more control needed to read/write the bit but also limits the cell endurance. We’ve seen commercialization of storage up to four bits-per-cell, and talk about five. A Japanese company is now ready to start talking about their new 7 bits-per-cell solution.


Image courtesy of Plextor, up to 4 bits-per-cell

Moving from one to two bits-per-cell gives an easy doubling of capacity, and moving to three bits-per-cell is only another 50% increase. As more bits are added, the value of adding those bits diminishes, but the cost in the equipment to control the read and writes increases exponentially. There has to be a medium balance between how many bits-per-cell makes economic sense, and how much the control electronics costs to implement to enable those bits.

  • 1 bit per cell requires detection of 2 voltage levels, base capacity
  • 2 bit per cell requires detection of 4 voltage levels, +100% capacity
  • 3 bit per cell requires detection of 8 voltage levels, + 50% capacity
  • 4 bit per cell requires detection of 16 voltage levels, +33% capacity
  • 5 bit per cell requires detection of 32 voltage levels, +25% capacity
  • 6 bit per cell requires detection of 64 voltage levels, +20% capacity
  • 7 bit per cell requires detection of 128 voltage levels, +16.7% capacity

Also, the more bits-per-cell, the lower the endurance – the voltage variation when you store many bits only has to drift slightly to get the wrong result, and so repeated read/writes to a high capacity cell will make that voltage drift until the cell is unusable. Right now the market seems happy with three bits-per-cell (3bpc) for performance and four bits-per-cell (4bpc) for capacity, with a few 2bpc designs for longer term endurance. Some of the major vendors have been working on 5bpc storage, although the low endurance may make the technology only good for WORM – write once, read many, which is a common acronym for the equivalent of something like an old-school CD or non-rewritable DVD.

Floadia Corp., a Series C startup from Japan, issued a press release this week to state that it has developed st­­orage technology capable of seven bits-per-cell (7bpc). Still in the prototype stage, this 7bpc flash chip, likely in a WORM scenario, has an effective 10-year retention time for the data at 150C. The company says that a standard modern memory cell with this level of control would only be able to retail the data for around 100 seconds, and so the secret in the design is to do with a new type of flash cell they have developed.

The SONOS cell uses a distributed charge trap design relying on a Silicon-Oxide-Nitride-Oxide-Silicon layout, and the company points to an effective silicon nitride film in the middle where the charges are trapped to allow for high retention. In simple voltage program and erase cycles, the company showcases 100k+ cycles with a very low voltage drift. The oxide-nitride-oxide layers rely on SiO2 and Si3N4, the latter of which is claimed to be easy to manufacture. This allows a non-volatile SONOS cell to be used in NV-SRAM or embedded designs, such as microcontrollers.

It’s actually that last point which means we’re a long time from seeing this in modern NAND flash. Floadia is currently partnering with companies like Toshiba  to implement the SONOS cell in a variety of microcontrollers, rather than large NAND flash deployments, at the 40nm process node as embedded flash IP with compute-in-memory properties. Those aren’t at 7 bits-per-cell yet, to the effect that the company is promoting that two cells can store up to 8-bits of network weights for machine learning inference – when we get to 8 bits-per-cell, then it might be more applicable. The 10-year retention of the cell data is where it gets interesting, as embedded platforms will use algorithms with fixed weights over the lifetime of the product, except for the rare update perhaps. Even with increased longevity, Floadia doesn’t go into detail regarding cyclability at 7bpc at this time.

An increase from modern 3bpc to 6bpc NAND flash would afford a double density increase, however larger cells would be needed, which would negate the benefits. There’s also the performance aspect if the development of >4bpc ever made it to consumers, which hasn’t been touched upon.

It will be an interesting technology to follow.

Source: Floadia Press Release

POST A COMMENT

48 Comments

View All Comments

  • mode_13h - Monday, December 20, 2021 - link

    I was recently looking askance at Crucial's 4 TB refresh of their MX500. However, I found a review that went into considerable depth about Micron's shift in cell architecture and came away with the impression that endurance of their latest TLC memory could actually be somewhat comparable to their old MLC stuff. Not sure if that's accurate, but they've certainly regained some ground. Reply
  • Kvaern1 - Sunday, January 2, 2022 - link

    It's accurate.
    The TLC Samsung 980 Pro has the same TBW as the MLC 950 Pro and wipes the floor with it on all other parameters, at 25% of the GB price of a 950 Pro in 2016.
    Not to mention the vast majority of usecases will never wear out a TLC or even a QLC SSD and if your needs are beyond that you're now part of a very small market for which properly spec'ed professional parts exist and you should be aware of that.
    Reply
  • linuxgeex - Wednesday, December 15, 2021 - link

    P/E is Program/Erase, lol. The slowdown isn't logarithmic. It won't be floppy speed, or even SMR HDD speed. The main problem will almost certainly be that the energy cost per MB transferred will be higher, which will prevent Mobile adoption, which will seriously hamper scaling because that is where scaling starts. I suspect this is part of why their MCU efforts are at QLC, albeit there's low-power synergy with 2 cells = 8 bits as well. As for P/E, the article claims 100k P/E cycles. That's probably for when it's operating in SLC mode at 40nm. Generally you divide by 3 each time you add a level, so 100k / 3^7 is approx 45 7-layer P/E cycles, which is probably still OK for consumer-level photography memory. However only 10 years of retention when it's damn near an archival format... that is sucky and again will harm adoption and scaling. So for those reasons I suspect this will be dead in the water. Reply
  • vlad42 - Thursday, December 16, 2021 - link

    Yeah, P/E was a derp moment with no edit button. I realized the mistake right after hitting reply.

    Floppy speed was definitely meant as a hyperbole. I hope you are right that that this remains a niche product.
    Reply
  • back2future - Friday, December 17, 2021 - link

    "repeated read/writes to a high capacity cell will make that voltage drift until the cell is unusable"
    That's the difference to previous nand cells?
    Reply
  • back2future - Sunday, December 19, 2021 - link

    Maybe someone can elaborate, at what amount *read* rate on stored data (equal read address for longer period compared to writing cells with addresses being available empty pages) is impacting voltage drift? Thx Reply
  • back2future - Sunday, December 19, 2021 - link

    if this (https://media.springernature.com/lw785/springer-st... would be reference for 5V power supply voltage nand storage system (compared to 1.8V nand power supply, etc.) and told 5-6% deviation for slc comparable 1bit level storage voltage_th (threshold) is limit for reliable avoidance of bit error rate above acceptable rate, then voltage level for acceptable recognition for 0/1 of storage state is limited to about 0.2-0.25V deviation from reference voltage for each state (0V or maybe slightly below GND, 4-4.2V for a logical 1).
    These 5-6% are divided by 4 on MLC, div by 8 on TLC, /16 on QLC and /128 on 7bit level storage cell, what given relatively high 5V device supply might get into 1.9mV for limit of deviation from reference voltage for reliable recognition of cell state and stored bit data? Seen 0.15V drift for a 40days data retention time on room temperatures (P3 testing conditions: https://www.researchgate.net/profile/Onur-Mutlu-4/... data:image/jpeg;base64,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 ), this 10yrs retention time is the real progress and news for this? Still interested, what read rate is affecting cells voltage treshold and how does storage management invisibly to users monitoring statistics (and tools) refreshes cells in reaction to amount of read capacity leakages to cell gates?
    Reply
  • back2future - Sunday, December 19, 2021 - link

    Sorry, linking to graphs was not like intended:
    if this ( https://rb.gy/youkdw ) would be reference for 5V power supply voltage nand storage system (instead of compared to 1.8V nand power supply, etc.) and told 5-6% deviation for slc comparable 1bit level storage voltage_th (threshold) is limit for reliable avoidance of bit error rate above acceptable rate, then voltage level for acceptable recognition for 0/1 of storage state is limited to about 0.2-0.25V deviation from reference voltage for each state (0V or maybe slightly below GND, ~4-4.2V for a logical 1).
    These 5-6% for slc high state, are divided by 4 on MLC, div by 8 on TLC, /16 on QLC and /128 on 7bit level storage cell, what, given relatively high 5V device supply, might get into 1.9mV for limit of deviation from reference voltage for reliable recognition of cell state and stored bit data? Seen 0.15V drift for a 40days data retention time on room temperatures (P3 testing conditions: https://rb.gy/eebjgg, https://rb.gy/sbush0 ), this 10yrs retention time is the real progress and news for this? Still interested, what read rate is affecting cells voltage treshold and how does storage management invisibly to users monitoring statistics (and tools) refreshes cells in reaction to amount of read capacity leakages to cell gates?
    Reply
  • back2future - Monday, January 3, 2022 - link

    While for MLC cells it was mentioned, there could be a degradation with read accesses, resulting into higher demand for data refresh write for about 1 million reads on SLC compared to 100k-20k reads on MLC cells, data for TLC or QLC are rare. Samsung (for e.g. 845DC EVO 3-bit MLC read intensive, 850DC PRO 2-bit, 24-layer MLC NAND mixed and write intensive) advertises for read intensive use cases
    "Read-intensive use cases are
    typical of presentation platforms
    such as web servers, social media
    hosts, search engines and content-
    delivery networks. Data is written
    once, tagged and categorized,
    updated infrequently if ever, and
    read on-demand by millions of
    users. Planar NaND has excellent
    read performance, and limiting
    the number of writes extends the
    longevity of an SSD using it."

    with mixed loading for read/write on 50/50 to 70/30 assumptions.
    https://downloadcenter.samsung.com/content/UM/2017...
    details on endurance (retention?)
    https://downloadcenter.samsung.com/content/UM/2017...

    datacenters failed storage SSDs, parameters for accurate failure identification, table 5 (page 8)
    https://www.microsoft.com/en-us/research/wp-conten...
    Reply
  • back2future - Monday, January 3, 2022 - link

    retention for MLC (2012, some overview, page 7)
    https://citeseerx.ist.psu.edu/viewdoc/download?doi...
    SLC (P/E cycles) with varying recovery in seconds from programming (~100's) ~63yrs, (100's-1000's) ~20yrs
    MLC (~100's) ~20yrs, (~1000's) ~5yrs (also varying with prog. recovery from none/10s to 10000s/1d, with x10-x100 factor difference between for P/E cycles allowed for accepted retention needs, page 8 diagrams, and about x10 factor between SLC and 2-bit MLC NAND type, but absolute 1/2-1/3 data retention periods (years on 100's P/E) for MLC's on 2012 knowlegde and tech, just for overview on retention development and request for TLC/QLC/'7-bit'LC data and studies)
    Reply

Log in

Don't have an account? Sign up now