click to visit home page
leading the way to the new storage frontier
SSD history
top SSD companies
what's the state of DWPD?
popular SSD articles on
Capacitor hold up times in 2.5" military SSDs
should we set higher expectations for memory systems?
What were the big SSD ideas to learn and forget in 2015?
latency reasons for fading out DRAM in the virtual memory mix
SSD ad - click for more info
Non-Balanced Wear Leveling - a paper by Renice
Editor:- July 28, 2016 - Renice Technology recently published a paper - Non-Balanced Wear Leveling Algorithm (pdf) - which outlines the thinking behind a specific technique in its industrial SATA3 SSD controller - model RS3502-IT - to improve endurance upto 3x compared to traditional methods.

This is one of the several techniques used in this controller to overall get a 20x improvement in lifespan when using MLC. the article (pdf)

Editor's comments:- Ever since the first flash devices were evaluated it has been known that some blocks are much better than others.

As an example in this paper Renice shows that in a modern 16GB MLC flash chip - even after just 10 P/E cycles the controller is able to see a 3x difference between the fastest and average program time and over 30% difference between the slowest and fastest read times.

click image to read the article - principles of bad block management in flash SSDs
bad block management
in flash SSDs
The quality of wear resistance tells you something which can be used to grade blocks.

Renice's non-balanced wear leveling algorithm leverages these naturally occurring process variations so that "the higher wear resistance blocks are selected to be erased more times while the lower ones get protected instead."

Although there are no fundamentally new ideas presented in this paper - because the technique is just one permutation of many from the superset of all adaptive R/W techniques - this paper does provide a useful survey of classical wear leveling techniques along with their associated trade offs in performance and endurance.

I got a good sense of judgment and balance in this paper - given the unstated context.

Context is always important - and these techniques are discussed in the context of general purpose, simple low power industrial SSDs which use modest speed SSD processors and skinny RAM flash caches.

That's distinct thinking from new generation enterprise array controllers in which visibility into other SSDs in the same array, larger ratios of DRAM and knowledge about the applications software stack can also be leveraged to reduce endurance.

Here are more articles on these themes:-

LSI SandForce SSD processors - click for more info
the awards winning silicon
accelerating world's leading SSDs
from Seagate

data dematerialization in the DIMM?
Editor:- July 27, 2016 - Some of the big SSD ideas in recent years have been:-
  • in-situ processing, and
  • DIMM wars.
One way to interpret the essence of Symbolic IO's architecture - which was partially unveiled in May 2016 - may be as a coming together of the 2 concepts in the same place...

What got me thinking this way was a recent blog - a look at Symbolic IO's patents - by Robin Harris on his site - .

Symbolic IOs founder Brian Ignomirello who saw and liked Robin's post - said among other things on linkedinpulse - "yes we (do) materialize and dematerialize data." the article

PS - In a conversation I had about the market yesterday (which I'll write about next month) I noted how during the past year the SSD industry has been thinking much more about memory systems architecture as the next emerging core for innovation in the same kind of way that the market was buzzing about apps acceleration using SSDs on the SAN and in servers via PCIe cards 8 to 10 years ago.

It's because of all that previous market experience with PCIe SSDs in servers especially and the comparisons with other ways of getting similar results with arrays of SAS / SATA SSDs in storage - and the feel-good confidence from having made those difficult changes - that the data computing market is now receptive to being more ambitious with re-engineering memory.

The business incentive being that the gap between what is possible and what is being done every day with current products is so huge and wasteful. (Huge savings for users. Multi-billion dollar new markets for vendors.)

We've already seen a lot of different approaches coming down the pipe in the past year with technology announcements. But even though the implementation details are so different - they're tackling the same problem.

With more toys in the memory, SSD and software tool kit - there are now more permutations for delivering applications servers which exceed previous performance limits and slash away at legacy cost assumptions.

The DNA of the semicondata market continues its ruthless quest of doing more for less.

"Previous concerns about RAM being able to store only a limited amount of data are becoming a non-issue. Recently, Amazon introduced their X1 Instance, which lets customers rent computing instances with 2 terabytes of RAM for just $13.34 per hour. At such pricing levels, the economics of renting large clusters containing virtually any amount of RAM are well within reach."
Abe Kleinfeld, President & CEO at GridGain Systems in his blog - In-Memory Computing Will Dramatically Change Our Lives (July 14, 2016)

cloud storage news, vendors, articles  and directory - click here
SSDs in the cloud

All the marketing noise coming from the DIMM wars market (flash as RAM and Optane etc) obscures some important underlying strategic and philosophical questions about the future of SSD.

When all storage is memory - are there still design techniques which can push the boundaries of what we assume memory can do?
where are we heading with memory intensive systems?

Compared to earlier phases in the SSD market more is changing.
the SSD Bookmarks - series overview

revisiting animal brands in storage
Editor:- July 19, 2016 - a press release today from Seagate about new hard drives isn't something I would have mentioned here were it not for its abundance of animal brands which include:-BarraCuda, IronWolf and SkyHawk.

Which got me looking at 2 lists which I compiled a long time ago on this theme, namely:- As I've often said before - all the best animals have been taken. But it's interesting to look at the 3 in today's news story.


Seagate's press release today acknowledges that the BarraCuda was a well known brand which it had used before. But what about the others?


We've had a wolf before - as a tape library from StorageTek.

But the new IronWolf brand - as a marketing construct - cleverly combines several different metaphors simulataneously.
  • wolf - as in the animal metaphor

I haven't seen SkyHawk used for an HDD before - but it was used as the brand for a rackmount SSD launched by Skyera in August 2012. Skyera was later acquired by Western Digital which could have made it a problematic choice for a storage related product. Except that differences between HDDs and SSDs are now well understood and WDC EOLed that product line so Seagate's SkyHawk and WDC's SkyHawk aren't circling in the same marketing skies at the same time.

But even if they were - the general principle is you can't exclusively trademark such common words.

The main exception to this being a well known fruit which appears in the same scene as a serpent in the Book of Genesis.

For 13 years MRAM makers have been saying they will "soon" replace flash.
SSD's past phantom demons

Until about the middle of 2015 - it was still generally agreed that if you used classical (non adaptive, non DSP) controllers then the endurance estimates you needed to take into account were still the figures supplied by the semiconductor memory makers.

Then a new company came along - whose founders had been researching a different way of characterising flash endurance for over a decade.
SSD endurance myths and legends
Cadence logo - click for more info


SSD news

relating NVMdurance's machine learning to manual tuning

Editor:- July 29, 2016 - Nearly every SSD in the market today from the smallest SSD on a chip to the bewildering array of rackmnount systems can be viewed as a choice of how to select and mix the raw ingredients of SSD IP and integrate them into products which (for better or worse) match up to and satisfy user needs. How these decisions are made depends on the DNA of the product marketers, the technology teams, familiarity and ease of access to some technologies rather than others, business pressures and timing, the willingness to take risks, and sometimes - just luck.

But all products - no matter how complex they appear - can be analyzed as a specific set of choices made from the architecture and IP selections which are possible.

In many articles in the past I've shown you how - whether you're looking at the design of SSDs or systems - there are rarely more than 2, 3 or 6 raw available decisions which determine each piece of the jigsaw. And I know from the feedback I get from SSD specifiers and architects that these simple classifications can be useful in helping to compare different products and even in choosing which competitive approaches are similar enough to make comparisons worthwhile.

But when you get down into the details of implementation at each layer in the product design - every one of these dimensional options which go into the permutations blender to shape the total product identity - can itself be complex and multilayered.

Take the example of the raw magic tuning numbers which enable the raw R/W program, erase, threshold voltages, shaping and timing parameters inside a flash memory. The question of how much and when has been at the heart of what makes some SSDs better than others ever since flash was first used in SSDs.

Some SSD designers have spent their whole careers measuring and modeling how these choices interact with the flash cell and can be tweaked to improve speed, power consumption and reliability. You can get a flavor of this in my article - adaptive R/W and DSP ECC IP.

In a conversation with NVMdurance's CEO - Pearse Coyle earlier this year (April 2016) almost the first thing I did was try to relate and place the work they were doing within the simple frameworks I'd written about before.

So I asked him how similar it was to something which I wrote a long article about in April 2012 - when SMART announced a range of SandForce driven SSDs which had 5x higher endurance - while using exactly the same industry controller - but using magic tuning numbers which they had learned from analyzing the adaptive settings from their own adaptive controller design.

Pearse said - yes - he knew that work. And what NVMdurance was doing was the same type of thing.

He said that some leading companies which had the flash talent had done similar things in their proprietary SSDs before.

Pearse told me that as the complexity of flash increased - with more layers and TLC - it was becoming harder for designers to manually (or using human expertise) guarantee they were choosing the optimum magic numbers - because there were now so many variables involved.

Pearse said that what was different about NVMdurance was that they were delivering the magic numbers based on characterising a sample of typically 100 devices and then performing machine based simulations to see which numbers would work best - while also using a multi-stage life cycle model - which was designed to use different tuning after a fractional amount of the expected endurance had been used.

As far as he knew from his conversations with memory companies - no-one else had made the same kinds of investments in this machine intensive modeling - and that was the key difference - because NVMdurance had a proven process for delivering good tuning numbers over a variety of memory generations and types.

I hoped at the time that someone would write a paper saying more about it. Tom Coughlin has done that.

Machine learning enables longer life high capacity SSDs (pdf) - published this week describes the background principles and operation of NVMdurance's pathfinder and plotter software tools and shows you how NVMdurance have tackled this complex tuning problem to deliver a software delivered IP which can give endurance results which are similar to adaptive adaptive R/W controllers but which don't need such expensive processors or such complex run-time firmware. the article (pdf)

Toshiba samples 64 layer 3D TLC

Editor:- July 27, 2016 - Toshiba today said it is sampling 64 layer 3D TLC flash in a 32GB device and plans production in the first half of 2017.

Editor's comments:- You can judge the progress on this technology by the fact that in March 2015 - Toshiba was sampling 48 layer MLC.

Seagate unveils 2TB enterprise M.2

Editor:- July 26, 2016 - Seagate today unveiled a 2TB M.2 NVMe PCIe SSD aimed at the enterprise market. The Nytro XM1440 M.2 - which will ship in November 2016 - will offer 30K IOPS / Watt.

Memory1... if you want it - you can have it

the phoney war phase of DIMM wars has now ended

Editor:- July 20, 2016 - Diablo Technologies today announced the production release and volume availability of its Memory1 128GB DDR4 system memory module.

Editor's comments:- Diablo's Memory1 unveiling in August 2015 was part of a wave of similar announcements last summer. I commented on its significance and listed the other contenders which emerged in an article - who's working on SSD DIMM wars technology?

The phoney war phase of SCM DIMM wars has now ended with volume shipments of Memory1 (flash as DRAM).

It's now time for competitors who aren't yet shipping products in volume to start publishing full technical specifications for their own alternative memory products (if they dare) and for investment oriented stock-price puffing announcements about DIMM wars productsto cease and be replaced by papers, presentations and ads aimed at engineers.

trust me I'm a services marketer

Editor:- July 20, 2016 - 12 years ago a survey by identified that service related guarantees for enterprise SSD systems could be among the pivotal market adoption disinhibitors. But compared to the fast moving backdrop of enterprise technology it's interesting to note that the way marketers behave has changed so slowly.

It takes a long time for marketers to understand and learn why their potential customers aren't buying. Or why they aren't as excited by new products as their creators and investors. I touched on the deep seated reasons for this kind of disconnect in my article - decloaking hidden and missing segments in the analysis of market opportunities for enterprise rackmount flash (2014).

Pricing is an area where we began to observe innovation in the SSD market at around the same time and I wrote about some of the ways in which vendors were starting to sidestep the issues of complexity (which arise from having to know too many things which are unknown by most customers or unknowable) in my article -exiting the astrological age of enterprise SSD pricing.

If you haven't read it an inexact analogy is that if you're buying a plane you don't have to know the physics about how it flies. Others who do know physics and how the bits fit all together will certify that it's safe. The more important aspects for you as a buyer are how it will fit into your business plans. It takes a long time to learn those plane vendor things and become trusted. That's why in mature markets where there are these high barriers to entry - you don't hear about hundreds of new companies entering the plane market. Unlike the wild west of SSD systems.

And if you're still with me at this point. Price is a marketing service.

If you thought it was anything else and if you work in SSD sales or marketing you've got a lot of reading or training courses to get through.

Which brings me to a recent services related press release from Kaminario.

The message essence is their headline...

"Kaminario unveils storage industry's most comprehensive business assurance program."

How much of that claim you agree with or disagree with is up to you. And don't complain to me if you don't agree.

We've seen many similar sounding service related assurance offerings from other vendors too.

They can be summarized as - buy this stuff from us and we'll always look after your interests and make sure you don't regret it.

The details of such service related offers always sound like it's Christmas. John McClane will rescue his wife. Scrooge will avoid a bad end by giving away a turkey. And Dorothy will find her way from Oz.

But when it comes to long range service promises from any SSD company you need to use your common sense too.

Given what we've seen in the enterprise SSD market in recent years:- the acquisitions, the EOL product lines and the predictable EOL and obsolescence of most current platforms and architectures - it's worth reminding yourself that companies can only deliver on such long term promises if they are still in business, remain profitable and remain in control of their own destinies.

Mangstor gets another $5 million funding

Editor:- July 15, 2016 - Mangstor has raised another $5 million in funding according to a report in the Austin Business Journal.

See also:- VCs in SSDs

Court of Appeals affirms jury decision on DIMM wars trade secrets

memory channel storage
memory channel SSDs
Editor:- July 14, 2016 - One of the factors which stalled the anticipated business growth in the memory channel SSD market in 2014 and the first half of 2015 was uncertainty about the outcome of a long running patent and trade secret dispute between Diablo and Netlist related to how they had solved the line loading and latency problems associated with connecting significant amounts of control logic and memory in standard interfaces which had been originally designed to support low numbers of DRAM chips.

hybrid DIMMs
hybrid DIMMs
Most external observers stopped fretting about that in March 2015 when a court verdict seemed to clarify the situation.

But Netlist appealed that verdict and so there was still an element of uncertainty pending the outcome of the appeal hearing scheduled this month.

Now a press release by McDermott Will & Emery LLP (the law firm acting for Diablo) seems to close the book on this matter.

"McDermott represented Diablo at the appellate briefing and oral argument on July 7, 2016. Two business days after the argument, the Federal Circuit panel unanimously affirmed the judgment in favor of Diablo."

SST qualifies NOR SuperFlash on mixed signal platform

Flash Memory
flash & nvm
Editor:- July 12, 2016 - SST today announced qualification and availability of its low-mask-count embedded SuperFlash NOR NVM on GLOBALFOUNDRIES' 130 nm BCDLite advanced analog, mixed-signal and RF technology platform.

SST's embedded SuperFlash memory solution requires the addition of only 4 masking steps to enable cost-effective, high-endurance embedded flash for demanding battery-powered applications such as drones, intelligent motor control, and normally-off mobile computing.

Symbolic IO appoints CTO

Rackmount SSDs click for news and directory
rackmount SSDs
Editor:- July 12, 2016 - Symbolic IO (which unveiled its new memory intensive data architecture in May 2016) today announced that Rob Peglar, formerly VP, Advanced Storage at Micron has joined the startup's executive team as Senior VP and CTO.

"What Symbolic IO is doing, is quite frankly, the most innovative approach to stored data in 20 years, with huge implications on compute and how we architect systems in general and distributed systems in particular, " said Peglar. "It's not every day that a company comes along with a truly innovative and new technology. What Symbolic IO is doing is a once-in-a-generation, breakthrough approach to the problem of optimally storing and using data for efficient computation. Just like all the major players got their start, we've created new category called computational defined storage."

See also:- where are we heading with memory intensive systems?

custom SSDsdo custom SSDs cost more?

Editor:- July 12, 2016 - Do custom SSDs cost more?

Few questions in the SSD market have simple answers.

See my new blog - some thoughts about SSD customization.

IP-Maker releases Gen 3 NVMe PCIe reference design

SSD SoCs controllers
SSD controller chips
Editor:- July 11, 2016 - for designers of PCIe SSDs - IP-Maker has released its new Gen 3 NVMe PCIe reference design which is based on the VC709 evaluation kit by Xilinx.

It's integrated with Xilinx's Virtex-7 PCIe Gen3 hard IP and a soft DDR3 controller. The UNH-IOL NVMe compliant design uses a x4 lanes configuration.

the Top SSD Companies in Q2 2016

image shows megabyte waving the winners trophy - there are over 200 SSD oems - which ones matter? - click to read article
top SSD companies
Editor:- July 5, 2016 - Who are the top SSD companies - the companies which you absolutely have to look at if you've got any new projects involving SSDs?

For over 9 years has been answering that question with the Top SSD Companies which ranks companies by reader research volume. Time is precious for all of us and the crowd based intelligence of the series has helped millions of past SSD readers develop their own thinking about the market and contextualize and prioritize what they read about the market.

Now there's a new edition of the list - based on metrics in Q2 2016. And a new occupant of the significant #1 slot. Can you guess who it is? You don't need to guess. the article

How Flash Arrays Help US DoD and DHS protect against threats

Editor:- July 2, 2016 - A new blog by Zophar Sante, VP of Business Development at BiTMICRO - How AFAs Help US DoD and DHS outlines how the roles of solid state storage have changed in US government defense and security agencies in the past 20 years.

Among other things: - Zoph says - "The DoD and DHS are using what they learned from SSDs in field and applying the same technology to their data centers." the article

military storage directory and news
military SSDs
Editor's comments:- From the SSD history perspective BiTMICRO was a pioneer of high performance flash SSDs for the military market and one of the earliest advocates of flash in enterprise arrays.

Before the onset of the flash SSD era, however, DoD was already using rackmount SSDs in the late 1980s for mobile data capture and analysis. In those days the SSD memory technology in such boxes was inevitably DRAM.

You can read recollections about that in the 2010 retrospective paper - TMS History of Working With the US DoD (pdf) by the founder of Texas Memory Systems.
What happened before?
SSD ad - click for more info
SSD news page image - click to  enlarge
seeking the inner SSD
16 years ago - in July 2000

SST entered the SSD on a chip market with a 64MB PATA flash SSD packaged in a 32-pin DIP.
PBGA SSDs for rugged apps - click for more info
secure PBGA SLC SSDs
for extreme reliability in sensitive applications
from Mercury Systems

related guides

Targa Series 4 - 2.5 inch SCSI flash disk
2.5" removable military SSDs
for airborne apps - GbE / SATA / USB
from Targa Systems

related guides

industrial mSATA SSD
industrial grade mSATA SSDs
>2 million write cycles per logical block.
from Cactus Technologies

related guides

AccelStor NeoSapphire  all-flash array
1U enterprise flash arrays
InfiniBand or 10GbE iSCSI or 16G FC
NeoSapphire series - from AccelStor

related guides
"It's time for our industry to finally put to rest the outdated idea that flash arrays can offer either performance or reliability, but not both."
Dr. Weafon Tsao, VP - AccelStor in a press release (July 20, 2016) about the company's new NeoSapphire 3706-ES1 a 2U high-availability flash storage array - which - as well as a new NVMe array platform - will be shown at next month's Flash Memory Summit .

See also:- rackmount SSD segments vs user needs
Virtium  SSDs - click for more info
industrial SATA SSDs
efficiently matched to embedded needs
2.5" / 1.8" / Slim SATA / mSATA / CFast / M.2
StorFly – from Virtium

related guides
I think it's not too strong to say that the enterprise PCIe SSD market (as we once knew it) has exploded and fragmented into many different directions.
what's changed in enterprise PCIe SSD?
 dual ported  2.5 inch NVMe PCIe SSD from OCZ
2.5" NVMe PCIe SSDs
dual ported for HA configurations
the Z-Drive 6000 series - from OCZ
related guides
90% of the enterprise SSD companies which you know have no good reasons to survive.
market consolidation - why? how? when?
military SSD from Waitan
military SSD drives with secure erase
encryption and self-destruct
from Waitan

related guides

Why can't SSD's most ardent believers agree on a single shared vision for the future of solid state storage?
the SSD Heresies

storage search banner