Where Do Optane DIMMS Fit In?

An over-simplified look at Storage/Memory options for Servers. 

When you need more memory, NVM, and are willing to sacrifice some speed, Optane DIMMS make sense. They should be available early in 2018?

• DRAM DIMM alone is fastest and has lots of suppliers
• NVDIMM-N is available at high cost if NVM is needed
• Optane DIMMS allow more Random access memory at lower cost. its NVM. It is slower than DRAM.
• SSDs are improvement on HDD. Optane SSDS are fastest (latency) SSDs available
• Optane DIMMS take off in volume if the cost is significantly lower than DRAM DIMMS.

Option	Speed	Cost	Notes
NAND NVMe SSD	+	$	Fast enough for most
Optane SSD	++	$$	Fastest SSD Around
Optane DIMM	++++	$$$	Assume minimal DRAM
DRAM only	++++++	$$$$	Fastest, but not  NVM
NVDIMM-N	+++++	$$$$$	NAND+DRAM

HDDs are dead? On life support? Or enjoying mature lifestyle?

I saw more articles this week on death of HDD. Or that they will be dead in a couple years. If we want to use aging analysis, they are mid 50s, past midlife, not getting any younger but still active, healthy, and planning on watching their grandchildren grow for a couple decades.

Recent data:

• HDD units outship SSDs more than 2:1
• HDD Bits outship SSDs 10:1
• HDD increase in bits shipped was larger than SSD increase in bits.
• HDD units are dropping and EBs shipped are increasing at modest rates.

What is happening:

• SSDs are increasing penetration in PCs at a modest rate. Hovering around 50% by end of year
• Performance enterprise HDDs are being replaced by SSDs. But 10K and 15K HDDs still are close in sales to Enterprise SSDs. Even though there is no technical reason for this.
• Nearline HDDs are growing in capacity shipped. SSDs are a small cache (<2% of capacity)
• Slow capacity storage is 99% HDD or Optical or Tape

Why:

• SSDs still cost 7-10X more than HDDs per Bit. It turns out we are storing bits? Who knew?
• HDD ASP decreased in last year, SSD ASP increased. That was not supposed to happen.
• Nearline and enterprise capacity needs are driving large increase in HDD capacities.

Prediction:

• SSD ASP per bit being lower than HDD is almost a fantasy now. 2025 for being “close/ 2x”
• SSD penetration into PCs will grow from ~50% to ~70% over the next 6 years
• SSD will continue to grow at steady, no tipping point, rate. SSDs will account for 25% of bits shipped by 2022… or 2024 …. Or 2026 … let’s just say a long time

Mark Webb

www.mkwventures.com

3D Xpoint Optane for Enterprise and Consumer

Optane 3D Xpoint for Enterprise and Consumer

Intel announced more updates on status of their Optane products. I wanted to say launched but then I realized that actually no product is yet available to the public... soon it will be I hope.


1) Enterprise P4800x SSD: Its arguably the fastest SSD in the world depending on which metric you choose. Intel's focus is on low latency... which is important since transactions involving a queue depth of  32 are quite rare. Its also expensive and only shipping in one density and limited quantities to limited customers. It also supports a virtual memory activity where it looks like memory to the server. Still waiting on third party benchmarks but at this point it is fast and shipping somewhere for revenue.

On the downside, the internet is exploding with "it was supposed to be 1000x faster with 1000x endurance!!!!" and "I waiting 18 month for this?!!!!" .

OK its 8-10x faster and the cells last 2-3x as long as NAND. Its still a great drive for certain Enterprise Applications.


2) Intel Optane memory: This was announced to press at same time... but embargoed for a few more days. 16/32GB cache device announced also at CES.

As I mentioned when this came out earlier at CES... caching is a great idea. 95% of the performance at much lower cost... when it works. Intel showed data that when combined with a HDD is improved boot and program loading performance. There is some concern that these metrics were cherry picked but we will see when third party benchmarks comes out (THG???? Anandtech???)

The price was good $44-$77, it makes a difference in performance, and Intel is hyping the heck out of it. If PC OEMS push it... it could be a big deal. I am not sure what percentage of chipsets accept it today, but I will try it out ASAP when it comes out (See... Intel even tricked me into buying a Kaby Lake PC with 200 Chipset!).

It it better than more DRAM? or a 256GB SSD? who knows for now.


This just in... Optane, as a NVMe SSD/Cache is not 1000x faster and is not going to change the world like the steam engine, the internet, or the cell phone (SORRY) ... but it appears to be a option for fast performance in some applications ... if you can buy it somewhere.

More to come when it actually appears!

Mark Webb
www.mkwventures.com

Top 5 Things to Know About SSD Manufacturing

Top 5 Things to Know About SSD Manufacturing

SSDs are among the fastest growing technology areas in electronics. Growth of 40-80% per year in units has been typical since 2006. Questions about "when will they completely replace HDDs" are common for technical and business people alike.

As with most technology areas, Manufacturing is a huge factor in business success. Some topics in SSD Manufacturing:

1) Most SSD OEMS outsource some or all of their SSD manufacturing. Outsourcing to contract manufacturers is prevalent in the electronics industry. SSDs are no different. Flexible capacity, ability to achieve low costs through volume, minimal capital spending, time to market are all great reasons to outsource SSD manufacturing. EMS/ODM providers include top systems and memory module companies.

2) Many SSD OEMs utilize 3rd part controllers and designs. Controller companies like Silicon Motion, Phison, Marvell, Maxiotek and the former Sandforce can provide controllers and reference designs. While most companies strive to develop internal controllers, 3rd party controllers and designs are widespread in consumer and client SSDs. These controller companies work with NAND vendors to develop advanced error correction and features and may outperform internal controllers made by NAND manufacturers. They definitely have the development and time to market expertise.

3) Consumer and Client SSDs are under tremendous price pressure. A simple look at NAND ASPs compared to Client SSD ASPs will show that SSDs are under margin pressure. There is not much, if any, margin added by the non-NAND portion. How do we deal with this reality? Outsource to minimize engineering and manufacturing cost. It is difficult to spend millions on engineering in a segment with minimal margin uplift.

4) Form factors are changing and difficult to predict. All form factors generally move to smaller solutions ... but predicting exactly when is difficult. Most companies balance the future form factor (M.2/BGA) volumes with the conservative old form factor (2.5"). Outsource companies can provide all form factors and even design custom ones with minimal engineering cost.

5)  The above comments apply well to Intel, Sandisk, WD, Micron, Toshiba, Lite-on, Kingston, etc. Two companies are obviously different. Samsung has large enough scale and engineering resource to support controllers, internal manufacturing on a wide variety of designs. As long as they can execute and not run out of resources as form factors and interfaces change, that is great. Second, Apple is famous for custom interfaces and form factors and these pop in Macbook teardowns. They always look for internal processor support to meet needs. The strategy for custom engineering and the high margins on their products allow this.


For more specifics and numbers on SSD manufacturing and what strategy is best, contact us today

Mark Webb
MKW Ventures Consulting LLC.
www.mkwventures.com
SSD Manufacturing

Seagate on why HDD replacement is not easy

Article from Digitimes... Seagates input on HDD replacement.... yes I realize it may be biased :-)

SSDs not a simple solution for replacing HDDs: Q&A with Seagate executive

Max Wang, Taipei; Adam Hwang, DIGITIMES [Tuesday 5 January 2016]

During a Digitimes interview, Global Sales and Operations senior vice president B.S. Teh for Seagate Technology indicated that it is not simple for SSDs (solid-state drives) to replace HDDs (hard disk drives), simply because SSD prices are three times that of HDD prices for applications targeting consumer electronics and possibly more than 10 times for applications for enterprise storage.

Q: As slow growth in global PC demand and the increasing use of SSDs has affected the business operations of HDD vendors, how does Seagate cope with the impact?

A: Although global HDD shipments will decrease from 550-600 million drives in 2014 to nearly 500 million units in 2015, total storage capacity will increase from nearly 500 exabytes (10⁹ gigabyte) to 530-550 exabytes. While having stepped into SSDs with initial SSD models launched in 2013, Seagate focuses on the HDD business and develops models featuring high storage capacity and efficiency as well as low cost, for which Seagate aims to reduce the average shipment price for HDDs to one-tenth of that for SSDs. Seagate has been decreasing its reliance on PC-use HDDs through increased shipments for applications for cloud computing-based storage, consumer electronics, security surveillance and enterprise storage, with the revenue proportion for PC-use HDDs slipping from nearly 63% in 2010 to an estimated nearly 43% in 2015. For the PC-use market segment, Seagate will launch 1TB HDD models for use in notebooks in 2016.

Q: Apart from PC-use HDDs, how does Seagate look to global demand for storage from consumer electronics users and enterprises?

A: HDDs used in consumer electronics take up nearly 15% of Seagate's consolidated revenues at present. In a bid to enhance marketing of such HDDs, Seagate has acquired LaCie and Lyve. As demand for enterprise storage is much larger than that for consumer electronics storage in terms of capacity and shipment value, Seagate has invested US$700-800 million annually in R&D for software and hardware used in enterprise storage.

Q: In the market segment of enterprise storage, system vendors such as Hewlett-Packard and Dell procure HDDs for use in servers or storage equipment, but some of enterprises have skipped such vendors and acquired storage equipment through service providers, cloud computing service operators or ODMs/OEMs, has such change in business model influenced HDD vendors?

A: My personal opinion is that the influence is in order visibility and ordered volume, because orders released by system vendors are clearly visible with shipments able to be estimated while orders released by ODMs/OEMs or service providers are more likely to fluctuate and ordered volumes are relatively difficult to estimate. For shipments to the latter, Seagate has strictly controlled inventory level to minimize risks.

Q: How does Seagate view Dell's merger acquisition of EMC at US$33.15 per share for a total price of US$67 billion?

A: Both Dell and EMC are Seagate's clients and Seagate is happy to see the merger. Both companies' complementary resources can be integrated and the operational scale can be enlarged via the merger.

Q: Market analysts think that China-based Tsinghua Unigroup's stake investment in Western Digital will impact Seagate's business in the China market, what are your opinions?

A: Seagate is not worried about any negative impact related to the investment stake on Seagate's business cooperation with existing China-based clients. The reason is simple, that is, under free market competition, users are unwilling to concentrate HDD procurement in a single supplier no matter who invests in Western Digital.

Q: How do you view development in the Taiwan storage market?

A: There have been significant changes in the Taiwan storage market, mainly a shift from PC-use demand to large demand by data centers as well as some Taiwan-based makers', including Foxconn Electronics, Quanta Computer and Inventec, having engaged in server production which has become important for Taiwan and is expected to be expanded steadily over the next 5-10 years.


Mark@mkwventures.com
#CES2016
#Storagevisions

SSD Shipment Forecast in Units and TBs...

     Predicted SSD shipments based on IHS, IDC, DE published data and my own inputs.

     Nice growth ... CAGR is 15% in units going forward. 40% in TBs shipped.

     Neither will lead to SSDs overtaking HDDs in next few years

     Note1: Enterprise and Client are projected to be about the same

 If you plug in the TBs shipped and assume 30-35% ASP/GB reduction, you can see revenue increase is "Muted" ... maybe 5-10%. There is another article by a research firm showing 40% REVENUE growth CAGR for SSDs. This is definitely not true for SSD vendors. It might get closer to 40% if you include NAND vendors, SSD vendors, Storage systems (Like EMC/Netapp), in house systems (like Google/AWS) etc.

 40% CAGR

 15% CAGR

      Mark Webb, Mark@mkwventures.com

      #storagevisions, #CES2016

Consumer SSD adoption challenges

Getting to a market penetration in Consumer has not reached 50% yet ... it will close at 30% or less in 2015. Getting there has a number of challenges... some can be addressed ... others are more challenging

• SSDs cost more than HDDs.
• If we go with the cheapest SSD known to man and we use rack rate pricing for HDD, SSDs are 5x more expensive. it drops to 3x by 2018
• If we take minimum cost to PC ODM, a 240GB SSD would cost >$50. A 500GB HDD is $23. The difference is more than than the total OEM Profit margin on a notebook PC
• ODMs refuse to add 50c to a BOM ... let alone $20+
• Consumers don't know impact of SSDs on performance. Actually they don't judge PCs on amount of storage in GBs... not good for SSDs
• SSDs are not instant on. Its nice to say SSDs are 50 times faster than HDDs. In reality they boot 50% faster and they load applications 50% faster ... which might not be noticeable in most consumer uses
• There is no competition to have fastest storage in notebooks. Apple needs SSDs to keep its high performance $1000+ price point lead. Intel needs SSDs to compete in the same market. The average notebook is $500 and is not a major storage performance competition

There is hope:

• Corporate PCs are a major market and low density, high speed SSDs withe fast backups are required
• A competition could come out with either Lenovo, Acer, Dell, etc fully converting to SSD to push the market.  
• a 2:1 or Chromebook or alternative Cloud/small fast storage market would drive SSD sales up. a 128G SSD + 128GB cloud would be a perfect $500 convertable
• DRAM faces similar challenges. But the difference is that Intel pushes for Faster DRAM  and marketing pushes for it as well. and eventually, the price of the new memory matches the slower memory which causes sales tipping point. Intel could force people to use PCIe SSD on future chipsets.

Until then, combinations of HDD/SSD or HDD alone will be most of the PCs sold.

#storagevisions, #CES2016

Mark Webb, mark@mkwventures.com