Storage Memory Tipping Point

The storage tipping point is upon us
Ambuj Goyal 2/27/2013 2:01 AM EST
www.eetimes.com/electronics-blogs/other/4407874/storage-tipping-point-upon-us

Keeping pace with the onslaught of Big Data requires a revolutionary approach to storage. It’s well known that the performance of computing has advanced at a much faster rate than the systems that store and retrieve the information they generate.


For many, this game of catch-up has existed since the first digital storage systems were introduced more than 50 years ago. At the time, the concern was no longer about the performance of computing, but about creating a digital storage system that could keep up with it.

Thus began the subsequent watershed moves from paper punch cards to magnetic tape and then hard disk drives—moments that revolutionized computing and ultimately the world in which we live.

Today we find ourselves at another critical technological juncture that once again is demanding a revolutionary approach to storage—an approach that will help it keep pace with not only computing, but with the information onslaught of Big Data.
To understand where the storage industry is headed, one need only look to the reason that computing has historically outpaced it. Unlike the storage industry, computing has continually leveraged and advanced semiconductor trends while storage systems have remained mechanical, with motorized wheels of tape or spinning disks. In fact, computing shifted from mechanical devices more than a hundred years ago, while digital storage, for the most part, remains tethered to technologies born out of the 1950’s.

Not any longer. We are at the tipping point of a new era of computer storage that will witness entire systems based on flash semiconductor memory to handle fast moving, operational data in real-time. Though flash has been utilized in a variety of capacities over the past 30 years and in hybrid storage systems over the past several years, complete flash systems will dominate the landscape in the coming months and years.

All-flash systems will not only provide exponential performance gains over mechanical and hybrid systems, they will help organizations dramatically lower data center energy consumption rates due to their inherent low power-consuming memory and lack of moving parts—no small feat. According to a 2011 study by Stanford University, data centers account for 2 percent of all the electricity consumed in the U.S.

Improved performance, reliability, and durability

To be sure, such systems will be the storage platform of choice to handle ever-growing and increasingly critical workloads such as credit card processing, stock exchange transactions, manufacturing and order processing systems. Even app stores on the web are starting to use flash-only storage.

Such attributes as improved performance, reliability, and durability make flash systems desirable today, but virtually mandatory for the future. That’s because the tsunami of Big Data shows no sign of receding. Researchers predict that the digital universe—all the digital information created around the world—will hit 8 zettabytes by 2015. That’s about all the data found in the U.S. Library of Congress times 800 million.

Today we find ourselves at a tipping point of computer storage, once again, where the challenges of computing are no longer at issue but, rather the storing and retrieving of the information they generate and share.

Through our acquisition of Texas Memory Systems last fall, we have systems that can store almost 24 terabytes of storage in a unit the size of a pizza box, and that provide access to data 100 times faster than mechanical storage. If we were to stack 42 such pizza boxes in a rack, it would provide 1 petabyte of storage, which is more storage than any single operational application requires.
The industry is moving rapidly in the direction of all-flash storage for operational information. Such systems will not only help organizations respond to, and exploit the challenges of Big Data today and tomorrow, but once again will change the future of computing and the possibly the world along with it.
Ambuj Goyal is general manager of IBM System Storage & Networking.

Where is DRAM Innovation?

The article, Hynix 30 nm DRAM layout, process integration adapt to change ,  discusses advances in DRAM memory at Hynix. DRAM memory has not been able to shrink the memory cell as quickly as flash memory. Leading edge flash memory products with dimensions around 20nm or less are being introduced to production, while DRAM memory is still above 30nm (see figure 4 in the article below).


While flash memory has a key advantage of keeping the information even without power, there is still a place for DRAM memory. Many of the process technology advances are being implemented at a slower rate in DRAM production. However major memory cell and circuit improvements are not being pursued. For example, storing multiple bites in one physical flash memory cell has been done for several years. There are 3-bit-per-cell (TLC) NAND and 2-bit-per-cell (MLC) flash available in the market, but there is no DRAM product with multiple bits in the same cell.

Ron

Insightful, timely, and accurate semiconductor consulting.
Semiconductor information and news at - http://www.maltiel-consulting.com/

MLC Flash Memory New Future

A new development by Macronix has the potential of extending flash NAND memory technology for several additional generations.


In 2012 IEDM conference Macronix engineers presented a paper on radically improving flash memory program /erase cycling endurance to more than 100 million cycles by localized heat treatment .  Currently, most advance flash NAND products are limited to less than 100,000 cycles. The larger memory devices, called MLC flash, can store 2 or 3 bits in each memory cell. However, their cycling endurance is limited to less than 10,000 cycles. The new heating method will increase the cycling endurance of MLC flash. An improved cycling endurance would enable development of higher density MLC flash cells with larger numbers of bits per cell.

Macronix's new heat treatment that heals the memory cell can impact other layers in the memory cell. For example, it can change electromigration properties of metal lines nearby. It can also produce mechanical stress around the heat spots. The impact of the heat treatment has to be optimized, since the potential of creating larger flash memory looks promising. Already Macronix will present a flash memory chip with 6 bits per cell at the 2013 ISSCC.


Ron

Insightful, timely, and accurate semiconductor consulting.
Semiconductor information and news at - http://www.maltiel-consulting.com/