Emerging Memory Technologies

Some experts predict it will be at least another decade before new memory technologies offer the low prices and wide availability to compete with NAND-based flash memory. Nonetheless, it’s worthwhile to look at potential NAND-flash successors, including phase-change RAM (PRAM), resistive RAM (ReRAM), and magnetoresistive RAM (MRAM).

In December’s Circuit Cellar magazine, now available online, Faiz Rahman describes and compares the newest memory technologies available for embedded systems.

“I cover only those devices that are now commercially available, but bear in mind that many other technologies are being hotly pursued in academic and corporate research labs worldwide,” says Rahman, an Ohio University visiting professor who received his PhD in Electrical Engineering from Imperial College, London.

For example, last summer MIT Technology Review reported on a startup company’s testing of crossbar memory. The new technology, according to an August 14, 2013, article written by Tom Simonite, can store data 40 times as densely as the most compact memory available and is faster and more energy-efficient.

Here are the commercially-available technologies Rahman considers and some of his insights. (For the full article with more details, including an update on manufacturers of the latest memory devices, check out the December issue.)

PHASE-CHANGE RAM
One of the most interesting memory types to emerge in recent years is one that stores data as order or disorder in small islands of a special material. The structural transition

The structure of phase-change RAM cells in reset and set states is shown.

The structure of phase-change RAM cells in reset and set states is shown.

between ordered and disordered phases is driven by controlled heating of the material island…

There have been several recent advances in phase-change RAM (PRAM) technology. Perhaps the most remarkable is the ability to control the cell-heating current precisely enough to create several intermediate cell-resistance values. This immediately increases the memory capacity as each cell can be made to store more than one bit. For example, if eight resistance values can be created and distinguished, then the cell can be used to store three bits, thus tripling the memory capacity. This is now a routinely used technique implemented with PRAM devices.

MAGNETORESISTIVE RAM
We have all wished for a computer with no start-up delay that could be ready to use almost as soon as it was powered up. Such a computer will need to use an inexpensive

A spin-torque magnetoresistive RAM cell’s structure includes a free layer, a tunnel barrier, and a fixed layer.

A spin-torque magnetoresistive RAM cell’s structure includes a free layer, a tunnel barrier, and a fixed layer.

but fast nonvolatile memory. This combination is difficult to come by, but proponents of magnetoresistive RAM (MRAM) think boot times could soon become outdated as this new memory becomes a mature product….

MRAM’s nonvolatility alone will not make it a potential game-changing technology. Its high-access speed is what makes it special. Unlike other nonvolatile memory (e.g., EEPROMs and flash), MRAM boasts typical access speeds of 35 ns and potentially as short as 4 ns, with further developments. This combined with MRAM’s extremely high endurance and data retention periods of more than 20 years even makes the technology suitable for use as CPU cache memories, which is a very demanding application.

One further advantage of MRAM is that its basic architecture—where the access transistor can be formed directly on top of the magnetic tunnel junction (MTJ)—enables very dense integration, greatly reducing the cost of storage per bit and making MRAM well suited for use in solid-state disks.

FERROELECTRIC RAM
In many ways, DRAM is an example of an ideal memory, if it weren’t for its volatility… The problem is that the charge stored in a DRAM cell tends to disappear due to self-discharge

A ferroelectric RAM cell’s organizational structure is shown.

A ferroelectric RAM cell’s organizational structure is shown.

after only a few milliseconds. This means that all DRAM chips have to be periodically read and every cell’s state must be restored every few milliseconds. The requirement for periodic “refresh” operations increases the power consumption of DRAM banks, in addition to endangering data integrity in the case of even short power supply dips.

Within this backdrop, ferroelectric RAM (FRAM) became a potential game changer when it was introduced in the early 1990s…The permanence of induced electrical polarization in ferroelectric capacitors endows FRAMs with their nonvolatility. To write a particular bit, a FRAM’s cell capacitor is briefly charged in one direction to polarize the ferroelectric material between its plates. The capacitor voltage can then be removed and the bit state will be retained in the directional sense of the dielectric material’s polarization. No charges may leak away, and the polarization can be maintained for many years making FRAM, in a sense, a nonvolatile analog of DRAM….

A big advantage of using FRAM in microcontrollers is that just one memory can be used for program, data, and information storage instead of having to use separate flash, SRAM, and EEPROM blocks, which has been the trend so far.

RESISTIVE RAM
Phase-change memory uses programmed heat-generating current pulses to affect memory cell resistance changes. However, resistive RAM (ReRAM)—a still developing memory breed—uses voltage pulses to make resistance changes. This memory technology

A typical resistive RAM cell’s structure is shown.

A typical resistive RAM cell’s structure is shown.

utilizes materials and structures where suitable voltages can alter memory cells’ resistive states so they can store one or more data bits, similar to PRAM.

There are strong hints that ReRAM is capable of very fast switching with symmetric read and write times of less than 10 ns. This comes with a remarkably low power consumption, which should make this technology ideal for many applications.

As if these attributes were not enough, ReRAM cells are very small and can be placed extremely close together, which results in high-density memory fabrics.

Rahman’s article also introduces manufacturers offering products with the latest memory technologies, but he declares no single memory device the best. Despite manufacturers extolling their particular products, those that succeed will need to be available in high volume and at low cost, he says. They also must offer high-storage densities, he says, a bar most new memory technologies struggle to reach.

Q&A: Marilyn Wolf, Embedded Computing Expert

Marilyn Wolf has created embedded computing techniques, co-founded two companies, and received several Institute of Electrical and Electronics Engineers (IEEE) distinctions. She is currently teaching at Georgia Institute of Technology’s School of Electrical and Computer Engineering and researching smart-energy grids.—Nan Price, Associate Editor

NAN: Do you remember your first computer engineering project?

MARILYN: My dad is an inventor. One of his stories was about using copper sewer pipe as a drum memory. In elementary school, my friend and I tried to build a computer and bought a PCB fabrication kit from RadioShack. We carefully made the switch features using masking tape and etched the board. Then we tried to solder it and found that our patterning technology outpaced our soldering technology.

NAN: You have developed many embedded computing techniques—from hardware/software co-design algorithms and real-time scheduling algorithms to distributed smart cameras and code compression. Can you provide some information about these techniques?

Marilyn Wolf

Marilyn Wolf

MARILYN: I was inspired to work on co-design by my boss at Bell Labs, Al Dunlop. I was working on very-large-scale integration (VLSI) CAD at the time and he brought in someone who designed consumer telephones. Those designers didn’t care a bit about our fancy VLSI because it was too expensive. They wanted help designing software for microprocessors.

Microprocessors in the 1980s were pretty small, so I started on simple problems, such as partitioning a specification into software plus a hardware accelerator. Around the turn of the millennium, we started to see some very powerful processors (e.g., the Philips Trimedia). I decided to pick up on one of my earliest interests, photography, and look at smart cameras for real-time computer vision.

That work eventually led us to form Verificon, which developed smart camera systems. We closed the company because the market for surveillance systems is very competitive.
We have started a new company, SVT Analytics, to pursue customer analytics for retail using smart camera technologies. I also continued to look at methodologies and tools for bigger software systems, yet another interest I inherited from my dad.

NAN: Tell us a little more about SVT Analytics. What services does the company provide and how does it utilize smart-camera technology?

MARILYN: We started SVT Analytics to develop customer analytics for software. Our goal is to do for bricks-and-mortar retailers what web retailers can do to learn about their customers.

On the web, retailers can track the pages customers visit, how long they stay at a page, what page they visit next, and all sorts of other statistics. Retailers use that information to suggest other things to buy, for example.

Bricks-and-mortar stores know what sells but they don’t know why. Using computer vision, we can determine how long people stay in a particular area of the store, where they came from, where they go to, or whether employees are interacting with customers.

Our experience with embedded computer vision helps us develop algorithms that are accurate but also run on inexpensive platforms. Bad data leads to bad decisions, but these systems need to be inexpensive enough to be sprinkled all around the store so they can capture a lot of data.

NAN: Can you provide a more detailed overview of the impact of IC technology on surveillance in recent years? What do you see as the most active areas for research and advancements in this field?

MARILYN: Moore’s law has advanced to the point that we can provide a huge amount of computational power on a single chip. We explored two different architectures: an FPGA accelerator with a CPU and a programmable video processor.

We were able to provide highly accurate computer vision on inexpensive platforms, about $500 per channel. Even so, we had to design our algorithms very carefully to make the best use of the compute horsepower available to us.

Computer vision can soak up as much computation as you can throw at it. Over the years, we have developed some secret sauce for reducing computational cost while maintaining sufficient accuracy.

NAN: You wrote several books, including Computers as Components: Principles of Embedded Computing System Design and Embedded Software Design and Programming of Multiprocessor System-on-Chip: Simulink and System C Case Studies. What can readers expect to gain from reading your books?

MARILYN: Computers as Components is an undergraduate text. I tried to hit the fundamentals (e.g., real-time scheduling theory, software performance analysis, and low-power computing) but wrap around real-world examples and systems.

Embedded Software Design is a research monograph that primarily came out of Katalin Popovici’s work in Ahmed Jerraya’s group. Ahmed is an old friend and collaborator.

NAN: When did you transition from engineering to teaching? What prompted this change?

MARILYN: Actually, being a professor and teaching in a classroom have surprisingly little to do with each other. I spend a lot of time funding research, writing proposals, and dealing with students.

I spent five years at Bell Labs before moving to Princeton, NJ. I thought moving to a new environment would challenge me, which is always good. And although we were very well supported at Bell Labs, ultimately we had only one customer for our ideas. At a university, you can shop around to find someone interested in what you want to do.

NAN: How long have you been at Georgia Institute of Technology’s School of Electrical and Computer Engineering? What courses do you currently teach and what do you enjoy most about instructing?

MARILYN: I recently designed a new course, Physics of Computing, which is a very different take on an introduction to computer engineering. Instead of directly focusing on logic design and computer organization, we discuss the physical basis of delay and energy consumption.

You can talk about an amazingly large number of problems involving just inverters and RC circuits. We relate these basic physical phenomena to systems. For example, we figure out why dynamic RAM (DRAM) gets bigger but not faster, then see how that has driven computer architecture as DRAM has hit the memory wall.

NAN: As an engineering professor, you have some insight into what excites future engineers. With respect to electrical engineering and embedded design/programming, what are some “hot topics” your students are currently attracted to?

MARILYN: Embedded software—real-time, low-power—is everywhere. The more general term today is “cyber-physical systems,” which are systems that interact with the physical world. I am moving slowly into control-oriented software from signal/image processing. Closing the loop in a control system makes things very interesting.

My Georgia Tech colleague Eric Feron and I have a small project on jet engine control. His engine test room has a 6” thick blast window. You don’t get much more exciting than that.

NAN: That does sound exciting. Tell us more about the project and what you are exploring with it in terms of embedded software and closed-loop control systems.

MARILYN: Jet engine designers are under the same pressures now that have faced car engine designers for years: better fuel efficiency, lower emissions, lower maintenance cost, and lower noise. In the car world, CPU-based engine controllers were the critical factor that enabled car manufacturers to simultaneously improve fuel efficiency and reduce emissions.

Jet engines need to incorporate more sensors and more computers to use those sensors to crunch the data in real time and figure out how to control the engine. Jet engine designers are also looking at more complex engine designs with more flaps and controls to make the best use of that sensor data.

One challenge of jet engines is the high temperatures. Jet engines are so hot that some parts of the engine would melt without careful design. We need to provide more computational power while living with the restrictions of high-temperature electronics.

NAN: Your research interests include embedded computing, smart devices, VLSI systems, and biochips. What types of projects are you currently working on?

MARILYN: I’m working on with Santiago Grivalga of Georgia Tech on smart-energy grids, which are really huge systems that would span entire countries or continents. I continue to work on VLSI-related topics, such as the work on error-aware computing that I pursued with Saibal Mukopodhyay.

I also work with my friend Shuvra Bhattacharyya on architectures for signal-processing systems. As for more unusual things, I’m working on a medical device project that is at the early stages, so I can’t say too much specifically about it.

NAN: Can you provide more specifics about your research into smart energy grids?

MARILYN: Smart-energy grids are also driven by the push for greater efficiency. In addition, renewable energy sources have different characteristics than traditional coal-fired generators. For example, because winds are so variable, the energy produced by wind generators can quickly change.

The uses of electricity are also more complex, and we see increasing opportunities to shift demand to level out generation needs. For example, electric cars need to be recharged, but that can happen during off-peak hours. But energy systems are huge. A single grid covers the eastern US from Florida to Minnesota.

To make all these improvements requires sophisticated software and careful design to ensure that the grid is highly reliable. Smart-energy grids are a prime example of Internet-based control.

We have so many devices on the grid that need to coordinate that the Internet is the only way to connect them. But the Internet isn’t very good at real-time control, so we have to be careful.

We also have to worry about security Internet-enabled devices enable smart grid operations but they also provide opportunities for tampering.

NAN: You’ve earned several distinctions. You were the recipient of the Institute of Electrical and Electronics Engineers (IEEE) Circuits and Systems Society Education Award and the IEEE Computer Society Golden Core Award. Tell us about these experiences.

MARILYN: These awards are presented at conferences. The presentation is a very warm, happy experience. Everyone is happy. These things are time to celebrate the field and the many friends I’ve made through my work.