Fins on transistors change processor power and performance

Editor's note: This article is by IBM Research Scientist Dr. Sani Nassif.

IBM, University of Glasgow and the Scottish Funding Council are collaborating on a project to simulate 3D microprocessor transistors at a mere 14 nanometer scale (the virus that causes the common cold is more than twice as large at 32 nanometers). Using a silicon-on-insulator (SOI) substrate, the FinFET (fin field-effect transistor) project, called StatDES, promises to keep improving microprocessor performance and energy conservation.

Evolving from flat to 3D transistors

Microprocessors in everything from mainframes to phones are almost all built with planar complimentary metal-oxide-semiconductor field-effect transistors – CMOS FETs. A design that goes back to the late 1950s, these transistors sit next to one another on the chip. It's a design that is falling out of favor as we work towards more powerful, more efficient devices that don't take up more energy to operate.

FinFET transistor’s raised pillar of silicon (the “fin”) is the conduit for current flow, and is modulated by a gate that surrounds the fin. The gate acts much like how stepping on a garden hose stops the water from flowing.

In flat devices, this modulation comes from one side only (the top), while FinFETs allow this modulation from two sides, and therefore allow the flow to be turned off much more effectively. This increased effectiveness translates to improved performance and reduced wasted energy.

And the industry is quickly catching on to FinFETs. The design is 37 percent faster in low-voltage applications and uses 50 percent less power than CMOS FETs.

Meeting the challenge to scale FinFET technology

The StatDES project is tweaking the FinFET design to improve its scalability. Up until now, they have been made by etching grooves in a bulk wafer, so extra steps are required to ensure that each FinFET is insulated from the others. IBM avoids the issues of etching grooves in the wafer by putting the transistors on an insulating Silicon-Oxide using standard SOI.

Gold Standard Simulations Ltd. (GSS), established by IBM's project partner University of Glasgow, has also shown reduced performance in recent research of FinFETs on bulk wafers at 22 nm. Using SOI appears to mitigate this phenomenon.

The shape affects current flow in the same way that the shape of that garden hose affects the amount of water flowing through it. University of Glasgow Professor and GSS CEO Asen Asenov writes that as more current is conducted through the device, it crowds into the apex of the triangle. As a result, the triangular shape fins result in a 12 – 15 percent performance reduction compare to rectangular shape fins.

Asenov told the EE Times that “moving to FinFETs constructed on SOI wafers could solve a number of problems ... The buried oxide layer means you don't have the problem of filling trenches.”

The easier-to-fabricate SOI FinFETs with rectangular fins can deliver 20 – 25 percent improvement in performance compared to the current mass production bulk FinFETs.

The StatDES project is set to simulate 14 nm SOI FinFETs, and make predictions that will help designers determine how they will get the maximum utilization of this advanced technology.

What FinFET on SOI means for IT

When FinFETs become widely available, the industry can expect the continuation of the historical trends of technology performance, over time – Moore’s Law. Today’s planar devices will not be able to follow this trend.

Without moving to FinFETs, we would be stuck with the computers and devices we have today.


Getting Hot with Data Retrieval

IBM scientists and developers spanning from Almaden, California; Tucson, Arizona and Zurich, Switzerland recently achieved a significant breakthrough in distributed FLASH cache for enterprise transaction processing. The technology was recently unveiled at the IBM EDGE 2012 conference in Orlando, Florida and was demonstrated to show a latency improvement of more than 5x for certain workloads. The advancement will make finding documents faster and with real time analytics.

We recently caught up with one IBM's storage technologies scientist Dr. Ioannis Koltsidas in Switzerland to understand the achievement. 
"In this era of Big Data, this technology can help with
real time analytics for banking transactions, medical data
and billing systems," said Dr. Koltsidas

Can you explain what was achieved in simple terms?

Ioannis Koltsidas: Sure, simply put we have created a novel caching framework that exploits synergies between storage area network (SAN) storage and servers called Triton. In complex global IT environments it is not uncommon to have multiple servers connected to a SAN. Within these environments there is hot data, which is accessed often, and cold data, which isn’t. We’ve developed several novel technologies that enable users to access the hot data at a fraction of the SAN latency by storing it in local caches based on Flash memory.

What are some of the applications for this technology?

IK: I’d say that most data-intensive applications will benefit from this technology. We are especially looking at applications such as transaction processing for brokerage workloads, document retrieval and content management, as well as Virtual Machine storage in scale-out environments. Also, in this era of Big Data, this technology can help with real time analytics for banking transactions, medical data and billing systems, for instance.

Using large solid state drive arrays such as the IBM EXP30 Ultra  we can store up to 10 Terabytes in the cache. So if an organization has a lot of hot data we can make it quick to retrieve. 

What specifically did you contribute?

IK: I helped in designing a smart way to manage the cache so that high performance and high scalability can be achieved. More specifically, an algorithm that recognizes which data is hot and which is not. It nearly knows what you want before you do, because it looks for patterns in what data is accessed and when.

What’s next for the technology?

IK: It will be generally available in 2013, but we will continue to refine the code and look to port it to different server and storage platforms and make it available to both native and virtual environments. We also see a strong opportunity with IBM PureSystems and Netezza

Last question, what is your own personal motivation in this research?

IK:  My PhD thesis focused on databases for flash storage so this is a topic near and dear to me.  As I mentioned we are also now firmly in the era of Big Data and as nearly any scientist will tell you its always good to have strong market demand for your research.


SuperMUC Gets Powered Up

SuperMUC, the fastest supercomputer in Europe and fourth fastest in the world, officially went live on Friday, 20 July during a gala event at the Leibniz Rechenzentrum near Munich, Germany.
Prof. Dr. Karl-Heinz Hoffmann, president of the BAdW, Prof. Dr. Arndt Bode, Chairman of the Board of LRZ, Martina Koederitz, IBM Germany, Federal Minister Annette Schavan and State Minister Dr. Wolfgang Heubisch (from left) power on SuperMUC.
Speaking at the event, Thierry Van der Pyl, Director of Components and Systems Research at the European Commission, said, "With SuperMUC you are a shining example of where there is a will, there is a way. Europe thanks you for your efforts."
It was nearly six years ago in October 2006 when Nicholas Stern, the former World Bank chief economist and now head of the Economic Service of the British government, commissioned a report called the Stern Review on the Economics of Climate Change. The groundbreaking 700-page document was a wake up call to the world on the dire economic consequences of global warming. He pointed out the importance of reducing carbon emissions stating, "The benefits of strong, early action on climate change outweigh the costs."

That was the spark IBM experts needed to develop a vision and roadmap for an emission-free data center, since data centers consume an estimated 2 percent of the energy in the United States alone.

In a first step demonstration, IBM developed an innovative microchannel cooler, thus proving that a processor can actually be cooled with up to 60 degrees Celsius hot water. The technology was unveiled to the public in March 2008 at the annual CeBIT event to much excitement and fanfare.

The project soon caught the attention of Prof. Dimos Poulikakos, head of the Laboratory of Thermodynamics in New Technologies, at the Swiss university, ETH Zurich. Prof. Poulikakos was so enamored with the concept that he signed a contract with IBM to build a first-of-a-kind hot water-cooled supercomputer dubbed "Aquasar". Through the direct use of waste heat to provide warmth to university buildings, Aquasar's carbon footprint is reduced by up to 85 percent.

By 2025, chip stacks with embedded liquid cooling,
communications in three dimensions and minimal 

power consumption will shrink
supercomputers to the size of a sugar cube
Then in December 2010, IBM brought the concept of a hot-water cooled supercomputer to the Leibniz Rechenzentrum in Garching and signed a contract for SuperMUC, a three petaflop hot water-cooled supercomputer. Roughly 20 months later it was named the fastest supercomputer in Europe and was fourth fastest on the Top500 list.

IBM scientists have now set their sights and minds on the next milestone of 3D chip stacking.

"As we continue to deliver on our long-term vision of a zero-emission data center, we may eventually achieve a million-fold reduction in the size of SuperMUC, so that it can be reduced to the size of a desktop computer with much higher efficiency than today," said Dr. Bruno Michel, manager, Advanced Thermal Packaging, IBM Research.


Breakthrough in high-performance computing

IBM scientists (left to right)
Alessandro Curioni, Yves Ineichen and Costas Bekas
Yves Ineichen, a pre-doc at the Paul Scherrer Institute (PSI) working at IBM Research – Zurich, together with coauthors Costas Bekas and Alessandro Curioni and PSI, ETHZ coauthors Andreas Adelmann and Peter Arbenz have been awarded the European Supercomputing PRACE Award 2012 for their paper "A Fast and Scalable Low Dimensional Solver for Charged Particle Dynamics in Large Particle Accelerators."

We spoke to Yves about his research at IBM and the potential impact of his work.

Yves, congratulations on winning the PRACE Award 2012 for building a general-purpose framework for multi-objective optimizations. What interested you in pursuing this research?

Thank you so much. The Paul Scherrer Institute has a project called SwissFel to build a free-electron laser accelerator. It's an extremely complex machine with numerous parameters or quality objectives that are mutually conflicting. My work approaches this machine as a mathematical, multi-objective optimization model.

Can you explain that in layperson's terms?

Sure. We encounter multi-objective optimization issues all the time in our daily lives. Let's say you want to buy a car, and you want to get the most value for the least amount of money. This is an everyday situation where we make decisions based on several — often conflicting — parameters. That's what we call a multi-objective optimization issue. If money were no object, you could buy the most expensive car with all the features anyone could want. But most of us want to maximize what we call optimality. That's not so simple because, if you improve one objective, it's likely that the others will deteriorate. In a nutshell, our work is to develop computational simulations to model this optimization process. The problem is computationally intensive; to tackle it we developed massively parallel implementations, in which we can utilize hundreds of thousands of cores.

What potential applications does this modeling tool have?

Simply put, the modeling tool accommodates change. Instead of remodeling, say, a factory floor, which can involve a costly "what if" search for an optimal solution, a computer simulation allows for many solutions to be tested at a negligible fraction of the cost. You see, it really makes a difference not to treat individual issues separately but all together. This not only yields a more optimal solution, it helps us to understand better the problem at hand.

Clients at IBM's Industry Solutions Lab (ISL) want this technology. IBM Research – Zurich has hosted executives from such sectors as automotive, aviation, supply chain, city planning — they all face these issues.

It could be important for many future applications, such as in the healthcare industry and many more. It's general enough to be applicable elsewhere in the future as well, and that's the beauty of it. It requires massively parallel computer power to solve, and that's the research field in software systems that interest me the most. And it fits right in with IBM's Smarter Planet concept, so I've enjoyed a lot of support.

What do you think was the crucial aspect of your work that earned the PRACE prize?

The core of the achievement was taking the original software for the model of the accelerator at PSI and scaling it from 10 to 10,000 parallel processors to optimize the model of the accelerator. Of particular difficulty was to design and implement algorithms and tools that schedule and deploy all the very dynamic parts (optimizers, forward solvers, etc.) of the framework on the parallel machine, keeping the load at a maximum, while also maximizing the computational efficiencies of the all individual blocks. The flexibility of the Blue Gene platform was key in achieving this goal. These efforts are the heart of what is called massive parallelization. Finally, I need to stress that our optimizer framework works for any number of different models, and this versatility is what makes our achievement so noteworthy.

All the best for your future research.

Thanks, there's still plenty of work to be done.

See also the original press release on the PRACE 2012 award.


Your personal shopping assistant

It's mobile, informative, and smart.

Have you ever found yourself in the supermarket staring at a shelf full of different cereal boxes, wishing someone could just point out the one with the best price, lowest sugar content, and the best reviews? New solutions for smarter retail will soon give customers the same type of information they get online when researching or comparing products – delivered inside the store as they shop.

A new augmented reality mobile shopping app being developed by researcher scientists at IBM’s lab in Haifa, Israel, is about to change the way we shop in stores. When shoppers use their smart phone or tablet video camera to pan over products on the shelf, the application will instantly display recommendations and offers based on their specific preferences.

Coupon via mobile shopping app.

"We're going way beyond simple facial recognition for products to provide superimposed information that points out the products shopper prefer – whether based on previous purchases, price, consumer rating, sodium content, environmentally friendly packaging, or other considerations," said Amnon Ribak, project leader for the augmented shopping advisor.

For example, a shopper looking for a high-quality facial moisturizer can specify important characteristics of the product, such as having a sun protection factor (SPF) of 15, is hypoallergenic, was not tested on animals, and that is on sale.

As the shopper points a smart device camera at the shelf of moisturizers in the pharmacy, the app recognizes the merchandise and displays information on the device’s screen, superimposed on the product images. It also highlights information based on the shopper's stated preferences, and can offer coupons or special discounts that may apply.

"The idea of standing in an aisle in the supermarket and having your mobile device point out the gluten-free cookies you need can be a real time saver," Ribak said. "This has the potential to completely change the shopping experience from one of hunting, reading, and searching to simply picking up those products you prefer." 

Product recognition doesn't require bar codes or RFID tags. It is done using a blend of different approaches, including image recognition for the packaging that matches the colors and shapes to a database collection, optical character recognition techniques, as well as on-shelf context and positioning. 
To develop this new technology, Ribak leads a team of research scientists whose image processing expertise has already contributed advances in such areas as license plate recognition at night or inclement weather for the Swedish toll road system; identification of malignant tumors in medical images; and optical recognition for ancient texts in libraries across Europe.

The researchers wrote algorithms that combine techniques used in facial recognition, color and shape matching, and associations with surrounding products. The app can take into account the mobile device’s camera angle, and distance from a shelf to help distinguish between products.

"Our first mission was to create our own mini-supermarket in the lab, so we could test the various approaches and challenges involved," Ribak said. "We've already submitted a number of patent applications based on the new techniques we discovered to overcome the challenges in recognizing products with less than ideal lighting, shadows, and reflections."

Aside from assisting shoppers, the new application could also help retail managers organize their stores, instantly point out what's missing on the shelves, or summarize which products were on sale during the week. As more and more shoppers use the application, it will give retailers deeper insight into how their customers shop – which is an analytics goldmine for optimized shelf and store arrangement.   

Read more about IBM's e-commerce technology on the Smarter Planet blog.