Power/Performance Bits: Aug. 31

Securing memory
Researchers at Columbia University suggest several ways to make computing more secure without imposing a system performance penalty. The efforts focus on memory security, specifically pointers.

“Memory safety has been a problem for nearly 40 years and numerous solutions have been proposed. We believe that memory safety continues to be a problem because it does not distribute the burden in a fair manner among software engineers and end-users,” said Simha Sethumadhavan, associate professor of computer science at Columbia, whose research focuses on how computer architecture can be used to improve computer security. “With these two papers, we believe we have found the right balance of burdens.”

The first effort, called ZeRO: Zero-Overhead Resilient Operation Under Pointer Integrity Attacks, features a set of memory instructions and a metadata encoding scheme that protects the code and data pointers of a system. The team said that ZeRO requires minor changes to a system’s architecture and can easily be added to modern processors. Even when under attack, ZeRO can perform all these functions and avoid crashing a system.

“ZeRO offers memory security at no cost and it is a perfect complement to systems that mitigate memory attacks,” said Mohamed Tarek, a fourth-year PhD student at Columbia. “The keys to widespread adoption of security techniques are low-performance overhead and convenience.”

The second approach, called No-FAT: Architectural Support for Low Overhead Memory Safety Checks, is a system that makes security checks faster with an 8% effect on the computer’s performance, which the team said is 10x faster than current software technique for detecting memory errors.

No-FAT speeds fuzz testing and builds on a recent trend in software towards binning memory allocators, which uses buckets of different sizes to store memory until it is needed by the software. The researchers found that when binning memory allocation is used by the software, it is possible to achieve memory security with little impact on performance and is compatible with existing software.

The two techniques are currently being used in design of a processor for the Air Force Research Lab.

More light from OLEDs
Engineers at the University of Michigan developed a new electrode for organic light-emitting diodes. The approach prevents light from being trapped in the light-emitting part of an OLED, enabling OLEDs to maintain brightness while using less power.

About 80% of the light produced by an OLED gets trapped inside the device due to waveguiding, where light that doesn’t come out of the device at an angle close to perpendicular gets reflected back and guided sideways through the device. Most of that is trapped between the two electrodes on either side of the light-emitter, particularly by the transparent electrode between the light-emitting materials and the glass.

“Untreated, it is the strongest waveguiding layer in the OLED,” said Jay Guo, U-M professor of electrical and computer engineering. “We want to address the root cause of the problem.”

The transparent electrode is typically made of indium tin oxide (ITO). Instead, the researchers substituted a layer of silver five nanometers thick, deposited on a seed layer of copper.

“Industry may be able to liberate more than 40% of the light, in part by trading the conventional indium tin oxide electrodes for our nanoscale layer of transparent silver,” said Changyeong Jeong, a Ph.D. candidate in electrical and computer engineering at U-M.

In tests, the team found that the edge of the light-emitting layer was almost completely dark, while the light coming through the glass was about 20% brighter. Plus, they say it could be extended to other solid-state LEDs such as perovskites, quantum-dots, or III-V based LEDs.

The researchers said that the electrode is easy to fit into existing processes for making OLED displays and light fixtures. The University of Michigan has filed for patent protection.

Stretchy self-healing circuits
Researchers at Virginia Tech constructed soft, stretchable, self-healing circuits that can sustain damage while under load without losing conductivity. They are also reconfigurable and recyclable.

The soft circuits are created by dispersing liquid metal droplets in an elastomer, creating electrically insulated, discrete drops. They drops are then selectively connected.

“To make circuits, we introduced a scalable approach through embossing, which allows us to rapidly create tunable circuits by selectively connecting droplets,” said Ravi Tutika, a postdoctoral researcher at Virginia Tech. “We can then locally break the droplets apart to remake circuits and can even completely dissolve the circuits to break all the connections to recycle the materials, and then start back at the beginning.”

The circuits can also work under extreme damage. If a hole is punched in these circuits, the metal droplets can still transfer power. Instead of cutting the connection completely, the droplets make new connections around the hole to continue passing electricity. They can also stretch over 10 times its original length without losing electrical connection.

The researchers say soft robotics and wearables are two possible applications. “We’re excited about our progress and envision these materials as key components for emerging soft technologies,” said Michael Bartlett, an assistant professor at Virginia Tech. “This work gets closer to creating soft circuitry that could survive in a variety of real-world applications.”