Power/Performance Bits: March 16


Adaptable neural nets Neural networks go through two phases: training, when weights are set based on a dataset, and inference, when new information is assessed based on those weights. But researchers at MIT, Institute of Science and Technology Austria, and Vienna University of Technology propose a new type of neural network that can learn during inference and adjust its underlying equations to... » read more

Power/Performance Bits: March 8


Non-toxic, printable piezoelectric Researchers at RMIT University and University of New South Wales developed a flexible and printable piezoelectric material that could be used in self-powered electronics including wearables and implantables. "Until now, the best performing nano-thin piezoelectrics have been based on lead, a toxic material that is not suitable for biomedical use," said Dr N... » read more

5G as a wireless power grid


Abstract "5G has been designed for blazing fast and low-latency communications. To do so, mm-wave frequencies were adopted and allowed unprecedently high radiated power densities by the FCC. Unknowingly, the architects of 5G have, thereby, created a wireless power grid capable of powering devices at ranges far exceeding the capabilities of any existing technologies. However, this potential c... » read more

Power/Performance Bits: Jan. 19


Electronic skin for health tracking Researchers at the University of Colorado Boulder developed a stretchy electronic 'skin' that can perform the tasks of wearable fitness devices such as tracking body temperature, heart rate, and movement patterns. "Smart watches are functionally nice, but they're always a big chunk of metal on a band," said Wei Zhang, a professor in the Department of Chem... » read more

Power/Performance Bits: Dec. 7


Logic-in-memory with MoS2 Engineers at École Polytechnique Fédérale de Lausanne (EPFL) built a logic-in-memory device using molybdenum disulfide (MoS2) as the channel material. MoS2 is a three-atom-thick 2D material and excellent semiconductor. The new chip is based on floating-gate field-effect transistors (FGFETs) that can hold electric charges for long periods. MoS2 is particularly se... » read more

Power/Performance Bits: Nov. 23


Graphene energy Researchers from the University of Arkansas, University of Pennsylvania, and Universidad Carlos III de Madrid built a circuit capable of capturing graphene's thermal motion and converting it into an electrical current. "An energy-harvesting circuit based on graphene could be incorporated into a chip to provide clean, limitless, low-voltage power for small devices or sensors,... » read more

Building Billions Of Batteryless Devices


Later this month, Arm will celebrate its 30 year anniversary and the engineering milestones that have resulted in more than 180 billion Arm-based chips being shipped in everything from sensors to smartphones to the world’s fastest supercomputer. In each of these cases, much of Arm’s success has been in our dedication to delivering the highest performance per watt. But while Arm may ha... » read more

Blog Review: Oct. 7


In a blog for Arm, University of Southampton PhD student Sivert Sliper looks at how energy-driven and intermittent computing could be used to power trillions of IoT devices and introduces a SystemC-based simulator for such systems. Mentor's Chris Spear explains why transaction classes should extend from uvm_sequence_item rather than uvm_transaction when designing UVM testbenches. Cadence'... » read more

A Summary Of Piezoelectric Energy Harvesting For Autonomous Smart Structures


The technology of energy harvesting has great potential to enable energy autonomy of wireless sensors. The drop of power requirements of micro-electronic devices allows confidence that piezoelectric energy harvesting (PEH) is able to reliably power a wireless sensor network (WSN). The present work summarizes results of ongoing research in the field of PEH. With the aid of a performance metric a... » read more

Power/Performance Bits: Aug. 4


Assessing code similarity Researchers from Intel, MIT, and Georgia Institute of Technology created an automated engine designed to learn what a piece of software intends to do by studying the structure of the code and analyzing syntactic differences of other code with similar behavior. The machine inferred code similarity (MISIM) program, a subset of Intel's work on machine programming, was... » read more

← Older posts Newer posts →