| Title | (Invited Paper) Energy-Efficient System Design for IoT Devices |
| Author | Hrishikesh Jayakumar, Arnab Raha, Younghyun Kim, Soubhagya Sutar, Woo Suk Lee, *Vijay Raghunathan (Purdue University, U.S.A.) |
| Page | pp. 298 - 301 |
| Keyword | Internet of Things, IoT, low power design, energy efficient design |
| Abstract | It is projected that, within the coming decade, there will be more than 50 billion smart objects connected to the Internet of Things (IoT). These smart objects, which connect the physical world with the world of computing infrastructure, are expected to pervade all aspects of our daily lives and revolutionize a number of application domains such as healthcare, energy conservation, transportation, etc. In this paper, we present an overview of the challenges involved in designing energy-efficient IoT edge devices and describe recent research that has proposed promising solutions to address these challenges. First, we outline the challenges involved in efficiently supplying power to an IoT device. Next, we discuss the role of emerging memory technologies in making IoT devices energy-efficient. Finally, we discuss the potential impact that approximate computing can have in increasing the energy-efficiency of wearables and other compute- intensive IoT devices. |
| Title | (Invited Paper) Energy Delivery for Self-Powered IoT Devices |
| Author | Khondker Z. Ahmed, Monodeep Kar, *Saibal Mukhopadhyay (Georgia Tech, U.S.A.) |
| Page | pp. 302 - 307 |
| Keyword | IoT power delivery, bias gating, high conversion ratio, boost, buck |
| Abstract | Distributed small-scale electronics for IoT applications
are on the rise. Power delivery for such electronics requires
innovative design techniques to improve energy efficiency. This
paper summarizes energy delivery challenges for IoT devices and
discusses several design techniques for efficient power delivery
units. Such design solutions cover challenges like energy
harvesting from very low input voltage, maximized energy
harvesting, energy delivery with multiple voltage domains and
design using low voltage devices to sustain higher than
breakdown voltages. |
| Title | (Invited Paper) Efficient Embedded Learning for IoT Devices |
| Author | Swagath Venkataramani, Kaushik Roy, *Anand Raghunathan (Purdue University, U.S.A.) |
| Page | pp. 308 - 311 |
| Keyword | Internet of things, Machine learning, Accelerators, Approximate computing, Spintronic Devices |
| Abstract | The pervasiveness of IoT devices will usher an unprecedented growth in the amount of digital data produced and consumed. Realizing the rich class of applications enabled by IoT devices requires large-scale machine learning systems to make sense of the raw data and derive meaningful, actionable information. State-of-the-art machine learning algorithms are highly compute and data intensive, posing significant computational challenges across the spectrum of computing devices, from low-power client devices to the cloud. As benefits due to semiconductor technology scaling diminish, addressing the computational gap requires identifying new sources of computing efficiency. In this paper, we highlight 3 approaches viz. machine learning accelerators, approximate computing and post-CMOS technologies that demonstrate significant promise in bridging the efficiency gap. |
| Title | (Invited Paper) Computing with Coupled Spin Torque Nano Oscillators |
| Author | Karthik Yogendra (Purdue University, U.S.A.), Deliang Fan (Univerisity of Central Florida, U.S.A.), Yong Shim, Minsuk Koo, *Kaushik Roy (Purdue University, U.S.A.) |
| Page | pp. 312 - 317 |
| Keyword | coupled oscillators, frequency locking, non-Boolean computation, spin torque nano oscillators, spin transfer torque |
| Abstract | This paper gives an overview of coupled oscillators and how such oscillators can be efficiently used to perform computations that are unsuitable or inefficient in von-Neumann computing models. The “unconventional computing” ability of coupled oscillatory system is demonstrated through Spin Torque Nano Oscillators (STNOs). Recent experiments on STNOs have demonstrated their frequency of oscillation in few tens of gigahertz range, operating at low input currents. These attractive features and the ability to obtain frequency locking using a variety of techniques, make STNOs an attractive candidate for non-Boolean computing. We discuss coupled STNO systems for applications such as edge detection of an image, associative computing, determination of L2 norm for distance calculation, and pattern recognition. |