No abstract

No abstract

This paper presents a batteryless system-on-chip (SoC) that operates off energy harvested from indoor solar cells and/or thermoelectric generators (TEGs) on the body. Fabricated in a commercial 0.13 μW process, this SoC sensing platform consists of an integrated energy harvesting and power management unit (EH-PMU) with maximum power point tracking, multiple sensing modalities, programmable core and a low power microcontroller with several hardware accelerators to enable energy-efficient digital signal processing, ultra-low-power (ULP) asymmetric radios for wireless transmission, and a 100 nW wake-up radio. The EH-PMU achieves a peak end-to-end efficiency of 75% delivering power to a 100 μA load. In an example motion detection application, the SoC reads data from an accelerometer through SPI, processes it, and sends it over the radio. The SPI and digital processing consume only 2.27 μW, while the integrated radio consumes 4.18 μW when transmitting at 187.5 kbps for a total of 6.45 μW.

Superconducting logic offers the potential to perform computation at tremendous speeds and energy savings. However, a "semantic gap" lies between the level-driven logic that traditional hardware designs accept as a foundation and the pulse-driven logic that is naturally supported by the most compelling superconducting technologies. A pulse, unlike a level signal, will fire through a channel for only an instant. Arranging the network of superconducting components so that input pulses always arrive simultaneously to "logic gates" to maintain the illusion of Boolean-only evaluation is a significant engineering hurdle. In this paper, we explore computing in a new and more native tongue for superconducting logic: time of arrival. Building on recent work in delay-based computations we show that superconducting logic can naturally compute directly over temporal relationships between pulse arrivals, that the computational relationships between those pulse arrivals can be formalized through a functional extension to a temporal predicate logic used in the verification community, and that the resulting architectures can operate asynchronously and describe real and useful computations. We verify our hypothesis through a combination of detailed analog circuit models, a formal analysis of our abstractions, and an evaluation in the context of several superconducting accelerators.

When extremely low-energy processing is required, the choice of data representation makes a tremendous difference. Each representation (e.g. frequency domain, residue coded, logscale) comes with a unique set of trade-offs-some operations are easier in that domain while others are harder. We demonstrate that race logic, in which temporally coded signals are getting processed in a dataflow fashion, provides interesting new capabilities for in-sensor processing applications. Specifically, with an extended set of race logic operations, we show that tree-based classifiers can be naturally encoded, and that common classification tasks can be implemented efficiently as a programmable accelerator in this class of logic. To verify this hypothesis, we design several race logic implementations of ensemble learners, compare them against state-of-the-art classifiers, and conduct an architectural design space exploration. Our proof-of-concept architecture, consisting of 1,000 reconfigurable Race Trees of depth 6, will process 15.2M frames/s, dissipating 613mW in 14nm CMOS. CCS Concepts • Computer systems organization → Architectures; • Computing methodologies → Machine learning; • Hardware → Hardware accelerators.