Helix Semiconductors, formerly Semitrex, is an Irvine, California-based fabless semiconductor company that designs chips for improved power management. The company's patented capacitive voltage reduction technology uses cascading capacitors to store power and convert voltages on chips, reducing the energy consumption of electronic devices.The company also has offices throughout the United States and in Europe.
The endeavor to emulate the extraordinary efficiency and adaptability inherent in the human brain via spike-based neuromorphic computing presents significant potential across a diverse array of applications. The attainment of this objective necessitates the translation of biological principles into artificial systems, a task that continues to pose a complex challenge requiring a profound comprehension of the mechanisms by which neural systems produce robust computational outcomes. This tutorial paper provides a comprehensive overview of the foundational concepts and emerging design trends in spike-based neuromorphic computing, covering advances from materials and circuits to hardware architectures and learning mechanisms. It begins with an examination of key aspects of brain biology and their influence on neuromorphic design, followed by a brief discussion of biologically plausible neuron and synapse models. The paper then defines the core principles and defining attributes of neuromorphic computing, highlighting the trade-offs and design choices underlying current implementations. Building on these foundations, it explores the critical properties of neuromorphic systems, surveys a variety of learning algorithms, and reviews hardware-level realizations of bioinspired neurons and synapses. Subsequent sections discuss state-of-the-art spiking neural network architectures, mapping and compilation strategies, and representative application domains. By providing this end-to-end perspective, the article aims to guide the development of future neuromorphic systems that more closely emulate brain efficiency, scalability, and resilience.
Phase modulated continuous wave (PMCW) radar sensors have received recent attention for their design flexibility and high antenna scalability needed in imaging radars for automotive driving applications. A challenge in digital radars is the detection of weak, distant targets in the presence of self-interference (SI) and any strong targets in the proximity, which places a high dynamic range requirement. Conventional matched filters (MFs) used for range processing in digital radars provide limited dynamic range. To address this problem, we present a mismatched filter (MMF) framework that employs parallel MMFs, each optimized for a distinct low correlation zone. Fusion approaches to combine the resulting range-Doppler maps (RDMs) are proposed to reduce computational complexity. Under typical automotive driving target scenarios, we show that the proposed MMF design outperforms MF designs in achieving high dynamic range conditions under SI and nearby strong targets. The designed soft-fusion approach is also shown to provide better performance in comparison to hard fusion of the RDMs.
Non-idealities of the track-and-hold (T&H) circuit in analog-to-digital converters (ADCs) can severely limit the ADC linearity. In practical applications, traditional calibration techniques are ineffective in suppressing these effects due to the multi-dimensional dependency of the non-idealities on e.g., input voltage, frequency and temperature. To address this, we propose a calibration solution that combines circuit knowledge of the error mechanisms with a data-driven approach into a shallow neural network (NN) containing just 5 neurons. Due to the small size of the NN, the output of the network can be interpreted and referred back to the underlying circuit non-idealities improving the predictability and reliability of the model. The effectiveness of the NN-based calibration is verified on silicon measurements of 10 different 12-bit SAR ADC samples manufactured in a 65nm CMOS technology, demonstrating an average improvement up to 6.8dB and 13.3dB on the measured SNDR and SFDR, respectively. To the best of the author’s knowledge, this is the first demonstration of a compact, interpretable NN-based calibration solution tested over amplitude, frequency, and temperature for multiple samples, while maintaining physics-based insight into the correction process.
This work proposes and analyzes a methodology to characterize the scattering parameters of multiport passives up to 170 GHz by consecutive single-ended two-port measurements. The generalized methodology is based on duplicating the device under test with linear combinations of load and open terminations to create a system of equations that can be solved for full characterization. The methodology is applied to a D-band differential four-port quadrature hybrid (QH) coupler designed in 22-nm FDSOI technology. Measurement results are presented for even- and odd-mode and differential-mode over five samples. Moreover, a quantitative and qualitative study is presented to highlight the method’s sensitivity to variability in measurement, device under test, and terminations.
This communication presents a wideband, circularly polarized, single-layer reflectarray design, with a bandwidth sufficient to cover both a downlink band from 10.7 to 12.75 GHz and an uplink band from 13.75 to 14.5 GHz. The unit cell is based on a double circular loop that also features an air gap for enhanced bandwidth. The unit cell design is optimized with a group delay-based approach, which is done by optimizing the unit cell geometry and analyzing the impact of the air gap on the linearity of the phase curves. This unit cell design has a phase range of about 500 degrees , thereby minimizing the number of phase wraps required in the reflectarray layout. A circular prototype with a diameter of 11.7 lambda at 11.725 GHz is fabricated to validate its performance, exhibiting a 1 dB bandwidth of 34% and peak gain of 28 dBi with a clear agreement with simulated results. The reflectarray is intended to be used in satellite applications whereby the downlink and uplink bands are contained within the operating bandwidth of the proposed design
