Energy efficiency

A 0.19-PEF Bandwidth/Power Scalable Dynamic Amplifier

A 0.19-PEF Bandwidth/Power Scalable Dynamic Amplifier 150 150

Abstract:

This letter presents an energy-efficient dynamic amplifier. It utilizes source-coupled input boosting and time-domain differential sampling techniques to boost the effective input signal by $4\times $ compared to its floating inverter amplifier (FIA) prototype without noise or power penalties. With discharge-based dynamic biasing, the bandwidth (BW) and power of the amplifier …

View on IEEE Xplore

A Noise-Shaping SAR-Based ExG Sensing Frontend With Dynamic Input-Impedance Boosting and Prediction-Assisted Mismatch-Shaping DEM

A Noise-Shaping SAR-Based ExG Sensing Frontend With Dynamic Input-Impedance Boosting and Prediction-Assisted Mismatch-Shaping DEM 150 150

Abstract:

This article presents a noise-shaping successive approximation register (NS-SAR)-based direct-digitizing electrophysiological (ExG) sensing frontend (SFE) fabricated in a standard 180-nm CMOS process. To address the challenges of large motion artifacts and high electrode–tissue impedance (ETI), we propose three key innovations in our proposed SFE that enable accurate ExG …

View on IEEE Xplore

A 1.1-nJ/Conversion RC-Discharge-Based Resistance Sensor With ±0.65% (3σ) 1 -Point Trimmed Inaccuracy in 0.18-μm CMOS Technology

A 1.1-nJ/Conversion RC-Discharge-Based Resistance Sensor With ±0.65% (3σ) 1 -Point Trimmed Inaccuracy in 0.18-μm CMOS Technology 150 150

Abstract:

This letter presents an energy-efficient RC discharge-based sensor readout circuit for sub-kilo-ohm resistance measurements. An SAR logic is implemented to adjust the DAC capacitor array to equalize the RC time constants of the resistance-sensing and DAC branches, thereby eliminating the high static current required to bias the small sensing resistor. …

View on IEEE Xplore

LUT-Based Convolutional Tsetlin Machine Accelerator With Dynamic Clause Scaling for Resources-Constrained FPGAs

LUT-Based Convolutional Tsetlin Machine Accelerator With Dynamic Clause Scaling for Resources-Constrained FPGAs 150 150

Abstract:

The rapid growth of machine learning (ML) workloads, particularly in computer vision applications, has significantly increased computational and energy demands in modern electronic systems, motivating the use of hardware accelerators to offload processing from general-purpose processors. Despite advances in computationally efficient ML models, achieving energy-efficient inference on resource-constrained edge devices …

View on IEEE Xplore

A 40-GS/s 8-bit Time-Interleaved ADC Featuring SFDR-Enhanced Sampling and Power-Efficient Time-Domain Quantization in 28-nm CMOS

A 40-GS/s 8-bit Time-Interleaved ADC Featuring SFDR-Enhanced Sampling and Power-Efficient Time-Domain Quantization in 28-nm CMOS 150 150

Abstract:

This article reports a 40-GS/s 8-bit time-interleaved (TI) time-domain (TD) gated-ring-oscillator analog-to-digital converter (GRO-ADC). An interleaving number of 32 is achieved with a single-channel 8-bit GRO-ADC operating at 1.25 GS/s, leading to a low front-end design complexity compared to recently published arts. The sampling front end employs a linearity-enhanced boosted …

View on IEEE Xplore

MITTA: A Multi-Task Transformer Accelerator With Mixed Precision Structured Sparsity and Hierarchical Task-Adaptive Power Management

MITTA: A Multi-Task Transformer Accelerator With Mixed Precision Structured Sparsity and Hierarchical Task-Adaptive Power Management 150 150

Abstract:

This article presents MITTA, the first silicon-proven transformer accelerator optimized for multi-task inference across both natural language processing (NLP) and image processing domains. MITTA accelerates a task-sharing algorithm that minimizes sub-task computation by reusing both activations and weights from a shared base task, requiring only sparse delta computation for sub-tasks. …

View on IEEE Xplore

Design and Analysis of a Three-Stream STT-MTJ TRNG With XOR and Majority Voter Logic as Postprocessing Architectures

Design and Analysis of a Three-Stream STT-MTJ TRNG With XOR and Majority Voter Logic as Postprocessing Architectures 150 150

Abstract:

True random number generators (TRNGs) are critical for hardware security, providing unpredictable entropy for cryptographic applications. Spin-transfer torque magnetic tunnel junction (STT-MTJ) devices offer a promising entropy source due to their low-power consumption, nonvolatility, and stochastic switching behavior. This work presents an MTJ-based TRNG that produces three independent bit streams. …

View on IEEE Xplore

EMO-CIM: An Input/Stationary-Data Similarity-Aware Computing-In-Memory Design for Variable Vector-Wise Computation in Edge Multioperator AI Acceleration

EMO-CIM: An Input/Stationary-Data Similarity-Aware Computing-In-Memory Design for Variable Vector-Wise Computation in Edge Multioperator AI Acceleration 150 150

Abstract:

We propose an edge multioperator computing-in-memory (EMO-CIM) design that supports variable vector-wise multiply-and-accumulate (MAC) in CNN, Depthwise (DW)-Convolution, and Attention operators. It features: 1) a single EMO-CIM bank (ECB) excels in variable vector-wise MAC (V-MAC) for multioperators; 2) merging local input-shared compute units (LISCUs) with a decode-unit and adder-tree (DUAT) facilitates …

View on IEEE Xplore

An Optimal Modulation Bits-to-RF Digital Transmitter Using Time-Interleaved Multi-Subharmonic Switching

An Optimal Modulation Bits-to-RF Digital Transmitter Using Time-Interleaved Multi-Subharmonic Switching 150 150

Abstract:

This article presents a fully integrated bits-to-RF transmitter (Tx) featuring deep power back-off (PBO) enhancements, leveraging a multi-subharmonic switching (multi-SHS) digital power amplifier (DPA) with time-interleaving and a harmonic-rejection digital-to-phase converter (DPC). This work employs a nonuniform optimal modulation (OM) constellation, where symbol probability is inversely related to its amplitude, …

View on IEEE Xplore