FLARE: FP-Less PTQ and Low-ENOB ADC Based AMS-PiM for Error-Resilient, Fast, and Efficient Transformer Acceleration

Encoder-based transformers, powered by self-attention layers, have revolutionized machine learning with their context-aware representations. However, their quadratic growth in computational and memory demands presents significant bottlenecks. Analog-Mixed-Signal Process-in-Memory (AMS-PiM) architectures address these challenges by enabling efficient on-chip processing. Traditionally, AMS-PiM relies on Quantization-Aware Training (QAT), which is hardware-efficient but requires extensive retraining to adapt models to AMS-PiMs, making it increasingly impractical for transformer models. Post-Training Quantization (PTQ) mitigates this training overhead but introduces significant hardware inefficiencies. PTQ relies on dequantization-quantization (DQ-Q) processes, floating-point units (FPUs), and high-ENOB (Effective Number of Bits) analog-to-digital converters (ADCs). Particularly, High-ENOB ADCs scale exponentially in area and energy ($2^{ENOB}$), reduce sensing margins, and increase susceptibility to process, voltage, and temperature (PVT) variations, further compounding PTQ's challenges in AMS-PiM systems. To overcome these limitations, we propose RAP, an AMS-PiM architecture that eliminates DQ-Q processes, introduces FPU- and division-free nonlinear processing, and employs a low-ENOB-ADC-based sparse Matrix Vector multiplication technique. Using the proposed techniques, RAP improves error resiliency, area/energy efficiency, and computational speed while preserving numerical stability. Experimental results demonstrate that RAP outperforms state-of-the-art GPUs and conventional PiM architectures in energy efficiency, latency, and accuracy, making it a scalable solution for the efficient deployment of transformers.

Brief Architectural Survey of Biopotential Recording Front-Ends since the 1970s

Measuring the bioelectric signals is one of the key functions in wearable healthcare devices and implantable medical devices. The use of wearable healthcare devices has made continuous and immediate monitoring of personal health status possible. Implantable medical devices have played an important role throughout the fields of neuroscience, brain-machine (or brain-computer) interface, and rehabilitation technology. Over the last five decades, the bioelectric signals have been observed through a variety of biopotential recording front-ends, along with advances in semiconductor technology scaling and circuit techniques. Also, for reliable and continuous signal acquisition, the front-end architectures have evolved while maintaining low power and low noise performance. In this article, the architecture history of the biopotential recording front-ends developed since the 1970s is surveyed, and overall key circuit techniques are discussed. Depending on the bioelectric signals being measured, appropriate front-end architecture needs to be chosen, and the characteristics and challenges of each architecture are also covered in this article.

Trend Investigation of Biopotential Recording Front-End Channels for Invasive and Non-Invasive Applications

This paper presents the trend of biopotential recording front-end channels developed from the 1970s to the 2020s while describing a basic background on the front-end channel design. Only the front-end channels that conduct electrical recording invasively and non-invasively are addressed. The front-end channels are investigated in terms of technology node, number of channels, supply voltage, noise efficiency factor, and power efficiency factor. Also, multi-faceted comparisons are made to figure out the correlation between these five categories. In each category, the design trend is presented over time, and related circuit techniques are discussed. While addressing the characteristics of circuit techniques used to improve the channel performance, what needs to be improved is also suggested.