DPD-NeuralEngine: A 22-nm 6.6-TOPS/W/mm$^2$ Recurrent Neural Network Accelerator for Wideband Power Amplifier Digital Pre-Distortion

TL;DR

This paper introduces DPD-NeuralEngine, a highly efficient 22 nm ASIC accelerator for neural network-based digital pre-distortion in communication systems, achieving high throughput and power efficiency for wideband signals.

Contribution

It presents the first AI-based DPD ASIC accelerator using a GRU neural network, optimized for high speed and power efficiency in communication hardware.

Findings

Achieves 256.5 GOPS throughput at 2 GHz

Power efficiency of 1.32 TOPS/W

Power-area efficiency of 6.6 TOPS/W/mm$^2$

Abstract

The increasing adoption of Deep Neural Network (DNN)-based Digital Pre-distortion (DPD) in modern communication systems necessitates efficient hardware implementations. This paper presents DPD-NeuralEngine, an ultra-fast, tiny-area, and power-efficient DPD accelerator based on a Gated Recurrent Unit (GRU) neural network (NN). Leveraging a co-designed software and hardware approach, our 22 nm CMOS implementation operates at 2 GHz, capable of processing I/Q signals up to 250 MSps. Experimental results demonstrate a throughput of 256.5 GOPS and power efficiency of 1.32 TOPS/W with DPD linearization performance measured in Adjacent Channel Power Ratio (ACPR) of -45.3 dBc and Error Vector Magnitude (EVM) of -39.8 dB. To our knowledge, this work represents the first AI-based DPD application-specific integrated circuit (ASIC) accelerator, achieving a power-area efficiency (PAE) of 6.6 TOPS/W/mm$^2$.