CORVET: A CORDIC-Powered, Resource-Frugal Mixed-Precision Vector Processing Engine for High-Throughput AIoT applications

TL;DR

This paper introduces CORVET, a resource-efficient, adaptive vector processing engine utilizing CORDIC-based MAC units, designed for high-throughput, low-power AIoT edge applications with flexible precision and improved performance.

Contribution

It presents a novel, runtime-adaptive vector engine that combines CORDIC-based MAC units with resource-efficient design, enabling dynamic mode reconfiguration and significant throughput and energy efficiency improvements.

Findings

Achieves up to 4x throughput improvement within same hardware resources.

Provides 33% time savings and 21% power reduction per MAC stage.

Demonstrates higher compute density and energy efficiency than prior state-of-the-art.

Abstract

This brief presents a runtime-adaptive, performance-enhanced vector engine featuring a low-resource, iterative CORDIC-based MAC unit for edge AI acceleration. The proposed design enables dynamic reconfiguration between approximate and accurate modes, exploiting the latency-accuracy trade-off for a wide range of workloads. Its resource-efficient approach further enables up to 4x throughput improvement within the same hardware resources by leveraging vectorised, time-multiplexed execution and flexible precision scaling. With a time-multiplexed multi-AF block and a lightweight pooling and normalisation unit, the proposed vector engine supports flexible precision (4/8/16-bit) and high MAC density. The ASIC implementation results show that each MAC stage can save up to 33% of time and 21% of power, with a 256-PE configuration that achieves higher compute density (4.83 TOPS/mm2 ) and energy efficiency (11.67 TOPS/W) than previous state-of-the-art work. A detailed hardware-software co-design methodology for object detection and classification tasks on Pynq-Z2 is discussed to assess the proposed architecture, demonstrating a scalable, energy-efficient solution for edge AI applications.