CORVET: A CORDIC-Powered, Resource-Frugal Mixed-Precision Vector Processing Engine for High-Throughput AIoT applications
This provides a scalable, energy-efficient solution for AIoT applications, though it is incremental as it builds on existing hardware optimization techniques.
The paper tackles the challenge of efficient edge AI acceleration by proposing a runtime-adaptive vector engine with a CORDIC-based MAC unit, achieving up to 4x throughput improvement, 33% time savings, 21% power savings, and high compute density (4.83 TOPS/mm²) and energy efficiency (11.67 TOPS/W).
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.