A runtime-reconfigurable convolutional engine using tensor multiplication with multiple computing modes in 22-nm CMOS
J Qian, Y Ji, C Li�- Microelectronics Journal, 2024 - Elsevier
The ultra-low power consumption and flexible configurability of hardware are urgent for
resource-constrained artificial intelligence of things (AIoT). Thus, we propose a
convolutional engine using tensor multiplication. It consists of a reconfigurable processing
element (RPE) array to dynamically adjust convolutional operations with varying kernel
sizes during runtime. Implemented in a 22-nm CMOS process, the proposed RPE cluster
achieves high energy efficiency, flexibility, and resource utilization with low-cost hardware�…
resource-constrained artificial intelligence of things (AIoT). Thus, we propose a
convolutional engine using tensor multiplication. It consists of a reconfigurable processing
element (RPE) array to dynamically adjust convolutional operations with varying kernel
sizes during runtime. Implemented in a 22-nm CMOS process, the proposed RPE cluster
achieves high energy efficiency, flexibility, and resource utilization with low-cost hardware�…
Showing the best result for this search. See all results