2 papers
cs.ET2024
A New Dataflow Implementation to Improve Energy Efficiency of Monolithic 3D Systolic Arrays
Prachi Shukla, Vasilis F. Pavlidis, Emre Salman +1
Systolic arrays are popular for executing deep neural networks (DNNs) at the edge. Low latency and energy efficiency are key requirements in edge devices such as drones and autonom…
cs.ET2022
Temperature-Aware Monolithic 3D DNN Accelerators for Biomedical Applications
Prachi Shukla, Vasilis F. Pavlidis, Emre Salman +1
In this paper, we focus on temperature-aware Monolithic 3D (Mono3D) deep neural network (DNN) inference accelerators for biomedical applications. We develop an optimizer that tunes…