Pagoda: Time and Energy Rooflines for DNN Workloads on Edge Accelerators Across Power Modes
This work develops time and energy roofline characterizations for Orin AGX across power modes, coupled with analytical models of compute and memory for DNN inference, and extends these models to DNN training, and demonstrates power-mode tuning that achieves up to \(15\%\) lower energy with small inference-time impact f...