PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices

TL;DR

PerfSAGE is a novel graph neural network model that accurately predicts inference latency, energy, and memory footprint for any deep neural network on various edge hardware platforms, facilitating efficient DNN deployment.

Contribution

This work introduces PerfSAGE, a GNN-based predictor capable of generalizing to arbitrary DNN graphs and outperforming prior models in accuracy and versatility.

Findings

Achieves <5% MAPE across multiple hardware targets

Outperforms previous GNN-based predictors in accuracy

Predicts performance on arbitrary DNN graphs without modifications

Abstract

The ability to accurately predict deep neural network (DNN) inference performance metrics, such as latency, power, and memory footprint, for an arbitrary DNN on a target hardware platform is essential to the design of DNN based models. This ability is critical for the (manual or automatic) design, optimization, and deployment of practical DNNs for a specific hardware deployment platform. Unfortunately, these metrics are slow to evaluate using simulators (where available) and typically require measurement on the target hardware. This work describes PerfSAGE, a novel graph neural network (GNN) that predicts inference latency, energy, and memory footprint on an arbitrary DNN TFlite graph (TFL, 2017). In contrast, previously published performance predictors can only predict latency and are restricted to pre-defined construction rules or search spaces. This paper also describes the EdgeDLPerf dataset of 134,912 DNNs randomly sampled from four task search spaces and annotated with inference performance metrics from three edge hardware platforms. Using this dataset, we train PerfSAGE and provide experimental results that demonstrate state-of-the-art prediction accuracy with a Mean Absolute Percentage Error of <5% across all targets and model search spaces. These results: (1) Outperform previous state-of-art GNN-based predictors (Dudziak et al., 2020), (2) Accurately predict performance on accelerators (a shortfall of non-GNN-based predictors (Zhang et al., 2021)), and (3) Demonstrate predictions on arbitrary input graphs without modifications to the feature extractor.