WCDT: Systematic WCET Optimization for Decision Tree Implementations

TL;DR

This paper presents a systematic method to optimize the worst-case execution time of decision tree models on embedded systems, using a surrogate model and an optimization algorithm to reduce WCET by up to 17%.

Contribution

It introduces a linear surrogate model for estimating decision tree execution time and an optimization algorithm to produce WCET-efficient implementations.

Findings

Optimization reduces WCET by up to 17%.

Surrogate model accurately estimates path execution times.

Algorithm systematically improves decision tree implementations.

Abstract

Machine-learning models are increasingly deployed on resource-constrained embedded systems with strict timing constraints. In such scenarios, the worst-case execution time (WCET) of the models is required to ensure safe operation. Specifically, decision trees are a prominent class of machine-learning models and the main building blocks of tree-based ensemble models (e.g., random forests), which are commonly employed in resource-constrained embedded systems. In this paper, we develop a systematic approach for WCET optimization of decision tree implementations. To this end, we introduce a linear surrogate model that estimates the execution time of individual paths through a decision tree based on the path's length and the number of taken branches. We provide an optimization algorithm that constructively builds a WCET-optimal implementation of a given decision tree with respect to this surrogate model. We experimentally evaluate both the surrogate model and the WCET-optimization algorithm. The evaluation shows that the optimization algorithm improves analytically determined WCET by up to $17\%$ compared to an unoptimized implementation.