MonoSparse-CAM: Efficient Tree Model Processing via Monotonicity and Sparsity in CAMs

TL;DR

MonoSparse-CAM introduces a CAM-based optimization that leverages tree-based model sparsity and monotonicity, significantly reducing energy consumption and improving computational efficiency for hardware deployment.

Contribution

It presents MonoSparse-CAM, a novel technique exploiting TBML sparsity and monotonicity in CAM circuitry to enhance processing performance on hardware.

Findings

Reduces energy consumption by up to 28.56x compared to raw processing.

Achieves 18.51x energy savings over state-of-the-art methods.

Improves computational efficiency by at least 1.68x.

Abstract

While the tree-based machine learning (TBML) models exhibit superior performance compared to neural networks on tabular data and hold promise for energy-efficient acceleration using aCAM arrays, their ideal deployment on hardware with explicit exploitation of TBML structure and aCAM circuitry remains a challenging task. In this work, we present MonoSparse-CAM, a new CAM-based optimization technique that exploits TBML sparsity and monotonicity in CAM circuitry to further advance processing performance. Our results indicate that MonoSparse-CAM reduces energy consumption by upto to 28.56x compared to raw processing and by 18.51x compared to state-of-the-art techniques, while improving the efficiency of computation by at least 1.68x.