MonoSparse-CAM: Efficient Tree Model Processing via Monotonicity and Sparsity in CAMs
This work addresses energy-efficient hardware acceleration for tree-based models on tabular data, representing an incremental improvement over existing CAM-based techniques.
The paper tackled the challenge of efficiently deploying tree-based machine learning models on hardware using CAM arrays by introducing MonoSparse-CAM, which exploits sparsity and monotonicity to reduce energy consumption by up to 28.56x compared to raw processing and improve computation efficiency by at least 1.68x.
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.