# Register Your Forests: Decision Tree Ensemble Optimization by Explicit CPU Register Allocation

arXiv: https://arxiv.org/abs/2404.06846 · HTML: https://mlsanity.com/paper/2404.06846/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 20 references that are in the map.
- First posted on arXiv 10 Apr 2024.

## Builds on (most cited first, 5 of 5)

- [TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems](https://mlsanity.com/paper/2010.08678/) (2020)
- [ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers](https://mlsanity.com/paper/1812.11677/) (2018)
- [Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems](https://mlsanity.com/paper/1810.07751/) (2018)
- [A Tensor Compiler for Unified Machine Learning Prediction Serving](https://mlsanity.com/paper/2010.04804/) (2020)
- [GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks](https://mlsanity.com/paper/1806.01107/) (2018)

## Abstract (arXiv)

Bringing high-level machine learning models to efficient and well-suited machine implementations often invokes a bunch of tools, e.g.~code generators, compilers, and optimizers. Along such tool chains, abstractions have to be applied. This leads to not optimally used CPU registers. This is a shortcoming, especially in resource constrained embedded setups. In this work, we present a code generation approach for decision tree ensembles, which produces machine assembly code within a single conversion step directly from the high-level model representation. Specifically, we develop various approaches to effectively allocate registers for the inference of decision tree ensembles. Extensive evaluations of the proposed method are conducted in comparison to the basic realization of C code from the high-level machine learning model and succeeding compilation. The results show that the performance of decision tree ensemble inference can be significantly improved (by up to ≈1.6×), if the methods are applied carefully to the appropriate scenario.