Featured research (7)

For timing-sensitive edge applications, the demand for efficient lightweight machine learning solutions has increased recently. Tree ensembles are among the state-of-the-art in many machine learning applications. While single decision trees are comparably small, an ensemble of trees can have a significant memory footprint leading to cache locality issues, which are crucial to performance in terms of execution time. In this work, we analyze memory-locality issues of the two most common realizations of decision trees, i.e. native and if-else trees. We highlight, that both realizations demand a more careful memory layout to improve caching behavior and maximize performance. We adopt a probabilistic model of decision tree inference to find the best memory layout for each tree at the application layer. Further, we present an efficient heuristic to take architecture-dependent information into account thereby optimizing the given ensemble for a target computer architecture. Our code-generation framework, which is freely available on an open-source repository, produces optimized code sessions while preserving the structure and accuracy of the trees. With several real-world data sets, we evaluate the elapsed time of various tree realizations on server hardware as well as embedded systems for Intel and ARM processors. Our optimized memory layout achieves a reduction in execution time up to 75 % execution for server-class systems, and up to 70 % for embedded systems, respectively.

Lab head

Jian-Jia Chen
Department
  • Institute of Process Control Technology, Automation und Robotics

Members (3)

Mikail Yayla
  • Technische Universität Dortmund
Junjie Shi
  • Technische Universität Dortmund
Mario Günzel
  • Technische Universität Dortmund
Georg von der Bruggen
Georg von der Bruggen
  • Not confirmed yet
Niklas Ueter
Niklas Ueter
  • Not confirmed yet
Georg von der Brüggen
Georg von der Brüggen
  • Not confirmed yet
Christian Hakert
Christian Hakert
  • Not confirmed yet
Harun Teper
Harun Teper
  • Not confirmed yet