---
res:
  bibo_abstract:
  - <jats:p>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.</jats:p>@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Kuan-Hsun
      foaf_name: Chen, Kuan-Hsun
      foaf_surname: Chen
  - foaf_Person:
      foaf_givenName: Chiahui
      foaf_name: Su, Chiahui
      foaf_surname: Su
  - foaf_Person:
      foaf_givenName: Christian
      foaf_name: Hakert, Christian
      foaf_surname: Hakert
  - foaf_Person:
      foaf_givenName: Sebastian
      foaf_name: Buschjäger, Sebastian
      foaf_surname: Buschjäger
  - foaf_Person:
      foaf_givenName: Chao-Lin
      foaf_name: Lee, Chao-Lin
      foaf_surname: Lee
  - foaf_Person:
      foaf_givenName: Jenq-Kuen
      foaf_name: Lee, Jenq-Kuen
      foaf_surname: Lee
  - foaf_Person:
      foaf_givenName: Katharina
      foaf_name: Morik, Katharina
      foaf_surname: Morik
  - foaf_Person:
      foaf_givenName: Jian-Jia
      foaf_name: Chen, Jian-Jia
      foaf_surname: Chen
  bibo_doi: 10.1145/3508019
  bibo_issue: '6'
  bibo_volume: 21
  dct_date: 2022^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/1539-9087
  - http://id.crossref.org/issn/1558-3465
  dct_language: eng
  dct_publisher: Association for Computing Machinery (ACM)@
  dct_title: Efficient Realization of Decision Trees for Real-Time Inference@
...