Language-Based Deployment Optimization for Random Forests (Invited Paper)

Jannik Malcher, Daniel Biebert, Kuan-Hsun Chen, Sebastian Buschjäger, Christian Hakert, Jian-Jia Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

66 Downloads (Pure)

Abstract

Arising popularity for resource-efficient machine learning models makes random forests and decision trees famous models in recent years. Naturally, these models are tuned, optimized, and transformed to feature maximally low-resource consumption. A subset of these strategies targets the model structure and model logic and therefore induces a trade-off between resource-efficiency and prediction performance. An orthogonal set of approaches targets hardware-specific optimizations, which can improve performance without changing the behavior of the model. Since such hardware-specific optimizations are usually hardware-dependent and inflexible in their realizations, this paper envisions a more general application of such optimization strategies at the level of programming languages. We therefore discuss a set of suitable optimization strategies first in general and envision their application in LLVM IR, i.e. a flexible and hardware-independent ecosystem.
Original languageEnglish
Title of host publicationLCTES '24
Subtitle of host publication25th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems, Copenhagen, Denmark, 24 June 2024
EditorsAviral Shrivastava, Yulei Sui
Place of PublicationNew York, NY
PublisherACM Publishing
Pages58-61
Number of pages4
ISBN (Electronic)9798400706165
ISBN (Print)979-8-4007-0616-5
DOIs
Publication statusPublished - 20 Jun 2024
Event25th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems, LCTES 2024 - Copenhagen, Denmark
Duration: 24 Jun 202424 Jun 2024
Conference number: 25

Conference

Conference25th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems, LCTES 2024
Abbreviated titleLCTES 2024
Country/TerritoryDenmark
CityCopenhagen
Period24/06/2424/06/24

Fingerprint

Dive into the research topics of 'Language-Based Deployment Optimization for Random Forests (Invited Paper)'. Together they form a unique fingerprint.

Cite this