MLonMCU

While there exist many ways to deploy machine learning models on microcontrollers, it is non-trivial to choose the optimal combination of frameworks and targets for a given application.

Thus, automating the end-to-end benchmarking flow is of high relevance nowadays. MLonMCU allows performing complex benchmarks of edge ML workloads, frameworks and targets with minimal efforts

Visibility
Publicly available!
License

Apache License 2.0

ISA Compliance
Status
Date of Availability
Contact

Technical University of Munich
Philipp van Kempen
Arcisstr. 21
80333 München
Deutschland

Contact Email
philipp.van-kempen [at] tum.de
Asset Reference Description

Supported as Target Simulator

Asset Reference
Asset Reference Description

Supported as RISC-V kernel library

Asset Reference
Asset Reference Description

Supported as Deployment Backend

Asset Reference Description

Planned to be supported as part of TVM deployment backend

Target TRL at the end of phase 1
TRL4: Versuchsaufbau im Labor --> Plattform mit Parametrisierung
Target TRL at the end of phase 2
TRL5: Versuchsaufbau in vereinfachter Einsatzumgebung --> Optimierte Plattform
Component is required for safety critical systems
Nein
Category
Compiler
Software Library