Merge branch 'main' of github.com:tum-ei-eda/mlonmcu into main

.github/workflows/demo.yml

@@ -57,6 +57,15 @@ jobs:
       matrix:
         python-version: ["3.10"]
     steps:
+    - name: Maximize build space
+      uses: easimon/maximize-build-space@master
+      with:
+        root-reserve-mb: 16384
+        temp-reserve-mb: 8192
+        remove-dotnet: 'true'
+        remove-android: 'true'
+        remove-haskell: 'true'
+        remove-codeql: 'true'
     - uses: actions/checkout@v3
       with:
         submodules: recursive
@@ -90,6 +99,8 @@ jobs:
       run: |
         source .venv/bin/activate
         mlonmcu setup -H home/ -v
+    - name: Check Disk
+      run: df
     - name: Install environment-specific Python packages
       run: |
         source .venv/bin/activate

CITATION.cff

@@ -1,51 +1,40 @@
-# This CITATION.cff file was generated with cffinit.
-# Visit https://bit.ly/cffinit to generate yours today!
-
 cff-version: 1.2.0
-title: 'MLonMCU: TinyML Benchmarking with Fast Retargeting'
-message: >-
-  If you use this software in publications, please
-  cite it as below.
-type: software
+message: If you use this software, please cite both the article from preferred-citation and the software itself.
 authors:
-  - given-names: Philipp
-    name-particle: van
-    family-names: Kempen
-    email: [email protected]
-    affiliation: Technical University of Munich
-    orcid: 'https://orcid.org/0000-0002-1135-8070'
-  - family-names: "Stahl"
-    given-names: "Rafael"
-    email: [email protected]
-    affiliation: Technical University of Munich
-  - family-names: "Müller-Gritschneder"
-    given-names: "Daniel"
-    email: [email protected]
-    affiliation: Technical University of Munich
-  - family-names: "Schlichtmann"
-    given-names: "Ulf"
-    email: [email protected]
-    affiliation: Technical University of Munich
+  - family-names: van Kempen
+    given-names: Philipp
+  - family-names: Stahl
+    given-names: Rafael
+  - family-names: Mueller-Gritschneder
+    given-names: Daniel
+title: 'MLonMCU: TinyML Benchmarking with Fast Retargeting'
+version: v0.2.0
 repository-code: 'https://github.com/tum-ei-eda/mlonmcu'
 url: 'https://tum-ei-eda.github.io/mlonmcu/'
 repository-artifact: 'https://pypi.org/project/mlonmcu/'
-abstract: >-
-  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. A tool called
-  MLonMCU is proposed in this paper and demonstrated
-  by benchmarking the state-of-the-art TinyML
-  frameworks TFLite for Microcontrollers and TVM
-  effortlessly with large number of configurations in
-  a low amount of time.
-keywords:
-  - TinyML
-  - neural networks
-  - microcontrollers
-license: Apache-2.0
-commit: TODO
-version: v0.2.0
 date-released: '2022-10-13'
+license: Apache-2.0
+preferred-citation:
+  authors:
+    - family-names: van Kempen
+      given-names: Philipp
+    - family-names: Stahl
+      given-names: Rafael
+    - family-names: Mueller-Gritschneder
+      given-names: Daniel
+    - family-names: Schlichtmann
+      given-names: Ulf
+  title: 'MLonMCU: TinyML Benchmarking with Fast Retargeting'
+  doi: 10.1145/3615338.3618128
+  url: https://doi.org/10.1145/3615338.3618128
+  type: conference-paper
+  pages: 32–36
+  year: '2024'
+  isbn: '9798400703379'
+  collection-title: Proceedings of the 2023 Workshop on Compilers, Deployment, and Tooling for Edge AI
+  conference:
+    name: CODAI '23
+  publisher:
+    name: Association for Computing Machinery
+    address: New York, NY, USA
+

README.md

@@ -6,10 +6,11 @@
 [![GitHub license](https://img.shields.io/github/license/tum-ei-eda/mlonmcu.svg)](https://github.com/tum-ei-eda/mlonmcu/blob/main/LICENSE)
 
 [![cicd workflow](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/cicd.yml/badge.svg)](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/cicd.yml)
+[![lint workflow](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/style.yml/badge.svg)](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/style.yml)
 [![demo workflow](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/demo.yml/badge.svg)](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/demo.yml)
-[![container workflow](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/container.yml/badge.svg)](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/container.yml)
 [![bench workflow](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/bench.yml/badge.svg)](https://github.com/tum-ei-eda/mlonmcu/actions/workflows/bench.yml)
 
+
 This project contains research code related to the deployment of inference or learning applications on tiny micro-controllers.
 
 
@@ -133,6 +134,14 @@ with mlonmcu.context.MlonMcuContext() as context:
     pass
 ```
 
+## List of interesting MLonMCU forks
+
+- MINRES TGC support: https://github.com/Minres/mlonmcu/tree/develop
+
+## List of existing MLonMCU extensions/plugins
+
+- ABC Example Plugin: coming soon!
+- MINRES TGC Support: coming soon!
 
 ## Development
 
@@ -162,6 +171,33 @@ Regarding coding style, it is recommended to run `black` before every commit. Th
 
   - Came up with MLonMCU Python package
 
+## Publications
+
+- **MLonMCU: TinyML Benchmarking with Fast Retargeting** ([https://dl.acm.org/doi/10.1145/3637543.3652878](https://dl.acm.org/doi/abs/10.1145/3615338.3618128))
+
+  *CODAI '23: Proceedings of the 2023 Workshop on Compilers, Deployment, and Tooling for Edge AI*
+
+  BibTeX
+
+  ```bibtex
+  @inproceedings{10.1145/3615338.3618128,
+    author = {van Kempen, Philipp and Stahl, Rafael and Mueller-Gritschneder, Daniel and Schlichtmann, Ulf},
+    title = {MLonMCU: TinyML Benchmarking with Fast Retargeting},
+    year = {2024},
+    isbn = {9798400703379},
+    publisher = {Association for Computing Machinery},
+    address = {New York, NY, USA},
+    url = {https://doi.org/10.1145/3615338.3618128},
+    doi = {10.1145/3615338.3618128},
+    abstract = {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. A tool called MLonMCU is proposed in this paper and demonstrated by benchmarking the state-of-the-art TinyML frameworks TFLite for Microcontrollers and TVM effortlessly with a large number of configurations in a low amount of time.},
+    booktitle = {Proceedings of the 2023 Workshop on Compilers, Deployment, and Tooling for Edge AI},
+    pages = {32–36},
+    numpages = {5},
+    keywords = {TinyML, neural networks, microcontrollers},
+    location = {Hamburg, Germany},
+    series = {CODAI '23}
+  }
+  ```
 
 ### Other
 This package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template. However most of the templates was manually changed to be in Markdown instead of reStructuredText.

mlonmcu/flow/tvm/backend/tvmc_utils.py

@@ -30,10 +30,8 @@ def get_pass_config_tvmc_args(pass_config):
 
 
 def get_disabled_pass_tvmc_args(disabled_passes):
-    args = []
-    for item in disabled_passes:
-        args.extend(["--disabled-pass", item])
-    return args
+    arg = ",".join(disabled_passes)
+    return ["--disabled-pass", arg]
 
 
 def get_input_shapes_tvmc_args(input_shapes):

resources/templates/default.yml.j2

@@ -202,7 +202,7 @@ platforms:
       # validate: true
 # List of supported targets in the environment
 targets:
-  default: etiss_pulpino
+  default: etiss
   etiss_pulpino:
     enabled: true
     features: