.png){kind=icon}
.png){kind=icon}
Return
TinyGen: Portable and Compact Code Generation for Tiny Machine Learning
.png){kind=icon}
PRE
AI
DOI：10.1145/3771775.3786278.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Tiny machine learning (TinyML) enables low-power micro-controllers to leverage the power of artificial intelligence without relying on remote computing resources. Typically, developing a TinyML application relies primarily on existing TinyML frameworks, which provide runtime APIs for loading and executing machine learning models. However, such framework-based TinyML development has limitations in terms of portability, programmability, and resource efficiency, motivating the need for a new approach to the TinyML development and deployment process. To address these challenges, this work introduces Tiny-Gen, a new code generation framework for Tiny-ML. TinyGen generates portable high-level code directly from a target model without depending on external runtime APIs. It statically analyzes the tensor and operator usage of the target model to enable compact code generation. This work demonstrates that TinyGen reduces binary code size by 31.2% on average compared to an existing TinyML framework while requiring fewer lines of code to write TinyML applications.
Keywords:
Tiny machine learning
systems for machine learning
automatic code generation
multi-level intermediate representation
Journal
P
IF:
0
Papers:
18
Citations:
0