Importance of FPU
This study aims to reveal the importance of the Floating Point Unit (FPU) in TinyML applications.
We use FC and CNN models deployed on the NUCLEO-L4R5ZI board for our experiments.
Model Type:
Models
/params_MACs.png#only-light)
/dark/params_MACs.png#only-dark)
/params_MACs.png#only-light)
/dark/params_MACs.png#only-dark)
Error
/error.png#only-light)
/dark/error.png#only-dark)
/error.png#only-light)
/dark/error.png#only-dark)
Execution Time
/exe.png#only-light)
/dark/exe.png#only-dark)
/exe.png#only-light)
/dark/exe.png#only-dark)
Flash Size
/flash.png#only-light)
/dark/flash.png#only-dark)
/flash.png#only-light)
/dark/flash.png#only-dark)
RAM Usage
/ram.png#only-light)
/dark/ram.png#only-dark)
/ram.png#only-light)
/dark/ram.png#only-dark)
Summary
The only effect of the FPU is on the execution time of the basic models which is very significant. Still, if using int8 only, utilizing the CMSIS-NN library can be even more beneficial and there is no need for the FPU.