View source for ML-TN-006 — Keyword Spotting and Asymmetric Multiprocessing on Orca SBC

{{InfoBoxTop}}
{{AppliesToMachineLearning}}
{{AppliesTo Machine Learning TN}}
{{AppliesTo ORCA TN}}
{{AppliesTo ORCA SBC TN}}
{{InfoBoxBottom}}


__FORCETOC__
= History =
{| class="wikitable" border="1"
!Version
!Date
!Notes
|-
|1.0.0
|December 2021
|First public release
|-
|}

=Introduction=
This Technical Note (TN) describes a demo application used to show the combination of an inference algorithm, namely keyword spotting, and an asymmetric multiprocessing scheme (AMP). This use case can serve as the basis for more complex applications that have to carry out the following tasks:
* Acquiring data from sensors in real-time
* Executing a computationally expensive inference algorithm on the collected data.

This scenario is quite common in the realm of AI at the edge and generally it can not be addressed with a microcontroller-based solution. On the other hand, a classic embedded processor running a complex operating system such as Linux might not be suited either because unable to handle tight real-time constrained tasks. 

In such cases, the power and the flexibility of the NXP i.MX8M Plus can be of much help, as this SoC features a heterogeneous architecture — an ARM Cortex-A53 complex and an ARM Cortex-M7 core — and a Neural Processing Unit (NPU).  

The idea is to exploit this heterogeneous architecture to implement an AMP configuration where 
* The Cortex-A53 complex — running Yocto Linux — is devoted to execute the inference algorithm with the hardware acceleration provided by the NPU 
* The Cortex-M7 core takes care of data acquisition. 

=Testbed=
The testbed is illustrated in the following picture. Basically, it consists of an Orca SBC

=Implementation=

=Testing=