Changes

Mito8M is the first DAVE Embedded Systems' system-on-module (SoM) based on a core implementing the According to [https://encommunity.wikipedianxp.org/wikicom/ARM_architecture#64docs/32-bit_architecture ARMv8DOC-A343798 NXP documentation] architecture. Traditionally, ARM cores that are based on 32-bit [https://en.wikipedia.org/wiki/ARM_architecture#AArch32 ARMv7-A] architecture exhibit ''eIQ Machine Learning Software is a limited RAM bandwidth even if they are coupled with 64-bit width SDRAM banks. As an example, please see [[SBCX-TN-006:_Characterizing_the_RAM_bandwidth_of_Axel_Lite_SoM#Testbed_general_configuration|this Technical Note]] where we characterized the SDRAM bandwidth collection of Cortex A9-based Axel Lite SoM. When dealing with computationally heavy tasks, a limited RAM bandwidth efficiency may turn out software and development tools for NXP microprocessors and microcontrollers to be a severe bottleneck bounding the overall performancedo inference of neural network AI models on embedded systems.''

Besides an intrinsic increased computational power over their predecessors, ARMv8-A-based SoC's are also expected to improve RAM bandwidth significantly. This technical note Technical Note (TN for short) illustrates several benchmark tests that were run on hot to use eIQ in combination with Mito8M , DAVE Embedded Systems's latest SoM to characterize its bandwidth. It is worth to remember that Mito8M , which is built upon the [https://www.nxp.com/products/processors-and-microcontrollers/arm-processors/i.mx-applications-processors/i.mx-8-processors/i.mx-8m-family-armcortex-a53-cortex-m4-audio-voice-video:i.MX8M i.MX8M processor by NXP].