i.MX 8M Plus – New Kid in Town
IconBox Title
SolidRun Whitepaper
September 2, 2020
i.MX 8M Plus
"New Kid in Town"
Over the last three years, NXP gradually released its i.MX 8M family members. The i.MX 8M was followed by the i.MX 8M Mini and i.MX 8M Nano and recently the i.MX 8M Plus has been announced.
The i.MX 8 series of processors by NXP provides secure, advanced, and embedded grade products with minimum longevity of 10 – 15 years. Within the series, the i.MX 8 family has advanced graphics and vision, the i.MX 8X family is Safety focused, and the i.MX 8M family is focused on advanced computing, audio, video and voice capabilities.
In the last few weeks, we have been approached by many of our global customers, who were confused by the unfolding variety of the i.MX 8M family, asking to clarify the benefits and use cases for the upcoming general availability of the i.MX 8M Plus (currently at the pre-production stage).
Our product marketing team provided answers to the following questions:
- How will the new SoC family complement the existing i.MX 8M Applications Processors family members, e.g. i.MX 8M, i.MX 8M Mini?
- Which market segments does it address?
THE I.MX 8M PLUS KEY ADVANTAGES
The i.MX 8M Plus family of processors is based on ARM ® Cortex ® A53 and Cortex M7 cores. Machine learning and vision system, advanced multimedia and industrial networking, as well as High Reliability, are key features that position it well for applications such as smart building, advanced retail, smart city, and industrial IoT.
The new i.MX 8M Plus family member offering is a significant leap that expands the feature set and performance in several domains. As can be seen in the SolidRun expert analysis (figure 1), while the i.MX 8M has fewer relative advantages in “Advanced Multimedia” and the i.MX 8M Mini in terms of “Power Efficiency” – the i.MX 8M Plus has a unique and wide offering that some are even crowning it as the potential successor of the successful i.MX 6 SoC family…
Figure 1: i.MX 8M Plus Benchmark
MACHINE LEARNING / AI
i.MX 8M Plus has an integrated machine learning accelerator that can process neural networks roughly thirty times faster than Arm® processor cores. Two major capabilities are enabling machine learning / AI performance: Neural Processing Unit (NPU) and Image Signal Processor (ISP).
Neural Processing Unit (NPU) – the i.MX 8M Plus is the first i.MX processor with a built-in machine learning accelerator. Using its integrated NPU, the processor can detect complex neural network functions such as human pose and emotion detection, multi-object surveillance and recognition of over 40,000 English words.
NXP’s software development environment for machine learning is eIQ™. It enables the use of ML algorithms on i.MX 8M Plus family SoCs and includes inference engines, neural network compilers, and optimized libraries. Arm NN SDK is an Inference engine for Arm Cortex-A CPU cores, works with Caffe, TensorFlow, TensorFlow Lite, and ONNX models. This inference engine is offered by Arm® free of charge and provides a set of open-source Linux software tools that enables machine learning workloads on power-efficient devices.
TensorFlow Lite, also known as TF lite was developed by Google, enabling machine-learning on embedded devices with low latency at the edge, conducting classification, regression or other tasks without the need for a round trip to a server. TF lite achieves lower latency and smaller binary size by using techniques such as pre-fused activations and quantized kernels that allow smaller and (potentially) faster models. eIQ™ for TensorFlow Lite middleware, delivers the ability to run inferencing on Arm® Cortex®-M. The software development environment for machine learning enables the use of ML algorithms on the i.MX family SoCs.
Figure 2: i.MX 8M Plus NPU Framework
OpenVX™ is an open, royalty-free standard for cross platform acceleration of computer vision applications. It enables real time power-optimized computer vision processing for applications such as face, body and gesture tracking, robotics, surveillance and more.
IMAGE SIGNAL PROCESSOR (ISP)
The i.MX 8M Plus includes capabilities for ML / AI inputs based on two-camera ISP and eight microphones creating a comprehensive ML solution. According to NXP, the integrated ISP brings real-time image processing to high-definition video and performs algorithms that extract the maximum image details in high-contrast scenery including various lens distortion correction.
INDUSTRIAL NETWORKS AND RELIABILITY
The new i.MX 8M Plus has critical industrial features such as dual CAN-FD interfaces, time-sensitive networking support with Ethernet and ECC. The i.MX 8M Plus processor is designed to support industry 4.0 applications through multiple high-speed interfaces, time-sensitive networking (TSN) capability, ethernet port supporting multiple data collection and gateway applications.
Another industrial advantage is real-time processing by an integrated Cortex-M7 processor that performs local, real-time control. This feature can eliminate the need for an external microcontroller for the system. High reliability is gained by the applying Error Correcting Code (ECC) in critical points of the system. The 14 nm FinFET process provides lower soft error rates while delivering high processing speed and low power consumption.
ADVANCED MULTIMEDIA
The i.MX 8M Plus processor features an H.265 video encoder efficient for live video streaming compression to the cloud, local storage, etc. A Video Processing Unit (VPU) efficiently encodes and decodes high-definition video. In addition, a variety of advanced graphical features are provided.
One of the main offerings, supporting increasing demand from the application side is the unique Voice solution. The processor can perform local voice processing tasks such as speaker and voice recognition at low power use and high-performance efficiency.
Figure 3: i.MX 8M Plus Features and Benefits (based on NXP site)
TARGET APPLICATIONS
As can be seen in the analysis, the i.MX 8M Plus applications processors excel in machine learning (ML), advanced multimedia and industrial IoT applications. Its unique feature set is ideal for supporting the growing demand for edge intelligence. SolidRun experts mapped three interesting application segments to follow:
Retail: POS interfaces, smart digital signage and building control.
Smart City: Surveillance, crowd and traffic control and transportation management.
Industrial IoT: Machine vision, robot monitoring, industrial gateway, smart industrial cameras and various factory automation applications.
SolidRun has been chosen as an alpha partner for early iMX 8M Plus. Global availability is scheduled to be in Q1, 2021.
SolidRun offers a variety of ready to use feature-rich i.MX 8M plus SoMs/CoMs and SBCs in commercial and industrial grade. OEM’s can enjoy SolidRun’s high engineering and ecosystem support for further HW/SW integration and customization.
For more information please contact: [email protected]
https://www.solid-run.com/wp-content/uploads/2023/11/RZ_G2L_01.jpg
630
1200
Mona Ganem
https://solid-run.com/wp-content/uploads/2020/12/SolidRun-with-under-line-01-1-300x107.png
Mona Ganem2023-11-29 12:52:582023-11-29 16:11:46RZ/G2L: Emerging New Player in the IoT SoC Domain
https://www.solid-run.com/wp-content/uploads/2023/10/HB-P8.jpg
630
1200
Mona Ganem
https://solid-run.com/wp-content/uploads/2020/12/SolidRun-with-under-line-01-1-300x107.png
Mona Ganem2023-10-12 18:54:432023-10-12 19:34:33SolidRun Unveils the HummingBoard 8P Edge AI
https://www.solid-run.com/wp-content/uploads/2023/09/Composition.png
1080
1920
Mona Ganem
https://solid-run.com/wp-content/uploads/2020/12/SolidRun-with-under-line-01-1-300x107.png
Mona Ganem2023-10-12 15:07:312023-10-12 18:59:05Empowering Edge AI Solutions with Hailo-8 AI Processor
Thank you for your message. It has been sent.
