Difference between revisions of "Getting started with AI on NXP i.MX8M Plus/Introduction/Overview/i.MX8M Plus hardware specifications"

From RidgeRun Developer Connection
Jump to: navigation, search
(Created page with "<table> <caption>Characteristics with positive and negative sides</caption> <thead> <tr> <th>Characteristic</th> <th>Negative</th> <th>Positive</th>...")
 
m
 
(24 intermediate revisions by 2 users not shown)
Line 1: Line 1:
−
<table>
+
<noinclude>
−
  <caption>Characteristics with positive and negative sides</caption>
+
{{Getting started with AI on NXP i.MX8M Plus/Head|previous=Introduction/Overview|next=Introduction/Overview/Development tools|metakeywords=i.MX8M Plus hardware specification, Variscite DART-MX8M-PLUS, Winograd Algorithm}}
−
  <thead>
+
</noinclude>
−
    <tr>
+
 
−
      <th>Characteristic</th>
+
 
−
      <th>Negative</th>
+
<!-- If you want a custom title for the page, un-comment and edit this line:
−
      <th>Positive</th>
+
{{DISPLAYTITLE:Getting started with AI on NXP i.MX8M Plus - <descriptive page name>|noerror}}
−
    </tr>
+
-->
−
  </thead>
+
 
−
  <tbody>
+
The board used in this entire research is the Variscite DART-MX8M-PLUS based on NXP i.MX8M Plus and some of the main characteristics are listed in the table below.
−
    <tr>
+
 
−
      <th>Mood</th>
+
{| class="wikitable"
−
      <td>Sad</td>
+
|- style="font-weight:bold;"
−
      <td>Happy</td>
+
! Hardware module
−
    </tr>
+
! Specification
−
    <tr>
+
|-
−
      <th>Grade</th>
+
| CPU
−
      <td>Failing</td>
+
| - 4 cores ARM Cortex A53.<br />- Frequency: [1200, 1800] Hz.<br />- Supported 32 and 64 bits.<br />- One thread per core.
−
      <td>Passing</td>
+
|-
−
    </tr>
+
| GPU
−
  </tbody>
+
| - 3D GPU GC7000UltraLite.<br />- 2D GPU GC520L.
−
</table>
+
|-
 +
| NPU
 +
| - Reaches up to 2.3 TOP/s.<br />- Optimized for voice and image<br /> recognition, object detection. <br />- Uses Winograd Algorithm. <br />- Supports 8 and 16 bits operations. 
 +
|-
 +
| RAM
 +
| - 4 GB.<br />- LPDDR4-4000.
 +
|}
 +
 
 +
{{Ambox
 +
|type=notice
 +
|small=left
 +
|issue='''Note:''' For more information please visit the Official [https://variwiki.com/index.php?title=DART-MX8M-PLUS Variscite site].
 +
|style=width:unset;
 +
}}
 +
 
 +
<noinclude>
 +
{{Getting started with AI on NXP i.MX8M Plus/Foot|Introduction/Overview|Introduction/Overview/Development tools}}
 +
</noinclude>

Latest revision as of 11:03, 21 March 2023




NXP Partner Program Registered Vertical.jpg NXP Partner Program Horizontal.jpg
Previous: Introduction/Overview Index Next: Introduction/Overview/Development tools
Getting started with
AI on NXP i.MX8M Plus
Ridgerun-logo.svg
Introduction
Overview
Development kit
Quick getting started
Development
Gatesgarth and Hardknott Yocto versions
Integrating multimedia software stack
Integrating Artificial Intelligence software stack
Developing software for the board
Neural Processing Unit
Introduction
Profiling the NPU
Use Case experiments: Smart Parking
Introduction to the use case
License Plate Detection
License Plate Recognition
Bash scripts for CPU usage and time estimation
Serial experiments
Parallel Experiments
Results
GStreamer
Exploring Rosetta element for character recognition
Example pipelines
Contact Us




The board used in this entire research is the Variscite DART-MX8M-PLUS based on NXP i.MX8M Plus and some of the main characteristics are listed in the table below.

Hardware module Specification
CPU - 4 cores ARM Cortex A53.
- Frequency: [1200, 1800] Hz.
- Supported 32 and 64 bits.
- One thread per core.
GPU - 3D GPU GC7000UltraLite.
- 2D GPU GC520L.
NPU - Reaches up to 2.3 TOP/s.
- Optimized for voice and image
recognition, object detection.
- Uses Winograd Algorithm.
- Supports 8 and 16 bits operations.
RAM - 4 GB.
- LPDDR4-4000.


Previous: Introduction/Overview Index Next: Introduction/Overview/Development tools



Retrieved from "http://developer.ridgerun.com/wiki/index.php?title=Getting_started_with_AI_on_NXP_i.MX8M_Plus/Introduction/Overview/i.MX8M_Plus_hardware_specifications&oldid=48125"