Multi Source Translation Content

cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 

Multi Source Translation Content

Discussions

Sort by:
NET-N1886 QorIQ LS1043A 处理器硅片启动技巧 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 本次会议将提供有助于加速 QorIQ LS1043A 处理器硅片启动的技巧。 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 本次会议将提供有助于加速 QorIQ LS1043A 处理器硅片启动的技巧。 智能网络
View full article
FTF-ACC-F1276.pdf <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 本次会议将解释飞思卡尔如何帮助客户使用 MPC577xK MCU 开发 76-81 GHz 短程和长程雷达应用,并将解释雷达算法的概念,包括 SDADC 或 MIPI CSI 采样、Chirp 生成、数据压缩、R、V FFT、检测和跟踪算法等实际方面,以及新飞思卡尔 IP 的优势,这些优势可以帮助客户提高系统分辨率和准确性。在本次会议中,客户将详细了解如何使用 MPC577xK MCU 开发快速调制雷达系统,包括其带来的 BOM 成本优势。 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 本次会议将解释飞思卡尔如何帮助客户使用 MPC577xK MCU 开发 76-81 GHz 短程和长程雷达应用,并将解释雷达算法的概念,包括 SDADC 或 MIPI CSI 采样、Chirp 生成、数据压缩、R、V FFT、检测和跟踪算法等实际方面,以及新飞思卡尔 IP 的优势,这些优势可以帮助客户提高系统分辨率和准确性。在本次会议中,客户将详细了解如何使用 MPC577xK MCU 开发快速调制雷达系统,包括其带来的 BOM 成本优势。
View full article
APF-SNT-T1360 - 南京、深セン <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> このセッションでは、ハードウェアとソフトウェアの互換性を確保しながら、QorIQ T2081とT1040の通信プロセッサ・ファミリ間で移行する方法について説明します。このセッションでは、これらのプロセッサ間での移行と、これらのプロセッサの共通ボードの設計中に存在するハードウェア、ソフトウェア、およびボード レベルの考慮事項についても説明します。 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> このセッションでは、ハードウェアとソフトウェアの互換性を確保しながら、QorIQ T2081とT1040の通信プロセッサ・ファミリ間で移行する方法について説明します。このセッションでは、これらのプロセッサ間での移行と、これらのプロセッサの共通ボードの設計中に存在するハードウェア、ソフトウェア、およびボード レベルの考慮事項についても説明します。
View full article
.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 理解和使用.sdcard格式 Yocto Communiy BSP 和 Release BSP 中默认启用的一个非常有用的功能是在 .sdcard 中生成烘焙图像的选项格式。 如果 .sdcard默认情况下未选择格式,可以在 conf/local.conf 文件上通过添加 IMAGE_FSTYPES 来启用它,如下所示: IMAGE_FSTYPES="sd卡" 值得注意的是,如果指定了这个变量,那么只会创建类型定义的文件系统。此变量最常用的默认值是: IMAGE_FSTYPES="tar.bz2 ext3 sd卡" .sdcard 格式创建一个包含所有必要分区的映像,并将引导加载程序、内核和 rootfs 加载到该映像中。您可以使用 dd 将此文件中的数据低级复制到 SD 卡设备,如以下命令示例所示: $ sudo dd if=.sdcard of=/dev/sd bs=1M && 同步 .sdcard 上使用的分区文件 .sdcard 分区如下所示: IMAGE_ROOTFS_ALIGNMENT 为引导加载程序保留的未分区空间 引导空间 Kernerl 和其他数据 根文件系统大小 根文件系统。 在 RootFS 分区上授予更多可用空间 .sdcard 的大小文件将完全取决于 rootfs 的大小。这意味着,除非我们向 rootfs 分区添加额外的空间,否则生成的文件将不会对我们所有的 SD 卡容量进行分区。(当然,一旦加载到 SD 卡上,总是可以选择编辑分区) 为了添加更多空间,您可以使用 IMAGE_ROOTFS_EXTRA_SPACE 变量。您可以将其添加到 local.conf 文件中,并添加以 KB 为单位的可用磁盘空间。例如,如果您想保证 1GB 的额外空间,您可以将以下行添加到您的 local.conf 文件。 IMAGE_ROOTFS_EXTRA_SPACE = "1048576" 值得注意的是,这是 IMAGE_OVERHEAD_FACTOR 变量的附加空间,该变量定义了应用于初始图像大小的乘数。这仅适用于乘数乘以 默认情况下,构建过程对此变量使用乘数 1.3。当使用此方法确定最终生成的图像大小时,此默认值会导致 30% 的可用磁盘空间添加到图像中。这意味着在安装后脚本之前应该有 30% 的可用磁盘空间。如果您希望获得更多空间,可以按如下方式编辑此变量: 图像开销因子 = "1.5" 这将导致在安装后脚本之前向映像中添加 50% 的可用磁盘空间,并且不考虑可能来自包管理系统的开销。 IMAGE_ROOTFS_SIZE 是如何计算的 这个变量也是以千字节为单位,它由 OpenEmbedded 构建系统使用一种算法来确定,该算法考虑了用于生成图像的初始磁盘空间、图像的请求大小(通过开销因素)以及要添加到图像的额外可用空间(通过额外空间变量)。 构建系统首先运行 du(磁盘使用情况)命令来确定 rootfs 目录树的大小。如果 IMAGE_ROOTFS_SIZE 当前值大于磁盘使用量乘以开销因子,则仅添加额外的空间。如果 IMAGE_ROOTFS_SIZE 小于磁盘使用量乘以开销因子,则在添加额外空间之前将磁盘使用量乘以开销因子。 IMAGE_ROOTFS_SIZE 必须设置为默认值,该值通常非常低,因为它只是在每次烘焙图像时初始化并根据实际尺寸要求进行更新。 您也可以直接使用此变量来选择要分配给 RootFS 的空间。例如,将 RootFS 设置为 2GB 需要在 local.conf 文件中添加以下内容: IMAGE_ROOTFS_SIZE = “2097152” 图像开销因子 = “1.0” 在这个例子中,我们将开销因子保留为 1,这样就不会添加额外的空间,因为我们指定了我们想要的 rootfs 大小。 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 你知道发生了什么事吗?在 tmp/deploy/images/ / 文件夹中,较短的 sdcard 文件名只是较长文件名的链接。运行 dd 命令时我总是使用较长的文件名。 另外,我发现引导加载程序中存在严重的 CRC 环境错误。无论出于何种原因,总是要求您第一次从新映像的卡启动时中断启动,然后输入“saveenv”(不带引号),然后重置。这也许可以解决你的问题。每次我将新图像写入 SD 卡时,我都必须这样做。 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 您可能从网页上复制粘贴了命令“IMAGE_ROOTFS_SIZE = “2097152””,但其中的双引号字符( “ ”)有误。请将其替换为“linux double quote "”,解析错误即可消失。 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 根据第一段,该文档似乎在说这些变量中的任何一个都应该添加到 conf/local.conf。 然而,当我添加 IMAGE_ROOTFS_SIZE = “2097152” 图像开销因子 = “1.0” 到我的 conf/local.conf 文件,我收到 bitbake 错误: 错误:/home/user/yocto/build/conf/local.conf:26 处的 ParseError:未解析的行:'IMAGE_ROOTFS_SIZE =“2097152”' 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 是否会逐步淘汰这一模式,转而采用“WIC”模式?rocko repo 无法构建 .sdcard默认文件。 有人知道是否有关于 WIC 文件格式的类似描述以及如何使用它吗? 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 您能分享一下您的解决方案吗?谢谢 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 事实证明,如果更改制造工具脚本,制造工具也可以创建多个分区。该文档包含在制造工具下载中。我计划使用 *.sdcard 图像对我的设备上 eMMC 进行编程,并且无论如何都需要使用制造工具。制造工具中的默认设置甚至不使用 *.sdcard 图像,所以我想我现在不需要解决这个特定问题。 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> jtis我也有同样的问题。我正在尝试做同样的事情。 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 你好, gusarambula ,这份文档包含非常重要和有用的信息,希望下次你能在教程中向我们解释所有可以使用命令“dd”应用于带有 i.MX 的 SD 的选项。 请继续努力 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 非常感谢您的反馈! Bio_TICFSL ,我终于可以提到你了。您能否对此文档提出评论? 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 非常好的文档,特别是关于扩展分区容量的主题,看起来像是一个常见问题解答。 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 非常好的文档! 回复:.sdcard 指南格式 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 很棒的文件,古斯塔沃。
View full article
i.MX Multimedia Explained: How-to Effectively Create Multimedia Application for i.MX Applications Processors Lecture including a live demo, showing how to develop multimedia application for i.MX applications processors, taking advantages of the hardware multimedia accelerators of the i.MX SoC.  Presented by Daniele DallAcqua Presented at DwF Istanbul - May 12, 2015 Session ID: EUF-DES-T1474 Lecture including a live demo, showing how to develop multimedia application for i.MX applications processors, taking advantages of the hardware multimedia accelerators of the i.MX SoC.  Presented by Daniele DallAcqua Presented at DwF Istanbul - May 12, 2015 Session ID: EUF-DES-T1474 i.MX Applications Processors Re: i.MX Multimedia Explained: How-to Effectively Create Multimedia Application for i.MX Applications Processors Great presentation! Very complete. Would you share the hands on source code? I'm specially interested in the src/hmi.c and media_server.c.
View full article
调整 S08P MCU <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 本文档的目的是展示调整微控制器单元 (MCU) 的重要性,并展示未调整和调整后的设备之间的差异。 概述
View full article
DwF MCU及汽车解决方案 - 天安 - 2015-03-19 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 汽车和联网汽车 汽车 MCU 概述,包括 Kinetis 和 S12 MagniV 混合信号 MCU 汽车模拟和传感器概述,包括 BCC 和高压传感器 洞察与创新 Kinetis 微控制器概述 - Kinetis 性能优势及应用 设计、软件和服务 Freescale MQX™实时操作系统介绍 Arm® 处理器 Kinetis Cortex ® -M 微控制器 传感器 软件和工具
View full article
eIQ FAQ This document will cover some of the most commonly asked questions we've gotten about eIQ and embedded machine learning. Anything requiring more in-depth discussion/explanation will be put in a separate thread. All new questions should go into their own thread as well What is eIQ? The NXP® eIQ™ machine learning (ML) software development environment enables the use of ML algorithms on NXP EdgeVerse™ microcontrollers and microprocessors, including MCX-N microcontrollers, i.MX RT crossover MCUs, and i.MX family application processors. eIQ ML software is made up of several pieces of enablement including inference engines, neural network compilers and optimized libraries. This software leverages open-source and proprietary technologies and is fully integrated into our MCUXpresso SDK and Yocto development environments, allowing you to develop complete system-level applications with ease. eIQ enablement also enables models to use the new eIQ Neutron NPU found on the MCX-N and i.MX RT700 microcontroller devices and upcoming future NPU enabled embedded devices like i.MX95.  What are the key pieces of eIQ enablement?  eIQ Time Series Studio - PC tool to create and deploy classical machine learning and neural network models for time series analysis eIQ Inference Engines - Included as part of MCUXpresso SDK or Yocto Linux, this software is used to do inferencing of pre-trained neural network models on embedded devices eIQ Toolkit - Contains the Neutron Converter tool for enabling neural network models to be accelerated with eIQ Neutron NPUs eIQ Model Zoo - browse models tested on NXP silicon eIQ Model Watermarking Extension - Enhance copyright protections on custom models eIQ Model Creator - Partnership with ModelCat for vision-based model development How much does eIQ cost? eIQ Time Series Studio, eIQ Toolkit, and eIQ Inference engines are complimentary and royalty free. eIQ Model Creator has a subscription fee with ModelCat.  What is the development flow for developing and deploying AI/ML models with eIQ? There are two options depending on if already have a model or not, or if interested in Time Series or not: 1) Deploy a neural network model using the eIQ Inference Engines 2) Use eIQ Time Series Studio (TSS) to train and deploy a time series model using a simple C library eIQ Inference Engines What is the key enablement for using eIQ Inference Engines? 1) The inference engine, like TensorFlow Lite for Microcontrollers, that is included in the MCUXpresso SDK 2) eIQ Neutron Converter Tool - used to convert a quantized TFLite model into a Neutron-enabled TFLite model that can be parsed by the eIQ software. This is only required if using an eIQ Neutron NPU enabled device.  You can use any workflow to create and train your ML model. The model just needs to be exported as TFLite file so it can be converted by the eIQ Neutron Converter Tool and/or use the TFLM inference engine.  What inference engines are available in eIQ? i.MX apps processors and i.MX RT MCUs support different inference engines. The best inference engine can depend on the particular model being used, so eIQ offers several inference engine options to find the best fit for your particular application.  Inference engines for i.MX: TensorFlow Lite (Supported on both CPU and GPU/NPU) ARM NN (Supported on both CPU and GPU/NPU) OpenCV (Supported on only CPU) ONNX Runtime (Currently only supported on CPU) Inference engines for MCX and i.MX RT TensorFlow Lite for Microcontrollers ExecuTorch (Coming Soon) What devices are supported by eIQ inference engines? eIQ inference engines are available for the following i.MX application processors: i.MX 8M Plus i.MX 8M i.MX 8M Nano i.MX 8M Mini i.MX 8ULP i.MX 8X i.MX 93 i.MX 95 eIQ inference engines are available for the following MCX MCUs: MCX-N eIQ inference engines are is available for the following i.MX RT crossover MCUs: i.MX RT1180 i.MX RT1170 i.MX RT1160 i.MX RT1064 i.MX RT1060 i.MX RT1050 i.MX RT700 i.MX RT685 i.MX RT595 Can eIQ inference engines run on other NXP MCU devices? There's no special hardware module required to run eIQ inference engines and it is possible to port the inference engines to other NXP devices.  Is eIQ Toolkit required to use eIQ inference engines?  eIQ Toolkit is required if using a device with an eIQ Neutron NPU as it includes the Neutron Converter tool which is used to convert a model to be accelerated by the NPU.  For devices that do not have an NPU, eIQ Toolkit is optional enablement from NXP to provide an option to generate models that can then be used with the eIQ inference engines. However if you already have your model development flow in place, or want to use pre-created models from a model zoo, you can use those models with eIQ inference engines as well.  What is the eIQ Neutron NPU?  The new eIQ Neutron NPU is a Neural Processing Unit developed by NXP which has been integrated into the MCX N, i.MX RT700, and i.MX95 devices, with many more to come. It was designed to accelerate neural network computations and significantly reduce model inference time. The scalability of this module allows NXP to integrate this NPU into a wide range of devices all while having the same eIQ software enablement.  For more details on the NPU for MCX N see this Community post.  How can I start using the eIQ Neutron NPU?  There are hands-on NPU lab guides available for MCX N or i.MX RT700 that walk through the steps for converting and running a model with the eIQ Neutron NPU. There is also an app note AN14700 - i.MX RT700 eIQ Neutron NPU Enablement and Performance which has more details.  What TFLite operators are supported bythe eIQ Neutron NPU on different devices?  The details and constraints for supported operators can be found in the MCUXpresso SDK documentation.  eIQ Time Series Studio What is eIQ Time Series Studio (TSS)?   eIQ TSS is software application that provides an automated machine-learning workflow that streamlines the development and deployment of time series-based machine learning models across microcontroller (MCU) class devices such as the MCX portfolio of MCUs and i.MX RT portfolio of crossover MCUs. Time Series Studio supports a wide range of sensor input signals, including voltage, current, temperature, vibration, pressure, sound, time of flight, among others, as well as combinations of these for multimodal sensor fusion. The automatic machine learning capability enables developers to extract meaningful insights from raw time-sequential data and quickly build AI models tailored to meet accuracy, RAM and storage criteria for microcontrollers. The tool offers a comprehensive development environment, including data curation, visualization and analysis, as well as model autogeneration, optimization, emulation and deployment. eIQ Time Series Studio was previously included in eIQ Toolkit but is now available as a standalone installer for both Windows and Linux. A web based version is also under development.   What devices are supported by the eIQ Time Series Studio?   TSS will generate a C library that can be included in your application and does not require an Deep Learning inference engine, so it can be deployed to a much wider range of NXP devices as it has very minimal flash and RAM requirements.  MCX FRDM-MCXA153 FRDM-MCXC444 FRDM-MCXN947 FRDM-MCXW17 i.MX RT MIMXRT1060-EVK MIMXRT1170-EVK MIMXRT1180-EVK i.MXRT685 i.MXRT595 i.MXRT700 LPC LPC55S69-EVK Kinetis FRDM-K66F FRDM-KV31F FRDM-K32L3A6 DSC MC56F83000-EVK MC56F80000-EVK i.MX i.MX93 i.MX 8M Plus Can eIQ Time Series Studio create models that can take advantage of the eIQ Neutron NPU?  Yes, TSS now supports creating both Classical Machine Learning (CML) models as well as Neural Network models. Neural Network models can be accelerated by the NPU. However in many cases it will make more sense to use the CML models for time series applications as they can be just as accurate for many time series datasets but will be much faster and use far less memory due to their smaller model size. Even when using NPU acceleration Neural Network models can be slower than their far smaller CML model counterparts. However in some situations Neural Networks may give better accuracy for complex multi-modal analysis. TSS make it easy to determine if a NN or CML model is the best fit for a particular dataset.  But as many time series applications perform well with CML models then it opens up running time series AI on a wide variety of devices even if they do not have an integrated NPU.  How can I start using the eIQ Time Series Studio tool?  There is a hands-on lab guide available to walk through how to use the tool as well as documentation and guides in the tool itself.  General eIQ Questions How can I get eIQ? For MCU devices: eIQ inference engine libraries and examples are included as part of MCUXpresso SDK for supported devices. Make sure to select the “eIQ” middleware option. eIQ Neutron Converter Tool that converts your own neural network model to use the Neutron NPU can be found in eIQ Toolkit.  eIQ Time Series Studio is available as a standalone installer For i.MX devices: eIQ is distributed as part of the Yocto Linux BSP. Starting with the 4.19 release line there is a dedicated Yocto image that includes all the Machine Learning features: ‘imx-image-full’. For pre-build binaries refer to i.MX Linux Releases and Pre-releases pages. There is eIQ Toolkit - for model conversion.   What documentation is available for eIQ? For i.MX RT and MCX devices:  eIQ MCUXPresso SDK documentation can be found online here.  For i.MX devices: The eIQ documentation for i.MX is integrated in the Yocto BSP documentation. Refer to i.MX Linux Releases and Pre-releases pages. i.MX Reference Manual: presents an overview of the NXP eIQ Machine Learning technology. i.MX Linux_User's Guide: presents detailed instructions on how to run and develop applications using the ML frameworks available in eIQ (currently ArmNN, TFLite, OpenCV and ONNX). i.MX Yocto Project User's Guide: presents build instructions to include eIQ ML support (check sections referring to ‘imx-image-full’ that includes all eIQ features). It is recommended to also check the i.MX Linux Release Notes which includes eIQ details. For i.MX devices, what type of Machine Learning applications can I create?  Following the BYOM principle described above, you can create a wide variety of applications for running on I.MX. To help kickstart your efforts, refer to PyeIQ – a collection of demos and applications that demonstrate the Machine Learning capabilities available on i.MX. They are very easy to use (install with a single command, retrieve input data automatically) The implementation is very easy to understand (using the python API for TFLite, ArmNN and OpenCV) They demonstrate several types of ML applications (e.g., object detection, classification, facial expression detection) running on the different compute units available on i.MX to execute the inference (Cortex-A, GPU, NPU). Can I use the python API provided by PyeIQ to develop my own application on i.MX devices? For developing a custom application in python, it is recommended to directly use the python API for ArmNN, TFLite, and OpenCV. Refer to the i.MX Linux User’s Guide for more details. You can use the PyeIQ scripts as a starting point and include code snippets in a custom application (please make sure to add the right copyright terms) but shouldn’t rely on PyeIQ to entirely develop a product. The PyeIQ python API is meant to help demo developers with the creation of new examples. What eIQ example applications are available for MCUs? eIQ example applications can be found in the \boards\ \eiq_examples directory:  What are Glow and DeepViewRT inference engines in the MCUXpresso SDK?  These are inference engines that were supported in previous versions of eIQ but are now deprecated as new development has focused on TensorFlow Lite for Microcontrollers. These projects are still available in MCUXpresso SDK 2.15 for legacy users, but it is highly recommended that any new projects use TensorFlow Lite for Microcontrollers.   How can I learn more about using TensorFlow Lite with eIQ? There is a hands-on TensorFlow Lite for Microcontrollers lab available. There is also a i.MX TensorFlow Lite Lab that provide a step-by-step guide on how to get started with eIQ for TensorFlow Lite for i.MX devices.  What application notes are available to learn more about eIQ? i.MX RT700 eIQ Neutron NPU Enablement and Performance  Anomaly Detection App Note  Handwritten Digit Recognition  Datasets and Transfer Learning App Note  Security for Machine Learning Package  i.MX 8M Plus NPU Warmup Time App Note  What is the advantage of using eIQ instead of using the open-sourced software directly from Github? eIQ supported inference engines work out of the box and are already tested and optimized, allowing for performance enhancements compared to the original code. eIQ also includes the software to capture the camera or voice data from external peripherals. eIQ allows you to get up and running within minutes instead of weeks. As a comparison, rolling your own is like grinding your own flour to make a pizza from scratch, instead of just ordering a great pizza from your favorite pizza place.  Does eIQ include ML models? Do I use it to train a model? eIQ has options to both create model and run pre-existing models so you can Bring Your Own Model (BYOM) and run it on NXP embedded devices. eIQ provides the ability to run your own specialized model on NXP’s embedded devices.  MCUXpresso SDK and the i.MX Linux releases come with several examples that use pre-created models that can be used to get a sense of what is possible on our platforms, and it is very easy to substitute in your own model into those examples. eIQ Time Series Studio can be used to create and deploy time series models eIQ Model Creator is an option to create your own vision based models with our partner ModelCat I’m new to AI/ML and don’t know how to create a model, what can I do? A wide variety of resources are available for creating models, from labs and tutorials, to automated model generation tools like eIQ Time Series Studio, eIQ Model Creator, Google Cloud AutoML, Microsoft Azure Machine Learning, or Amazon ML Services, to 3 rd party partners like ModelCat, SensiML and Au-Zone that can help you define, enhance, and create a model for your specific application. I’m interested in anomaly detect or time series models on microcontrollers, where can I get started? The eIQ Time Series Studio (TSS) tool, included as part of the eIQ Toolkit, is perfect for getting started with time series or anomaly detection models. It allows you to import time series datasets, generate models, and deploy them to NXP microcontrollers.  There is also ML-based System State Monitor Application Software Pack which provides an example of gathering time-series data, in this case vibrations picked up by an accelerometer, and includes Python scripts to use the data that was collected to generate a small model that can be deployed on many different microcontrollers (including i.MX RT1170, LPC55S69, K66F) for anomaly detection. The same concepts and technique can be used for any sort of times series data like magnetometers, pressure, temperature, flow speed, and much more. This can simplify the work of coming up with a customer algorithm to detect the different states of whatever system you're interested in, as you can let the power of machine learning figure all that out for you.  There is also an on-device trained anomaly detection model example that can be found on the Application Code Hub. Troubleshooting: Why do I get an error when running Tensorflow Lite Micro that it "Didn't find op for builtin opcode"? The full error will look something like this: Didn't find op for builtin opcode 'PAD' version '1' Failed to get registration from op code ADD Failed starting model allocation. AllocateTensors() failed Failed initializing model The reason is that with MCUXpresso SDK, the TFLM examples have been optimized to only support the operands necessary for the default models. If you are using your own model, it may use extra types of operands. To fix this issue, add that operator to MODEL_GetOpsResolver function found in source\model\model_name_ops_npu.cpp Also make sure to also increase the size of the static array s_microOpResolver to match the number of operators An alternative method is also described in the TFLM Lab Guide on how to use the All Ops Resolver. Add the following header file #include"tensorflow/lite/micro/all_ops_resolver.h" and then comment out the micro_op_resolver and use this instead:  //tflite::MicroOpResolver &micro_op_resolver = //MODEL_GetOpsResolver(s_errorReporter); tflite::AllOpsResolver micro_op_resolver; Why do I get the error “Internal Neutron NPU driver error 281b in model prepare!” or "Incompatible Neutron NPU microcode and driver versions!" when using the Neutron NPU? The version of the eIQ Neutron Converter Tool needs to be compatible with the NPU libraries used by your project. See more details in this post on using custom models with eIQ Neutron NPU.  Sometimes in eIQ Toolkit the Validation page hangs and it stays stuck on "Converting Model". How do I work around this?  On the Validation section of the wizard, you will need to wait for the "Input Data Type" and "Output Data Type" selection boxes to be populated before clicking on the "Validation" button at the bottom. It may take a minute or two for those selection boxes to pop up on the left hand side. Once they do, then click on Validate and it should no longer hang.  How do I use my GPU when training with eIQ Toolkit? eIQ Toolkit 1.10 only supports GPU training on Linux due to the latest TensorFlow versions no longer supporting GPU on Windows.  Why do I get a blank or black LCD screen when I use the eIQ demos that have camera+LCD support on RT1170 or RT1160? There are different versions of the LCD, so you need to make sure you have the software configured correctly for the LCD you have. See this post for more details on what to change. There is a Javascript error in Time Series Studio when I start the training.  There is a bug where if the eIQ Portal window is closed after opening the Time Series Studio then that error comes up. Try relaunching Time Series Studio but keep the original eIQ Portal window open.  The eIQ Time Series Studio in eIQ Toolkit v1.17 is v1.3.4 but it says there's a newer version?  The eIQ Toolkit v1.17 contains an older version of eIQ Time Series Studio. The latest version can always be found on the eIQ Time Series Studio website. General AI/ML: What is Artificial Intelligence, Machine Learning, and Deep Learning? Artificial intelligence is the idea of using machines to do “smart” things like a human. Machine Learning is one way to implement artificial intelligence, and is the idea that if you give a computer a lot of data, it can learn how to do smart things on its own. Deep Learning is a particular way of implementing machine learning by using something called a neural network. It’s one of the more promising subareas of artificial intelligence today. This video series on Neural Network basics provides an excellent introduction into what a neural network is and the basics of how one works.  What are some uses for machine learning on embedded systems? Image classification – identify what a camera is looking at Coffee pods Empty vs full trucks Factory defects on manufacturing line Produce on supermarket scale Facial recognition – identifying faces for personalization without uploading that private information to the cloud Home Personalization Appliances Toys Auto Audio Analysis Wake-word detection Voice commands Alarm Analytics (Breaking glass/crying baby) Anomaly Detection Identify factory issues before they become catastrophic Motor analysis Personalized health analysis What is training and inference? Machine learning consists of two phases: Training and Inference Training is the process of creating and teaching the model. This occurs on a PC or in the cloud and requires a lot of data to do the training. eIQ is not used during the training process. Inference is using a completed and trained model to do predictions on new data. eIQ is focused on enhancing the inferencing of models on embedded devices. What are the benefits for “on the edge” inference? When inference occurs on the embedded device instead of the cloud, it’s called “on the edge”. The biggest advantage of on the edge inferencing is that the data being analyzed never goes anywhere except the local embedded system, providing increased security and privacy. It also saves BOM costs because there’s no need for WiFi or BLE to get data up to the cloud, and there’s no charge for the cloud compute costs to do the inferencing.  It also allows for faster inferencing since there’s no latency waiting for data to be uploaded and then the answer received from the cloud. What processor do I need to do inferencing of models? Inferencing simply means doing millions of multiple and accumulate math calculations – the dominant operation when processing any neural network -, which any MCU or MPU is capable of. There’s no special hardware or module required to do inferencing. However specialized ML hardware accelerators, high core clock speeds, and fast memory can drastically reduce inference time. Determining if a particular model can run on a specific device is based on: How long will it take the inference to run. The same model will take much longer to run on less powerful devices. The maximum acceptable inference time is dependent on your particular application. Is there enough non-volatile memory to store the weights, the model itself, and the inference engine Is there enough RAM to keep track of the intermediate calculations and output As an example, the performance required for image recognition will be very dependent on the model is being used to do image recognition. This will vary depending on how many classes, what size of images to be analyzed, if multiple objects or just one will be identified, and how that particular model is structured. In general image classification can be done on i.MX RT devices and multiple object detection requires i.MX devices, as those models are significantly more complex. eIQ provides several examples of image recognition for i.MX RT and i.MX devices and your own custom models can be easily evaluated using those example projects.  How is accuracy affected when running on slower/simpler MCUs? The same model running on different processors will give the exact same result if given the same input. It will just take longer to run the inference on a slower processor. In order to get an acceptable inference time on a simpler MCU, it may be necessary to simplify the model, which will affect accuracy. How much the accuracy is affected is extremely model dependent and also very dependent on what techniques are used to simplify the model. What are some ways models can be simplified? Quantization – Transforming the model from its original 32-bit floating point weights to 8-bit fixed point weights. Requires ¼ the space for weights and fixed point math is faster than floating point math. Often does not have much impact on accuracy but that is model dependent. Fewer output classifications can allow for a simpler yet still accurate model Decreasing the input data size (e.g. 128x128 image input instead of 256x256) can reduce complexity with the trade-off of accuracy due to the reduced resolution. How much that trade-off is depends on the model and requires experimentation to find. Software could rotate image to specific position using classic image manipulation techniques, which means the neural network for identification can be much smaller while maintaining good accuracy compared to case that neural network has to analyze an image that could be in all possible orientations. What is the difference between image classification, object detection, and instance segmentation? Image classification identifies an entire image and gives a single answer for what it thinks it is seeing. Object detection is detecting one or more objects in an image. Instance segmentation is finding the exact outline of the objects in an image. Larger and more complex models are needed to do object detection or instance segmentation compared to image classification.   What is the difference between Facial Detection and Facial Recognition? Facial detection finds any human face. Facial recognition identifies a particular human face. A model that does facial recognition will be more complex than a model that only does facial detection.  How come I don’t see 100% accuracy on the data I trained my model on? Models need to generalize the training data in order to avoid overfitting. This means a model will not always give 100% confidence , even on the data a model was trained on. What are some resources to learn more about machine learning concepts?  Video series on Neural Network basics  ARM Embedded Machine Learning for Dummies Google TensorFlow Lab Google Machine Learning Crash Course Google Image Classification Practica YouTube series on the basics of ML and TensorFlow (ML Zero to Hero Series) i.MX 8 i.MX RT Re: eIQ FAQ Hi David,   eIQ Toolkit 1.0.5 is using TensorFlow version is 2.3.2, so to use the GPU when training you will need to install cuDNN v7.6 and CUDA 10.2. If you have newer versions of those tools installed on your PC you may need to uninstall those first before installing the version needed for the 1.0.5 version of eIQ Toolkit. I've also updated the FAQ with this information and it will be in the documentation in the next version of eIQ Toolkit that is released. -Anthony Re: eIQ FAQ Hi @anthony_huereca , I am using eIQ tool on model training for i.MXRT1170 platform. I find eIQ tool is always use PC CPU resource, so when it perform the model training that will occupy around 60 ~ 80% CPU resource. But it not use any GPU resource. Is there any method to configure eIQ tool to use GPU resource on the model training ? In case that will have better performance on the AI training. Is it? Thanks. David  
View full article
Example_C40_Ip_ECC_Fault_Skip_S32K312_DS34_RTD2211_v1 ************************************************************************************************ * 详细说明: * 此示例展示了如何跳过在 C40_Ip_Read() 期间导致无法纠正的 ECC 错误异常的指令。 * ----------------------------------------------------------------------------------------------- * 测试硬件:S32312EVB-Q172 * MCU:S32K312 * 调试器:S32DS 3.4、PEMicro Multilink * 目标:internal_FLASH ************************************************************************************************* 回复: Example_C40_Ip_ECC_Fault_Skip_S32K312_DS34_RTD2211_v1 Hi @danielmartynek      RTD3.0.0 P01里有这个选项,RTD3.0.0 P07里则没有这个选项了。     目前已移植到RTD3.0.0 P07版本上验证可以了。     用C40_Ip_ReportEccUnCorrectedError();替换了C40_Ip_DsiHandler(); 回复: Example_C40_Ip_ECC_Fault_Skip_S32K312_DS34_RTD2211_v1 @danielmartynek  请问下在RTD3.0.0 P07下,C40_Ip_DsiHandler函数已经没有了,该怎么处理异常呢?请帮忙指导下,谢谢。
View full article
iMX8MP and Deserializers Hi all! We are using the i.MX 8M Plus in our Digital Video Registrator. We are currently tasked with modifying the design to connect at least two (4 better) cameras using SerDes chips. In researching this, I see that connecting the DS90UB960 or DS90UB954 might be problematic because the processor does not support virtual channels. Is there any information or positive experience regarding the connection of other deserializers (from TI, Analog Devices, THine Electronics, etc.)? Best regards, Serge Re: iMX8MP and Deserializers Hi, Thank you for your interest in NXP Semiconductor products, As you mention, serializers are not available for i.MX 8M Plus due to the lack of virtual channel, there is a reference for i.MX 8 series processors using i.MX8QM and i.MX8QXP, i.MX 95 supports VC and has a serializer reference as well. Regards Re: iMX8MP and Deserializers I understand that two cameras cannot be connected to a single MIPI interface using a deserializer. However, are there any proven deserializer solutions for connecting a single/two camera to a single/two CSI/MIPI interfaces? Is it possible to use, for example, the MAX96714 ? Re: iMX8MP and Deserializers Hi, No, there has not been any solutions proven like the one described, Regards, Re: iMX8MP and Deserializers That’s very strange. I personally saw and held in my hands a solution based on the THCV242A + iMXMP —though I don't recall whether it connected one camera or two... Re: iMX8MP and Deserializers Hi @sfatyushkin since the platform doesn't support virtual channel, you would only be able to stream from a single camera at a time per CSI/MIPI port. For example two deserializers each connected to one CSI/MIPI port. Here is a resource on GMSL if you wanna take a look. If you don't need continuous streaming or can tolerate a lower capture rate from all four sensors, another potential approach could be to implement a custom driver that switches between camera streams, starting and stopping each sensor as needed. Ideally, you'd also need a way to synchronize this with a userspace application to ensure frames are captured and associated with the correct camera. Best regards, Daniel Gonzalez Embedded SW Engineer at RidgeRun Developers wiki: https://developer.ridgerun.com Website: www.ridgerun.com
View full article
When using the FRDM-MCXN947's I3C interface for I2C communication, the Clk stretching capability fai Hello, I'm currently encountering a problem: I want to use the I3C interface of the FRDM-MCXN947 for I2C communication,but the slave device I'm connecting to experiences clock stretching during data preparation,so I have to wait for the slave device to release the SCL signal before data transfer can begin. I've tried using the configurable registers (such as MCONFIG[SKEW] = 0, MCONFIG[HKEEP] = 0b11, MCONFIG[MSTENA] = 0b11) from the MCXNP184M150F70RM reference file, but it doesn't seem to be working. How can I resolve this? #FRDM-MCXN947 #I3C  Communication & Control(I3C | I2C | SPI | FlexCAN | Ethernet | FlexIO) MCXN Re: When using the FRDM-MCXN947's I3C interface for I2C communication, the Clk stretching capability Hi @kevin_Jhuang  The register settings are currently applied before I3C_MasterInit(), so they may be overwritten by the SDK initialization. Please enable: masterConfig->disableTimeout = true; Then configure MSTENA = 3, HKEEP = 3, and SKEW = 0 after I3C_MasterInit(). Please clear the corresponding register fields before writing them instead of using |=. After initialization, please read back MCONFIG to verify that the settings are still active. Also provide the MSTATUS and MERRWARN values captured immediately after the clock-stretching failure. Please also confirm that SCL and SDA are configured for open-drain operation and that external pull-up resistors are installed. BR Harry Re: When using the FRDM-MCXN947's I3C interface for I2C communication, the Clk stretching capability Hi Harry: Thank you very much for your reply. I have tried setting MCONFIG again for testing. 1. In the test, disableTimeout was set to true. 2. The image shows the current register settings, including the values ​​of MCONFIG, MSTATUS, and MERRWARN, as well as the I2C bus signal. (The difference between configuration A and configuration B is the setting of MSTENA: Configuration A: MCONFIG[MSTENA] = 3, Configuration B: MCONFIG[MSTENA] = 1). 3. The SDA/SCL IO pins should be set to openDrainEnable = kPORT_OpenDrainDisable as per the example, and pull-up resistors(4.7K) should be present. Currently, it seems that the I2C bus stretching function cannot be implemented. Re: When using the FRDM-MCXN947's I3C interface for I2C communication, the Clk stretching capability Following the above reply,configure B picture Thank you Re: When using the FRDM-MCXN947's I3C interface for I2C communication, the Clk stretching capability Hi @kevin_Jhuang  I can reproduce the issue and will continue investigating it. I will update you once I have any findings. BR Harry Re: When using the FRDM-MCXN947's I3C interface for I2C communication, the Clk stretching capability Hi @kevin_Jhuang  I checked this issue with our internal team. Based on their testing, when MSTENA = 11b (I2C Controller mode) is used, the following conditions should also be met: PPBAUD = 0 I2CBAUD < 15 BR Harry
View full article
FRDM-i.MX95:支持 FRAMOS IMX900 和 H.264 1080p120 你好, 我想确认以下关于FRDM-i.MX95的信息: FRDM-i.MX95 目前是否支持 FRAMOS FSM:GO-IMX900C-M12-L102B-PM-A1Q1(索尼 IMX900 彩色传感器)? 如果支持,所需的传感器驱动程序、设备树配置和 NEO-ISP 调优文件是否可用?哪个BSP/SDK版本提供此功能? 这款摄像机能否通过 i.MX95 CSI/ISP 流水线以 120 FPS 或更高的帧速率运行 1920×1080 彩色图像? 要将此相机模块连接到 FRDM-i.MX95,需要哪种适配器板和电缆? i.MX95 硬件 VPU 是否支持 1920×1080 @ 120 FPS 的单流 H.264 编码? 在禁用 B 帧和低延迟设置的情况下,预期的输入到比特流延迟或最小内部缓冲是多少? 是否支持从相机/ISP 流水线到 H.264 硬件编码器的 DMA-BUF 零拷贝? 如果目前不支持 FRAMOS IMX900 模块,您能否推荐一款支持 FRDM-i.MX95 的彩色全局快门 MIPI CSI-2 摄像头,该摄像头能够以 1920×1080 @ 120 FPS 或更高的帧率拍摄? 谢谢! 图形与显示 Linux 多媒体 Re: FRDM-i.MX95: FRAMOS IMX900 and H.264 1080p120 Support 你好, 1> 这是我们合作伙伴支持的传感器之一,因此 NXP 并未完全支持它,我建议您联系 Framos 寻求帮助。 2> 如需了解更多信息,请联系 Framos,方法同上。 3> 2k@120FPS 达到 ISP 带宽限制,1080p 应该不会有问题,但请再次向 Framos 确认支持的功能。 4> 请向 Framos 查询是否有可用的资源。 5> 最大吞吐量为 4K@60fps,因此对于 1080p@120fps 应该是可以实现的。 6> 我们不提供 i.MX95 VPU 在低延迟模式下的具体输入到比特流延迟数据。这必须在具有目标软件配置的硬件上进行测量。 7> 是的,支持。 此致敬礼/Saludos, 阿尔多。
View full article
MIMXRT1052CVJ5B power supply problem As indicated by the MIMXRT1050HDUG, there are two versions of the MCU. How do I determine my specific version to guide my power supply design? i.MXRT 105x Re: MIMXRT1052CVJ5B供电问题 Thanks! Re: MIMXRT1052CVJ5B供电问题 Hi @Simon_CHan , Thank you for your interest in NXP's RT series products and for using the NXP community. You can refer to ERR011093 in Chip Errata for the i.MX RT1050. The Errata documentation states that this issue has been fixed in A1 silicon. Therefore, the simplest method is to check the chip silkscreen for Silicon Rev: A indicates A0, and B indicates A1. If it's version B, the issue has been fixed; if it's version A, you need to control DCDC_IN/DCDC_IN_Q within the 2.8 V–3.0 V range as required by Errata. I hope the above is helpful to you. Best Regards May
View full article
关于 S32K312 FlexCAN 中增强型 RX FIFO 支持的说明 你好, Here it says it supports这里写着支持 And here it says only for CAN FD而这里又写着仅支持 CAN FDI。我目前正在使用 S32K312,想请教一下关于 FlexCAN 增强型 RX FIFO 支持的具体情况。 据我所知,S32K312 FlexCAN 模块支持传统接收 FIFO。但是,在查看参考手册时,我发现一些章节表明Classical CAN支持增强型RX FIFO,而其他部分似乎表明不支持增强型RX FIFO。 请问 S32K312 中的 FlexCAN 模块是否支持增强型接收 FIFO 功能?如果支持,在使用经典 CAN 帧时是否存在任何具体的限制或条件? 如有任何澄清或提及相关文件,将不胜感激。 谢谢! Re: Clarification on Enhanced RX FIFO Support in S32K312 FlexCAN 您好, 问:如果 MCR[FDEN] 位被禁用(FlexCAN 处于经典 CAN 模式),控制器是否仍能支持增强型接收 FIFO 来接收经典 CAN 消息? A:是的,即使 FDEN=0,增强型 RXFIFO 仍可启用,且 FlexCAN 仅接受经典 CAN 消息,这些消息会根据设定的过滤条件,发送到常规 MB 或该增强型 RXFIFO。 问:如果此配置支持增强型 RX FIFO,是否有任何参考应用程序、示例项目或文档可以演示其用法? 答:您可以参考下面的示例,其中将 FlexCAN 的 FDEN 设置为 1,但如有需要,您可以在配置工具中轻松禁用该功能,同时还可以修改有效载荷和位时序。 https://community.nxp.com/t5/S32K-知识库/示例-S32K344-FlexCAN-IP-TX-RX-EnhanceRXFIFO-测试-S32DS3-4/ta-p/1536225 问:是否可以直接通过 MEX 配置工具配置增强型接收 FIFO,还是需要在应用程序代码中手动配置? A: 配置工具中仅提供少量配置选项: - 启用/禁用增强型接收 FIFO - 标准和扩展滤波器元素的数量 - 水印设置 滤波器表必须在代码中进行配置。请参阅上面的演示。 BR, Petr Re: Clarification on Enhanced RX FIFO Support in S32K312 FlexCAN 嗨,彼得, 感谢您的回复,关于此事我还有几个问题。 如果 MCR[FDEN] 位被禁用(FlexCAN 处于经典 CAN 模式),控制器是否仍能支持 增强型接收 FIFO 来接收经典 CAN 消息吗? 如果此配置支持增强型 RX FIFO,是否有任何参考应用程序、示例项目或文档可以演示其用法? 是否可以直接通过 MEX配置工具,还是需要在应用程序代码中手动配置? 谢谢 Re: Clarification on Enhanced RX FIFO Support in S32K312 FlexCAN 您好, 表 493 仅说明,如果在 FlexCAN 模块中启用了 CAN FD 功能(MCR[FDEN]),则无法启用和使用传统 RXFIFO。每个 FlexCAN 实例均支持传统 RXFIFO,但它无法接收 CAN FD 消息,仅支持经典 CAN 消息。正因如此,才推出了增强型 RXFIFO,它能够同时处理这两种情况。   通常,每个 FlexCAN 实例都支持 CAN FD。各实例在可用内存大小和增强的RXFIFO支持方面存在差异。 如果用户想同时启用 RXFIFO 和 CAN FD 选项,则需要增强 RXFIFO。Enhance RXFIFO 能够存储多达 20 条消息(包括经典 CAN 和 CAN FD)。但是它仅适用于大多数 S32K3 设备的单模块(FlexCAN 0)。 更多信息请参阅第73.3.8章增强型 RX FIFO 和 73.3.9设备 RM 的旧版 RX FIFO。 BR, Petr
View full article
S32K3 の LDREX/STREX/CLREX は SRAM で動作するようです。 少し前に質問をしました - https://community.nxp.com/t5/S32K/Understanding-Atomics-ie-STREX-LDREX-on-S32K3/mp/2356118 - 回答では、チェック対象のメモリがSRAMにある場合、ISR/IRQなどがメインスレッドと競合するのを防ぐために、LDREX/STREX/CLREXをシングルコアでのみ使用している場合でも、その動作に頼ることはできないと示唆しているように思えました。 テストを行った結果、期待通りに動作しているようです。LDREX/STREX/CLREXは単一コアからのアクセスを競合しないように設計されている、という点について設計チームから確認をいただけますでしょうか?DMAとCortex-M7コア間の排他的アクセスのようなものを防ぐことはできないと分かっていますが、コア自身との排他的アクセスはどうでしょうか? Re: LDREX/STREX/CLREX on S32K3 - seems to work in SRAM? こんにちは、 @kscz さん。 私もテストしてみましたが、その結果に基づいて議論を再開しました。 最新情報が入り次第、ご連絡いたします。 よろしくお願いいたします。 ダニエル Re: LDREX/STREX/CLREX on S32K3 - seems to work in SRAM? こんにちは、 @kscz さん。 SRAMにおける動作はTCMにおける動作と同じであるとの確認を得ました。以前の回答をそれに合わせて更新しました。ご指摘ありがとうございます。 BR、ダニエル
View full article
无法测量 LS1028A 评估板 J12 引脚上的 1PPS 信号? 启动开发板后,我使用 echo 1 > /sys/class/ptp0/ppt0/pps_enable 命令启用了 PPS 输出。然后,通过运行 cat /sys/class/pps/pps0/assert,我可以看到时间戳在递增。但是,我无法捕获 1588_PULSE_OUT2 引脚上的 PPS 信号。 我在论坛中搜索了类似的问题,然后通过参考 devicetree/bindings/ptp/ptp-qoriq.txt 文档修改了设备树。步骤如下 首先,我使用以下命令在主板上获得了 QORIQ_CLK_HWACCEL 3 的时钟值。数值为 400 MHz: root@ls1028ardb:# find /sys/kernel/debug/clk -name "clk_summary" -exec cat {} ; | grep -i hwaccel cg-hwaccel3 0 0 0 400000000 0 0 50000 Y deviceless no_connection_id cg-hwaccel0 0 0 0 400000000 0 0 50000 Y deviceless no_connection_id cg-hwaccel2 0 0 0 600000000 0 0 50000 Y f200000.display clk_core cg-hwaccel1 0 0 0 1200000000 0 0 50000 Y deviceless no_connection_id 所以我修改了设备树文件 fsl-ls1028a.dtsi 如下: ethernet@0,4 { compatible = "pci1957,ee02", "fsl,enetc-ptp"; reg = <0x000400 0 0 0 0>; clocks = <&clockgen QORIQ_CLK_HWACCEL 3>; little-endian; fsl,extts-fifo; // The following lines are newly added fsl,cksel = <1>; fsl,tclk-period = <10>; fsl,tmr-prsc = <100>; fsl,tmr-add = <0x40000000>; fsl,tmr-fiper1 = <0x3B9AC9F6>; fsl,max-adj = <2999999999>; }; 启动后,修改后的节点条目可见: root@ls1028ardb:~# ls /sys/class/ptp/ptp0/device/of_node/ clocks compatible fsl,cksel fsl,extts-fifo fsl,max-adj fsl,tclk-period fsl,tmr-add fsl,tmr-fiper1 fsl,tmr-prsc little-endian name reg 即使经过这些修改,我仍然无法正确捕获信号。因此,我检查了 RCW 值。详细日志如下 Reset Configuration Word (RCW): 00000000: 3c004010 00000030 00000000 00000000 00000010: 00000000 018f0000 0030c000 00000000 00000020: 020031a0 00002580 00000000 00003296 00000030: 00000000 00000010 00000000 00000000 00000040: 00000000 00000000 00000000 00000000 00000050: 00000000 00000000 00000000 00000000 00000060: 00000000 00000000 200e705a 00000000 00000070: bb580000 00000000 在 LS1028ARDBRM.pdf 文档中,我发现对于 1PPS 输出,EC1_SAI4_5_PMUX[835:833] 字段必须设置为 101。字地址是偏移量 0x68 处(字 26)的 32 位字,值为 0x200e705a。提取此字段:向右移动 1 并掩盖下方 3 位:(0x200e705a > > 1) & 0x7 = 0x5,即二进制 101 — 所以这也是正确的。但是,我仍然无法捕获信号。 我想知道我的设备树配置是否不正确,或者是否存在其他硬件限制。我附上了 ptp-qoriq.txt 文件、LS1028ARDBRM.pdf、以及示波器捕获以供参考。 Re: Unable to measure 1PPS signal on J12 pin of LS1028A evaluation board? 我用以下命令进行了环回测试,结果没有信号。CPLD 确实有可能没有正确路由信号。 root@ls1028ardb:~# find /sys/kernel/debug/ -name fiper1-loopback /sys/kernel/debug/0000:00:00.4/fiper1-loopback root@ls1028ardb:~# echo 1 > /sys/kernel/debug/0000:00:00.4/fiper1-loopback root@ls1028ardb:~# cat /sys/class/ptp/ptp0/fifo root@ls1028ardb:~# cat /sys/class/ptp/ptp0/fifo root@ls1028ardb:~# cat /sys/class/ptp/ptp0/fifo 我使用的 CPLD 软件版本是 LS1028ARDB_HDL_2020_0330_1829_V8。是否需要额外编程?还是这个版本有问题?至于路由问题,我会让我们的硬件团队进行检查。 Re: Unable to measure 1PPS signal on J12 pin of LS1028A evaluation board? 你好 文档支持 LS1028A 可以在 LS1028ARDB J12 上输出 PPS,但你的症状很可能指缺少主板 RCW/CPLD 多路复用器路由或外部 FIPER 引脚编程不完整,而不是缺乏 PPS 支持。 此致 回复: Unable to measure 1PPS signal on J12 pin of LS1028A evaluation board? 这是由于脉冲宽度设置得太小,所用的示波器无法捕获到它造成的。
View full article
我能否从 nxp 中取出胶带 我能否将我的芯片设计从 nxp 中剥离出来? Re: can i tape out from nxp 亲爱的拉吉-里特维克   感谢您联系恩智浦并对我们的产品感兴趣。 我们想澄清的是,恩智浦并不为外部芯片设计提供开放式代工或带出服务。通常情况下,需要定制硅带输出的客户会直接与台积电和 GlobalFoundries 等商业代工厂联系、 您能否告诉我们您的询问是否与任何特定的恩智浦产品或设备有关?如果需要,我们很乐意为您提供进一步的帮助。 如果需要,请随时提供更多详细信息,我们很乐意提供力所能及的帮助。 祝您愉快
View full article
Query Regarding nnshark and NPU Inference on MCM-i.MX8M-Plus Hi team, We are currently evaluating NPU inference and profiling on the MCM-i.MX8M-Plus platform from Compulab. We had initially raised this query with CompuLab support, and they advised us to contact NXP directly regarding nnshark usage and NPU validation. We attempted to integrate nnshark into the image and verified that the recipe builds successfully. However, no standalone nnshark executable is available on the target, and only library files such as libgstsharktracers.so and libgstshark.so are present. We would like clarification on whether nnshark is intended to be used only through GStreamer tracers/plugins or if a standalone utility is expected. Additionally, we tested TensorFlow Lite inference using the VX delegate and profiling enabled. While the delegate loads successfully, we would like guidance on validating proper NPU utilization and understanding expected CPU usage behavior during inference. I have attached the detailed procedure followed for nnshark integration and inference testing for reference. Could you please help clarify: Intended usage method for nnshark Whether a reference image/package exists with nnshark support Recommended approach for validating NPU execution Any recommended TensorFlow Lite models or pipeline optimizations for the NPU Thank you for your support. Re: Query Regarding nnshark and NPU Inference on MCM-i.MX8M-Plus Hi, Please find the attached log file and NNShark screenshot. Initially, I updated the MMC boot arguments by interrupting U-Boot during startup. After the system booted, I verified the BSP release version and executed the GStreamer pipeline after enabling NNShark profiling through environment variables. Thank you. Re: Query Regarding nnshark and NPU Inference on MCM-i.MX8M-Plus Hi @cris_m  While running the pipeline with the TensorFlow Lite VX delegate, the logs still report “accl = cpu”, which is causing confusion regarding whether inference is actually being offloaded to the NPU or not. >>>Please share your log file. Including the commands and methods you use to run the model. Whether nnshark is expected to provide a standalone executable or only GStreamer tracer libraries >>>NNShark is a GstShark-based analysis tool used to monitor multiple pipeline metrics for evaluating SoC hardware utilization.  >>>On the i.MX8M Plus, NNShark is primarily used for real-time profiling and performance validation of AI pipelines via the GStreamer/NNStreamer tracer. This is typically done by setting the GST_TRACERS and GST_DEBUG environment variables before running the GStreamer pipeline. You can get more details following below link: https://github.com/nxp-imx/nnshark How to conclusively verify NPU utilization during inference execution >>>Which version of BSP are you using? B.R Re: Query Regarding nnshark and NPU Inference on MCM-i.MX8M-Plus Thank you for your response and for sharing the reference document. I would like to mention that I have already followed the procedure described in Chapter 8.1 (Object detection pipeline example) and have shared the same details in the attached NPU_test.txt document earlier, along with screenshots/logs from the GStreamer pipeline execution. While running the pipeline with the TensorFlow Lite VX delegate, the logs still report “accl = cpu”, which is causing confusion regarding whether inference is actually being offloaded to the NPU or not. Additionally, my earlier query regarding nnshark usage was not addressed. Specifically, I would like clarification on: Whether nnshark is expected to provide a standalone executable or only GStreamer tracer libraries How nnshark is intended to be used for profiling/validation on i.MX8M Plus How to conclusively verify NPU utilization during inference execution Please also let me know if I may have missed any step during the setup or testing procedure. Could you please review the attached procedure/logs and help clarify these points? Thank you. Re: Query Regarding nnshark and NPU Inference on MCM-i.MX8M-Plus Hi @cris_m  Please refer to Chapter 8 (Vision Pipeline with NNStreamer) in the attachment. Also you can find how to run Machine Learning application on i.MX 8M Plus with NPU acceleration.  B.R Re: Query Regarding nnshark and NPU Inference on MCM-i.MX8M-Plus Hello, Could you please review the logs shared earlier and let us know if there are any issues with the procedure that was followed, or if any additional steps are required? Thank you. Re: Query Regarding nnshark and NPU Inference on MCM-i.MX8M-Plus Hi @cris_m  Please run the attachment .sh file. i have tested it on my imx8mp evk board without any problem. B.R Re: Query Regarding nnshark and NPU Inference on MCM-i.MX8M-Plus Yes. It worked. Thank you. Best regards
View full article
Relaying PCIe data between two endpoints via RC on iMX95 FRDM PRO As part of the patches attached with this blog, we will relay the pcie write transaction from Endpoint-A to Endpoint-B connected to iMX95FRDM PRO.   Linux-imx used - lf-6.18.2-1.0.0 Attached are the following files:-   imx95-19x19-frdm-pro-pcie0-ep-dtbs - EP A shall use the dtb built with this dtbs imx95-19x19-frdm-pro-pcie1-ep-dtbs - EP B shall use the dtb built with this dtbs rc_pcie_dma_relay.c - driver used on RC to relay pcie write from EP-A to EP-B conf_pcie0.sh - script to be executed on Endpoints A and B to configure the EPF driver //To build the dtb and relay kernel driver 1. git clone  git clone https://github.com/nxp-imx/linux-imx.git git checkout origin/lf-6.18.y 2. Copy the dtbs to arch/arm64/boot/dts/freescale/ Copy rc_pcie_dma_relay.c to drivers/pci/   3. Make the following changes as per this diff   diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile index aa3cfdf1aafc..56e3db653208 100644 --- a/arch/arm64/boot/dts/freescale/Makefile +++ b/arch/arm64/boot/dts/freescale/Makefile @@@ -1205,6 +1205,16 @@ dtb-$(CONFIG_ARCH_MXC) += imx95-15x15-frdm-8mic-reve.dt  dtb-$(CONFIG_ARCH_MXC) += imx95-19x19-frdm-pro.dtb imx95-19x19-frdm-pro-aud-hat.dtb + +dtb-$(CONFIG_ARCH_MXC) += imx95-19x19-frdm-pro-pcie0-ep.dtb +dtb-$(CONFIG_ARCH_MXC) += imx95-19x19-frdm-pro-pcie1-ep.dtb + +imx95-19x19-frdm-pro-pcie0-ep-dtbs := imx95-19x19-frdm-pro.dtb \ +                      imx95-19x19-frdm-pro-pcie0-ep.dtbo + +imx95-19x19-frdm-pro-pcie1-ep-dtbs := imx95-19x19-frdm-pro.dtb \ +                      imx95-19x19-frdm-pro-pcie1-ep.dtbo +  imx95-19x19-frdm-pro-os08a20-isp-dtbs := imx95-19x19-frdm-pro.dtb \                                          imx95-19x19-frdm-pro-os08a20.dtbo  dtb-$(CONFIG_ARCH_MXC) += imx95-19x19-frdm-pro-os08a20-isp.dtb   4. Add the following to drivers/pci/Makefile +obj-m      += rc_pcie_dma_relay.o 5. Trigger the kernel build. You will obtain rc_pcie_dma_relay.ko, imx95-19x19-frdm-pro-pcie0-ep.dtb and imx95-19x19-frdm-pro-pcie1-ep.dtb. 6. We are only using pcie0 M.2 Key M slots of Endpoint A and Endpoint B so you only need to upload this dtb to both the endpoint boards - imx95-19x19-frdm-pro-pcie0-ep.dtb and boot linux with it after passing 'iommu.passthrough=1' at uboot mmcargs. This is to disable smmu for our tests. RC will boot with the default dtb - imx95-19x19-frdm-pro.dtb 7. Connect the Endpoint-A to RC's K1 via M.2 Key M to Key M cable. Similarly connect the other Endpoint-B to other RC's K2 M.2 slot via Key M to Key M cable. 8. Execute this script on both the endpoints - ./conf_pcie0.sh 9. Then reboot the RC iMX95 FRDM Pro and ensure that you see both the endpoints:-   0000:01:00.0 and 0001:01:00.0 are the enumerated endpoints. 10. Upload rc_pcie_dma_relay.ko to the RC board and insert it like this:-  insmod rc_pcie_dma_relay.ko src_phys=0x910100000 dst_phys=0xa10100000 relay_len=0x100000 chunk_len=0x10000 you will observe similar logs on dmesg:-   [ 4949.082087] rc_pcie_dma_relay: init src=0x910100000 dst=0xa10100000 len=1048576 chunk=65536 [ 4949.082150] rc_pcie_dma_relay src_before: [0]=0xdeadbeef [1]=0xdeadbeef [2]=0xdeadbeef [3]=0xdeadbeef [ 4949.082171] rc_pcie_dma_relay dst_before: [0]=0x00000000 [1]=0x00000000 [2]=0x00000000 [3]=0x00000000 [ 4949.125779] rc_pcie_dma_relay dst_zeroed: [0]=0x00000000 [1]=0x00000000 [2]=0x00000000 [3]=0x00000000 [ 4949.141380] rc_pcie_dma_relay src_after: [0]=0xdeadbeef [1]=0xdeadbeef [2]=0xdeadbeef [3]=0xdeadbeef [ 4949.141427] rc_pcie_dma_relay dst_after: [0]=0xdeadbeef [1]=0xdeadbeef [2]=0xdeadbeef [3]=0xdeadbeef [ 4954.272981] rc_pcie_dma_relay: verify OK for 1048576 bytes [ 4954.273000] rc_pcie_dma_relay: DMA relay verify PASSED   11. Finally, via devmem5 on RC, you can verify the data of EP-A transferred to EP-B  ./devmem5 r 0xa10100000 w   IMX95EVK
View full article
when FRDM-A-S32K358 on sale? I heard that the FRDM-A-S32K358 is being released as a development board for the S32K358. When will this product be released? Digiikey says it will be released on May 18, 2026, but I would like to know the exact date. Re: when FRDM-A-S32K358 on sale? Hi I'm sorry, but for now I only see that the FRDM-A-S32K358 will be released in 2026 Q2, without a specific date. Best Regards, Robin
View full article