Texas Instruments MSPM0G5187 and AM13Ex MCUs integrate TinyEngine NPU for Edge AI applications
Texas Instruments MSPM0G5187 and AM13Ex are two new microcontroller (MCU) families featuring the company's TinyEngine neural processing unit (NPU) to enable low-latency, high-efficiency Edge AI/Machine Learning inference on the chips. TI claims that the TinyEngine NPU can run AI models with up to 90 times lower latency and more than 120 times lower energy utilization per inference than similar MCUs without an accelerator. The MSPM0G5187 is a general-purpose, low-power Arm Cortex-M0+ MCU, while the AM13Ex Arm Cortex-M33 microcontroller targets real-time motor control, starting with the AM13E23019 SKU. TI MSPM0G5187 general-purpose Cortex-M0+ MCU Key features and specifications: CPU - Arm Cortex-M0+ @ 80 MHz Memory - 32 KB RAM with ECC Storage - 128 KB flash with ECC, 8 KB data flash with ECC Accelerators TinyEngine NPU for AI/ML delivering up to 2.56GOPS (Giga Operations Per Second) at 80MHz MATHACL math accelerator Peripherals USB - 1x USB 2.0 (12 Mbps) Audio
NXP i.MX 93W wireless MPU SiP pairs dual-core Arm Cortex-A55 processor with NXP iW610 WiFi 6, Bluetooth LE, and 805.15.4 radio
NXP i.MX 93W is the company's first integrated wireless MPU System-in-Package (SiP) and combines a dual-core Cortex-A55 processor (NXP i.MX 93) with an iW610 WiFi 6, Bluetooth LE, and 802.15.4 tri-radio into a single chip. The 14.2 x 12 mm package also includes all the external radio components needed for wireless connectivity, replacing up to 60 discrete components on the PCB. NXP says it reduces the PCB area, simplifies PCB design and regulatory approval, and speeds up time-to-market. NXP i.MX 93W specifications: CPU Dual-Core Arm Cortex-A55 at up to 1.7 GHz Arm Cortex-M33 core at 250 MHz for real-time control GPU - 2D graphics accelerator AI accelerator - Arm Ethos-U65 microNPU Memory I/F - Up to 3.7GT/s 16-bit LPDDR4/LPDDR4X with inline ECC Storage I/F - 2x SD 3.0/SDIO 3.0/eMMC 5.1 Display Interfaces MIPI DSI up to 1080p60 LVDS up to 720p60 24-bit parallel RGB Camera Interface - 2-lane MIPI CSI up
F&S FSSM8MP SMARC Module Features NXP i.MX 8M Plus with Dual GbE and Edge AI
FRANK OS 1.0 porta l’esperienza dei desktop anni ’90 nel mondo dei microcontroller con finestre sovrapponibili, applicazioni integrate e un’interfaccia che richiama Windows 95. #FRANKOS #FreeRTOS #RP2350 #Microcontroller
FRANK OS 1.0 Launches With a Retro Windows 95-Like Desktop
｢ Unlike typical desktop systems, FRANK OS is not based on the Linux kernel. Instead, it is built on the real-time operating system FreeRTOS, commonly used in embedded and IoT devices. On this RTOS foundation, the project implements its own graphical environment, system libraries, and applications ｣
#frankos #freertos #windows95 #iot #embedded #retro
https://linuxiac.com/frank-os-launches-with-a-retro-windows-95-like-desktop/
Qualcomm Snapdragon Wear Elite wearable platform offers 5G RedCap, WiFi 6, Bluetooth 6.0, built-in AI accelerator
Qualcomm Snapdragon Wear Elite is described as the "world’s first Personal AI wearable platform", and features an NPU for on-device AI delivering up to 12 TOPS of performance at low power, supporting 2B parameter models. It delivers up to 5x single-core CPU improvement and up to 7x faster GPU compared to the previous-generation Snapdragon W5+ Gen 2 Wearable Platform while offering up to 30% more battery life for multi-day battery life, thanks to a 3nm architecture. The new Snapdragon Wear Elite platform also supports fast charging with up to 50% charge in under 10 minutes. Snapdragon Wear Elite specifications: CPU - Up to 2.1 GHz GPU Qualcomm Adreno 3D GPU supporting OpenGL ES 3.2, Vulkan 1.2, and OpenCL 2.0 APIs 2.5D GPU co-processor clocked at up to 500 MHz ISP - Qualcomm Spectra AI accelerator - Qualcomm Hexagon NPU; up to 12 TOPS of AI performance; support for up tp 2B
STM32 + FREERTOS + SDIO + FATFS
Подключение SD-карты к микроконтроллеру — классическая задача, но путь от инициализации аппаратного интерфейса до работы с файлами в многозадачной среде усыпан скрытыми камнями. В этой статье я на практике разберу полный цикл интеграции SDIO, файловой системы FatFs и ОСРВ FreeRTOS на STM32.
Excited to speak at #OCX26 this April in Brussels! My session will compare #FreeRTOS, #Zephyr, and Eclipse #ThreadX — helping you pick the right open source RTOS for your next project.
OCX is packed with sessions for everyone in open source, embedded, and beyond.
Don’t miss out: https://www.ocxconf.org/event/2026/register
AMD launches Ryzen AI Embedded P100 and X100 processors with up to 50 TOPS of AI performance
morgan
cnx-software.com
LinuxGizmos.com
Linux Easy
jbz
Habr
BlueberryCoder