Jetson Nano & Xavier NX carrier board offers 3x M.2 sockets, 10x RS232/RS485 interfaces

Jetson Nano & Xavier NX Carrier Board

Geniatech NVJ100AI/NVJ100AIX is a carrier board fitted with either Jetson Nano or Jetson Xavier NX SoM with good expansion capabilities thanks to three M.2 sockets and ten RS232 and/or RS485 interfaces, plus the usual Gigabit Ethernet, USB ports, HDMI video interface, etc… Geniatech NVJ100AI/NVJ100AIX specifications: SoM Geniatech NVJ100AI  – NVIDIA Jetson Nano with CPU – Quad-core Arm Cortex A57 MPCore processor @ up to 1.43 GHz GPU – Maxwell GPU, 128 CUDA core up to 512 GFLOPS (FP16) System Memory – 4GB LPDDR4 Storage – 16GB eMMC flash AI Performance – Up to 472 GFLOPS in 10 Watts mode Geniatech NVJ100AIX – NVIDIA Jetson Xavier NX CPU – Hexa-core NVIDIA Carmel ARMv8.2 64-bit CPU with 6MB L2 + 4MB L3 cache GPU – 384-core NVIDIA Volta GPU with 48 Tensor Cores Dedicated AI accelerators – 2x NVDLA Engines, 7-Way VLIW Vision Processor System Memory – 8GB LPDDR4 Storage – 16GB […]

u-blox introduces WiFI 5/6 & Bluetooth 5 M.2 cards

u-blox is well known for its wireless modules be it WiFi, Bluetooth, GPS, or cellular connectivity that are soldered unto CPU modules or boards. But the company has now introduced two M.2 cards with WiFi 5 or WiFi 6 and Bluetooth 5.x that work with NXP i.MX evaluation and development boards. M2-JODY-W2 M.2 card The M2-JODY-W2 card comes with the following features: Connectivity Wi-Fi 5 1×1 SISO IEEE 802.11ac data rates up to 433 Mbit/s (PHY, MCS9), beamforming Supports 802.11d/e/h (DFS)/i/k/r/u/v/w/ai Wi-Fi 20, 40, and 80 MHz channels Bluetooth BR/EDR and Bluetooth low energy v5.0 supporting 2 Mbit/s Access point mode for up to 8 stations 2x u.FL antenna connectors Host interfaces SDIO & UART host interfaces PCM interface for Bluetooth audio Security Hardware encryption engines: AES and TKIP WPA, WAPI, WPA2, WPA3, WPS, and Easy Connect Dimensions – M.2 Type 2230 Key E form factor Certifications – Chipset is […]

IZIRUN open-hardware STM32 development boards expose GPIOs through M.2 connector (Crowdfunding)

M.2 sockets are typically used to connect wireless or storage expansion boards to laptops, computers, and SBC’s. But nothing precludes them from being used for another purpose, and earlier this year we wrote about Sparkfun MicroMod MCU boards with an M.2 connector for GPIOs, I2C, SPI, etc… IZITRON has expanded the concept with three slightly larger (IZIRUN) STM32 boards routing more IOs to the M.2 connector, and additional features such as built-in EEPROM and buttons. IZIGOBOARD carrier board is then used to host the STM32F0, STM32F4, or STM32F7 board in order to ease development. IZIRUN STM32 development boards IZIRUN boards specifications: Microcontroller IZIRUNF0 – STMicro STM32F030CCT6 Cortex-M0 MCU @ 48 MHz with 256KB flash, 32 KB SRAM IZIRUNF4 – STMicro STM32F407VET6 Cortex-M4 MCU @ 168 MHz with 512KB flash, 192KB SRAM IZIRUNF7 – STMicro STM32F769NIH6 Cortex-M7 MCU @ 216 MHz with 2MB KB flash, 532KB SRAM On-board RAM – IZIRUNF7 […]

Intel 5G Solution 5000 5G M.2 module developed with MediaTek, Fibocom

Qualcomm very recently unveiled Snapdragon X65 and X62 5G M.2 card reference designs to help OEM’s develop their own 5G modules for integration into PC’s and CPE’s. But as one should have expected, more options are coming, and Intel have now announced their own “5G Solution 5000” 5G M.2 card for laptops at Computex 2021 in collaboration with MediaTek and Fibocom. Fibocom FM350-GL (Intel 5G Solution 5000) specifications: Modem technologies – 5G NR, 4G LTE, 3D WCDMA Frequency bands – Sub 6GHz for global coverage Data throughput 5G NR – Up to 4.7 Gbps downlink; up to 1.25 Gbps uplink 4G LTE – Up to 1.6 Gbps Cat 19downlink; up to 150 Mbps uplink Built-in eSIM Host interface – PCIe Gen 3 Dimensions – 30 x 52  x2.3 mm (M.2 card) Temperature Range – -10 to +55°C The 5G module targets platforms built upon Intel Tiger Lake and Alder Lake […]

Notecard LTE Cat-M / NB-IoT M.2 modem sells for $49+ with 10 years of connectivity

If the IoT is ever going to take off, it needs low-cost hardware and connectivity. LoRaWAN is free, apart from the hardware costs, but for projects that need wider coverage and/or higher bitrate cellular connectivity is the way to go and we’ve seen in the past that Hologram offers a free developer SIM card for global IoT projects plus some low-cost cellular IoT plans, as well as 1CNE plans to offer a 10-year plan for 10 Euros. Blues Wireless has taken a different approach as they combine hardware and cellular connectivity with their Notecard LTE-IoT modems (LTE Cat 1/Cat M or NB-IoT) shipping for 10 years of connectivity for up to 500MB data. Notecard has four variants with the following key features and specifications: MCU – Arm Cortex-M4 MCU with 2MB flash Cellular connectivity NOTE-NBGL-500 – Narrowband Cat-M/NB-IoT/GPRS (Global) via  Quectel BG95-M3 modem NOTE-NBNA-500 – Narrowband Cat-M/NB-IoT (North America) via […]

M1108 AI accelerator chip delivers up to 35 TOPS for high-end edge AI applications

Last week, Mythic announced a breakthrough with compute-in-memory technology based on a 40 nm process with what the company claims to be the industry’s first Analog Matrix Processor. The M1108 AMP AI accelerator chip targets high-end edge AI applications including smart home, AR/VR, drones, and is said to set a benchmark in the industry for high performance and low power in a single cost-effective device, also available in M.2 and PCIe form factors. The M1108 comes with an array of flash cells, ADCs, a 32-bit RISC-V nano-processor, a SIMD vector engine, SRAM, and a high-throughput Network-on-Chip (NOC) router. With 108 AMP tiles, the M1108 provides up to 35 Trillion-Operations-per-Second (TOPS) enabling ResNet-50 at up to 870 fps. This enables a power-efficient execution of complex AI models such as ResNet-50, YOLOv3, and OpenPose Body25. The industry leader NVIDIA also has a similar AI accelerator chip NVIDIA Xavier AGX which delivers up […]

InferX X1 SDK, PCIe and M.2 Boards for edge inference acceleration

Last week, Flex Logix announced the InferX X1 AI Inference Accelerator at Linley Fall Conference 2020. Today, they announced the InferX X1 SDK, PCIe board, and M.2 board.  InferX X1 Edge Inference SDK  The  InferX Edge Inference SDK is simple and easy. The input to the compiler can be an open-source high-level, hardware-agnostic implementation of the neural network model that can be TensorFlow Lite or ONNX model. The compiler takes this model and looks for the available X1 resources and generates a binary executable file. This goes to the runtime which then takes the input stream, for example, a live feed from a camera. The user has to specify which compiler model, then the InferX X1 driver takes it and sends it to hardware.  The binary file generated is fed to InferX X1 through the runtime. Then it takes the input data stream with a user-specified model and gives the […]

Hailo-8 M.2 and mini PCIe AI accelerator cards deliver up to 26 TOPS

[Update Sep 3, 2020: The post has been edited to correct Google Coral M.2 power consumption] If you were to add M.2 or mPCIe AI accelerator card to a computer or board, you’d mostly have the choice between Google Coral M.2 or mini PCIe card based on the 4TOPS Google Edge TPU, or one of AAEON AI Core cards based on Intel Movidius Myriad 2 (100 GOPS) or Myriad X (1 TOPS per chip). There are also some other cards like Kneron 520 powered M.2 or mPCIe cards, but I believe the Intel and Google cards are the most commonly used. If you ever need more performance, you’d have to connect cards with multiple Edge or Movidius accelerators or use one M.2 or mini PCIe card equipped with Halio-8 NPU delivering a whopping 26 TOPS on a single chip. Hailo-8 M.2 accelerator card key features and specifications: AI Processor – […]