edge ai News - CNX Software - Embedded Systems News

edge ai

Posted on by Jean-Luc Aufranc (CNXSoft) - 8 Comments on UP Squared Pro TWL AI Dev Kit Review – Intel N150 + Hailo-8L accelerator tested on Ubuntu 24.04

UP Squared Pro TWL AI Dev Kit Review – Intel N150 + Hailo-8L accelerator tested on Ubuntu 24.04

Intel N150 SBC Hailo-8L module with Heatsink

I’ve been asked to review three Intel-based UP AI development kits running Ubuntu 24.04 Pro. Last time, I tested the UP TWL SBC with Nx Meta and UP AI Toolkit, and most AI workloads would pass, but since these were running on the Intel N150 CPU or GPU, the performance was not optimal for most. I’ll now switch to the UP Squared Pro TWL “mid-range” AI devkit review with another Intel Processor N150 SBC fitted with a 13 TOPS Hailo-8L M.2 AI accelerator. Both the UP TWL and UP Squared Pro TWL come with a 64GB eMMC flash, and I found out it was rather tight since AI software and models can take a lot of space. The UP Squared Pro TWL has a few M.2 sockets, so I’ll install an NVMe SSD to expand storage before installing the UP AI toolkit. As usual, I’ll run a few benchmarks and […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on AMD Ryzen Embedded 8840U COM Express Type 6 Compact module takes up to 128GB DDR5

AMD Ryzen Embedded 8840U COM Express Type 6 Compact module takes up to 128GB DDR5

SolidRun Ryzen R8000 COM6 Compact Module

SolidRun has unveiled a new COM Express Type 6 Compact module powered by the AMD Ryzen Embedded 8840U Series with up to 39 TOPS of AI performance for industrial, medical, automation, and edge AI applications. The module supports up to 128GB DDR5 of memory via two SO-DIMM sockets, on-module M.2 NVME SSD storage, and features an Intel i226 2.5GbE controller. It exposes I/Os through standard board-to-board connectors, including 16-lane PCIe Gen4, four DisplayPort video outputs, eDP or LVDS display interface, two SATA, various USB ports, and more. Ryzen R8000 CoM6 specifications: SoC – AMD Ryzen Embedded 8840U CPU – 8-core/16-thread Zen4 processor up to 3.3 GHz / 5.1 GHz (Turbo) GPU – AMD Radeon 780M with 12x Compute Units @ 2700 MHz (RDNA3 graphics) AI 16 TOPS NPU (AMD XDNA) Total combined 39 TOPS of AI performance Memory – 2x SODIMM DDR5-5600 with/without ECC up to 128GB RAM Storage – […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 4 Comments on NestDisk – An Intel N150 NAS, mini PC, and AI Box with four M.2 PCIe slots

NestDisk – An Intel N150 NAS, mini PC, and AI Box with four M.2 PCIe slots

NestDisk NAS Mini PC AI Box

Youyeetoo NestDisk in an Intel N150 mini PC that can be used as a mini NAS or AI box, thanks to four M.2 PCIe slots that can be fitted with NVMe SSDs or AI accelerator cards and two 2.5GbE network ports. The computer features 12GB LPDDR5 of memory, a 64GB eMMC flash, two HDMI 2.1 ports, a headphone jack, WiFi 6 connectivity, a full-function USB-C port, and three USB 3.2 ports. It’s not a fanless design, since it’s actively cooled with a 30mm internal “silent fan”, and an external USB dual fan accessory is available as an option. NestDisk specifications: SoC Intel Processor N150 (default) Quad-core “Twin Lake” processor @ up to 3.6 GHz (Turbo) with 6MB cache GPU – 24EU Intel UHD graphics @ 1000 MHz Options for Processor N250, N350, or N350 CPUs (but not for sale yet) Memory – 12GB LPDDR5 (option for 6GB, 16GB); note: soldered […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 2 Comments on Edgi-Talk machine learning development kit features Infineon PSOC Edge E84 Edge AI SoC (Crowdfunding)

Edgi-Talk machine learning development kit features Infineon PSOC Edge E84 Edge AI SoC (Crowdfunding)

Edgi-Talk machine learning platform

Edgi-Talk is a machine learning platform/development kit powered by an Infineon PSOC Edge E84 Arm Cortex-M55/M33 SoC featuring Arm Helium, an Arm Ethos-U55 micro NPU, and an ultra-low-power NNLite neural network accelerator, all of which enable AI/ML processing at varying power/performance levels. The devkit also comes with 128 MB PSRAM, 128MB QSPI flash, a 4.3-inch capacitive touchscreen display, two digital microphones, a speaker, WiFi 6 and Bluetooth LE 6.0 wireless connectivity, motion and environmental sensors, as well as a 40-pin Raspberry Pi header and two PMOD connectors for expansion. Edgi-Talk specifications: SoC – Infineon PSOC Edge E84 CPU Arm Cortex-M55 @ 400 MHz with FPU, MPU, Arm Helium support, 256KB i-TCM, 256KB D-TCM, and 5MB SRAM Arm Cortex-M33 @ 200 MHz with 1MB SRAM, 64KB ROM GPU – Low-power 2.5D GPU NPU – Dual architecture Arm Ethos-U55 NPU + NNLITE NPU System Memory – 128 MB PSRAM Storage 128 MB […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on COM Express Type 6 module targets Edge AI applications with an up 99 TOPS Intel Core Ultra 9 “Arrow Lake” CPU

COM Express Type 6 module targets Edge AI applications with an up 99 TOPS Intel Core Ultra 9 “Arrow Lake” CPU

COM Express Type 6 Intel Core Ultra 9 285H Arrow Lake CPU module

AAEON COM-ARHC6 is a COM Express Type 6 Compact module powered by a choice of Intel Arrow Lake processors up to the 16-core Core Ultra 9 285H processor, delivering up to 99 TOPS for high-performance Edge AI applications such as diagnostic imaging equipment and automated optical inspection. The Computer-on-Module features two SO-DIMM sockets for up to 128GB DDR5 at 6400MHz, an optional 256GB NVMe SSD BGA chip, a 2.5GbE controller, two MIPI CSI connectors, and two standard 220-pin board-to-board connectors exposing SATA, display (HDMI, DP, LVDS/eDP, VGA), SATA, and USB interfaces, as well as several PCIe and PEG interfaces. COM-ARHC6 COM Express Type 6 Compact Arrow Lake Computer-on-Module AAEON COM-ARHC6 specifications: Arrow Lake-H SoC Intel Core Ultra 5 225H 14-core (4P+8E+2LPE) processor up to 4.9 GHz (P) / 4.3 GHz (E) / 2.5 GHz (LPE) with 18MB cache, 7x Xe Intel Arc 130T GPU (63 TOPS), Intel AI Boost (13 […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 4 Comments on Banana Pi BPI-CM6 – A SpacemiT K1 RISC-V system-on-module compatible with Raspberry Pi CM4/CM5 carrier boards

Banana Pi BPI-CM6 – A SpacemiT K1 RISC-V system-on-module compatible with Raspberry Pi CM4/CM5 carrier boards

Banana Pi BPI-CM6 and carrier board

Banana Pi BPI-CM6 system-on-module (SoM) is powered by a SpacemiT K1 octa-core RISC-V processor and compatible with most carrier boards for the Raspberry Pi CM4 or CM5 modules. It ships with 8GB LPDDR4 and 16GB eMMC flash by default, a Gigabit Ethernet PHY, and a WiFi 5 and Bluetooth 4.1 wireless module. It exposes most interfaces through three 100-pin board-to-board connectors with HDMI 1.4, MIPI DSI, three MIPI CSI, five PCIe 2.1 lanes, USB 3.2/2.0 interfaces, and more. While it can work with Raspberry Pi CM4/CM5 carrier boards using two of the B2B connectors, the company also designed the BPI-CM6 IO carrier board to make full use of all the interfaces, especially the PCIe lanes. Banana Bi BPI-CM6 SoM Let’s check the module itself first. Banana Pi BPI-CM6 specifications: SoC – SpacemIT K1 CPU – 8-core X60 RISC-V (RV64GCVB) processor @ 1.6 GHz (roughly Cortex-A55 equivalent) GPU – Imagination IMG […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on COM-HPC Mini Computer-on-Module (CoM) features up to Intel Core Ultra 7 255H “Arrow Lake” processor

COM-HPC Mini Computer-on-Module (CoM) features up to Intel Core Ultra 7 255H “Arrow Lake” processor

COM-ARHm COM-HPC Mini module

AAEON HPC-ARHm is a COM-HPC Mini R1.2 module powered by a choice of 28W Intel Core Ultra Arrow Lake and Meteor Lake processors with Intel Arc/Arc 140T/130T GPU and up to 96 TOPS of combined AI performance. The Computer-on-Module supports up to 64GB LPDDR5x, offers three 4K-capable display interfaces through two DDI (DP/HDMI) and one eDP interface, dual 2.5GbE networking, twelve USB interfaces, including four 10 Gbps USB 3.2, sixteen PCIe Gen4/Gen3 lanes, and more. It primarily targets Edge AI solutions such as UAVs, robots, IC testing equipment, and healthcare imaging devices. HPC-ARH-m COM-HPC Mini module specifications: Meteor Lake-H or Arrow Lake-H SoC (one or the other) Intel Core Ultra 5 125H 14-core/18-thread (4P+8E+2LPE) processor @ up to 4.9 / 3.6 / 2.5 GHz with 18MB cache, 7x Xe-Cores Intel Arc graphics @ 2.2 GHz (18 TOPS), Intel AI Boost NPU (11 TOPS); PBP: 28W Intel Core Ultra 7 155H […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on ASUS IoT PE3000N – An MIL-STD-810H-grade, modular NVIDIA Jetson T5000 Edge AI platform for robotics and automation solutions

ASUS IoT PE3000N – An MIL-STD-810H-grade, modular NVIDIA Jetson T5000 Edge AI platform for robotics and automation solutions

ASUS Jetson T5000 Edge AI computer 10GbE Fakra camera connectors

Debashis just wrote about the Firefly EC-ThorT5000 embedded PC powered by an NVIDIA Jetson Thor T5000 system-on-module yesterday, and the ASUS IoT PE3000N is another rugged, modular Edge Platform powered by the 2,070 FP4 TFLOPS SoM offering MIL-STD-810H compliance, 12-60V input, 25GbE links, and support for up to sixteen GMSL cameras. The PE3000N features one HDMI 2.0 video output, GbE and 10GbE RJ45 ports, M.2 sockets for storage and wireless expansion, a PCIe x4/x8 slot, and several USB ports, as well as four 25GbE links and AGX CSI connector for up to 16x GMSL cameras for “high-bandwidth sensor fusion and advanced machine vision”, even in the most challenging environments. The Jetson T5000 embedded system also offers a scalable chassis and modular I/O layers that support interfaces such as PoE, GMSL, CAN, and QSFP28 within a compact 2U height. ASUS IoT PE3000N specifications: SoM – NVIDIA Jetson Thor T5000 module CPU […]

Banana Pi BPI-R4 Pro networking SBC