artificial intelligence

Posted on by Jean-Luc Aufranc (CNXSoft) - 21 Comments on Duo 256M is a compact SBC based on SG2002 multi-architecture SoC

Duo 256M is a compact SBC based on SG2002 multi-architecture SoC

Duo 256M SBC

Duo 256M is a small board powered by SOPHGO SG2002 multi-architecture Arm/RISC-V/8051 SoC with 256MB of on-chip RAM and a 1 TOPS NPU, a microSD card for storage, a camera connector, a USB-C port for power and programming, and two headers for GPIO expansion. We covered the SOPHGO SG2002 (and SG2000)  Arm+RISC-V+8051 AI SoC earlier this month saying a couple of boards were expected very soon. We’ve already covered Sipeed LicheeRV Nano with optional Ethernet or WiFi 6, and now we’ll look at the Duo 256M designed by Milk-V Technology in more detail since it’s available now. Duo 256M specifications: SoC – SOPHGO SG2002 Main core – 1GHz 64-bit RISC-V C906 or Arm Cortex-A53 core (selectable) Minor core – 700MHz 64-bit RISC-V C906 core Low-power core – 25 to 300MHz 8051 MCU core NPU – 1 TOPS INT8, supports BF16 Integrated 256MB DDR3 (SiP) Storage MicroSD card slot 32Gbit NAND […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 11 Comments on Testing AMD Ryzen 9 7940HS’ AI Engine in Windows 11

Testing AMD Ryzen 9 7940HS’ AI Engine in Windows 11

AMD Ryzen 7940HS AI Engine Image Sorting

Some of the newer AMD Ryzen processors come with an AI Engine (also called NPU or IPU) that works in Windows 11 including the Ryzen 9 7940HS, Ryzen 7 7840HS, Ryzen 5 7640HS, Ryzen 7 7840U, and Ryzen 5 7640U. I’ve just completed the review of the GEEKOM A7 mini PC powered by an AMD Ryzen 9 7940HS CPU with Windows 11 – but need to wait before publishing it – so I decided to try the AI engine on the Ryzen 9 7940HS processor. The AI Engine relies on AMD XDNA architecture, and AMD provides instructions to get started with examples, demos, and developer resources. So I decided to try some examples, but for some reasons I’ll explain below, I eventually had to settle for some demos. Ryzen AI software installation (for the demos) The examples hosted on GitHub require us to install dependencies for the Ryzen AI software […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 14 Comments on SOPHGO SG2000/SG2002 AI SoC features RISC-V, Arm, and 8051 cores, supports Android, Linux, and FreeRTOS

SOPHGO SG2000/SG2002 AI SoC features RISC-V, Arm, and 8051 cores, supports Android, Linux, and FreeRTOS

SOPHGO SG2000 SG2002 block diagram

SOPHGO SG2000 and SG2002 are new SoCs featuring a bunch of RISC-V and Arm cores capable of running Linux, Android, and FreeRTOS simultaneously, and to maximize the fun an 8051 MCU core is also in the mix along with a 0.5 TOPS (SG2000) or 1 TOPS (SG2002) AI accelerator. More specifically we have one 1GHz C906 64-bit core capable of running Linux, one 1GHz Arm Cortex-A53 for Linux or Android, another 700 MHz C906 RISC-V core for FreeRTOS, and a 300 MHz 8051-core for real-time I/Os, as well as 256MB or 512MB SiP DRAM. The chip is designed for AIoT applications such as Smart IP cameras, facial recognition, and smart home devices. SOPHGO SG2000/SG2002 specifications: CPU cores 1x C906 64-bit RISC-V core @ 1GHz 1x C906 64-bit RISC-V core @ 700MHz 1x Arm Cortex-A53 core @ 1GHz MCU – 8051 8-bit microcontroller core @ 25 to 300 MHz with 6KB […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 1 Comment on Sapphire Edge+ VPR-4616-MB mini-ITX motherboard features “AMD Embedded+” architecture with Ryzen R2314 & Versal VE2302

Sapphire Edge+ VPR-4616-MB mini-ITX motherboard features “AMD Embedded+” architecture with Ryzen R2314 & Versal VE2302

AMD Embedded+ mini-ITX motherboard

Sapphire Edge+ VPR-4616-MB is a new mini-ITX motherboard on the “new” AMD Embedded+ “architecture” comprised of an AMD Ryzen Embedded R2314 processor and an AMD Versal AI Edge VE2302 adaptive SoC (also called FPGA SoC…). The motherboard supports up to 64GB ECC/non-ECC DDR4 memory for the CPU, 8GB of memory for the adaptive SoC, supports SATA and NVMe storage, dual video output, 2.5GbE networking, and offers a range of USB ports and M.2 sockets for expansion. AMD Embedded+ solutions target sensor fusion, AI inferencing, industrial networking, control, and visualization applications. SAPPHIRE Edge+ VPR-4616-MB specifications: AMD Embedded+ Architecture Adaptive SoC Subsystem Main IC – AMD Versal AI Edge VE2302 with dual Arm Cortex-A72 core processor @ up to 1.6 GHz, dual-core Arm Cortex-R5F, 23 TOPS AI engine, FPGA fabric, etc… System Memory – 2x 4GB LPDDR4 Storage 1Gbit OSPI NOR flash for local boot 64 Kbit EEPROM for Board-ID Expansion 160-pin […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on DFI MTH968 Intel Core Ultra “Meteor Lake” COM Express module to power industrial AI PCs

DFI MTH968 Intel Core Ultra “Meteor Lake” COM Express module to power industrial AI PCs

Intel Core Ultra Meteor Lake COM Express

DFI MTH968 is a COM Express Compact Type 6 computer-on-module equipped with an Intel Core Ultra Meteor Lake processor designed for industrial AI PCs thanks to the integrated Neural Processor Unit (Intel AI Boost) and designed for industrial automation, smart transportation, and smart agriculture. It’s not quite the first COM Express module based on the new Core Ultra Meteor Lake SoCs, as we previously covered the ADLINK cExpress-MTL and conga-TC700 with a similar range of features, and the MTH968 provides another alternative with the company highlighting a fanless wide temperature design operating from -40°C to 85°C, DDR5 memory, and NVMe SSD storage (soldered on module). DFI MTH968 specifications: Meteor Lake U/H-series SoC (one or the other) Intel Core Ultra 7 165H 16-core (6P+8E+2LPE) processor @ 0.9 / 1.4 / 5.0 GHz (Turbo) with 24MB cache, 8x Xe-cores Intel Arc graphics @ 2.3 GHz, Intel AI Boost NPU; TDP: 28W Intel […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on PANZER-PLUS fanless AIoT computer to support Ubuntu 24.04, Android 14, Yocto 5.0

PANZER-PLUS fanless AIoT computer to support Ubuntu 24.04, Android 14, Yocto 5.0

PANZER-PLUS fanless AIoT gateway

Taiwan-based MayQueen Technologies has recently introduced the PANZER-PLUS fanless AIoT computer powered by an NXP i.MX 8M Plus Arm SoC with support for Ubuntu 22.04, Android 12/13, and Yocto 4.0 “Kirkstone”, but the company also claims it is working on Ubuntu 24.04 and Android 14 operating systems, as well as Yocto 5.0 “Scarthgap”. The company initially pinged us in 2018 about its NXP iMX6UL-powered PANZER fanless box PC and contacted us again last week with the new PANZER-PLUS model equipped with an NXP i.MX 8M Plus AI processor, which I found only mildly interesting until the company informed me about (planned) software support. So let’s have a closer look. PANZER-PLUS specifications: SoC – NXP i.MX8M Plus CPU – Quad-core Arm Cortex-A53 processor @ 1.8GHz MCU – Arm Cortex-M7 real-time core @ 400 MHz GPU – Vivante GC520L 2D GPU, Vivante GC7000UL 3D GPU VPU – 1080p60 hardware decoder (HEVC, H.264, […]

Posted on by Debashis Das - 1 Comment on M.2 E-Key Wi-Fi 7 HAT for Raspberry Pi 5 also supports Google TPU

M.2 E-Key Wi-Fi 7 HAT for Raspberry Pi 5 also supports Google TPU

Mcuzone MPW7 M.2 E Key Wi Fi 7 HAT for RPi 5 with Google TPU Support

The Mcuzone MPW7 HAT for the Raspberry Pi 5 is designed to work with 2230 Wi-Fi 7 M.2 E-Key modules like the Intel BE200, AX210, and AX200, but the M.2 socket can also take Wi-Fi 6/6E modules as well as Google’s Tensor Processing Units (TPUs). It also integrates Bluetooth support via a 1.25mm USB interface on the HAT. Previously, we have covered many different HATs for the Raspberry Pi module, such as the Mcuzone MPS2280 M.2 NVMe HAT, Mcuzone MP4GM 4G LTE HAT, and the Sixfab 5G Modem Kit. Feel free to check those out if you are interested in Raspberry Pi 5 HATs. Mcuzone MPW7 M.2 E-Key Wi-Fi 7 module specification: M.2 E-Key socket supports 2230 modules WiFi modules compatibility – Supports M.2 E-Key modules like BE200, AX210, AX200, MT7922, Intel 8265C, etc… Bluetooth connectivity – 1.25mm 4-pin USB interface for Bluetooth integrated into the WiFi module connected to […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 31 Comments on Banana Pi BPI-M7 – A thin Rockchip RK3588 SBC with dual 2.5GbE, M.2 NVMe storage, HDMI 2.1, and more

Banana Pi BPI-M7 – A thin Rockchip RK3588 SBC with dual 2.5GbE, M.2 NVMe storage, HDMI 2.1, and more

Banana Pi BPI-M7

Banana Pi BPI-M7 SBC is powered by a Rockchip RK3588 SoC and comes with a low profile design that reminds me of boards from Khadas such as the Khadas Edge2 or VIM4 SBCs but with a few extra ports thanks to the larger form factor. The Banana Pi BPI-M7 single board computer is equipped with up to 32GB RAM and 128GB eMMC flash and features an M.2 2280 socket for one NVMe SSD, three display interfaces (HDMI, USB-C, MIPI DSI), two camera connectors, dual 2.5GbE, WiFi 6 and Bluetooth 5.2, a few USB ports, and a 40-pin GPIO header for expansion. Banana Pi BPI-M7 specifications: SoC – Rockchip RK3588 octa-core processor with CPU – 4x Cortex‑A76  cores @ up to 2.4 GHz, 4x Cortex‑A55 core @ 1.8 GHz GPU – Arm Mali-G610 MP4 “Odin” GPU Video decoder – 8Kp60 H.265, VP9, AVS2, 8Kp30 H.264 AVC/MVC, 4Kp60 AV1, 1080p60 MPEG-2/-1, VC-1, […]