With NXP i.MX 8M Plus AI processor nearing mass production, we’ve seen many companies introduce i.MX 8M Plus systems-on-module at Embedded World 2021. But as one would come to expect, there should also be single board computers based on the new processor, and Advantech has unveiled the RSB-3720 2.5-inch SBC (aka Pico-ITX SBC) compatible with the company’s UIO40-Express expansion boards. RSB-3720 specifications: SoC – NXP i.MX8M Plus dual or quad-core Arm Cortex-A53 processor up to 1.8GHz (1.6 GHz for industrial temperature range) with Cortex-M7 real-time core, Vivante GC7000UL 3D GPU, 1080p60 H.265/H.264/VP9 decoder, 1080p60 H.265/H.264 encoder, 2.3 TOP/s Neural Network Accelerator System Memory – 4GB or 6GB LPDDR4 4000MT/s Storage – 16 GB eMMC Flash for OS, 8 MB QSPI NOR Flash for board information, microSD socket Video Output – HDMI 2.0a up to 3840 x 2160 at 30Hz Single or dual-channel 24 Bit LVDS with backlight power, 5/12V, Max. […]
NXP unveils i.MX 8ULP Cortex-A35/M33 secure processors with optional Azure Sphere certification
NXP may have just unveiled plans for i.MX 9 processor family with Arm Ethos U65 microNPU, and advanced security using the company’s EdgeLock enclave, but NXP also introduced new members to its popular i.MX 8 series with i.MX 8ULP and i.MX 8ULP-CS (Cloud Secured) processors. Both processors come with a mix of Cortex-A35 application processor(s) and Cortex-M33 real-time core, as well as Energy Flex low-power architecture and EdgeLock secure enclave, but i.MX 8ULP-CS includes Microsoft Pluton for secure cloud connectivity and lacks 2D/3D graphics and the HiFi 4 audio DSP. NXP i.MX 8ULP and 8ULP-CS key features and specifications: CPU i.MX 8ULP – Up to two Arm Cortex-A35 @ 1.0 GHz and Arm Cortex-M33 @ 216 MHz, i.MX 8ULP-CS – One Arm Cortex-A35 @ 1.0 GHz and Arm Cortex-M33 @ 216 MHz GPU (i.MX 8ULP only) – 2D GPU, and 3D GPU with support for OpenGL ES 3.1, OpenCLTM, Vulkan […]
Edge AI video processing system combines SocioNext SC2000 4K camera SoC with Hailo-8 AI accelerator
We’ve previously written about Hailo-8 AI accelerator delivering up to 26 TOPS at low power (3 TOPS per watt), and found in AI edge systems such as Foxconn BOXiedge server powered by a Socionext SynQuacer SC2A11 24x Cortex-A53 cores SoC and capable of analyzing up to 20 streaming camera feeds in real-time for video analytics. Leopard Imaging has now created a much more compact Edge AI processing solution with EdgeTuring based on Hailo-8 M.2 card and Socionext SC2000 4K camera SoC, and designed for low-power video analytics. EdgeTuring features and specifications: Camera SoC / Image Processor – Socionext SC2000 quad-core Cortex-A7 processor @ 650MHz with 4Kp30 H.265/H.264 encoder, up to 1.2 Gigapixel per second processing, LPDDR-3 memory (PoP) AI Module – Hailo-8 M.2 Module for up to 26 TOPS Camera Dual camera but only one sensor works for AI Sensors – 2x Sony IMX477 CMOS Image Sensor, diagonal 7.857 mm […]
This mini-computer is set to outperform NVIDIA Xavier by eight times
When it comes to high-end AI-edge computer boards, we have seen Hackboard 2 with support for Windows 10 operating system and optional 4G or 5G cellular connectivity. Fast Sense Studios is a Russian-based startup designing powerful on-board computers to bring edge AI capabilities to mobile robotics. At Embedded World 2021, the company has unveiled the Fast Sense X Robotics AI Platform that integrates the power of six computers into a single module. The company claims the newly launched edge AI computer outperforms the NVIDIA Xavier with over 8x higher performance in mobile robots thanks to the advanced DNN inference hardware. Apart from the Intel UHD GPU, the computer also integrates up to 3 Coral Edge TPU devices and up to 2 Myriad X devices allowing it to give optimum results even when on heavy workloads. “We believe in the future where reliable physical agents become relevant for routine tasks that […]
The first Rockchip RK3566 TV box is out with H96 Max running Android 11
Rockchip RK3566 is a quad-core Cortex-A55 processor with plenty of peripherals designed for AIoT and NVR applications. While it still supports features like high-dynamic range or video post-processing, it’s not really optimized for TV boxes, but this has not stopped the maker of H96 Max “8K UltraHD” TV box to launch an RK3566 model with 4GB RAM and 8GB RAM now sold for respectively $59.99 and $76.99 on Banggood. H96 Max RK3566 TV box specifications: SoC – Rockchip RK3566 quad-core Cortex-A55 processor with Arm Mali-G52 EE GPU, 0.8 TOPS NPU/AI accelerator System Memory / Storage configuration 4GB DDR3, 32GB eMMC flash, and MicroSD card 8GB DDR3, 64GB eMMC flash, and MicroSD card Video Output – HDMI 2.0a up to 4Kp60 with 3D support, Video decoding 4Kp60 H.264/H.265/VP9 VC1 up to 1920 x 1080 @ 60fps MPEG-4 up to 1920 x 1080 @ 60fps HDR10 and HLG modes Audio – Optical […]
Geniatech XPI-3288 Raspberry Pi lookalike features Rockchip RK3288 SoC
Geniatech XPI is a family of single board computers following Raspberry Pi 3 form factor. We first covered XPI-S905X SBC in 2018, which was followed by XPI 3128 board last year. The company has now launched another model with Geniatech XPI-3288 SBC powered by Rockchip RK3288 32-bit quad-core Cortex-A17 processor coupled with 2G RAM and 16GB eMMC flash. Geniatech XPI-3288 specifications: SoC – Rockchip RK3288 quad-core Cortex-A17 processor @ up to 1.6GHz with Arm Mali-T764 GPU System Memory – 2GB RAM Storage – 16GB eMMC flash (8/32GB optional), MicroSD card slot Video Output – HDMI up to 4Kp60 (may be limited to 4Kp30 on some older 4K TVs) Video decoding H.264 up to HP level 5.1 @ 2160p24 (3840×2160) MPEG-1/-2/-4, AVS, VP8, MVC up to 1080p60 (1920×1080) VC-1 up to AP level 3 @ 1080p30 (1920×1080) H.263 @ 576p60 (720×576) Connectivity Gigabit Ethernet port Optional dual-band 802.11b/g/n/ac WiFi 5 and […]
It’s raining i.MX 8M Plus systems-on-module at Embedded World 2021
NXP introduced i.MX 8M Plus AI SoC with a built-in 2.3 TOPS neural processing unit (NPU) last year, and we’ve already covered several early announcements about i.MX 8M Plus systems-on-module (SoM) with Variscite VAR-SOM-MX8M-PLUS and DART-MX8M-PLUS, TechNexion EDM-G-IMX8M-PLUS and AXON-E-IMX8M-PLUS respectively using SO-DIMM edge connectors and board-to-board connectors, as well as SolidRun i.MX 8M Plus SoM that was announced together with the HummindBoard Mate carrier board with dual Gigabit Ethernet. But as Embedded World 2021 Digital is taking place virtually until Friday, other companies have now made their own announcements of i.MX 8M Plus SoMs as the processor enters mass production this month, and since as far as I know, it’s pin-to-pin and software compatible with earlier i.MX 8M Nano/Mini SoCs, the update must have been easy. That means we’ve got a longish list of modules, and I have probably missed some. Supported operating systems are basically the same across […]
NVIDIA introduces lower cost Jetson TX2 NX SO-DIMM module
NVIDIA Jetson AI modules and developer kits range from the entry-level Jetson Nano module (5W, ~0.5 TOPS) to the high-end Jetson Xavier AGX module (30W, 32 TOPS). The higher-end modules usually come with a 400-pin board-to-board, while cheaper/cost-down modules like Jetson Nano and Jetson Xavier NX feature a 260-pin SO-DIMM connector and small form factor. But so far all Jetson TX2 modules came with a 400-pin connector, but this has changed with the introduction of the Jetson TX2 NX SO-DIMM system-on-module that is offered as a cost-down version of Jetson TX2 4GB module. NVIDIA Jetson TX2 NX specifications with highlights in bold or strikethrough showing the difference against Jetson TX2 4GB: Processor – Dual-Core NVIDIA Denver 2 64-Bit CPU and Quad-Core Arm Cortex-A57 MPCore processor @ up to 2.0 GHz GPU – 256-core NVIDIA Pascal GPU @ up to 1.3 GHz AI Performance – 1.33 TFLOPS Video Encode H.265 – […]