ODYSSEY-X86J4105 SBC Unboxing and Re_Computer Case Review

Seeed Studio ODYSSEY-X86J4105 is an Intel Celeron J4105 Gemini Lake SBC that also happens to integrate an Arduino compatible Microchip SAMD21 Arm Cortex M0+ microcontroller that makes it suitable as an all-in-one Arduino platform. But it can do much more with 8GB RAM, an optional 64GB eMMC flash, HDMI & USB-C DisplayPort 4K video outputs, dual Gigabit Ethernet, and support for both SATA and NVMe storage. The board runs Windows 10 Enterprise by default (if you purchase the board with an eMMC flash), and supports Linux distributions as well. Seeed Studio sent me a review sample, so I’ll start by checking out the hardware first. ODYSSEY-X86J4105 Unboxing I received ODYSSEY-X86J4105864 with a built-in 64GB eMMC flash pre-loaded with Windows 10 Enterprise. Let’s have a quick look at the board with USB, Ethernet and video output ports previously described, as well as built-in dual-band Wi-Fi 5 & Bluetooth 5.0 module, and M.2 sockets for NVMe and SATA SSD, SATA HDD/SSD, as …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

NVIDIA Jetson Developer Kits Comparison – Nano vs TX2 vs Xavier NX vs AGX Xavier

NVIDIA launched Jetson Xavier NX developer kit yesterday, and I included a short comparison table in the announcement between Jetson Nano, TX2, Xavier NX, and AGX Xavier developer kits. But I thought it might be worthwhile to have a more detailed comparison in a separate post, so here we are. As expected, usually the more you spend on a board, the better the performance and features. The exception is Jetson TX2 that’s the same price as the new Jetson Xavier NX devkit, but delivers about a fifth of the FP16 AI performance. So as today, there’s little reason to buy a TX2 board for a new project unless you need some of the required features that are missing on Xavier NX. Jean-Luc Aufranc (CNXSoft)Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011. www.cnx-software.com Support CNX Software – …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

NVIDIA Jetson Xavier NX SoM Launched for $459, Third-Party Carrier Boards & Edge Computers Available

NVIDIA announced the Jetson Xavier NX system-on-module last November with an NVIDIA Xavier SOC with 6 NVIDIA Carmel Arm v8.2 cores, a 384-core NVIDIA Volta GPU and two NVDLA deep learning accelerators for a combined 21 TOPS at 15 Watts. The 69.6 x 45 mm module also includes 8 GB LPDDR4x RAM and a 16GB eMMC flash with a 260-pin SO-DIMM providing various I/Os from PCIe to MIPI CSI and display interfaces such as HDMI and eDP. NVIDIA expected the module to be “available in March for $399 to companies looking to create high-volume production edge systems”, and at the time I thought it would be hard to purchase for simple mortals, but the company just sent an email announcing the launch of the module and it’s now listed for $459 on Arrow Electronics with no stock and a 16 weeks lead time. While there’s no Jetson Xavier NX development kit, the SoM is pin-to-pin compatible with Jetson Nano module, …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

NVIDIA Jetson Nano Developer Kit-B01 Gets an Extra Camera Connector

Launched in March 2019, NVIDIA Jetson Nano developer kit offered an AI development platform for an affordable $99. The kit is comprised of Jetson Nano module and a carrier board, and the version I received last November ended with “A02”. Jetson Nano developer kit is now getting updated with B01 carrier board that adds an extra MIPI CSI connector and other few changes, including compatibility with NVIDIA Jetson Nano production module (with eMMC flash instead of MicroSD card). Jetson Nano developer kit-B01 specifications: B01 Jetson Nano CPU Module 128-core Maxwell GPU Quad-core Arm A57 processor @ 1.43 GHz System Memory  – 4GB 64-bit LPDDR4 @ 25.6 GB/s Storage  – microSD card slot Video Encode – 4K @ 30 | 4x 1080p @ 30 | 9x 720p @ 30 (H.264/H.265) Video Decode – 4K @ 60 | 2x 4K @ 30 | 8x 1080p @ 30 | 18x 720p @ 30 (H.264/H.265) Dimensions – 70 x 45 mm B01 Baseboard 260-pin …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Testing NVIDIA Jetson Nano Developer Kit with and without Fan

Jetson Nano 52Pi-ICE Tower Cooling Fan

A few weeks ago I received NVIDIA Jetson Nano for review together with 52Pi ICE Tower cooling fan which Seeed Studio included in the package, and yesterday I wrote a getting started guide showing how to setup the board, and play with inference samples leveraging the board’s AI capabilities. I’ll now test the board with the stock heatsink in both 5W and 10W modes, and see if thermal throttling does occur, and then I’ll fit the tower cooling fan to find out if we can extract more performance that way and how much lower the CPU temperature is. Jetson Nano Stress Tests with Stock Heatsink Let’s install SBC-Bench testing utility, check it’s properly installed, and run it in 5W mode: The temperature never went over 44.5°C, and no throttling occurred. tegrastats during 7-zip multi-core test: Only two Cortex-A57 cores are used even under load, and power consumption is around 3.3 Watts. Let’s run sbc-bench in 10W mode: The maximum temperature …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Getting Started with NVIDIA Jetson Nano Devkit: Inference using Images, RTSP Video Stream

Jetson Nano RTSP Stream Inference

Last month I received NVIDIA Jetson Nano developer kit together with 52Pi ICE Tower Cooling Fan, and the main goal was to compare the performance of the board with the stock heatsink or 52Pi heatsink + fan combo. But the stock heatsink does a very good job of cooling the board, and typical CPU stress tests do not make the processor throttle at all. So I had to stress the GPU as well, as it takes some efforts to set it up all, so I’ll report my experience configuring the board, and running AI test programs including running objects detection on an RTSP video stream. Setting up NVIDIA Jetson Nano Board Preparing the board is very much like you’d do with other SBC’s such as the Raspberry Pi, and NVIDIA has a nicely put getting started guide, so I won’t go into too many details here. To summarize: Download the latest firmware image (nv-jetson-nano-sd-card-image-r32.2.3.zip at the time of the review) …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

NVIDIA Jetson Nano Review with 52Pi ICE Tower Cooling Fan – Part 1: Unboxing

Jetson Nano Review with ICE Tower Cooling Fan

If you remember soon after Raspberry Pi 4 launch, there were talks about the SBC overheating under load, and depending on room temperature and workload a heatsink may be needed for the board to perform optimally at all times. This gave birth to “interesting” solutions such as 52Pi ICE Tower Cooling Fan, an oversized cooling solution for Raspberry Pi 4. It does the job however, and it allows me to overclock Raspberry Pi 4 to 2.0 GHz while keeping the CPU temperature under 55°C in a room at 28°C. But the latest Raspberry Pi Foundation board is not the only SBC to suffer from overheating, as at least one user noticed the board would just shutdown under load. The solution was to switch from 10W mode to 5W mode, not an ideal solution since it’s also lowering performance. But 52Pi is coming to the rescue again, as they adapted their ICE tower cooling fan to Jetson Nano SBC. Seeed Studio …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

NVIDIA Jetson Xavier NX SoM Delivers up to 21 TOPS for AI Workloads at the Edge

NVIDIA Jetson Xavier NX

NVIDIA has just announced Jetson Xavier NX system-on-module, with the company claiming it is the “world’s smallest, most powerful AI supercomputer for robotic and embedded computing devices at the edge” with a 70x45mm “Jetson Nano” form factor, and delivering either up to 14 TOPS at 10 Watts or 21 TOPS at 15 Watts. The company expects the module to be used in small commercial robots, drones, intelligent high-resolution sensors for factory logistics and production lines, optical inspection, network video recorders, portable medical devices, and other industrial IoT systems. Jetson Xavier NX specifications: SoC – NVIDIA Xavier with 6-core NVIDIA Carmel ARM v8.2 64-bit CPU, 6MB L2 + 4MB L3 caches, and a 384-core NVIDIA Volta GPU with 48 Tensor Cores, 2x NVDLA deep learning accelerators delivering up to 21 TOPS at 15 Watts System Memory – 8 GB 128-bit LPDDR4x @ 51.2GB/s Storage – 16 GB eMMC 5.1 flash Video Encode 2x464MP/sec 2x 4K @ 30 (HEVC) 6x 1080p @ …

Support CNX Software – Donate via PayPal or become a Patron on Patreon