Geniatech on ARMdevices.net
Toradex

Category: Nvidia

Page 1 of 17 1 2 3 4 … 17

Toradex shows Deep Learning Accelerators, Edge AI with Gyrfalcon, Xnor.ai, Movidius and More

Posted by Charbax – March 14, 2019

Toradex shows their deep learning inference solutions at Embedded World 2019, using power-efficient, Arm-based System on Modules, as machine learning and deep learning using neural networks progress is accelerating with successful new applications in computer vision for the embedded world. Toradex simplifies the integration of these technologies into products with its System on Modules, training deep learning models on high-performance computers with frameworks like TensorFlow, with optimizations needed to improve performance on low-power embedded Linux devices such as the ones Toradex partners with Au-Zone, Xnor.ai and Antmicro and others to bring to the embedded market. Implementing these dedicated neural network accelerators can boost the performance of embedded devices while keeping power consumption low, as shown in Toradex’s solutions with Intel Movidius Myriad and Gryfalcon Lightspeeur. Toradex partners with Allied Vision to showcase the brand-new Alvium industrial MIPI CSI-2 camera as a crucial component in the pasta detection demo which uses an Apalis System on Module featuring the NXP i.MX 8 QuadMax SoC with Cortex-A72, Cortex-A53 and dual OpenCL-capable GPU. To learn more about the demo, see CNX-Software's blog post. A real-world application example of deep learning is Manta, a camera-based drowning detection system from Coral Detection Systems which is solar-powered, and the video analytics are done on a Toradex Apalis module featuring a Nvidia TK1 SoC with a CUDA-enabled GPU. If a person is at risk of drowning, the system can alert its user acoustically or via smartphone.

Linux microPlatform, secure IoT updates with Foundries.io and Toradex

Posted by Charbax – October 13, 2018

At Linaro Connect Vancouver 2018, Foundries.io and Toradex discuss Linux microPlatform, what microPlatform is and how it helps Toradex to build their next generation Software Platform.

Linux microPlatform is an open source, minimal, secure, updatable Operating System based on OpenEmbedded / Yocto Project. Toradex ports the microPlatform to its Arm-based System on Modules and it uses it as the basis for its future Software Planform called Torizon.

Linux microPlatform modularized the embedded software stack utilizing Docker Containers, and so it provides a robust and simple to update platform. It includes a secure Uptane-compliant over-the-air update solution using OSTree.

Founderies.io provides continuous updates to Linux microPlatform, as they believe the latest software is the most secure software.

Toradex also elaborates on its plans to simplify developers’ lives with its Torizon platform leveraging Linux microPlatforms, such as simplifying application development, enabling a modern DevOps workflow and easing migration from Windows-based systems.

Get early access to all videos (weeks/months before everyone else), get business cards to companies filmed, support my video-blogging work, become a member at http://youtube.com/charbax/join

Nvidia Press Conference at Computex 2018

Posted by Charbax – June 6, 2018

Jensen Huang, Founder and CEO of Nvidia, Announces Jetson Xavier which I have filmed a separate interview about here, he does not launch the rumored GTX2080 or GTX1180 next-gen graphics cards yet, provides update on Max-Q thinner full GPU gaming laptops, talks DGX-2 supercomputer "The World's Largest GPU" (an update on the DGX which I filmed here) with 2 petaflops of performance in one node, 512GB frame buffer which has set 5 world records: fastest single chip, fastest single node, fastest at scale, fastest inference, and highest inference throughput.

$1299 Nvidia Jetson Xavier dev kit, 8-core ARMv8, 512-core Volta GPU for AI Robotics

Posted by Charbax – June 4, 2018

Nvidia launes Jetson Xavier with 20x the performance of Jetson TX2 and 10x the energy efficiency with 512-core Volta GPU with Tensor Cores in an embedded module with more than 9 billion transistors it runs at under 30W, with multiple operating modes at 10W, 15W, and 30W. The Jetson Xavier ARM SoC has 6 kinds of high-performance processors on its SoC, a Volta Tensor Core GPU, an eight-core ARM64 CPU, dual NVDLA deep learning accelerators, an image processor, a vision processor and a video processor. Jetson Xavier has a peak performance of up to 30 TOPS (trillion operations per second) of mixed-precision FP32/FP16/INT8 performance. It can encode dual 4K60 H265 and decode dual 4K60 H265 at up to 12bit. Comes with 16GB LPDDR4x RAM with 137GB/s memory bandwidth, 32GB eMMC storage. It also has a dual NVDLA DL/ML Accelerator Engines which are open source available at http://nvdla.org and a 7-way VLIW Vision Accelerator. Nvidia Jetson Xavier runs using the Nvidia Isaac platform, a toolbox for the simulation, training, verification and deployment of Jetson Xavier. This robotics software consists of: Isaac SDK, APIs and tools to develop robotics algorithm software and runtime framework with fully accelerated libraries, Isaac IMX (Intelligent Machine Acceleration) applications, a collection of NVIDIA-developed robotics algorithm software, Isaac Sim, a highly realistic virtual simulation environment for developers to train autonomous machines and perform hardware-in-the-loop testing with Jetson Xavier. The Nvidia Jetson Xavier developer kit, which includes the Isaac robotics software, will be priced at $1,299, with early access starting in August from distributors worldwide.

IBM Supercomputer on Power9 and Nvidia GPU

Posted by Charbax – April 8, 2018

Using IBM Power9 and Nvidia Volta GPU technology, the Summit system is a proven AI pioneer expected to deliver in excess of 200 Peta flops of performance, likely making it one of the world’s most powerful supercomputer.

Diamond Systems Zeta SBC, Ethernet switch solutions, Sabre enclosures at Embedded World 2018

Posted by Charbax – March 7, 2018

Diamond Systems founder Jonathan Miller shows the company’s newest products at Embedded World 2018 including the COM-based Zeta SBC, EPSM-10GX (used to connect to a carrier board) and EPS-24G2X Ethernet switch solutions. As Miller explains, the EPS-24G2X brings out all the signals including those for the two 10G SFI ports. There is a lot of Ethernet available via this solution. It’s all about communication, sharing information and so some people want more ports. The switches discussed are examples of those found in unmanned vehicles as well as many other rugged applications. Included in these new products is the EPS-12GMini, one of the world’s smallest 12-port Ethernet switches is a two-board design enabling its small form factor for on-board vehicle use (military and industrial).

The rugged enclosure called SABRE is the newest of Diamond Systems’ enclosures, this rugged box provides protection in the harshest environments and enables complete solutions for their customers. The one on display, Sabre, at this show is for the COM Express Mini form factor and it accommodates the 12-port switch. On the front is a set of three military connectors. Next is a an Industrial MIDI enclosure with a variety of I/O brought out to the front which accommodates an Eagle SBC which uses Toradex Apalis ARM modules and Diamond Eagle carrier board that goes inside along with a variety of I/O (serial ports, CAN ports, connectors, display, analog). Diamond has an ongoing relationship with partner Toradex who I also filmed at EW2018 here

More boards on display in their booth includes the Analog I/O modules: DMM-16-AT along with DMM-16RP-AT which is bus agnostic. Eaglet, a more compact version of the earlier noted Eagle SBC. The discussion turns to PC/104 where Miller notes the longevity of the product and long value it has had as a form factor. A little later, PCIe MiniCards are shown and discussed as used: I/O; CAN module, Analog I/O module; Ethernet and digital I/O.

Pandora box with connectors on the board for connecting directly into the box. Plug in and go. Typically used on a controller.

Products shown on the right half of the booth are proven designs that they have had on the market now already for a while. A large part of the sales are based on these designs and are custom in some fashion depending on customer's request.

Next for Diamond are more small things, COM Express, small form factors and more. You can read more about their solutions at http://diamondsystems.com

Toradex Apalis iMX8QM, NXP i.MX 8QM, and more demos at EW2018

Posted by Charbax – March 7, 2018

Toradex booth tour at Embedded World 2018 featuring their new Toradex Apalis iMX8 QM System on Module (SoM) based on the NXP’s i.MX 8QuadMax processor. Toradex’s demos featuring the Apalis iMX8QM includes one with Qt 3D Studio. The Apalis iMX8QM offers one click OS installation via the Toradex Easy Installer and offers 2x Arm Cortex-A72 cores, 4x Cortex-A53 cores, and 2x Cortex-M4 cores. The Apalis iMX8QM also contains on-board dual-band 802.11ac 2x2 MU-MIMO Wi-Fi and is Bluetooth 5 ready. This SoM offers advanced hardware security and safety features, and is ideal for signal processing, computer vision and HMI applications. Interested third parties can sign up for early access for the Apalis iMX8QM here

In addition, Toradex is also showing their soon to be available Toradex Colibri iMX8X SoM, based on NXP’s i.MX 8X processor. With 2-4x Arm Cortex-A35 cores and 1x Cortex-M4 core, the SoM is ideal for industrial automation, HMI, robotics, building applications and healthcare. The Colibri iMX8X also contains on-board dual-band 802.11ac 2x2 MU-MIMO Wi-Fi and is Bluetooth 5 ready.

Toradex also showcases some of their other demos such as a Deep Learning demo featuring its Toradex Apalis TK1 SoM in collaboration with its partner Vertex.AI, the demo highlights Vertex.AI’s Vision deep learning and object detection software, and is a complete end-to-end deep learning demo, showcasing pasta detection. Additionally, Toradex has a demo in collaboration with its partner, Roboception, which integrates Toradex’s Apalis TK1 SoM for high-performance onboard processing, the demo has onboard SLAM for indoor and outdoor navigation, accurate visual-intertial motion estimation, and standard interfaces for an intuitive WEB-GUI.

Toradex also has a range of demos highlighting its Toradex partner ecosystem. From CODESYS’ real-time SoftPLC with EtherCAT, Crank’s low- and high-end UI, DiSTI’s safety focused HMI, Green Hills’ INTEGRITY RTOS on Colibri iMX6, Antmicro’s Android on Vision Kit, Acontis’ optimized EtherCAT, TES’ 3D Surround View/Guiliani, Mender.io’s over-the-air updates, Christmann’s Apalis computer cluster, Gumstix’s voice control carrier board, MVTec’s HPeek and more.

To stay up-to-date with news from Toradex, you can sign up to their newsletter here.

Blade Shadow cloud gaming pc service launched in UK and California

Posted by Charbax – February 24, 2018

Here I film at the UK launch of the Blade Shadow cloud PC gaming service, at the Meltdown London e-sports bar, where they have setup a bunch of Shadow PCs for cloud based gaming PC streaming service
here powering their League of Legends tournament. Blade Shadow is a French startup who I also interviewed at CES here they have now launched their service to cover the UK and they have also activated their West Coast USA server to serve customers in California. For about $35 per month you get remote access to "your own" Xeon gaming desktop with an Nvidia GTX1080 GPU, 12GB RAM, 256GB SSD running Windows 10 Pro.

Shadow Blade cloud PC Xeon/GTX1080 for cloud gaming, cloud 4K60/8K video-editing

Posted by Charbax – January 25, 2018

French startup Blade presents their awesome Shadow cloud PC service at €30/month that streams a very powerful $2000 (equivalent) desktop PC hosted on their server powered by a high-end 8-threaded Intel Xeon server CPU with an Nvidia GTX1080 GPU, 12GB RAM, 256GB SSD (with harddrive/SSD storage expansion options available) running a full Windows 10 Pro desktop remotely in their server, using low-lag Internet technologies that they have developed, fast codecs (to have at least 15mbit/s Internet bandwidth available is recommended for a good experience), fast tricks that they have developed to make this all possible, to offer cloud gaming or high-end video-editing, 3D graphics rendering, audio processing, or anything else that might be useful to run on advanced PC hardware that you can think of, and you can then run that through client applications either running on their AMD APU based Shadow PC thin client that they offer to their subscribers (for a smooth up to 4K60 or 1080p144hz gaming experience), or you can run clients on a Chromebook, any Android phone, Android TV, Macbooks, any Windows machine, Linux, iPhone, iPad, their service runs on everything. Currently their service works well in France, initially it was just for French users who had Fiber to the home connections, but now it also runs smoothly onto any ADSL, Cable even LTE devices in France, the service is also supported in Belgium and a few other countries nearby France. Because for a good service, the user has to be within as few hops in the global backbone internet network as possible, to experience as little lag times as possible. Advanced professional gamers have tested this system and they have reported that they cannot feel any difference between the Shadow cloud gaming service and a local desktop gaming machine. The lag time are said to depend more on the speed of the PC monitor than of the internet back to their cloud server system. They are about to expand their offering to cover the whole of California as they are setting up a cloud server system right now in the Silicon Valley also. They plan to expand their services globally in the near future according to demand.

Nvidia DGX Station, world’s most powerful desktop, a Supercomputer at the office

Posted by Charbax – November 28, 2017

Nvidia DGX Station is the world’s first and fastest personal supercomputer for leading-edge AI development at Supercomputing developers desk, it has the computing capacity of four server racks in a desk-friendly package, using less than one twentieth the power. It’s the only personal supercomputer with four Nvidia Tesla V100 GPUs, next generation Nvidia NVLink, and new Tensor Core architecture. DGX Station delivers 3X the training performance of today’s fastest workstations, with 480 TFLOPS of water cooled performance (3X Faster Than the Fastest Workstations) and FP16 precision. It's designed to be whisper quiet at one tenth the noise of other deep learning workstations, it’s designed for easy experimentation at the office.

Filmed in 4K60 at Supercomputing 2017 in Denver using Panasonic GH5 ($1999 at Amazon.com) on firmware 2.1 (aperture priority, AF continuous tracking) with Leica 12mm f1.4 ($1297 at Amazon.com) with Sennheiser MKE440 stereo shotgun microphone ($325 at Amazon.com), get $25 off renting cameras and lenses with my referral link at https://share.lensrentals.com/x/wWbHqV