Category: Nvidia

Page 1 of 16 1 2 3 4 16

Nvidia DRIVE PX Pegasus board for self-driving cars has 2 Octa-core ARM SoCs with 512-core CUDA GPU and 2 discreet GPUs for a total of 320 Billion calculations per second

Posted by Charbax – October 11, 2017

Nvidia DRIVE PX Pegasus board is launched for self-driving cars which includes two ARM SoCs each feature Octa-core Nvidia Xavier Custom ARM processors with Volta 512-core CUDA GPU which supports up to 8K video encode and decode, 7Billion transistors each ARM SoC built on TSMC 16nm FinFET+ with also two next-generation discrete GPUs separately on the board with hardware created for accelerating deep learning and computer vision algorithms, the 4 chips on the board can compute 320 Billion calculations per second with an overall 1TB per second memory bandwidth.

Read more:
http://www.marketwired.com/press-release/nvidia-announces-worlds-first-ai-computer-to-make-robotaxis-a-reality-nasdaq-nvda-2236493.htm
https://www.nvidia.com/en-us/self-driving-cars/drive-px/
https://arstechnica.com/cars/2017/10/nvidias-drive-px-pegasus-is-its-newest-self-driving-supercomputer/
https://www.theverge.com/2017/10/10/16449416/nvidia-pegasus-self-driving-car-ai-robotaxi
https://www.engadget.com/2017/10/10/nvidia-introduces-a-computer-for-level-5-autonomous-cars/

Nvidia Tegra X2 in Jetson TX2 Developer Kit, dual Denver2 + quad ARM Cortex-A57, Pascal GPU

Posted by Charbax – March 17, 2017

Nvidia Tegra X2 features two Nvidia custom Denver 2 cores, four ARM Cortex-A57 cores with Nvidia's Pascal GPU (made of 256 CUDA cores) made on TSMC's 16nm FinFET+. Nvidia Tegra X2 (codenamed "Parker") delivers up to 1.5 teraflops of performance, about 50% more performance than Nvidia Tegra X1. Enabling Artificial Intelligence (AI), for building advanced robots, drones, smart cameras, portable medical devices, enabling the processing of complex deep neural networks on the edge of the IoT world. While X1 could do 4K at 30fps encode, 4K 10bit 60p decode, X2 can encode 4K H265 at 60p and decode 4K 12bit 60p. Memory bandwidth has more than doubled from 25.6GB/s to 58.3GB/s, you can buy the Nvidia Jetson TX2 Developer Kit for $599 at https://store.nvidia.com/store?Action=DisplayPage&Locale=en_US&SiteID=nvidia&id=QuickBuyCartPage

$1099 Lenovo Yoga 720 (15″)

Posted by juliusaugustus – February 28, 2017

The Lenovo Yoga has 4K 15" display (or FHD version) with the latest Intel core i7 Kaby Lake processor, up to 16gb of RAM, integrated Nvidia GTX 1050 graphics card for gaming. There is a proprietary port for charging. Newer Lenovo laptops feature a Microsoft precision touchpad for better input experience. Battery life varies from 7 to 8 hours. The price starts at $1099.

Diamond Systems ARM Computing EAGLE I/O-Rich SBCs and Carrier Boards

Posted by Charbax – January 30, 2017

Diamond Systems, a global supplier of compact, rugged, I/O-rich embedded computing solutions for real-world applications in a broad range of markets, unveiled its EAGLE family of compact, rugged ARM single-board computers and carrier boards designed to work with the Toradex Apalis family of ARM computer-on-modules (COMs), see my Toradex at ARM Techcon video here.

The product line is composed of two models, the full-size, full-featured Eagle and its smaller sized, low-cost Eaglet. For greatest convenience, customers may purchase a fully configured off the shelf solution from Diamond, including a select ARM module and heat sink installed, or they may purchase the baseboard and ARM module separately for greater configuration flexibility and lower unit cost. Development Kits, including the fully configured SBC, pre-configured Linux OS on a microSD card, and a full cable kit, are available from Diamond Systems.

Key highlights of the Eagle/Eaglet family are long product lifetime, configuration flexibility, and a wide range of I/O.

You can read the press release and access links to EAGLE product web pages, datasheets, photos here.

Since 1989, Silicon Valley-based Diamond Systems Corporation has provided compact, rugged, board- and system-level real world embedded computing solutions to companies in a broad range of markets, including transportation, energy, aerospace, defense, manufacturing, medical and research.

The company is renowned as an innovator of embedded I/O standards and technologies; it was an early adopter of PC/104 module technology, originated the FeaturePak I/O module and RSODIMM rugged memory module standards, and holds a patent for a unique analog I/O autocalibration technique.

Diamond's extensive product line includes compact, highly integrated single board computers (SBCs); an extensive line of expansion modules for analog and digital I/O, wired and wireless communications including multiprotocol serial ports and Ethernet switches, GPS, solid-state disk, and power supply functions; and complete, rugged, system-level solutions.

Interested developers can contact Diamond Systems directly here:
Mark Wilson
Marketing Manager
mwilson@diamondsystems.com
Diamond Systems Corporation
http://diamondsystems.com

Toradex NXP i.MX7 and NVIDIA TK1 Demos at ARM TechCon 2016

Posted by Charbax – January 27, 2017

Toradex is showcasing the popular TAQ balancing robot featuring a Colibri iMX7 SoM based on NXP’s new heterogeneous multicore i.MX7 processor with Dual-Core ARM Cortex-A7 and additional ARM Cortex-M4 core for low-power, real-time or connected-standby IoT. Amid Toradex's broad product portfolio is the new high performance Apalis TK1 SoM based on NVIDIA’s Tegra K1 featuring a Quad-Core ARM Cortex-A15 processor with 192 CUDA cores for high-end computer vision and 4k video applications for example. Other demos include an impressive Qt Linux fast boot demo featuring an automotive cluster on Apalis i.MX6.

Project developers can contact Toradex here:
seattle@toradex.com
http://www.toradex.com

Evomotion 360 cameras using Nvidia Tegra TK1, Quad 4K 360 camera

Posted by juliusaugustus – November 4, 2016

Evomotion dual Cameras offer 2.5k resolution for the recording of 360 degree video. The dual camerasuses Novatek processor. The dual cameras sell for about $100 for 1,000 pieces. Evomotion quad cameras at $2000 based on Nvidia Tegra TK1 has 4 hd cameras, and they even has one with 4 Blackmagic 4K cameras combined recorded onto a big PC and suitable high VR productions such as in Hollywood. You can experience me filming at this booth in 360 VR from my hat towards the 1st minute of this 360 video: https://www.youtube.com/watch?v=ktxThATWiKI

Unspoken VR Game on Oculus Rift

Posted by Charbax – May 31, 2016

Unspoken is a new Oculus Rift game the video-games company Insomniac is developing, integrating prototype VR controllers by Oculus Rift where one hand can hold a shield with the left hand and throw fireballs with the right hand. Filmed in 4K using Sony AX53

Nvidia GTX 1080 powered HTC Vive VR

Posted by Charbax – May 31, 2016

Nvidia is showing their best VR experience powered by 3 Nvidia GTX 1080 GPUs (costing $700 each) with a powerful and expensive gaming Intel desktop PC running Nvidia's Funhouse VR game with impressive graphics rendered by 1 GTX1080 GPU for each eye and a third GTX 1080 calculating all the physics in the game, experienced with the amazing $800 HTC Vive with its amazing controllers all tracked in the room using IR. The GTX1080 is the world's most powerful consumer PC GPU. Filmed in 4K using Sony AX53

$200 NVIDIA Tegra K1 Game Console 7’’ HD 2G 32G by JXD S192

Posted by Gennie – February 1, 2016

JXD S192 is a game console powered by NVIDIA Tegra K1 Quad-core ARM Cortex-A15 with NVIDIA Kepler GPU, features with 7’’ Full HD IPS display at 1920*1200 resolution, 2GB RAM, 32GB Flash, with 5MP front camera and 10000mAH battery, Bluetooth, WiFi and HDMI output. Bulk price at $200 for 1000pcs.

Distributors can contact JXD here:
JOJO Liu, Sales Director
jojo.liu@jxd.cc

Toradex shows Freescale i.MX7, Windows 10 IoT Core on ARM

Posted by Charbax – December 10, 2015

Toradex shows their upcoming Freescale i.MX7 based System on Module (SOM). The module is pin compatible with the existing Toradex Colibri Modules based on i.MX6, Vybrid, PXA and Nvidia Tegra. The i.MX7 is a heterogeneous asymmetric multicore system including a Dual-core ARM Cortex-A7 and a ARM Cortex-M4 microcontroller for real-time. The Toradex computer module will be available at the official i.MX7 launch early next year. Also first time in public, Toradex shows Microsoft Windows 10 IoT Core on an ARM based SOM which is designed to be used directly in volume. The module is based on a Nvidia Tegra 3 which is pin compatible with the I.MX7 and provides a fully HW accelerated DirectX driver.