from the meet-George-Jetson^W^W-Jetson-Xavier dept.
NVIDIA wants to power intelligent robots with Jetson Xavier
NVIDIA is hoping to play a bigger role in the future of robotics with its Isaac platform, powered by the new Jetson Xavier system-on-a-chip. If that name sounds familiar, it's because it's relying on the same the processor from the Xavier Drive self-driving SOC. The Xavier is over twenty times faster than the existing Jetson TX2 platform, NVIDIA CEO Jen-Hsun Huang revealed at Computex today. While that last SoC was useful for products like delivery robots and drones, Huang is calling the Xavier the "world's first computer for intelligent robots."
Under the hood, Jetson Xavier has six different processors: An octa-core Arm CPU; a Volta Tensor Core GPU; two NVDLA deep learning chips, as well as vision, video and image processors. Xavier is capable of 30 trillion operations per second, and it sports over 9 billion transistors. Just like with self-driving cars, all of that horsepower will help with things like sensor processing and computer vision. After all, a robot won't be truly intelligent until it can easily maneuver through any environment and naturally interact with humans and other machines.
Nvidia CEO Jensen Huang said that new GeForce GPUs will not launch until "a long time from now".
Also at The Verge.
Related Stories
Nvidia Announces Jetson Nano Dev Kit & Board: X1 for $99
Today at GTC 2019 Nvidia launched a new member of the Jetson family: The new Jetson Nano. The Jetson family of products represents Nvidia new focus on robotics, AI and autonomous machine applications. A few months back we had the pleasure to have a high level review of the Jetson AGX as well as the Xavier chip that powers it. The biggest concern of the AGX dev kit was its pricing – with retail costs of $2500 ($1299 as part of Nvidia's developer programme), it's massively out of range of most hobbyist users such as our readers.
[...] The Jetson Nano is a full blown single-board-computer in the form of a module. The module form-factor and connector is SO-DIMM and is similar to past Nvidia modules by the company. The goal of the form-factor is to have the most compact form-factor possible, as it is envisioned to be used in a wide variety of applications where a possible customer will design their own connector boards best fit for their design needs.
At the heart of the Nano module we find Nvidia's "Erista" chip which also powered the Tegra X1 in the Nvidia Shield as well as the Nintendo Switch. The variant used in the Nano is a cut-down version though, as the 4 A57 cores only clock up to 1.43GHz and the GPU only has half the cores (128 versus 256 in the full X1) active. The module comes with 4GB of LPDDR4 and a 16GB eMMC module. The Jetson Nano module will be available to interested parties for $129.
$99 without storage.
Related: Nvidia Reveals Jetson Xavier SoC for Robots
(Score: 2) by JoeMerchant on Tuesday June 05 2018, @12:59PM (1 child)
I'm fine with current performance levels, what I want is stuff that works, out of the box, no tweaking required.
Україна досі не є частиною Росії Слава Україні🌻 https://news.stanford.edu/2023/02/17/will-russia-ukraine-war-end
(Score: 0) by Anonymous Coward on Tuesday June 05 2018, @02:22PM
Because as I understand it, Volta was infuriating a lot of scientist types by returning different/nonstandard results for a lot of math types that didn't meet IEEE754 or equivalent standards.
(Score: 0) by Anonymous Coward on Tuesday June 05 2018, @04:00PM
all we have to do is defund these scumbags but hey, just keep acting stupid instead so we never have freedom respecting graphics cards.