Notebookcheck
, , , , , ,
search relation.
, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
 

Nvidia presents improved Xavier SoC for autonomous machines

The latest Xavier SoC is derived from the Volta architecture that also spawned the new Turing architecture found inside the new GeForce RTX 2000 GPUs. (Source: Anandtech)
The latest Xavier SoC is derived from the Volta architecture that also spawned the new Turing architecture found inside the new GeForce RTX 2000 GPUs. (Source: Anandtech)
Nvidia may be the gaming GPU market leader, but the green team is also keen on advancements in the supercomputer and AI world. With the new scalable Xavier SoC, Nvidia is boosting the processing power for autonomous machines , bringing us closer to a world in which the AI controls most of the technologies in our life.
Bogdan Solca,

Working For Notebookcheck

Are you a techie who knows how to write? Then join our Team! English native speakers welcome!

News Writer - Details here

Besides professional and gaming graphics solutions, Nvidia has recently taken an interest in artificial intelligence and neural network applications that expand the way autonomous machines interact with the environment. Derived from las year’s Volta architecture, just like the new Turing architecture featured in the freshly launched gaming GPUs, the new Xavier system-on-chip for autonomous machines introduces the Carmel architecture that powers the processing unit of the chip.

The latest Xavier SoC was presented at the Hot Chips summit as using the 12 nm FFN manufacturing process from TSMC and coming with numerous specialized processors such as:
•    Carmel CPU with eight custom ARM 8.2 cores
•    Volta GPU with 512 CUDA Tensor Cores
•    Deep Learning Accelerator capable of 11.4 deep learning int8 TOPs
•    Programmable Vision Accelerator capable of processing 1.7 TOPs
•    Image signal processor with native HDR capabilities and 2.4 GPixel/s processing
•    Multimedia accelerators (stereo sound, optical flow)
•    Lens distortion correction hardware
•    Support for 256-bit LPDDR4x/5
•    20 GB/s NVLink with multi-PCIe Gen 4.0 controllers
•    Support for 4x displays with HBR3 and HDMI 2.0 outputs
•    a total of 9 billion transistors over a surface of 350 mm2

Regarding scalability, the Xavier SoC can power single chip variants (Jetson Xavier), as well as multi-chip versions including the Drive Xavier and Drive Pegasus versions. Nvidia is already working with Tesla and AI industry leaders to test the Xavier and improve the architecture. Additionally, the new SoC is designed to be energy efficient, but Nvidia did not provide any TDP figures for the time being.

, , , , , ,
search relation.
, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
 
All the components of the Xavier SoC (Source: Anandtech)
All the components of the Xavier SoC (Source: Anandtech)
Scaling options (Source: Anandtech)
Scaling options (Source: Anandtech)

Source(s)

static version load dynamic
Loading Comments
Comment on this article
Bogdan Solca
Bogdan Solca - Senior Tech Writer - 1571 articles published on Notebookcheck since 2017
I first stepped into the wondrous IT&C world when I was around seven years old. I was instantly fascinated by computerized graphics, whether they were from games or 3D applications like 3D Max. I'm also an avid reader of science fiction, an astrophysics aficionado, and a crypto geek. I started writing PC-related articles for Softpedia and a few blogs back in 2006. I joined the Notebookcheck team in the summer of 2017 and am currently a senior tech writer mostly covering processor, GPU, and laptop news.
contact me via: Facebook
Please share our article, every link counts!
> Notebook / Laptop Reviews and News > News > News Archive > Newsarchive 2018 08 > Nvidia presents improved Xavier SoC for autonomous machines
Bogdan Solca, 2018-08-21 (Update: 2018-08-21)