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/