Nvidia has Unveiled a 320 Teraflop Chip and Ofcourse, It’s Not for Gaming

Nvidia made an incredible reveal at CES 2017, a powerful computing platform for autonomous vehicles. Codenamed Pegasus, can be powered up to Level 5, fully drive a car without steering wheels, pedals or rear view mirrors.

This Drive PX platform will deliver over 320 trillion operations per second, that’s 10 times more than its predecessor. Nvidia claims to commercialize this product for companies in second half of 2018.

Nvidia says that its Level 5 automation shouldn’t be taken lightly since there are strict set of standards that need to be followed, thorough testing, rigorous amounts of calculation and analysis. Because ultimately it’s about the safety of passengers.

Intel is also working with BMW on fully automated driver-less vehicles that are expected to launch in 2021. But Nvidia’s claim seem both surprising and appealing. Because currently self-driving cars without human intervention are only theoretical.

This vision of Nvidia to bring about an automated computing solution for fully driver-less vehicles is most appealing to futurists and tech lovers. Although it seems like it will take many years or even decades to see robotic cars freely roaming our streets like we used to see in the movies.

Everything the vehicle sees with its sensors, all of the images, mapping data, and audio material picked up by its cameras, needs to be processed by giant PCs in order for the vehicle to make split-second decisions.

All this processing must be done with multiple levels of redundancy to ensure the highest level of safety. That’s one big reason why self driving operators choose SUVs and minivans. Large trunk space to fit in all the gizmo-computing hardware.

But Nvidia claims to have shrunk the product to the size of a license plate. Yet powerful enough for processing equal to a 100-server data centre. They’re also partnering up with DHL to deploy fully autonomous delivery trucks by 2019. Seems like Nvidia have their hands full with futuristic approach and Kaizen model of their R&D operations.