Nvidia Makes A ‘Quantum Leap’ At GTC 2022: Ada Lovelace RTX GPUs, Omniverse Cloud, DRIVE Thor Superchip For Autonomous Vehicles – NVIDIA (NASDAQ:NVDA)

NVIDIA Corps NVDA The GPU Technology Conference (GTC) was packed with company updates, led by the launch of a new generation of GeForce RTX GPUs. Here you can see some highlights of the event.

“Computing is advancing at incredible speed, the engine that powers this rocket is accelerated computing and its fuel is AI,” said Nvidia CEO Jensen Huang said at the beginning of the virtual event.

New GPUs: Nvidia on Tuesday unveiled the GeForce RTX 40 series, the company’s first line of GPUs based on the company’s new Ada Lovelace architecture. Ada advancements include a new streaming multiprocessor and RT core, as well as a new Tensor core. Ada also uses AI to generate new frames using previous frames to understand scene changes.

Huang called the new GPU series a “quantum leap” that opens up a path for developers to create fully simulated worlds.

Also Read :  This Week in Coins: Google Cloud, BNY Mellon News Doesn't Boost Bitcoin, Ethereum

AI trends: The Nvidia CEO also addressed broader AI trends surrounding large language models and recommendation systems.

“A single pre-trained model can perform multiple tasks, such as question answering, document summarization, text generation, translation, and even software programming,” Huang said.

He noted that the company’s new H100 GPU, which is in full production and expected to ship in the coming weeks, will provide the processing power needed to run these models.

Look at this: Bad Dog?! Jim Cramer Short’s stick after which he named his dog

The Metaverse: Omniverse is Nvidia’s platform for building and running Metaverse applications. NVIDIA OVX servers are designed to scale out metaverse applications.

NVIDIA’s second-generation OVX systems are powered by Ada Lovelace L40 data center GPUs, which Huang announced are now in full production.

Also Read :  CTERA Wins 2022 Cloud Computing Security Excellence Award

Huang also announced new deployment availability for the company’s Omniverse Cloud. Replicators to generate synthetic data, farms to scale renderings, and Isaac Sim to build and train AI robots are now available for Omniverse Cloud.

Autonomous vehicles: Today’s vehicles rely on different computers for various functions, but tomorrow’s vehicles will rely on software running on a centralized computer that improves over time, Huang said.

To fuel this transition, Nvidia introduced DRIVE Thor, which combines Hopper’s Transformer engine, Ada’s GPU, and Grace’s CPU.

“The new Thor superchip delivers 2,000 teraflops of power, replacing Atlan on the DRIVE roadmap and providing a seamless transition from DRIVE Orin, which has 254 TOPS of power and is currently deployed in production vehicles,” the company said.

Thor is also used as a processor for robotics, medical instruments, industrial automation, and more. Nvidia’s Orin processor is currently used in robotics applications. The company announced the new Jetson Orin Nano on Tuesday, saying it’s about 80 times faster than the previous model.

Also Read :  Mitigating Cloud Cyber Risk with Data-Centric Security

“Today we announced new chips, new advances in our platforms, and new cloud services for the first time,” Huang said toward the end of his presentation.

“These platforms are driving new breakthroughs in AI, new applications of AI, and the next AI wave for science and industry.”

Also Read: Investors Beware: Nvidia Stock Is “Caught in a Pretty Substantial Downtrend”

NVDA Price Action: Nvidia has a 52-week high of $307.11 and a 52-week low of $126.17.

The shares are up 3.50% to $136.38 as of Wednesday afternoon, according to Benzinga Pro.

Photo: courtesy of Nvidia.

Source link