Nvidia’s GTC (GPU Technology Conference) event has come to an end, and the keynote was packed with news. The new RTX 40 series graphics cards were obviously the standout announcements ushering in a whole new generation of graphics cards for PC gamers.
But as usual, Nvidia’s announcement went well beyond consumer games, touching on industries ranging from new products in the world of robotics and self-driving cars to advances in medicine and science.
GeForce RTX 4090 and 4080
Of course, the big announcement that kicked off the keynote was three new graphics cards. The RTX 4090 is the flagship model that Nvidia says is up to 2x faster than the previous generation (RTX 3090 Ti) in traditional gridded games. This huge map is based on Ada Lovelace, which is the basis for everything announced at GTC. It comes with 16,384 CUDA cores and 24GB of GDDR6X memory. And most importantly, the same 450 watts of power as the RTX 3090 Ti.
The RTX 4090 will be available on October 12th and will cost $1,599.
|RTX4090||RTX4080 16GB||RTX4080 12GB|
|memory||24GB GDDR6X||16GB GDDR6X||12GB GDDR6X|
|Increase clock speed||2520MHz||2505MHz||2610MHz|
The RTX 4080 takes a step down from there and comes in two different configurations. The 16GB model is $1,199 and the 12GB model is $900.
These GPUs are a bit handier at 320 W and 285 W respectively. However, the RTX 4090 has well over twice as many CUDA cores as the RTX 4090 12GB model, which is a huge gap. There is a big difference in specs between these two models of the RTX 4080, so it will be interesting to see how they stack up in terms of performance.
Along with the new GPUs, Nvidia also announced the third generation of RTX, which includes DLSS 3. Just like the transition from DLSS to the second generation, this appears to be a major advancement in technology. This time, machine learning can predict actual frames, not just pixels, leading to even bigger increases in framerates in games.
How fast? Well, Nvidia says up to four times faster thanks to the optical flow accelerator. This technology actually bundles three different Nvidia innovations into one, including DLSS Super Resolution, DLSS Frame Generation and Nvidia Reflex.
The other great feature of DLSS 3 is its ability to speed up CPU-limited games. Nvidia showed a demo of Microsoft flight simulator, which fits the bill in an extreme way. Seeing DLSS 3 boost frame rates from 64fps to 135fps is really impressive, especially in this type of game.
Nvidia says DLSS 3 will be four times faster overall than traditional rendering. DLSS 3 is out in October and Nvidia says more than 35 games and applications will support it at launch.
Finally, Nvidia announced Portal RTX, a modernized version of the popular PC game, now with DLSS 3 and ray tracing effects.
Nvidia drive Thor
Nvidia has been trying to get its foot in the door of the future of self-driving cars for years, but its latest product feels like a significant step in the right direction. Nvidia Drive Thor is the next generation super chip based on Hopper GPU architecture paired with Nvidia Grace CPU.
Drive Thor is the first automotive platform with an inference transformer engine.
Nvidia says Drive Thor will be available for automakers’ 2025 car models as a true successor to Drive Orin, which is currently in production. Thor replaces Drive Atlan, which was announced just last year.
Nvidia Drive Concierge
In addition to the new chip, Nvidia also showed Drive Concierge, a complete in-vehicle infotainment system. It replaces the instrument cluster on a typical car dashboard with what Nvidia calls a “digital cockpit”. The system supports Android Automotive, which makes it possible to customize systems by car manufacturers. Remarkably, the announcement comes just months after Apple’s landmark next-gen CarPlay announcement, which is doing something similar with its digital instrument cluster.
Of course, elsewhere in the vehicle, Drive Concierge also offers passengers features such as video conferencing, video streaming, digital assistants, cloud gaming via GeForce Now and full visualizations of the vehicle.
All of the design was done in Omniverse, and Nvidia says designing in Omniverse allows automakers to tweak all of these aspects of the car long before they’re a physical reality.
Omniverse Cloud and Nvidia’s Graphics Delivery Network
Omniverse Cloud was announced earlier this year as Nvidia’s full suite of cloud services for people building the future of the metaverse – without the need for all that power in your actual computer. New additions to the service suite include the robotics simulation application Nvidia Isaac Sim and the autonomous vehicle simulation Nvidia Drive Sim.
Interestingly, Omniverse Cloud was mentioned alongside what is known as the Nvidia Graphics Delivery Network (GDN), the distributed data center that powers Omniverse Cloud. Built on the same capabilities as GeForce Now, the company’s cloud gaming service, the GDN is the network that delivers all those high-performance, low-latency graphics to whoever needs them.
Nvidia spoke at length about all the ways Omniverse and digital twins are being used, even stating that any product in the future that is driven by software will need to have a digital twin for testing purposes.
Jetson Orin Nano
Nvidia announced the Jetson Orin Nano modules, the newest member of the Jetson family of small computers designed to accelerate AI processes and robotics. These new “System-on-Modules” are expected to deliver up to 40 trillion operations per second (TOPS) AI performance, 80 times the performance of their predecessor, the Orin NX modules.
The Orin Nano modules will be available in January, with the 8GB model starting at $199.
- Nvidia has announced two new major language models, the NeMo API for natural language AI applications and BioNeMo for chemistry and biology applications.
- Lowe’s has announced that it will make its library of over 600 photorealistic 3D product assets freely available to other Omniverse creators. The company also discussed its research into using interactive digital twins and a Magic Leap 2 AR headset to give employees “superpowers.”
- The Deutsche Bahn Rail Network has announced that it will use digital twins in the Omniversum to develop its future railway system.
- The second generation of Nvidia OVX has been announced, powered by the L40 GPU intended for building “complex industrial digital twins”. L40 uses 3rd generation RT cores and 4th generation Tensor cores for these intensive Omniverse workloads and has already been equipped for companies like BMW and Jaguar Land Rover. These new OVX systems will be available from Lenovo, Inspur and Supermicro in early 2023.
- Nvidia has announced that the H100 Tensor Core GPU has entered full production and is ready to launch its first hopper-based products in October
- In the medical world, Nvidia has announced IGX, a combined hardware and software platform specifically designed for use cases such as robotic surgery and patient monitoring.
- Nvidia also demonstrated how IGX has applications in the industrial world as well, specifically in creating safe autonomous factories that are all about human-machine collaboration.
- A partnership between Nvidia and the Broad Institute of MIT and Harvard that brings GPU-accelerated Clara Parabricks software to the Terra biomedical data platform, enabling researchers to speed up tasks like genome sequencing by up to 24x. Nvidia says it’s contributing its own deep learning model to “help identify genetic variants associated with diseases.”
- Nvidia and Booz Allen have announced an “enhanced collaboration” to leverage AI through GPU acceleration of their cybersecurity platform based on Nvidia’s Morpheus framework.