by

GeForce 3 birthday chat turns into an AI origin story

Nvidia chief executive Jensen Huang sat down with senior GeForce staff to mark the 25th anniversary of the GeForce 3 launch and pointed out that gaming lit the fuse for what became the modern AI revolution.

He said that GeForce 3 pushed the shift from fixed-function accelerators to programmable shaders. The point, Huang said, was to bake the “artistic” touch of developers into each game rather than ship the same visual soup.

He said that in the late 1990s, games started looking “the same” thanks to fixed-function kit like Riva 128 and TNT. Nvidia’s answer was programmable vertex and pixel shader architecture, which arrived with GeForce 3 and gave developers more control.

Huang said that shift towards programming later helped set up CUDA, adding parallelism to GPU computation. Nvidia’s pitch is that the road from shaders to compute ended up building the runway for AI.

Huang said: “Game was a medium for artistic expression. And that if you look at all these different games, we wanted them all to look different. And if you wanted them all to look different, you need the ability to express the artistry in some form of program.

It can’t be pre-coded. And our company really didn’t have much compiler technology capability. And so as we were transitioning from a fixed hardware-accelerated pipeline to a programmable fixed hardware pipeline, we realised that we had to move into and become a computing company.

He pointed to ray tracing as another early bet, since it was brutally expensive and forced Team Green to get clever rather than just throw raw grunt at it. He tied RTX to later-upscaling tech like DLSS, calling it “neural rendering” that brings “generative capability to computer graphics”.

He said steady gains in computing and rendering turned GPUs into more than fancy pixel-pumpers, then the AI crowd turned up and nicked the whole machine. You can see why Nvidia is happy to frame gaming as the respectable family member in this story.

Huang said: “So it’s been a great joy serving all of you. Thank you for everything you’ve done for GeForce. Without GeForce, there would be no CUDA. Without CUDA, there would be no AI. Without AI, there would be no today. And so all of you have made it possible.”

“There’s no doubt that advancements in computer graphics made Nvidia realise that GPUs are much more than just for rendering workloads, and the gradual improvements in CUDA and related technologies paved the way for the modern-day AI computation we see today. At the same time, when we talk about the future of gaming and Nvidia , the prospects look gloomy at the moment, but it appears that Team Green is eager to break traditional compute barriers by developing upscaling technologies that leverage AI to “generate” frames without the need for hefty hardware,” he said.

The company even rolled out the nostalgia visuals, with an Nvidia card shown in front of posters for ‘Jedi Knight II: Jedi Outcast’, ‘Blizzard Entertainment’ and ‘Max Payne’. If Nvidia can sell frame generation as the future, it gets to keep gaming around without pretending it is still the main event.

 

TOPICS:
CUDA  ·  dlss  ·  GeForce 3  ·  generative ai  ·  GPU history  ·  Nvidia  ·  programmable shaders  ·  ray tracing  ·  rtx

Latest articles

Share

Featured articles

AINews

Hot topics

No results found.

Latest reviews