NVIDIA discussion [2025]

Here's a list of NVIDIA's sessions at the upcoming GDC (except the last one):

Advanced Graphics Summit: Path Tracing Deep Dive: 'Indiana Jones and the Great Circle'
https://schedule.gdconf.com/session...ive-indiana-jones-and-the-great-circle/910009

Advanced Graphics Summit: From Myth to Reality: Full Ray Tracing Inside 'Black Myth: Wukong'
https://schedule.gdconf.com/session...l-ray-tracing-inside-black-myth-wukong/909932

Advances in RTX (Presented by NVIDIA)
https://schedule.gdconf.com/session/advances-in-rtx-presented-by-nvidia/911188

Path Tracing Nanite in NVIDIA Zorah (Presented by NVIDIA)
https://schedule.gdconf.com/session/path-tracing-nanite-in-nvidia-zorah-presented-by-nvidia/911196

RTX Neural Shading: Practical Techniques and Applications (Presented by NVIDIA)
https://schedule.gdconf.com/session...s-and-applications-presented-by-nvidia/911193

Visualizing Next-Gen Games With RTX Neural Rendering and Unreal Engine 5 (Presented by NVIDIA)
https://schedule.gdconf.com/session...nd-unreal-engine-5-presented-by-nvidia/911197

The Magic Behind Ray-Traced Lighting in Star Wars Outlaws (Presented by NVIDIA)
https://schedule.gdconf.com/session...-star-wars-outlaws-presented-by-nvidia/911198

Scale Up Ray Tracing in Games With RTX Mega Geometry (Presented by NVIDIA)
https://schedule.gdconf.com/session...-rtx-mega-geometry-presented-by-nvidia/911194

Creating Next-Gen Agents in Krafton's InZOI (Presented by NVIDIA)
https://schedule.gdconf.com/session...-in-kraftons-inzoi-presented-by-nvidia/911189

Achieving AI Teammates in 'NARAKA: BLADEPOINT' Mobile PC Version (Presented by NVIDIA)
https://schedule.gdconf.com/session...-mobile-pc-version-presented-by-nvidia/911190

Bringing AI NPCs to Life with NVIDIA ACE On-Device Small Language Models in Meaning Machine's Dead Meat (Presented by NVIDIA)
https://schedule.gdconf.com/session...machines-dead-meat-presented-by-nvidia/911191

Building AI Assistants to Help a Gamer’s Journey (Presented by NVIDIA)
https://schedule.gdconf.com/session...p-a-gamers-journey-presented-by-nvidia/911199

Advanced Graphics Summit: GPU Work Graphs: Towards GPU-Driven Games (AMD)
https://schedule.gdconf.com/session...u-work-graphs-towards-gpu-driven-games/909736
 
TSMC has proposed a joint venture with NVIDIA, AMD, Qualcom and Broadcom to run Intel foundries.

Nope, if you go to actual source (https://www.reuters.com/technology/...v-nvidia-amd-broadcom-sources-say-2025-03-12/) it says right in the beginning that "TSMC would take a stake of no more than 50% in joint venture operating Intel foundries-sources"

US government has been clear that Intel Foundries can't be sold outside.
If it's held private, Intel has to own 50.1% minimum, if it's made public, no outside investor can hold over 35 %.
 
The 50.1% requirement was set into place by the CHIPS Infrastructure act here in the US, specifically because Intel was receiving funding. If the current administration makes good on their threats to kill the CHIPS act, would the 50.1% rule still be binding? Even if technically true, would it be enforced? Given the proclivities of the current US leadership, I'm not so sure...
 
I think there's 2 aspects of this. There might not be a restriction on Intel having to maintain a set amount of ownership but there is almost certainly going to be restrictions on foreign ownership, if anything more so with the current administration.

From my perspective this was always going to be the issue with selling Intel and/or splitting it's foundry. The companies that would be most interested and capable in buying either would be non US entities which would almost certainly be blocked regardless of who is the government. While with US companies the ones most interested and capable are almost certainly going to run into anti-trust concerns.
 
Agreed re: foreign ownership, however keep in mind NVIDIA, AMD, Qualcomm and Broadcom are all "American" companies, only TSMC is the foreign investor here.

And so, with a proposed consortium of mostly American companies to satisfy a cursory foreign investment challenge, I refer back to my prior comment.
 
Well that was an interesting sales pitch. Jensen basically shat all over Hopper and waved away Blackwell Ultra. Must feel great for all the companies who spent billions on those chips.

Rubin and the silicon photonics stuff do look insane though. Hope TSMC has their CoWoS stuff sorted. The photonics chips are using CoWoS too.

Oh Blackwell is no longer one GPU, two dies they're walking that back. It's now 2 GPUs, 2 dies. Making Rubin Ultra 4 GPUs, 4 dies.

rubin-ultra.png
 
NVIDIA announced B300, releasing in 2H 2025, 50% faster than B200, and with 50% more VRAM. Then, Rubin will launch in 2H 2026, with 3x the performance of B300 (measured in FP4). Rubin will be two reticle sized GPUs fused together, Rubin Ultra will follow in 2H 2027, with 4x the performance of Rubin, it will be 4 reticle sized GPUs fused together.

In 2028, there will be the Feynman GPU arch, NVIDIA gave no details about it though.


 
"I don't know where that came from but nobody's invited us to a consortium," Huang, Nvidia's founder and CEO, told reporters in a GTC press briefing session, referring to the report.

"I'm not trying to say it's not news, but nobody invited me," said Huang.

"In the near term, based on what we know, we're not expecting a significant impact [from Trump tariffs] on our outlook," said Huang. "Long term, we want to retain the [supply chain] agility, but add a very significant part of our agility which is onshore."

"If we add onshore manufacturing by the end of this year, we should be quite good," Huang told reporters. TSMC is reportedly in talks with Nvidia to manufacture its latest Blackwell chips in the Arizona fabs.


TSMC, the world's biggest contract maker of chips, has said it plans to make a fresh in the U.S. that involves building five additional chip facilities.

"We're in it," Huang said, referring to TSMC's new chip fabrication facility in Arizona. "We are now running production silicon in Arizona."

 
Last edited:
Yeah, I mixed it in my mind with Rubin Ultra which was 4 instead of 2 GPUs per "single GPU"

Yep, Jensen said they're sticking with the old naming for Blackwell and changing it for Rubin. Something about aligning the naming with NVLink topology.
 
Back
Top