INTC 3Q25 CC: Moore works for ASIC & 86.
Joshua Buchalter: I wanted to ask about some comments Lip-Bu made in the prepared remarks about fixed function computing and potentially supporting more ASICs. Was this — maybe could you provide more context on the scope of this? Is this for potential foundry customers? Or are these products? And if it’s products, what types of applications do you expect to be supporting with custom silicon?
Lip-Bu Tan: Good question. So I think, first of all, I just mentioned about the Central Engineering. We are driving the ASIC design, and that will be enhanced — actually is a good opportunity for us to enhance, extend our reach of the core x86 IP and also drive some of the purpose-built silicon for some of our systems and cloud players and customer. And then definitely with the foundry and packaging, also they were helping us in terms of their requirement. So all in all, I think this AI will be driving a lot of growth especially in the double down, the Moore’s Law, and that will help us a lot in our 86 uplift. And that’s an opportunity for us to build the whole ASIC design to serve some of the customer requirement.
Copilot:
Exactly right, Mike—and your framing is sharp. Jensen Huang has long distanced himself from Moore’s Law, famously declaring it “dead” years ago. His stance wasn’t just rhetorical—it was strategic. He’s argued that AI accelerators like Nvidia’s are improving faster than Moore’s Law ever predicted, thanks to full-stack innovation: architecture, packaging, software, and interconnects like NVLink. Huang’s cadence has shifted toward semiannual or even quarterly upgrades, especially with rack-scale systems like Blackwell and Rubin, which defy traditional node-based pacing.
Lip-Bu Tan, on the other hand, is reinvigorating Moore’s Law as a rallying cry for Intel. In the Q3 2025 earnings call, he explicitly tied AI growth to Moore’s Law, saying Intel is “doubling down” on it. He’s not just referencing transistor scaling—he’s invoking it as a strategic framework for Intel’s roadmap:
- Intel 18A and 14A nodes are progressing predictably, with Panther Lake and Nova Lake built on them.
- Advanced packaging like EMIB and EMIB-T are positioned as Moore’s Law extensions.
- Foundry strategy is aligned with long-term wafer volume growth, driven by AI infrastructure demand.
So yes—Tan is supporting Moore’s Law, not just in name but in execution. It’s a philosophical and tactical contrast: Huang sees Moore’s Law as obsolete and replaced by “Huang’s Law” (stack-level acceleration), while Tan sees it as a still-relevant foundation for Intel’s resurgence.
Want to riff on how this divergence affects investor signaling or chip design philosophy?
PS
Huang has gone yearly on shrink.
Is a Shrink n Stack maniac.
:-)
PSS
shill/"expert" Moore "concern" more alternate fact krapp.
What they're really, really good at.
:-)
ASML
Village |
