Search results

On our NVIDIA and TSMC episodes, we explored two components of the silicon value chain: the fabless chip companies that design chips and the foundries that manufacture them.…

They make the primary chip inside every MacBook and iPhone chips today, they’re powering the AI Wave, manufacturing all of NVIDIA’s chips, they make the chips for a whole bunch of other fabless companies like Qualcomm, AMD, Broadcom, and hyperscalers like AWS…

History of the back and forth tradeoffs between Intel's powerful x86 chips and low power alternatives like ARM processors. Dobberpuhl's technology breakthroughs throughout his career that enabled true low-power + high-performance chips.…

ARM is in your phone, your car, data centers, the most advanced AI chips… there are hundreds (or thousands!) of ARM chips you encounter in your everyday life. In this episode, ARM Holdings CEO Rene Haas joins us to tell the story of. how.…

If you’re excited at all about Nvidia, AMD, Qualcomm, or even any of the chips that Amazon, Microsoft, Facebook, and Apple are making—all of those chips or nearly all of them are actually made by TSMC.…

What if we use the same semiconductor in silicon technology that we're using to make these other chips to turn the memory into chips? I think we can do that. That sounds like a good idea. Let's start a company around that.…

It would be cooler if you could be really good at a certain part of the stack and have tools, platforms, and other companies to allow anybody to make chips. Ben: Yeah, if there were design tools to help you make chips.…

David: If you think about all the chips in an iPhone, the A16 Pro, is built on the leading edge, but there are many, many other chips in there. Morris: Right. Ben: So you combine to one business development organization, 80=ish people. Morris: Yeah.…

You do any of this work, you cannot deploy it on anything but NVIDIA chips. That's not even like NVIDIA put in their terms of service that you can't deploy this on AMD chips. Ben: It literally doesn't work. David: Nope, it's full stack.…

It becomes imperative to network multiple chips, multiple servers of chips, and multiple racks of servers of chips together into one single “computer” in order to actually train these models.…