Things are going to get weird as the nanometer era draws to a close With 3nm production reaching maturity and 2nm on the way, TSMC is reportedly laying the groundwork for the next logical step, a 1nm fab. According to Taiwanese media, TSMC has its sights set on building advanced chip kit in the island nation's Chiayi Science Park, with a plan to produce state-of-the-art chips based on a 1nm …
Similar to how they refer to "3 nm" processes as N3, beyond N2 they are naming them A14 (1.4 nm) and A10 (1 nm)
And yes it bears repeating that nothing in modern processes has any feature size that's 3 nm in size, so no worries about becoming smaller than the diameter of a silicon atom anytime soon as they progress to 1 nm and smaller.
We're probably safe until we reach the scale of the quantum random walk (of a drunkhard) whenceforthwithwhile the entangled state of superposed Shannon information is simultaneously everywhere, and nowhere, until observed by a sober party. Beyond that point, it'll be either live turtles all the way down, or bowls of spicy turtle soup, also all the way down, there's just no way to tell which at this current junction, because, ironically -- behavior of the quantum field-effect is, bipolar (smelling of teen spirit!)!
More mature tech is wildly over-rated!
《...whenceforthwithwhile the entangled state of superposed Shannon information is simultaneously everywhere, and nowhere, until observed by a sober party. Beyond that point, it'll be either live turtles all the way down, or bowls of spicy turtle soup, also all the way down,...》
A nod to Joyce's "Finnegans Wake" - "Shenanegans Woke?"
Reminds me of Douglas Adams' "Infinite Improbability Drive" and Trillian's countdown on "The Heart of Gold" to normality:
"We have normality, I repeat we have normality." ... "Anything you still can't cope with is therefore your own problem."
I found this interview to be quite interesting.
https://archive.computerhistory.org/resources/access/text/2022/07/102792671-05-01-acc.pdf
'We use a three generation older technologies and it worked very well... That was the first generation. Xilinx worked with TSMC on CoWoS. Their codename was CoWoS. It’s a funny name for TSMC’s silicon interposer. That was a first-generation advanced package technology.
'Qualcomm was our biggest customer... I talked to one of their VP. I talked to them many, many times, until one time, I had dinner with one of their VP, and he just very casually told me, he said, you know, “If you want to sell that to me, I would only pay one cent per millimeter square.” One cent per millimeter square. He said, “That’s the only cost I will pay for it.” I said, “How come you didn't tell me earlier?” He said, “You should know that. Why I should tell you? You should know that.” But, I didn’t know that.
"I said, “Please go to figure out how much that CoWoS costs us.” Seven cents per millimeter square. So that's why we couldn't sell it. I said, “Let’s develop something that costs one cent, and you can relax the performance, and you sacrifice performance.” Our second generation called InFO meet that criteria and it was sell like a hotcake. So that one word saved my life and the InFO was why Apple was hooked by TSMC. Earlier, why TSMC couldn't get Apple business, early stage, because Samsung offer them a package solution by wire bond DRAM on top of CPU, on top of the AP, and TSMC couldn’t do that.'
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2025
