Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
Next-Gen Apple Chip Technology on Track to Reach Production in 2025
- Thread starter MacRumors
- Start date
- Sort by reaction score
Meh. When they get to .5nm then we’ll have something worth talking about. 😁
don't forget to get a nm ruler drop shipped from the Amazon marketplace for $3.87
1nm equals 10 Angstroms. A silicon atom is 1.92 Angstroms (0.192 nm) wide so process nodes cannot go smaller than that (and likely can't get close to that)
Both Intel and TSMC are starting to switch to Angstroms for their process node descriptions - Intel's 20A and 18A are basically 2.0 and 1.8 nm equivalent process nodes, same with TSMC's forthcoming A14 process node (equivalent to 1.4 nm).
Once that limit is reached there are other ways to keep driving performance forward, such as 3D lithography, looking to new materials, or continual improvements to existing process nodes.
The industry (TSMC, Intel, Samsung,...) counts in Angstroms (Ångström), 1nm = 10A. The 1.4 nm is labelled A14.
For further challenges and progress, here are the views of the reputed IMEC lab: https://www.imec-int.com/en/articles/smaller-better-faster-imec-presents-chip-scaling-roadmap
I'll cross that bridge when/if that occurs, and if my M1 MBA suffers as a result. No need for that now.
This is amazing "stuff"! In my lifetime, I've witnessed electrical engineering go from vacuum tubes > transistors > semiconductors > nano scale microprocessors containing 120 billion transistors. Many accolades to the clever and hard working engineers that gave us this technology.
Once they get below 1nm, processing will become so fast, that it will go back in time and be finished before you even ask for it.
Better performance per watt (efficiency?) and lesser consumption should lead to lesser heat with constant transistor density. However, the industry uses these advances to cram in more and more transistors, ensuring our hands never get cold in winter and our cats always find convenient sleeping places (aka cat-tops).
I am not in the industry or even adjacent to it, but I love articles like that, and deep dives like Anandtech does. I watched this the other night and it blew my mind:
Lol, what? So I invented Coca-Cola, I guess. Just because they buy it doesn't mean they paid for its development. TSMC was gonna make a 3nm node with or without Apple, they have plenty buyers.
I just don't agree with the few articles that have mentioned about possibly having the M4 come out on the 2nm node in 2025. It makes way more sense for the 2nm to be on M5 at the least as Apple just began the 3nm with M3.
It makes more logical sense for Apple to have the M4 on N3P or N3E near the end of this year before moving to 2nm.
It makes more logical sense for Apple to have the M4 on N3P or N3E near the end of this year before moving to 2nm.
It is just a marketing label, it does not correspond to an actual physical measurement
What is important is that there is a performance per watt improvement.
Die shrinks are a useful measure of improvement.
The new Mac mini is almost certainly coming
Apple skipped the M2 for the iMac and went straight from M1 to M3. It's possible they may do that again with M3 with respect to some Macs. I wouldn't be surprised if we see the following; Spring 2024 - M2 iPad Air / M3 iPad Pro WWDC 2024 - M4 MBA (13" / 15") Fall 2024 - M4 iMac / base MBP, M4...
forums.macrumors.com
Lots of presumptions in that about peoples work flows.Once Apple starts to take generative AI seriously, it will be.
How M1 Macs may lag behind
M1 CPUs support ARMv8.5A, which doesn’t support the new bfloat16 floating-point format now widely used in AI. That’s likely to put them at a disadvantage.eclecticlight.co
