Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
I wonder how hot this one is going up get? Frying pan hot?
Each decrease in "process size" improves power usage while improving speed - although frequently the chip designers use this to increase density of transistors which increases effective heat. They are still a fraction of the power the Intel chips were using before (or are still using).

With a 2025 debut - that would likely match with Apple introducing the A19 processor for the phones, and the M5 for the Computers/iPads.
 
  • Like
Reactions: coolfactor
Eh, 2nm is getting to the point of impossible if it means the entire transistor. A silicon atom is 0.13nm diameter. This would mean the entire transistor is 15 atoms wide. That's not technically impossible, but it's pretty darn close.

Also, not all transistors are the same size. A modern SoC will have dozens of different transistors types on it, of varying sizes. So measuring the smallest transistor doesn't really mean much if most of them are larger.

Rather, my understanding is that since about 65nm, TSMC has switched from measuring the size of the transistor to the width of the gate, or the width of the channel; which is a smaller subcomponent of the transistor. But having a gate width of 15 silicon atoms is more believable, since that means the entire transistor would be roughly twice as wide. And it tells you a bit more about the tech, since knowing the smallest feature size is still useful for the larger transistors on the die.
Is there a YouTube video that explains all
of this? I’d love to see this presented visually.
 
Just curious what happens beyond 1nm?

Intel already beat them to it, in marketing anyway. Angstroms are the next smallest unit of measurement. Well there probably is some metric word for the next tenth smaller than nanometer, but Intel is going with Angstroms.

After that it’s going to have to get quantum.
 
I wonder how hot this one is going up get? Frying pan hot?

The thinner the material, the less power is required to "push" electrons from one point to another, so less power to do the same work. Less heat generated for the same work. Heat is generated from friction. There are other factors, but that's the essence of the efficiency improvements.

Think of it like this: instead of having to jump in the car and drive to your store to buy a jug of milk, you can just open the window, reach out and grab one. Same end result... you have a jug of milk, but you had to do far less work to achieve that.
 
Based on my crude calculations, Intel's 80486DX2 CPU with 1.6 million transistors from 1992 would fit in the red dot on the M3 with 25 billion transistors. So I fully expect the M3 to fit in the same red dot applied to Apple's M25 SoC for Year 2057 (averaging a new Mx every ~18 months for next 34 years).

And if the M3 were manufactured using Intel's 600nm process from way back (and based on the 486DX2's 1.6M transistors in a die size of 12mmx6.75mm), the M3 would be a bit larger than the current 16" MacBook Pro footprint. Granted, the 486DX2 didn't have unified memory or NPUs, GPUs, etc, but still pretty amazing how far the process has come.

M3.png
 
Wonder whether Apple will release a 3nm M4 Pro chip before moving to 2nm chips in 2025
 
Cue all the "My new M3 Mac that I haven't bought yet is already out of date" comments.
I am sure that there are those out there that are thinking that, but hopefully they will put things in to perspective. I had the MacBook Air with M1 processor, 16gb memory and 1TB SSD. It did great until I needed more storage, memory, and ports to move into projects that required a lot more oomph. I was budgeting the a MacBook Pro with M3 processor but struggling with justifying the costs to get what I really wanted as opposed to getting something a bit more conservative.

Suffice it to say, I had to take my lumps when B&H had a MacBook Pro, 64gb memory with 2TB SSD, M1 Max Processor and a 16" screen, for $2,500 - brand new out of the box. Honestly, it's been well worth it. I've been putting it to task ever since I got it.

So with the 2nm coming out at some point, I feel confident in my purchase and hope everyone else takes my position that even if you buy the M3 (or any processor), the more Apple advances with future processors, the better off we will be when we do upgrade in a few years. Hoping too that more people begin to realize to upgrade only when you have barriers to projects or tasks you are doing.
 
Wonder whether Apple will release a 3nm M4 Pro chip before moving to 2nm chips in 2025
I'd say M5-M6 will be the ones that get the new chips depending on what year they come out but my guess is end of 2025-2026 is when these sorts of chips will be released for their computers.
 
I have been upgrading to the newest Pro iPhone every year since the X came out in 2017, it's basically the same iPhone in terms of performance feel at least. Even going from the 14 pro to the 15 pro's 3nm chip, it feels almost identical to me. But I don't do anything intensive on my iPhone like gaming though.
 
Based on my crude calculations, Intel's 80486DX2 CPU with 1.6 million transistors from 1992 would fit in the red dot on the M3 with 25 billion transistors. So I fully expect the M3 to fit in the same red dot applied to Apple's M25 SoC for Year 2057 (averaging a new Mx every ~18 months for next 34 years).

And if the M3 were manufactured using Intel's 600nm process from way back (and based on the 486DX2's 1.6M transistors in a die size of 12mmx6.75mm), the M3 would be a bit larger than the current 16" MacBook Pro footprint. Granted, the 486DX2 didn't have unified memory or NPUs, GPUs, etc, but still pretty amazing how far the process has come.

View attachment 2324271
Quite impressive analysis. I honestly didn't think we would ever get to this point.
 
I have been upgrading to the newest Pro iPhone every year since the X came out in 2017, it's basically the same iPhone in terms of performance feel at least. Even going from the 14 pro to the 15 pro's 3nm chip, it feels almost identical to me. But I don't do anything intensive on my iPhone like gaming though.
I still have a 6S as a backup and just to keep around and stare at the headphone jack and SIM slot and reminisce. ;)

But I don’t “feel” much difference between 6S and my 14Pro for most things, performance-wise, as I don’t game either. I’m sure everything I do is somehow faster, but the biggest noticeable everyday performance difference for me besides battery life: the 14Pro display is noticeably better/brighter, I didn’t think much of ProMotion at first, but it’s quite noticeable now and I think for me this is the feature that makes the 14Pro “feel/look” faster, with the smooth scrolling and animations, I wouldn’t want to go back to a 60Hz phone display.
 
  • Like
Reactions: smulji
I want to known when Apple is going to disclose their massive backend for EPYC/MI300 series for their expanded vertical cloud services, etc. They sure won't be using Nvidia or Intel as they cut ties with both years ago.
Is it certain that Apple is doing this?
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.