Apple Silicon's Next Big Upgrade Could Arrive in 2026

[MacRumors]

Apple could upgrade to considerably more advanced 2-nanometer chip fabrication technology as soon as 2026, according to analyst Ming-Chi Kuo.

In a recent post on Medium, Kuo explained that Apple will likely begin to use TSMC's 2-nanometer chip fabrication technology to produce iPhone chips as early as 2026. The iPhone 15 Pro's A17 Pro chip is the industry's first 3-nanometer chip, sporting performance and efficiency improvements thanks to its increased transistor density.

If so, this would mirror its use of the 5-nanometer node through the A14, A15, and A16 Bionic chips from 2020 to 2022, where the technology persisted for three years through successive chip generations. The 2026 timeframe would also presumably mean the 3-nanometer node persists for three years through the A17 Pro, "A18," and "A19" from 2023 to 2025.

Like 3-nanometer, 2-nanometer further reduces the smallest possible dimension used in chip manufacturing and increases transistor density, resulting in improved performance and efficiency.

According to Kuo, TSMC is strengthening its vertical integration capabilities with chip designer ARM in an effort to ensure a smooth transition from the current 3-nanometer technology to the next-generation 2-nanometer process. Apple and Nvidia are expected to be among the first clients to place orders for 2-nanometer chips.

Article Link: Apple Silicon's Next Big Upgrade Could Arrive in 2026

 

[phill85]

Hot take: 2028 at the earliest

 

[MacProFCP]

This is interesting to see. I wonder what the next tipping point will be for chip manufacturing. I remember when the concern was powering any chip above 3 Ghz and so we moved to multiple cores. Now we’re getting smaller and denser chips. What’s next? I don’t know but I’m excited to find out.

 

[coachgq]

Serious question. What happens when they get to 1nm? What’s the next step? .5, or some completely new technology all together?

 

[Leon Ze Professional]

From the wonderlust event, even Apple themselves didn't wheel out the big wigs to announce the A17 pro chip.

I don't know how everyone else felt?

But to me the A17 pro announcement felt rather flat as if Apple themselves weren't quite as excited about this chip as we all expected them to be.

 

[rukia]

TSMC's 2nm GAA will focus on efficiency and low power performance which is ideal for Apple's designs. There will be less improvements in performance for the higher power designs that Nvidia focuses on.

 

[sack_peak]

Serious question. What happens when they get to 1nm? What’s the next step? .5, or some completely new technology all together?

Source:

- https://www.imec-int.com/en/articles/smaller-better-faster-imec-presents-chip-scaling-roadmap
- https://www.tomshardware.com/news/imec-reveals-sub-1nm-transistor-roadmap-3d-stacked-cmos-20-plans

Based on 3nm (N3) deliverables assume the die shrink to apply to the iPhone chip a year later.

 

[maerz001]

well many here had high expectations of the 3nm. But seeing the numbers from Apple now for the A17 I don’t know what to expect for a 2nm. I am not hyped

 

[jonnysods]

What is the next smallest measurement after a nanometer?

 

[MacsRgr8]

Funny, I think that is when my wife is due for her next big silicone upgrade...oh wait! 🤣

I am sure that won't be from 3 nanometer to 2...?

 

[nfl46]

So, it will be in 2027/2028 because we know "delays" will happen. Lol.

 

[george88]

so 3-4 years for 3-2nm, and the move from 5-3nm gave a real world increase of 0-10%. Basically looks like we'll get 10-20% increase after the next 5 years, i.e 2-3% per year?

 

[MayaUser]

At this point a big upgrade can be happen between the N3 generations at this point

 

[Torty]

So, it will be in 2027/2028 because we know "delays" will happen. Lol.

And first devices only get little new SW features which are reserved for the next iteration. Miss the freedom of old windows PCs. It was up to you what graphics features you enabled in games.

 

[headlessmike]

Serious question. What happens when they get to 1nm? What’s the next step? .5, or some completely new technology all together?

0.2 nm, also known as 2 Å (for Ångström), is about as small as you can theoretically make anything with a semi-conductor material like silicon since that's the approximate distance between two atoms in the crystal. If we ever get anywhere near that with our current approach is debatable. Quantum effects become increasingly tricky to deal with as sizes shrink down to the level of atoms. More likely we'll have to hope for a major breakthrough somewhere else than shrinking transistors to keep advancing computing power at some point in the not too distant future.

 

[Sorinut]

What is the next smallest measurement after a nanometer?

Angstroms are next. 1 Å = 0.1 nm

 

[Porco]

Big upgrades by getting smaller.

It’s the worst best thing ever so far.

They could be late in their attempts to be early.

But it’s a rumour, that much can be confirmed.

 

[TallGuyGT]

From the wonderlust event, even Apple themselves didn't wheel out the big wigs to announce the A17 pro chip.

I don't know how everyone else felt?

But to me the A17 pro announcement felt rather flat as if Apple themselves weren't quite as excited about this chip as we all expected them to be.

I feel the same way. I was expecting higher performance and increased efficiency based on the change to 3nm. I think the iPhone is plenty fast, but disappointing if we see the same percentages on the M3 family. Also, battery life on my 14 Pro Max has been its weakest point, was hoping for an increase there even if nothing else changed.

 

[fwmireault]

Is A17 considered 'a big upgrade'? I don't think it is. We will see what will happen with the M-series chips, but so far I don't think the 3nm process is close to the expectations

 

[Pman17]

What is the next smallest measurement after a nanometer?

pico

 

[headlessmike]

Is A17 considered 'a big upgrade'? I don't think it is. We will see what will happen with the M-series chips, but so far I don't think the 3nm process is close to the expectations

The 5 nm process was refined several times, perhaps more-so than was often done with larger node sizes of yore because of the challenges of going to 3 nm. Maybe that's why we're not seeing a greater improvement. The 10 percent higher clock speeds in the A17 over the A16 also mitigate much of the efficiency gains.

 

[xxray]

From the wonderlust event, even Apple themselves didn't wheel out the big wigs to announce the A17 pro chip.

I don't know how everyone else felt?

But to me the A17 pro announcement felt rather flat as if Apple themselves weren't quite as excited about this chip as we all expected them to be.

Agreed. I felt that across the board. There were quite a few things I felt like Apple didn’t make a big deal about that I thought they would.

I thought they would’ve made a big deal about the chip, but only 10% CPU improvement and no noticeable efficiency gains for battery life. I thought they would’ve embraced USB-C, but felt just like a passing mention. I thought they would’ve made a big deal about the 15PM having apparently the thinnest bezels on a phone. But nope, just “thinner borders.”

The event was one of the worse ones I’ve seen in recent years. Just didn’t feel as fun, lighthearted, and groundbreaking as other events. I felt pretty disappointed after.

 

[CarAnalogy]

From the wonderlust event, even Apple themselves didn't wheel out the big wigs to announce the A17 pro chip.

I don't know how everyone else felt?

But to me the A17 pro announcement felt rather flat as if Apple themselves weren't quite as excited about this chip as we all expected them to be.

Maybe my expectations weren't high enough to be disappointed but I thought it was pretty good all things considered. Ray tracing was good. A performance boost with the same efficiency is always good and to be expected for a process shrink. I suppose it was just a tock kind of year. Remember Intel used to do the same thing, new design one year, same design on smaller process node the next. Each year had its own advantages.

 

[Populus]

Would be really cool that the first SoC built with the 2nm technology (and hopefully switching from FinFET to GAAFET), was the A20. “A20 Bionic, our fist 2nm chip.”

But I guess that depends more on TSMC and their roadmap. Let’s hope that the first 2nm chip will represent a much higher jump in performance/efficiency, not like the A17 Pro. Maybe the FinFET transistor technology is approaching its limits?

 

[falkon-engine]

If Intel executes on time, its 18A node will already have entered mass production. But that's a big IF.