Hard Truths About The Apple Silicon Replacement to the Mac Pro (2019)

[Confused-User]

Yes, obviously it's a trade-off where if the chip isn't ready then it isn't ready, but from a purely marketing perspective it's much better if your most expensive hardware isn't a generation behind your cheaper SKUs, especially when selling to consumers.

Apple's current situation works against itself where if you were in the market for an M1 Max Studio you might end up being "downsold" to an M2 Pro Mac Mini.

I completely agree, and as I said, I think Apple's marketing team would prefer that as well. Nevertheless, there are strong technical reasons for this trend to continue, even though I think there's a good chance we'll see the trend broken this year due to the N3 hiccup at TSMC. If TSMC can stick to their schedule in future years, it's more likely than not that Apple Marcom will just have to suck it up and do their best selling M3 Mac Pros while M4 Airs are starting to ship.

Hm, interesting, I wasn't thinking about this earlier, but if my first prediction about an M3 Mac Pro comes true (which is, recall, a low-confidence prediction!) then there's a pretty decent chance we wind up with no M3 generation of any other devices, unless they ship in the fall of this year. I can easily see some or all Macs going directly from M2 to M4 chips, moving to cores from the A17. Of course, Marcom would be very upset about this, so perhaps they will still be called M3, and they'll just have updated cores. Or, I suppose, the A17 could have nothing new beyond the original N3 design that was supposed to ship last year, and then all the Macs would indeed get M3s matching the M3 in the Mac Pro.

That would be interesting, because they'd still be very strong chips (new design + new process), and yet that would leave more advances for the A18, making it a more significant upgrade than it would otherwise have been.

The real takeaway... stock lots of popcorn, it's going to be a fun year!

 

[deconstruct60]

I agree that that's an unlikely choice for Apple to make, but it's not crazy. Numerous other machines have been designed that way in the past, including at least one by Apple (the 2006-2010 Mac Pro, with the CPU/RAM daughterboards).

This would likely be far more than just CPU+RAM. it is really GPU . Along with that probably drag in at least some of the TBv4 and/or video out. Very good chance the SSD module connectors as well. And some of the power management chips that have very tight coupling to the SoC main die.

Nothing on the card would be a commodity replaceable item. Nor will the card itself be a highly elastic commodity (the connector would probably be as proprietary as the 2009-2012 and 2013 were. So when Apple stops making them, essentially down to the 'used parts' market dynamics. )

 

[Confused-User]

Man, am I the only one watching Apple's WWDC videos?

No, you're just the only one who thinks that a video from 2.5 years ago is the gospel truth now and forever.

x86 macOS supports AMD GPUs (whether external via Thunderbolt or internal via PCIe). Apple Silicon macOS does not. As in you can write an ARM64 driver for your AMD GPU and attempt to install said driver and the video card will not function. Call that "Apple owning the whole stack" or whatever. I don't really care. I'm saying that they designed THAT OS and THAT hardware architecture so as to not support third party GPUs. It would stand to reason that if that wasn't the case, we'd already have people getting AMD GPUs to work with Apple Silicon Macs. However, unless I missed something, that hasn't happened.

False, at the very least by implication. They didn't want/need to support off-SoC GPUs when the SoCs were designed, so they didn't bother to put in features they'd only need in order to do that. That's very different from designing in features to prevent that. Adding those features to their SoC (at least, the SoC for the Mac Pro) and OS is simply not challenging for Apple.

And they've stated repeatedly that they do not want to support off-SoC GPUs. Furthermore, the person I was replying to was making a distinction between eGPUs and PCIe GPUs. You needn't insult my intelligence by assuming I don't know the difference between the two.

You're right, I have no need to do that...

 

[Confused-User]

This would likely be far more than just CPU+RAM. it is really GPU . Along with that probably drag in at least some of the TBv4 and/or video out. Very good chance the SSD module connectors as well. And some of the power management chips that have very tight coupling to the SoC main die.

Nothing on the card would be a commodity replaceable item. Nor will the card itself be a highly elastic commodity (the connector would probably be as proprietary as the 2009-2012 and 2013 were. So when Apple stops making them, essentially down to the 'used parts' market dynamics. )

True, about the GPU, to the extent that it's still integrated in the SoC. Which is really just saying that it's a damn expensive SoC.

As for the rest... maybe, but I doubt it. The whole point would be to keep those on the mainboard. You might need redrivers for the PCIev5, but that would be enough to carry TB4, SSD traffic, etc. You'd probably do separate links for video... I don't know enough to be sure. Or perhaps you'd just have native PCIe and native TB4 separate, with video on the TB4 links. Redrivers all around, and it would add some expense to be sure. Not enough to matter all that much on a Mac Pro.

Anyway, pointless speculating about this further - I don't think Apple is going to go this way.

 

[leman]

If you think about it Apple could possibly offer upgradeable RAM if they offer the SoC as a user upgradebale part. 😆

Wonder how much that would cost? 😜

Upgradable SoC doesn’t sound that hard - just put it on a separate slotted board with a high bandwidth connection to the rest of the system. Something like 32x PCIE 5 would more than sufficient for years to come.

Upgradeable RAM is much trickier. Replaceable RAM modules with that many pins would be tremendously hard to design and very very costly. Better approach would be to use tiered memory (where say each 256-bit fast RAM slice is backed by a single 64-bit DDR5 channel). Apple does have a patent on this but it’s fairly general. BTW, this is the model that Intel implements with latest Xeons - they have HBM2 RAM close to the chip and DDR5 as backing RAM.

 

[sam_dean]

Upgradable SoC doesn’t sound that hard - just put it on a separate slotted board with a high bandwidth connection to the rest of the system. Something like 32x PCIE 5 would more than sufficient for years to come.

Upgradeable RAM is much trickier. Replaceable RAM modules with that many pins would be tremendously hard to design and very very costly. Better approach would be to use tiered memory (where say each 256-bit fast RAM slice is backed by a single 64-bit DDR5 channel). Apple does have a patent on this but it’s fairly general. BTW, this is the model that Intel implements with latest Xeons - they have HBM2 RAM close to the chip and DDR5 as backing RAM.

No... what I meant was the SoC with built-in RAM will be sold as an 1pc upgrade part.

So if you want to go from M1 Ultra 32GB RAM to M2 Ultra 192GB then you'll need to get that single chip upgrade.

 

[leman]

No... what I meant was the SoC with built-in RAM will be sold as an 1pc upgrade part.

So if you want to go from M1 Ultra 32GB RAM to M2 Ultra 192GB then you'll need to get that single chip upgrade.

Yeah, that’s the first paragraph of my post.

 

[sam_dean]

Yeah, that’s the first paragraph of my post.

Your 2nd paragraph makes it appear that its a 2 part solution.

 

[leman]

Your 2nd paragraph makes it appear that it’s woa 2 part solution.

Two solutions to two problems which could be used together or separately 😁

 

[Yebubbleman]

I think it makes sense to distinguish between the policy and the technical underpinning. The way I understand it you talk about policy: Apple does not want to allow third-party GPUs in their new Macs (and I agree with this interpretation). But it's not like Apple's hardware is fundamentally incompatible with third-party GPUs. Sure, right now third-party GPUs won't work due to the limitations on how device memory mapping works (which is most likely a security feature, not a way to sabotage GPUs), not to mention that macOS does not contain any provisions for registering a custom GPU driver. But if Apple were to change their policy about third-party GPUs (which they probably won't), fixing these things shouldn't be too difficult.

They're not changing their policy. Hence why it's a moot point.

Yeah that's not happening. The SoC is the whole machine. You might as well swap/trade the whole machine.

Except it isn't the whole machine. It's the CPU, GPU, and RAM. That's not a whole computer. You have storage and you have PCIe slots and I/O. The 2009, 2010, and 2012 Mac Pros did the exact same thing with a backplane. The only difference is that the GPU wasn't involved and you could upgrade the RAM separately from the processor.

The highest end customers, aka the 2% that Mac Studio and Mac Pro AS won't address, have been floating between Mac and Windows for 15 years depending on what hardware is out that week. They don't care. They have no allegiance. Their only allegiance is to processing time.

I don't dispute this.

Again, you have to remember that the Mac Pro once covered a wide range of users, so it made sense for Apple put the resources into designing this machine (including the high end aspects of it). There were plenty of desktop Mac users that were happy to buy a $2500 Mac desktop and maybe one day upgrade some RAM, but that's it. Never touched storage, never used PCI slots. Apple's new systems cover most of those users better than ever before, and its only this tiny group of people at the top that are not serviced. If Apple sees any money to be made by doing something different for these people, they might, but I sincerely doubt it. Their focus and direction with Apple Silicon is clear, and I don't see them breaking from that to make a different kind of Mac for the 2% who already float between Mac and Windows.

They did say that they were going to get to the Mac Pro. It might not be everyone's cup of tea. But I think they realize that there are those that want (a) PCIe slots, (b) More than 192GB of RAM. I can't say whether or not they'll socket the SoC. Just that there's nothing that prevents them from doing so. They very clearly don't want third party GPUs. The notion that they'll reverse course on that is simply not realistic.

SSD was never on the SoC.

No. But the SSD controller is. Was on the T2 before Apple Silicon. But same distinction.

Fair enough, but it went from being hardwired to the logic board to separate with a connector with no reduction in performance. I think Apple is going to design a high-bandwidth connector to allow for things like GPUs.

In the case of the iMac Pro and 2019 Mac Pro, the SSD controller was on the T2 chip. The NAND chips were on separate boards, but they are not a complete SSD on their own. The same is more or less true of all other T2 Macs (though the NAND chips are on the logic board, so from a parts standpoint, it's somewhat moot). This is also true of all Apple Silicon Macs as well as all Mac Studio models. Furthermore, to replace those NAND modules means you lose the data one the ones you pull out and, as was the case with T2 storage, you'd need to DFU restore a Mac Studio to get replacement storage modules to function properly. It sucks, but it's nothing new at this point.

Very true. I just think that contrary to the OP’s three year old video, which didn’t even mention fusing two M1-Maxs together, Apple is capable of supporting internal expandability in the way that Mac Pro users want.

Fusing two M1 Max modules together doesn't change what Apple presented in that video. Graphics still works the same way. And Apple IS capable of supporting replacing the SSDs and they ARE capable of replacing the SoC. They are not going to allow third party GPUs given the direction they've chosen to go in for Apple Silicon Macs.

If you think about it Apple could possibly offer upgradeable RAM if they offer the SoC as a user upgradebale part. 😆

Wonder how much that would cost? 😜

Not sure how this logic follows considering the unified memory is on-chip. Unless you're meaning that the SoC being upgradeable is a way in which RAM is also upgradeable.

There are likely two factors driving Apple with the SSD Module design being used on higher end desktop Macs.


1. Costs. The more expensive the board to replace , the more they will save themselves money in repair inventory parts inventory costs and on 'damage' to AppleCare revenue ( hits on insurance pay offs ) with a more cost effective solution. It is Apple saving themselves as much as anyone else.

iMac Pro -- relatively very expensive GPU and VRAM soldered to the board. One NAND chip goes back and have to replace the whole board. Versus, two new NAND SSD Modules. ( in 'SSD Modules' the 'SSD' is an adjective, not a noun. Those are not SSDs. They are modules that belong to a single SSD. The 'NAND chip daughtercard is being replaced. The SSD is not. )

Mac Pro 2019 -- similar. NAND chip package dies and expensive Server grade , dual input PLEX PCI switch and very expensive double sided , super sized motherboard gone. Versus two new NAND SSD Modules.

iMac 2020 -- not quite as an expensive board. Solder from 128G - 2 TB. Using one NAND module to go from 4-8TB. Statistically when using substantively more NAND modules on the board shift the risk profile so that some hits are to a module ( and not whole motherboard).

Mac Studio Ultra -- see above iMac Pro case. Effectively, the same situation.


Back in 2017 era there was also a cost factor where Apple could get to higher SSD capacities by just using more NAND chips (and just easier to use two modules of them).

2. Decommision data retention policy. Some places require that a disk be pulled before 'retire' any system from some service on sensitive data. Maybe it will get used by someone else, but certainly won't be using those same drive(s).

If every single system in Apple's Mac line up had soldered on drivers some folks would stop buying.


3. Wear and likely user workloads. The one and only one internal drive 'mindset' that Apple fosters tends to drive some folks to hoard every last drop of data all onto one drive. It is a bit goofy to mix highly mutating intermediate fiels with those with average or worse zero change rate all onto one SSD. Don't really need a 1DWPD drive to store pictures archive that is likely never going to change. It is just two different workloads.

Short and intermediate term can get along but over the very long term it can bring higher failure rates.





Low power really isn't a issue either way. In either case the SSD controller and the Secure element ( encryption) are all sharing the same RAM over a shorter distance. That's less power right there. The NAND chips on a daughtercard or soldered to the board are going to use the same amount of power. The NAND chips are always off the package (and die) either way. The daughter card solution is incrementally further away but now down in the 'diminishing returns' of power savings. ( if could find NAND chips that consumed lower power , that would have a bigger impact than removing the daughter card socket transition 'losses'. )


The bigger issue with most Apple designs is the "thinness politburo' mandates for minimum z-height. Soldered to the main board is shorter, even if less volume efficient. iMac , Studio , MP don't have quite as rigid of a 'thin' mandate.

You make good points and, now that I think about it, I have no clue why the 2020 27-inch iMac "needed" a module board for 4TB and 8TB drives when the 2019 16-inch MacBook Pro never needed that for its SSD. And the "must decomission the drive before retiring" element definitely causes a lot of Macs to get destroyed when retired. Definitely wasteful.

 

[sam_dean]

Not sure how this logic follows considering the unified memory is on-chip. Unless you're meaning that the SoC being upgradeable is a way in which RAM is also upgradeable.

RAM is on the SoC, correct?

Make SoC socketed so if you want to upgrade RAM you also include the SoC.

RAM is placed on the SoC to improve performance and reduce latency.

 

[Yebubbleman]

RAM is on the SoC, correct?

Make SoC socketed so if you want to upgrade RAM you also include the SoC.

RAM is placed on the SoC to improve performance and reduce latency.

So, socket RAM ON the SoC?

 

[sam_dean]

So, socket RAM ON the SoC?

RAM is as is on the SoC. SoC it is on is socketed onto the logic board.

 

[leman]

RAM is as is on the SoC. SoC it is on is socketed onto the logic board.

That could work, with the caveat that these SoCs can get quite big and a single socket could become a problem. That’s why I’m thinking about putting the SoC and the supporting power circuitry on a separate modular board.

 

[sam_dean]

That could work, with the caveat that these SoCs can get quite big and a single socket could become a problem. That’s why I’m thinking about putting the SoC and the supporting power circuitry on a separate modular board.

Doing so would reduce performance and add more material that will add cost & space used.

 

[leman]

Doing so would reduce performance and add more material that will add cost & space used.

Performance would depend on the design of a connector, so I don't agree that using a modular board connector automatically means lower performance. And surely, a separate board will be more expensive (although don't underestimate the cost and complexity of these large CPU sockets).

But one of the main reasons why I think that an Apple-designed upgradeable Mac Pro would feature replaceable SoC boards rather than replaceable SoCs is the plug and play nature of the first solution. Requiring the user to dissasamole the heatsink, reapply thermal compound... that strikes me as very un-Apple. On he other hand, plugging in a mysterious-looking shiny black box into a sophisticated connector and securing it with a single press of a level, well, that sounds much better, doesn't it?

 

[diamond.g]

Performance would depend on the design of a connector, so I don't agree that using a modular board connector automatically means lower performance. And surely, a separate board will be more expensive (although don't underestimate the cost and complexity of these large CPU sockets).

But one of the main reasons why I think that an Apple-designed upgradeable Mac Pro would feature replaceable SoC boards rather than replaceable SoCs is the plug and play nature of the first solution. Requiring the user to dissasamole the heatsink, reapply thermal compound... that strikes me as very un-Apple. On he other hand, plugging in a mysterious-looking shiny black box into a sophisticated connector and securing it with a single press of a level, well, that sounds much better, doesn't it?

Bringing back Pentium 2/3 glory days... (Slot 1)

 

[PauloSera]

They did say that they were going to get to the Mac Pro.

They did, and what we know from the supply chain, is that it is basically a 2x Mac Studio.

 

[v0lume4]

RAM is as is on the SoC. SoC it is on is socketed onto the logic board.

Quick aside from the main convo at hand: Does the term "SoC" refer to everything on the substrate? Or does that term refer to just the M1/M2 chip itself? i.e. - The RAM chips are separate chips which I did not know -- naively -- until I saw the photos in this article: https://www.macrumors.com/2023/01/30/new-macbook-pro-features-smaller-heatsink/.

 

[sam_dean]

Quick aside from the main convo at hand: Does the term "SoC" refer to everything on the substrate? Or does that term refer to just the M1/M2 chip itself? i.e. - The RAM chips are separate chips which I did not know -- naively -- until I saw the photos in this article: https://www.macrumors.com/2023/01/30/new-macbook-pro-features-smaller-heatsink/.

Everything on the SoC package.

Example

 

[v0lume4]

Everything on the SoC package.

Cool. Thanks!

 

[v0lume4]

@sam_dean Just saw your edit with the photo. Super helpful. Are the "memory modules" (using the terminology from the article author) shown in the MR article from the other day the SSD storage?

The modules I'm asking about are the 2 big modules flanking the M1 chip/the four slim modules flanking the M2 chip.

New MacBook Pro Features Smaller Heatsink Due to Supply Chain Issues

The M2 Pro and M2 Max MacBook Pro models feature a considerably smaller heatsink due to supply chain issues, teardowns suggest. Top: M1 Pro logic...

www.macrumors.com

 

[sam_dean]

@sam_dean Just saw your edit with the photo. Super helpful. Are the "memory modules" (using the terminology from the article author) shown in the MR article from the other day the SSD storage?

The modules I'm asking about are the 2 big modules flanking the M1 chip/the four slim modules flanking the M2 chip.

New MacBook Pro Features Smaller Heatsink Due to Supply Chain Issues

The M2 Pro and M2 Max MacBook Pro models feature a considerably smaller heatsink due to supply chain issues, teardowns suggest. Top: M1 Pro logic...

www.macrumors.com

NAND flash memory without controller for the SSD is situated on the logic board.

This is why the Mac Studio cannot be upgraded with off the shelf SSDs.

IIRC the SSD controller is part of the SoC. This lowers production cost, complications, latencies... aka increasing performance per watt while producing material cost.

This image below is of the M1 Pro SoC.

The 4 black squares to the left and right of the center are the RAM. The rectangle that holds all the parts is called the package.

So imagine that rectangle as a socketed part. You replace the whole thing when you want to increase RAM or cores.

My method would satisfy the technical advantages Apple wants to implement and end users desire to upgrade their Macs when money comes in.

Caution: doing so adds cost, space, complications and other things that would increase the production material cost. I would not be surprised that the largest or major expense in making Macs with Apple Silicon is the requirement of using the leading edge node. All other parts not directly sourced from TSMC would be reduce.

If you compare the logic board size/weight & how spread out ICs and other parts are on the last Intel Mac mini vs Mac mini M1 you'd find it drastically different. Many questioend why Apple kept the enclosure PSU as is as they were oversized for a logic board that used no more than 39W and of a size that is similar to an iPhone while the Intel logic board encompassed the whole insides of the Mac mini.

Perhaps cost-wise keeping these hold over parts was cheaper or unchanged "as is".


BTW your username photo lends me to think you were a gear head so you would already knew what a Apple Silicon Mac SoC and logic board would look like.

Like the 2021 iMac 24" M1... many people have issue with the "chin". Many did not see Apple's product video that revealed where the M1 SoC, logic board and speakers were all placed within the chin.

As a class project a Chinese industrial design student eliminated the chin and placed them at the lowest part of the iMac to make a "butt".

I personally prefer the chin as the butt does not look on a LG OLED 4K TV and it still does not look great on an iMac. Advantge of the OLED TV is that you rarely look at its backside while on a Mac it is located in places where the back side is often seen or have I/O devices plugged and uplugged.

 

[v0lume4]

NAND flash memory without controller for the SSD is situated on the logic board.

This is why the Mac Studio cannot be upgraded with off the shelf SSDs.

IIRC the SSD controller is part of the SoC. This lowers production cost, complications, latencies... aka increasing performance per watt while producing material cost.

This image below is of the M1 Pro SoC.

The 4 black squares to the left and right of the center are the RAM. The rectangle that holds all the parts is called the package.

So imagine that rectangle as a socketed part. You replace the whole thing when you want to increase RAM or cores.

My method would satisfy the technical advantages Apple wants to implement and end users desire to upgrade their Macs when money comes in.

Caution: doing so adds cost, space, complications and other things that would increase the production material cost. I would not be surprised that the largest or major expense in making Macs with Apple Silicon is the requirement of using the leading edge node. All other parts not directly sourced from TSMC would be reduce.

If you compare the logic board size/weight & how spread out ICs and other parts are on the last Intel Mac mini vs Mac mini M1 you'd find it drastically different. Many questioend why Apple kept the enclosure PSU as is as they were oversized for a logic board that used no more than 39W and of a size that is similar to an iPhone while the Intel logic board encompassed the whole insides of the Mac mini.

Perhaps cost-wise keeping these hold over parts was cheaper or unchanged "as is".


BTW your username photo lends me to think you were a gear head so you would already knew what a Apple Silicon Mac SoC and logic board would look like.

Like the 2021 iMac 24" M1... many people have issue with the "chin". Many did not see Apple's product video that revealed where the M1 SoC, logic board and speakers were all placed within the chin.

As a class project a Chinese industrial design student eliminated the chin and placed them at the lowest part of the iMac to make a "butt".

I personally prefer the chin as the butt does not look on a LG OLED 4K TV and it still does not look great on an iMac. Advantge of the OLED TV is that you rarely look at its backside while on a Mac it is located in places where the back side is often seen or have I/O devices plugged and uplugged.

You'd be correct in calling me a gear head, but my knowledge is lacking when it comes to SoC's! Your responses helped a lot with that big question mark in my head where I wondered, "How is Apple offering all these different SKU's with RAM upgrades? The RAM isn't part of the main M1/M2 die, is it?" I now know that the answer is no.

Regarding your proposed upgrade solution: That'd be one heck of an expensive RAM upgrade if you're having to purchase a whole new SoC package or expansion card (containing the SoC) -- but I don't see why it couldn't work. I wonder how the cooler would be handled... if you can simply drop a new SoC into the socket then no biggie. If it sat on an expansion card, perhaps the expansion card could lie parallel to the motherboard, similar to NVMe drives. Then you could easily unmount/mount your cooler. That is, unless, Apple somehow sold a solution with the cooler already assembled.

I've missed a lot of the good discussion that's already occurred across the previous nine pages of this thread. I really don't know what we're going to see this year. I know Apple isn't stupid -- they outright admitted their mistakes with the Trash Can Mac Pro. But... I have this bad feeling that we're going to see a Trash Can-esque scenario with this next Mac Pro. I hope not!

 

[sam_dean]

You'd be correct in calling me a gear head, but the bulk of my knowledge lies with traditional, modular machines. I don't know as much about SoC's! But your responses helped a lot with that big question mark in my head where I wondered, "How is Apple offering all these different SKU's with RAM upgrades? The RAM isn't part of the main M1/M2 die, is it?" I now know that the answer is no.

Regarding your proposed upgrade solution: That'd be one heck of an expensive RAM upgrade if you're having to purchase a whole new SoC package or expansion card (containing the SoC) -- but I don't see why it couldn't work. I wonder how the cooler would be handled... perhaps the expansion card could lie parallel to the motherboard, similar to NVMe drives. Then you could easily unmount/mount your cooler. That is, unless, Apple somehow sold a solution with the cooler already assembled.

I've missed a lot of the good discussion that's already occurred across the previous nine pages of this thread. I really don't know what we're going to see this year. I know Apple isn't stupid -- they outright admitted their mistakes with the Trash Can Mac Pro. But... I have this bad feeling that we're going to see a Trash Can-esque scenario with this next Mac Pro. I hope not!

I expect Apple to use the same 2019 Mac Pro 14nm case design but the only user accessible part may be an updated PCIe slots.

2013 Mac Pro 22nm "trash can" design is an indirect predecessor for the 2021 Mac Studio 5nm as the functionality are similar but condensed down to a 3.7L enclosure.

I had a 2002 Power Mac G4 180nm and we never occupied any of the PCI expansion slots. The Mac Studio equivalent in 2002 would have been perfect for us. And no, the cube isn't it.

I would be surprised if Apple were to allow replaceable storage whether it be SATA or NVMe on those PCIe slots.

In truth there will be a severely limited audience for it as the Mac Studio would get a sizeable chunk of the users who bought a Mac Pro but need not the expansion slots and I expect it to sell at $6k or more and most I/O ports that almost all users need are already present in almost all Macs via TB3 ports that are PCIe-enabled.

As we progress from node to node the performance of workstations as desktops have trickled down to the laptop. That's why ~80% of PCs have been laptops for ~2 decades.

Failure of moving node to node induced Apple transitions in the past

- Jan 2006: PowerPC chip at 90nm to Intel chip at 65nm
- Nov 2020: Intel chip at 14nm to Apple chip at 5nm
- Sep 2023: 4nm/5nm to 3nm