"Apple would also not be beholden to Intel" - is this ironic in that Apple now seems to make (almost) every move to increase customer dependence on a proprietary Apple ?
You do realize Apple is using ARM processor architecture with their own additional components. Apple isn't designing or building an entirely different CPU, it's still using the current ARM architecture so they are still at least partially beholden on ARM. The problem with Intel is they are slow as a snail in developing better and faster CPUs. ARM has been the faster developer of new CPUs not Intel so why should Apple continue to be slowed down by Intel?
Apple is not a proprietary computer manufacturer. They have a few Apple-designed components but the vast majority of components are common. Read through an iFixit or other vendors teardown and you'll see all kinds of components without Apple's name on them. Even the bulk of macOS has been open-sourced, https://opensource.apple.com. ;
When it comes to ARM, Apple is an ARM ISA licensee: other than waiting on ARM to specify the layout of instructions and what they do, Apple has no constraints by ARM itself: they can achieve that ISA goal in any manner they want on their own timeframe, meaning Apple is then (at most) constrained from the outside by the foundry’s limitations and their own design ability.
The only way they could become less constrained by outside issues is to own a foundry for exclusive use. If we reach a limit for process miniaturization then it might become worthwhile for them to own one if they don’t keep advancing technology, because foundries are very expensive and become outdated (currently) very quickly.
...The first Macs using an Apple-designed 5-nanometer processor will be a 13.3-inch MacBook Pro and a redesigned iMac, Kuo proposes, with both models anticipated to outperform their Intel equivalents by between 50% and 100%.
Old rule from the PPC days when we used emulation to run Windows on a Mac was that Emulation dropped speed by about half. So if they have chips that are up to 100% faster, then Win10 under emulation should run at fairly normal speeds.
...The first Macs using an Apple-designed 5-nanometer processor will be a 13.3-inch MacBook Pro and a redesigned iMac, Kuo proposes, with both models anticipated to outperform their Intel equivalents by between 50% and 100%.
Old rule from the PPC days when we used emulation to run Windows on a Mac was that Emulation dropped speed by about half. So if they have chips that are up to 100% faster, then Win10 under emulation should run at fairly normal speeds.
I'll be surprised if Apple will support emulation. I just don't think it's needed with all the groundwork they've made to make it easy for developers and all the old ones like MS and Adobe that took so long to rewrite their apps now have both a lot of experience with Swift for ARM with their iOS and iPadOS apps, and have a lot more customers than they used to so the financial desire not to lose to a competitor is stronger.
If for some reason you still need an Intel Mac to do your work they use an Intel Mac.
That said, I have no problem with Apple creating another Rosetta option for this transition, but I'm not seeing it as the dire need it was when they were on PPC.
"We estimate that all Mac models will switch to ARM in 12-18 months," said Kuo.
ALL models? What, even the Mac Pro? That doesn't make sense to me. If I'd just spent perhaps in the teens of thousands on a 'future-proof' Mac Pro, I don't think I'd feel too happy if Apple then switched processor families across the line less than a year later.
Mind you, it's only how I'd have felt if I'd been a professional photographer who'd believed Apple's hype about the previous trashcan Mac Pro, and bought one in order to run Aperture on it… (Apple made a big fuss about this use case, and had at least one enticing video about it… and them promptly killed Aperture.)
Given this move, if its true, has been on the cards for years and the Mac Pro was designed with this change in mind we'd have to assume everything about the Mac Pro carries forward to the new CPU. All those PCIe Lanes, Monster Quad GPU set up, Afterburner Card all must be considered specs a ARM based Mac Pro can handle. I'd assume new mainboard as well but same overall layout.
Also, have to consider the old New MacPro (the trash can) was also designed to take an ARM CPU.
Apple should use this opportunity to really trounce the x86 performance enhancers elope.
Don’t just put the latest iPad cpu in the Mac.
Either build out a much more powerful chip with higher wattage requirements or add many CPUs in the mac with hardware traffic control and unity to negate any performance going to mdbsgrntbt.
Apple produces the A series at a nice cost. Significantly cheaper than intel chips.
Use that delta to leapfrog the Intel machines in performance.
"We estimate that all Mac models will switch to ARM in 12-18 months," said Kuo.
ALL models? What, even the Mac Pro? That doesn't make sense to me. If I'd just spent perhaps in the teens of thousands on a 'future-proof' Mac Pro, I don't think I'd feel too happy if Apple then switched processor families across the line less than a year later.
Mind you, it's only how I'd have felt if I'd been a professional photographer who'd believed Apple's hype about the previous trashcan Mac Pro, and bought one in order to run Aperture on it… (Apple made a big fuss about this use case, and had at least one enticing video about it… and them promptly killed Aperture.)
Why not? As long as they support Intel Macs for a reasonable period of time. Product envy will drive an earlier switch. With most major vendors investing in their ARM codebases already the compatibility argument is already mitigated.
I think one major advantage is not in component replacement (x64 > Aarch64 CPU) but in a component architecture shift to integrated components (CPU/GPU/RAM) with custom ISAs, wide memory, etc. It may take a while to match/beat the current Mac Pro but maybe a series of custom accelerator cards could build confidence.
"Apple would also not be beholden to Intel" - is this ironic in that Apple now seems to make (almost) every move to increase customer dependence on a proprietary Apple ?
You do realize Apple is using ARM processor architecture with their own additional components. Apple isn't designing or building an entirely different CPU, it's still using the current ARM architecture so they are still at least partially beholden on ARM. The problem with Intel is they are slow as a snail in developing better and faster CPUs. ARM has been the faster developer of new CPUs not Intel so why should Apple continue to be slowed down by Intel?
Apple is not a proprietary computer manufacturer. They have a few Apple-designed components but the vast majority of components are common. Read through an iFixit or other vendors teardown and you'll see all kinds of components without Apple's name on them. Even the bulk of macOS has been open-sourced, https://opensource.apple.com. ;
Unlike INTEL, ARM doesn't sell CPUs. Apple simply purchased the rights to develop its own CPU based on the architecture provided by ARM, which allows them to customize the SOC to fit there needs and have it fabricated by anyone they choose.
From the Mac perspective, Apple is betting the farm on this.
Say what you will about Tim & his team, but they got balls. Big ones.
I agree with the estimate that these new Macs will be 50-100% falser with CPUs that are 40-50% cheaper. If Apple can sell ARM Macs that are 2x as fast at a reduced price that has a significantly longer battery life, that's a compelling product.
What does it all mean for the chances of a decent file system?
What is wrong with APFS? Not great for spinning rust but it seems very good for SSDs. Any particular complaint?
Nothing wrong with APFS. Very good in fact. I just fear in the move to ARM that file management becomes iPadised. That would be bad.
Access to the file system has nothing to do with being on ARM v Intel or any other architecture Apple has used. It'll still be macOS on ARM just like it was macOS on Intel and PCC.
From the Mac perspective, Apple is betting the farm on this.
Say what you will about Tim & his team, but they got balls. Big ones.
I agree with the estimate that these new Macs will be 50-100% falser with CPUs that are 40-50% cheaper. If Apple can sell ARM Macs that are 2x as fast at a reduced price that has a significantly longer battery life, that's a compelling product.
What does it all mean for the chances of a decent file system?
What is wrong with APFS? Not great for spinning rust but it seems very good for SSDs. Any particular complaint?
Nothing wrong with APFS. Very good in fact. I just fear in the move to ARM that file management becomes iPadised. That would be bad.
Access to the file system has nothing to do with being on ARM v Intel or any other architecture Apple has used. It'll still be macOS on ARM just like it was macOS on Intel and PCC.
Yes, but if apple is trying to push tags instead of directories, I fear. An OS issue that they will use silicon changes to push at the same time. Maybe I am being too paranoid.
Switching to ARM is risky but the right thing for Apple to do. Apple has repeatedly demonstrated that it can excel at CPU design. From a developer standpoint supporting the ARM CPU is zero difficulty. You just tell Xcode to compile for ARM and you are done. Better, Apple has bitcode so it's possible to compile once and have your code recompiled for future versions of both the ARM and Intel CPUs if you distribute it via the App Store. It's going to be tough going at first while we wait for the apps we need the most to get converted but in a year or so, it won't be a problem at all. This should be a much smoother transition than the one from PowerPC to Intel or 68000 to PowerPC.
From the Mac perspective, Apple is betting the farm on this.
Say what you will about Tim & his team, but they got balls. Big ones.
I agree with the estimate that these new Macs will be 50-100% falser with CPUs that are 40-50% cheaper. If Apple can sell ARM Macs that are 2x as fast at a reduced price that has a significantly longer battery life, that's a compelling product.
How much cheaper does the entire machine become when you reduce the processor cost by half? I'm assuming that while this reduce the price and gives Apple an opportunity to adjust everything so that their profit margins are the same, that this will more than likely result in increasing the value of the produce in other areas as opposed to some specific price drop that is off kilter with psychological pricing.
For example, if this reduces the total cost by 47, I don't think a $1,299 MBP will now be $1,253. They may consider lowering it to $1,249 which eats additional profit from the previous machine, but they may run the numbers and find that they'd increase their unit sales enough to offset the low in per-unit profit for an increased profit for the product category.
Personally, I'd rather keep the MBP in question at $1,299 and at the same profit margin—it's a nonstarter for those that claim Apple has enough money and should reduce their prices because blah blah blah—and increase the quality or capability of other components to make up the difference.
I’m excited about the hardware transition, but worried about the software transition. Some pro software will take many years to transition. Some software houses might possibly even throw in the towel.
I really hope Apple is showing a very convenient, flexible and scalable way to compile for ARM macs.
Moving to AMD Zen 3 and beyond would be a seamless and zero cost direction! While increasing profits, lowering prices and increasing performance. Moving to ARM is a 5 year head ache where in fact ARM will never match nor surpass AMD.
Comments
The only way they could become less constrained by outside issues is to own a foundry for exclusive use. If we reach a limit for process miniaturization then it might become worthwhile for them to own one if they don’t keep advancing technology, because foundries are very expensive and become outdated (currently) very quickly.
If for some reason you still need an Intel Mac to do your work they use an Intel Mac.
That said, I have no problem with Apple creating another Rosetta option for this transition, but I'm not seeing it as the dire need it was when they were on PPC.
I think one major advantage is not in component replacement (x64 > Aarch64 CPU) but in a component architecture shift to integrated components (CPU/GPU/RAM) with custom ISAs, wide memory, etc. It may take a while to match/beat the current Mac Pro but maybe a series of custom accelerator cards could build confidence.
https://misterbg.org/AppleProductCycle.html
MR's latest: https://www.macrumors.com/2020/06/21/leaks-suggest-no-hardware-at-wwdc/
For example, if this reduces the total cost by 47, I don't think a $1,299 MBP will now be $1,253. They may consider lowering it to $1,249 which eats additional profit from the previous machine, but they may run the numbers and find that they'd increase their unit sales enough to offset the low in per-unit profit for an increased profit for the product category.
Personally, I'd rather keep the MBP in question at $1,299 and at the same profit margin—it's a nonstarter for those that claim Apple has enough money and should reduce their prices because blah blah blah—and increase the quality or capability of other components to make up the difference.