Apple Transitioning Macs to Custom Chips With 'Incredible' Performance Starting Later This Year

[djjeff]

I gave you the basis for my knowledge so you could determine its veracity and so the limits of my knowledge would be understood. I then told you which part of the statement I had knowledge about and which I did not.

Merely being a PPC designer does not qualify you as an authority as to IBMs corporate decisions.

I don't know what sort of evidence you would accept, but it's highly unlikely that any IBM employees with contemporaneous knowledge are willing to log in here and tell you what they were thinking at the time.

Something that is not supposition or conjecture would be a good start. I am not going to hold a discussion on someone's idea of what may or may not have happened.

 

[cmaier]

Merely being a PPC designer does not qualify you as an authority as to IBMs corporate decisions.


Something that is not supposition or conjecture would be a good start. I am not going to hold a discussion on someone's idea of what may or may not have happened.

The only one who knows WHY IBM made corporate decisions are the corporate officers who made the decisions, and they are not here. So if that’s the only evidence you will accept, you will be waiting a long time.

That said, knowing WHAT corporate decisions IBM made *IS* something I am an authority on, because I was competing with them at the time and i know what their chips were. I know their specs, I know what design decisions they made, I know what their circuits looked like, and I know how to look at all the information and reverse engineering and determine what the engineering goal is. You see dynamic logic, and you know the goal was speed, not power conservation. You see a monolithic power grid, and you know they weren’t too concerned about power dissipation because they didn’t build any way to stop static leakage for idle circuits. You see no clock gating and you know they don’t care about power dissipation because they don‘t stop unused wires from toggling. You see oversized drivers and you know they are focused on maximizing drive strength for speed.

So, yes, I am perfectly qualified to say what i said, which you objected to: IBM’s chips were focused on the highest possible performance, and not on power conservation for laptops and small-box computers. We also know that these chips WERE used in IBM’s workstations at the time (google search will prove that), so if your objection is to “the reason they cared about speed is they cared about workstations” then it’s not a huge logical leap.

 

[djjeff]

The only one who knows WHY IBM made corporate decisions are the corporate officers who made the decisions, and they are not here. So if that’s the only evidence you will accept, you will be waiting a long time.

I'm not waiting at all. If you cannot authoritatively speak to this why do you feel it necessary to speak to it in any context other than opinion?

 

[cmaier]

I'm not waiting at all. If you cannot authoritatively speak to this why do you feel it necessary to speak to it in any context other than opinion?

I just stated multiple facts. It’s not an “opinion” that IBM used dynamic logic, and that the purpose of dynamic logic is to achieve speed at the cost of much increased power consumption. It’s not an “opinion” that they didn’t use gated clocks, segregated power grids, etc. These are facts, not opinions. And it is a fact that these are all techniques that are correlated to designing for speed, not for power conservation.

I mean, I don’t even understand what your beef is with me. I didn’t state anything that was merely an unsubstantiated opinion.

 

[djjeff]

I just stated multiple facts. It’s not an “opinion” that IBM used dynamic logic, and that the purpose of dynamic logic is to achieve speed at the cost of much increased power consumption. It’s not an “opinion” that they didn’t use gated clocks, segregated power grids, etc. These are facts, not opinions. And it is a fact that these are all techniques that are correlated to designing for speed, not for power conservation.

None of which is relevant.

I mean, I don’t even understand what your beef is with me. I didn’t state anything that was merely an unsubstantiated opinion.

I have no beef with you. I stated that just because you were a PPC designer does not make you an authority on the decision making process. You acknowledge as much. So I am puzzled, after this admission, why you're still trying to speak as an authority.

 

[Alan Wynn]

Completely and 100% incorrect.

As a faculty member, I used to refer to this as: “proof by vehement assertion” and give zero credit. Given than you have not yet presented any proof for your arguments, and have ignored all the facts (like Intel/AMD do not have a system in the top 5 fastest machines) and actual experts, no real point in responding to you. My points are all easily verified by looking at Motorola’s sales data (should not be too hard to find on the web), and how IBM used its PowerPC chips (all for Big Iron - their fastest mainframes). None of that will matter to you, as you are unwilling to be swayed.

You also refuse to provide any objective criteria for success moving forward (either in this argument or for Apple’s choice), meaning that no matter what is said, nor what actually happens, you will still claim to be right.

 

[djjeff]

As a faculty member, I used to refer to this as: “proof by vehement assertion” and give zero credit. Given than you have not yet presented any proof for your arguments, and have ignored all the facts (like Intel/AMD do not have a system in the top 5 fastest machines) and actual experts, no real point in responding to you. My points are all easily verified by looking at Motorola’s sales data (should not be too hard to find on the web), and how IBM used its PowerPC chips (all for Big Iron - their fastest mainframes). None of that will matter to you, as you are unwilling to be swayed.

You can refer to it as whatever you want in your "appeal to authority" response and therefore I give this response zero credit. See, two can play at that game.

You also refuse to provide any objective criteria for success moving forward (either in this argument or for Apple’s choice), meaning that no matter what is said, nor what actually happens, you will still claim to be right.

Success in what? Apple changing to ARM? Does it really matter? Apple is making the transition. They'll be successful because anyone who wants to use a Macintosh will have no option but to use the ARM systems (after the transition).

 

[MyopicPaideia]

x86 won (for that time) because it was faster and would scale better than PPC (despite PPC being a RISC architecture).
[automerge]1593087019[/automerge]

What is this supposed to mean? Some Youtube blogger, like many here, thinks ARM is the cats meow?

Infinitely more credible source than you are, for example, and gives strong and thorough answers to every single one of your arguments. This is why all you can do is try to discredit it rather than argue against it. Same with @cmaier - you just try to discredit rather than prove your assertion. Given the fact that the video is 18 months old and has been 99.9% accurate to date is also a telling fact that makes this Youtube blogger a much more reliable source than some “Macrumors.com forum member” like yourself.

I am not vested either way, and so have done outside research on the topic, and have come to my own conclusions, but you certainly seem heavily vested in this. What do you personally stand to lose if by some quirk of fate you are actually wrong and there is an inherent advantage to RISC architecture over CISC as it is today? Is most of your savings bound up in Intel stock?

I mean everyone who has answered your questions you have not actually tried to have a proper debate with, you simply tried to discredit them. So why don’t you come with some advantages that CISC has over RISC instead, cite sources, etc like we all have done?

It seems to me the only real advantage CISC has right now is that it is the current mainstream for laptop and desktop computers. How this came about is actually most likely more of a business issue than a technical superiority one. Political or pulling rank decisions maybe, or it was able to become the first widely commercially successful platform, which gave it the support of an OS that became the defacto dominator for almost 20 years, and thus also the main target for software development? I mean it wouldn’t be the first time inferior technology won out for the sake of politics and business!!

 

[Admiral]

The cost of production of an Apples A12Z is around $50-60 while i9 is $400, now if Apple pockets all that savings or pass it the customers is yet to be seen, but my feeling is they would want those market share to make this a viable direction without sales of a new architecture somebody has to answer the investors.

If the performance is more than 30% greater compared to an equivalent Intel CPU at the time of release, there is no way Apple will lower selling prices. If it's 100%, look out.

 

[Alan Wynn]

If the performance is more than 30% greater compared to an equivalent Intel CPU at the time of release, there is no way Apple will lower selling prices. If it's 100%, look out.

Apple has had a remarkably consistent margin over the years, and I expect them to maintain it. They can produce cheaper machines with comparable specs to their current machines, machines with much better specs that cost about the same as the current machines, or some combination (somewhat better specs, somewhat lower price). That would be my expectation. I think increasing market share with an equivalent margin is a very compelling story to Wall Street.

 

[Abazigal]

It’s always fun to see Apple usher in a new world order.

 

[hobowankenobi]

Apple has had a remarkably consistent margin over the years, and I expect them to maintain it. They can produce cheaper machines with comparable specs to their current machines, machines with much better specs that cost about the same as the current machines, or some combination (somewhat better specs, somewhat lower price). That would be my expectation. I think increasing market share with an equivalent margin is a very compelling story to Wall Street.

Agreed. Increasing market share now means more than just hardware sales volume and add-on sales in Apple Stores. It also means services income (iCloud, App Store, iTunes, etc), which has become a substantial part of their revenue stream. They could even model lower hardware margins at some point if volume increases, and keep investors very happy.

 

[cmaier]

It’s always fun to see Apple usher in a new world order.

Yep.

1984: Mac - usher in the GUI and death of the command line
2001: iPod - usher in digital media and death of physical media
2007: iPhone - usher in computers in your pocket and the sharing economy, death of more industries than i can count
2012: iPad - usher in tablets and death of ultra books (ok, that one is minor)
2015: Apple Watch - usher in wearables and death of the swiss watch industry
2020: Apple Silicon - usher in death of the Wintel hegemony

 

[dgdosen]

Yep.

1984: Mac - usher in the GUI and death of the command line
2001: iPod - usher in digital media and death of physical media
2007: iPhone - usher in computers in your pocket and the sharing economy, death of more industries than i can count
2012: iPad - usher in tablets and death of ultra books (ok, that one is minor)
2015: Apple Watch - usher in wearables and death of the swiss watch industry
2020: Apple Silicon - usher in death of the Wintel hegemony

Many of those items are really, really, good - and they're reasons I'm an Apple fan, but is a world better without Swiss watchmakers and multiple competitive companies in the tech space?

Apple of 2020 looks alot like Microsoft of the 1990s:
- Higher walled gardens
-- iOS 14 has alot of what I'll call 'meta' - Meta that minimally increases the benefit of an app, but largely increases the amount of required development support on one platform
-- Apple Pay is great - but isn't the consumer served better by an open standard payment system?
- Inflexible business practices?: hey.com exposed a problem. I'm all for Apple making a profit on an App Store, and 30% was certainly fair at the onset of "App Stores" - but is it still? On top of that, there is no real innovation related to allowing people to find and use new offerings on their phones. Innovation is stagnating because it's under complete control by Apple.
- Unrelenting focus on profit growth: That is their fiduciary duty, but to me, it's short-term focused, and leads to some bad decision making and makes them look bad. I'm a much more wary of Apple as a company (just as I am for a company like Amazon) today than say, in 2010. I wonder how management will react when/if revenue growth slows.

In spite of that, I think this move to ARM (RISC-V?) is a good thing, I'll jump in feet first, because I believe that move to more open source hardware, in the long run, healthy for competition, good for consumers and great for innovation.

 

[cmaier]

Many of those items are really, really, good - and they're reasons I'm an Apple fan, but is a world better without Swiss watchmakers and multiple competitive companies in the tech space?

Apple of 2020 looks alot like Microsoft of the 1990s:
- Higher walled gardens

I wasn’t judging whether the list is good or bad. Just that each of these dates was clearly consequential.

 

[falainber]

It’s always fun to see Apple usher in a new world order.

But they do it only in the minds of their followers. Being last in porting their desktop OS to ARM hardly qualifies as ushering a new world order.

 

[cmaier]

But they do it only in the minds of their followers. Being last in porting their desktop OS to ARM hardly qualifies as ushering a new world order.

Yeah, the ripple waves when windows made arm machines really affected us all.

 

[Abazigal]

But they do it only in the minds of their followers. Being last in porting their desktop OS to ARM hardly qualifies as ushering a new world order.

It will be when Apple is the one to do it properly.

Therein lies the difference between Apple and a competitor like Microsoft - not in what they do, but how they go about doing it.

Bet-hedging is what Microsoft did with Windows for ARM. Look what it got them so far—next to nothing.

Apple knew very well that if there was even the slightest hint that they weren’t betting the farm on ARM Macs, the current Mac users would simply fight over the remaining stock of Intel Macs and then stay away in droves until Apple gave up and went back to making Intel Macs again.

Instead, we saw Tim Cook getting on stage and making himself 100% clear that Intel Macs were going away within 24 months and not coming back. They made it abundantly clear that it would be either ARM or the highway. Apple has shown they are ruthless enough to dump Intel and this will be crucial towards fostering greater adoption of ARM Macs and getting developers on board.

This is the lesson which Apple keeps teaching and which others keep ignoring - that in order to bring about meaningful change, you need to force it. Boldly and unapologetically.

 

[macsplusmacs]

But they do it only in the minds of their followers. Being last in porting their desktop OS to ARM hardly qualifies as ushering a new world order.

I see what you did there. You are comparing Microsoft's slow, incompatible with their apps port of windows to ARM to Apple's high performance, all your mac apps, plus native plus all your ios apps port to ARM.

Sure.

Whatever.

Microsoft was "totally" first there.

 

[dgdosen]

I wasn’t judging whether the list is good or bad. Just that each of these dates was clearly consequential.

I can completely agree with that.

But look at the affect created when saying they're 'conjuring up a new world order'... That sounds ominous to me...

 

[cmaier]

I can completely agree with that.

But look at the affect conjured up in saying they're 'conjuring up a new world order'... That sounds ominous to me...

Only because right wing folks a decade ago used it as a boogieman.

A new world order can be good, bad, or just different.

Are we better off or worse off with the gig economy vs what came before? It depends on who you ask. But iphone and the App Store are what made it happen.

Was the IBM/Windows regime better or worse than the apple/commodore/ti/Atari/etc regime that preceded it, or what came after it? Again, depends.

Any time these changes happen we certainly lose things. Hopefully the things we gain make it worth it, though our current situation suggests that this may not always be the case.

 

[macsplusmacs]

If the performance is more than 30% greater compared to an equivalent Intel CPU at the time of release, there is no way Apple will lower selling prices. If it's 100%, look out.

and lets not forget that the cost savings from the A series could be used to add more into these new macs, including in the case of imacs and notebooks, faceID cameras or higher rez front facing cameras that we all need now.

It will be interesting to see though. that is for sure!

 

[firewood]

- Unrelenting focus on profit growth: That is their fiduciary duty, but to me, it's short-term focused, and leads to some bad decision making and makes them look bad.

The type of decision making required to make Apple Silicon happen is the opposite of short-term focused. They had to have started to invest $$$ in this path way more than 3 years ago, and will need to invest billions today for stuff that will go into Macs 2+ years from now. Apple's careful (or lucky?) fiduciary management of a stable (and gigantic) long term cash flow has allowed that to happen and to succeed.

As for any potential lock down, Federighi on the Gruber talk show laughed at removing the Terminal command line, saying everybody at Apple uses it. Even SIP is still configurable.

 

[Stephen.R]

As for any potential lock down, Federighi on the Gruber talk show laughed at removing the Terminal command line, saying everybody at Apple uses it. Even SIP is still configurable.

The doomers won’t let that stop them from claiming “iOS lockdown of macOS is right around the corner” at every chance they get.

 

[macsplusmacs]

At least no one has posted "You can tear bootcamp from my cold dead hands" yet.

I know its going to be a loss for a few, but a very very few. Apple did the math here. they know the active use rate for Bootcamp is probably in my guess around 1% of total active mac users. So for the near term, stick with Intel and who knows maybe someday Microsoft will ship a ARM version that is not a total train wreck*

*would not put money on that.