News for hackers. Stuff that matters.
Re:Apple's long processor journey by therealmarv on Saturday February 15, 2020 @08:26PM (#22339247)
I hope to see AMD in this list soon. Apple is not using the best desktop and laptop processors nowadays.
Re:Apple's long processor journey by scarface74 on Saturday February 15, 2020 @08:44PM (#22339313)
The best laptop processor would be an Apple designed ARM chip.
Re:Apple's long processor journey by mdasen on Sunday February 16, 2020 @02:14AM (#22340297)
Possibly, but it would mean transitioning to a new instruction set. AMD processors wouldn't require a transition.

I used Macs through the PowerPC to Intel transition and it wasn't a great time. Apple had to do it because PowerPC processors were so incredibly far behind. Right now, Apple isn't behind since all their competitors are also using x86 processors. Maybe they could be ahead, but there isn't the same desperate need.

Maybe Apple should move to their own ARM chips. However, the AMD Ryzen 4000 series processors give them an easy upgrade without requiring a lot of work. Switching to ARM is a big commitment. Third party developers will need to recompile their programs. Apple will need a translation layer for older programs that aren't updated - and users will understand that they'll have older programs they've purchased stop working in a few years. It happened with the PowerPC to Intel transition, the MacOS 9 to MacOS X transition, and recently with the 32-bit to 64-bit transition with Catalina cutting off 32-bit support.

AMD's Ryzen 4000 parts are based on the 7nm TSMC process and they're able to stuff 8 cores into a 15 watt part. For comparison, the MacBook Pro 13" ships with 28 watt processors.

Is the Ryzen 4000 the best? I can't say. Is it a lot easier and less of a commitment? Definitely.

Re:Apple's long processor journey by scarface74 on Sunday February 16, 2020 @07:35AM (#22341258)
I used Macs through the 680x0 (LCII with a 68030/40 accelerator and lots of peripherals) to PPC (6100/60 with the “DOS Compatibility Card”) transition, left the Mac for awhile and came back with the G4 Mini and less than a year later with the Core Duo Mini.

The first time, the 6100/60 ran emulated code (especially with Speed Doubler) fast enough that there wasn’t a performance penalty. The second transition I had all native code.

But in general the strategy was the same. Wait until the software you need is compatible. During the first transition, my most used software was already shipping as a “fat binary”. I just unplugged my SCSI hard drive from one computer to the other.

The second time, all of the software I cared about was native.

It’s even easier now since the two most popular pieces of commercial software from Adobe and Microsoft are both subscription based. As soon as they port it, you won’t pay extra for it. Much of the other software that nerds use is open source and can be compiled easily for ARM (or Electron based).

No one is thinking that Apple will go full ARM. Most are thinking that the high end will be x86.

Re:Apple's long processor journey by arvinsim on Saturday February 15, 2020 @09:37PM (#22339487)
You are basing that on what metrics? It's all just speculation for now.

AMD 4000 mobile processors, on the other hand, already exist.

Re:Apple's long processor journey by scarface74 on Saturday February 15, 2020 @09:45PM (#22339511)
We know the performance/power trade offs of Apple’s ARM chips in iPad Pros.
Re:Apple's long processor journey by duskwuff on Saturday February 15, 2020 @11:39PM (#22339813)
And the odds are good that even that could be scaled up further for a laptop-class part. The iPad Pro is a passively cooled device which is expected to always run on battery power, after all; a laptop would have larger batteries and more thermal margin.

Not that it'd even have to be scaled up by much. The A13 (iPhone 11) already performs comparably to many Intel mobile parts; an -X variant (future iPad Pro) would surely improve upon that.

Re:Apple's long processor journey by zrm on Sunday February 16, 2020 @02:59AM (#22340468)
The scaling is really the question. ARM processors generally have better performance per watt because they're designed to prioritize power efficiency over absolute performance. The Intel parts Apple's ARM processors compare to on performance are the lowest power ones, which isn't exactly the sweet spot for Intel's microarchitecture.

If you gave the ARM designers the (higher) laptop power budget, almost certainly they'd increase performance at the expense of performance per watt. In other words they'd take more of the trade offs that Intel and AMD do. But to justify switching architectures it can't just be the same, it would have to be enough better to be worth the transition.

Re:Apple's long processor journey by amalter on Sunday February 16, 2020 @09:36AM (#22341702)
This has been exactly proven out by Amazon - https://aws.amazon.com/about-aws/whats-new/2019/12/announcin...

If Amazon can make a server class ARM chip that is competitive or better with their custom designed Xeons, I take it as a truism Apple could do the same for mobile.

Re:Apple's long processor journey by zrm on Sunday February 16, 2020 @11:41AM (#22342322)
There are a lot of reasons to expect that to work better for servers than laptops.

Most server workloads scale with core count, so winning in performance per watt is winning in general because you can scale performance by adding cores. A server with twice as many cores that are each half as fast is just as good, but that doesn't work for a laptop.

A server processor also doesn't have to win at every workload. If it can win at any workload, people can use it for only those, which makes it useful. That also doesn't really work for a laptop.

People run Linux on servers. It's portable. The architectural transition cost there is close to zero.

On top of that, Amazon is fudging the benchmarks in claiming it's faster. They're comparing performance "per-vCPU" which on Intel are hyperthreads rather than full cores. That's fine when Amazon is charging less for the ARM "vCPU" than the Intel hyperthread "vCPU", but you can't use that trick when running single-threaded workloads on a laptop.

Re:Apple's long processor journey by scarface74 on Sunday February 16, 2020 @12:50PM (#22342758)
And OS X is portable. It’s already been ported from PPC to x86 and parts of it back and forth between ARM and x86.
Re:Apple's long processor journey by zrm on Sunday February 16, 2020 @03:18PM (#22343532)
The operating system itself isn't the problem, it's all the applications. And the PowerPC transition was both easier and more worth it because the x86 processors were so much faster than the PowerPC processors of the time that they were competitive even when emulating PowerPC code, which wouldn't be the case this time.
Re:Apple's long processor journey by scarface74 on Sunday February 16, 2020 @04:11PM (#22343789)
“All the applications” don’t matter. Once you have the OS, Apple’s first party applications, Microsoft, Adobe, and a few Mac only niche apps, you cover most of your bases.

During the 680x0 to PPC transition, almost all of the applications that needed performance were already ported. The same was true for the x86 transition.

But more than likely, this time it will be the low end that would go ARM to optimize for battery life and the high end would stay x86.

Also the difference this time is that the two largest commercial vendors - Adobe and Microsoft already have ARM versions and Apple has Catalyst to make porting iPad apps to MacOS easier.

Also, during the last two translations, there was a lot more assembly code optimizations in third party apps than now. Especially going from 68K to PPC.

And sadly, there are a lot more Electron apps out there that would be easy to port.

Microsoft has struggled to get Windows ARM laptops because they also thought the performance/power ratio made it worth it.

Re:Apple's long processor journey by zrm on Sunday February 16, 2020 @05:37PM (#22344178)
> “All the applications” don’t matter.

Getting the most popular applications is the easy part, the hard part is the long tail. Only 1% of people may use a particular obscure application, but when there are a thousand such applications, the average person uses ten of them.

You also have to deal with a period of people wanting to run the applications they already own, not the newer version they have to pay to upgrade to or which isn't the same version the rest of their family or company uses on their existing hardware.

There are a lot of people who need nothing more than a web browser, but that's the target market for Chromebooks rather than MacBooks.

Re:Apple's long processor journey by scarface74 on Sunday February 16, 2020 @06:17PM (#22344334)
That 1% of applications is probably not performance critical and would work fine under emulation. But really, do you know the Mac scene? This isn’t Windows with thousands of line of business apps that have been running without upgrades for a couple of decades. Apple has already killed a lot of old apps when they dropped PPC compatibility and later 32 bit compatibility.

There are two existence proofs that Apple knows how to do this. They’ve done this twice and took customers with them both times. What are the Mac users who don’t like the transition going to do? Buy PCs and lose all compatibility with their apps?

The last thing that’s different this time is that Apple had a lot more to lose in 1994 when the Mac was all of their business and 2006 when the Mac was half of their business (the iPod was the other half). This time the Mac is only 10% of their business.

Also, many apps are going subscription. The upgrade would be “free”.

As far as performance. The most popular Mac has been the MacBook Air. The people buying those aren’t doing performance critical tasks using niche applications that won’t be ported.

Re:Apple's long processor journey by zrm on Sunday February 16, 2020 @09:09PM (#22345014)
> That 1% of applications is probably not performance critical and would work fine under emulation.

Each application having 1% of the users doesn't mean it's 1% when you add them all together. And they're all different applications. Why would you expect these to be less likely to be performance critical than any other?

Even for applications that aren't performance-critical, if the point is to save battery, emulation does the opposite.

> This isn’t Windows with thousands of line of business apps that have been running without upgrades for a couple of decades. Apple has already killed a lot of old apps when they dropped PPC compatibility and later 32 bit compatibility.

MacOS X 10.5 supported 64-bit Intel applications in 2007. That's more than a decade for old applications to accumulate. I doubt even most of the legacy Windows cruft is older than that anymore.

> There are two existence proofs that Apple knows how to do this. They’ve done this twice and took customers with them both times. What are the Mac users who don’t like the transition going to do? Buy PCs and lose all compatibility with their apps?

When they did it before, the new processors were a lot faster. There was a large benefit to offset the transition cost.

Existing Mac users don't immediately have to buy a PC, all they have to do is not buy a new Mac.

> The last thing that’s different this time is that Apple had a lot more to lose in 1994 when the Mac was all of their business and 2006 when the Mac was half of their business (the iPod was the other half). This time the Mac is only 10% of their business.

If the argument is can Apple stop making x86 Macs without going out of business, sure they can. If the argument is that Mac users should want to buy the first ARM model that comes out instead of holding onto their existing MacBook, not so much. It would have to be a real upgrade from what they already have, not just something equivalent but worse because it has to emulate some of their applications.

> As far as performance. The most popular Mac has been the MacBook Air. The people buying those aren’t doing performance critical tasks using niche applications that won’t be ported.

The MacBook Air has a Core i5. It's not exactly slow.

I'm also not sure what you mean by performance critical. Maybe they're not doing 3D rendering where you care quite a lot about the difference between three hours and five, but when people upgrade their hardware they still want it to go from responding in 500ms to 300ms instead of the other way around. And in that sense basically everything is performance critical.

Re:Apple's long processor journey by scarface74 on Sunday February 16, 2020 @10:05PM (#22345280)
Each application having 1% of the users doesn't mean it's 1% when you add them all together. And they're all different applications. Why would you expect these to be less likely to be performance critical than any other?

Care to give examples of “performance” critical Mac applications that people are using and are not likely to get ported relatively quickly?

Even for applications that aren't performance-critical, if the point is to save battery, emulation does the opposite.

What are these specialized applications? Audio, photo and video apps are historically the first to get ported. Adobe and Microsoft have historically taken a year or two.

Active Mac only developers like BareBones have have been the first to port their apps.

When they did it before, the new processors were a lot faster. There was a large benefit to offset the transition cost.

For reference 68K applications ran slower on the 6100/60 and 7100/66 than my 68030-40Mhz (accelerated) LCII. Out of the first generation PPC based Macs, only the 8100/80 was always faster than my 68030 Mac. My Mac was about half the speed of the high end 68040-40Mhz Quadras. In this case it’s the battery benefit.

And back in the 10.5 days, most apps were still 32 bit and using the Carbon APIs.

If the argument is that Mac users should want to buy the first ARM model that comes out instead of holding onto their existing MacBook, not so much. It would have to be a real upgrade from what they already have, not just something equivalent but worse because it has to emulate

And this is the same thing that happened the last two times. Users waited until the apps they cared about the most were ported. Especially for the PPC transition, it wasn’t until both the second generation high end 604s that PPC based Macs could run emulated programs faster. Heck the second generation lowend 603 based PPC Macs were slower emulating 68K Software than 601 based Macs.

I'm also not sure what you mean by performance critical. Maybe they're not doing 3D rendering where you care quite a lot about the difference between three hours and five, but when people upgrade their hardware they still want it to go from responding in 500ms to 300ms instead of the other way around. And in that sense basically everything is performance critical.

I can’t speak to the architecture of the PPC emulator for the x86 based Macs. But in the case of 68K programs that spent a lot of time calling OS routines, they would get a significant speed boost because they were calling native code - at the time emulated programs saw a significant speed boost by calling native QuickDraw routines.

The other advantage this time is that Apple is designing its own chips. It can make architectural decisions in the processor design to make emulation better.

Also, people are already using Electron apps, they couldn’t care too much about performance.

For a contemporary report of emulation speed of PPC Macs.

https://tidbits.com/1994/02/21/powerpc-reports-positive/

(reports were that PPC ran emulation at the speed of a low end 68040 Quadra without an FPU)

Re:Apple's long processor journey by duskwuff on Monday February 17, 2020 @12:06AM (#22345741)
The most likely possibility there is that Apple will release the system with some form of dynamic binary translation, much like they did for the PPC/x86 transition. It's also possible that Apple might make some customizations to their ARM core to accelerate the translation process, or even to allow some x86 code to be run directly.
Re:Apple's long processor journey by wu_187 on Sunday February 16, 2020 @11:22AM (#22342216)
The problem is the use-case. The software Mac laptops run would perform horribly on ARM. A Macbook Pro is not going to have an ARM processor.
Re:Apple's long processor journey by scarface74 on Sunday February 16, 2020 @01:04PM (#22342839)
Why do you think the software Macs run are so much different than the software that iPad Pros run? They run some of the same frameworks. Since when you run iOS apps in the simulator for Macs you actually running x86 builds of iOS apps linked against an x86 build of the iOS frameworks, it’s not hard to compare performance
Re:Apple's long processor journey by mindajar on Sunday February 16, 2020 @11:36AM (#22342294)
It already does, in the T2. It seems to me like future T* chips will run more and more of the system, leaving the x86 to become something like the MBP’s discrete GPU option. And then, like discrete GPUs, eventually an x86 CPU is only available in top-end models.
Re:Apple's long processor journey by vr46 on Sunday February 16, 2020 @04:28AM (#22340713)
Would these really be an upgrade? I thought we were hitting thermal and power limits these days? (Genuinely asking btw, have just bought a tricked-out MBP 16)
Re:Apple's long processor journey by scarface74 on Sunday February 16, 2020 @12:42PM (#22342713)
It depends on what you’re optimizing for. Having a laptop that has the battery life of an iPad would definitely be an upgrade.
Re:Apple's long processor journey by why_only_15 on Saturday February 15, 2020 @08:56PM (#22339355)
mac on arm is in the works apparently and is probably significantly more power efficient than AMD
Re:Apple's long processor journey by sjwright on Saturday February 15, 2020 @10:29PM (#22339630)
The T2 chip is probably what these rumors refer to. I imagine there's also ongoing engineering research to incrementally beef up the role of the T2 chip as a system controller and possibly also perform more system and background tasks in its ARM core.

That said, I've no doubt Apple is looking closely at an ARM future for Mac. I'm hoping that Apple does this, but as price & efficiency play, not to phase out x86. There's no reason Mac couldn't be indefinitely dual platform. We know macOS already has strong multi-binary support, so there's no technical impediment to that.

It could start with them releasing a MacBook Air with ARM as an option, ostensibly targeted towards developers and early adopters. It would need to have longer battery life and superior CPU + GPU performance at the same price point. From there they could progressively introduce ARM across their consumer range, guided by the performance numbers. And as software support broadens, they could begin progressively discontinuing x86 at the bottom of the product range.

Part of me wants to say that Apple shouldn't ever discontinue x86 support entirely, but if they're ever able to make chips that soundly trash anything from Intel and AMD, I doubt anyone would be too sad if they did.

Re:Apple's long processor journey by davnicwil on Sunday February 16, 2020 @04:16AM (#22340674)
> It could start with them releasing a MacBook Air with ARM as an option

I don't see this ever happening, it'll be all or nothing. Apple just doesn't differentiate its products on technical differences, it categorises them purely on what you can use them to do, as a branding/marketing strategy.

Despite developers and other people interested in the tech being a significant market for them, it's definitely not significant enough for them to change this.

Having a macbook that can't do things other macbooks can, with the tradeoff of different performance characteristics.. I just can't imagine it's something Apple would ever do.

Re:Apple's long processor journey by sjwright on Sunday February 16, 2020 @07:08AM (#22341180)
I strongly disagree and for exactly the same reason you gave: because there wouldn't be any need to differentiate on technical differences. Once all developers have cross-compiled their apps, the only difference between an ARM and x86 MacBook would end up being the ability to run Windows natively.

And yet, it's also ridiculously wrong to claim that Apple doesn't "differentiate on technical differences". While that's certainly true for their non-Mac products, Mac products have mostly stuck to the same formula used by Dell and HP.

Sure, Apple do place more emphasis on whole-product benefits and less emphasis on technical minutiae, but even that's splitting hairs. For example while they don't mention Intel's precise CPU product numbers in literature, they still differentiate SKUs based on tech specs like Intel Turbo Boost speeds. And when you buy an iMac, they'll still let you pick between the Radeon Pro 570X, 575X, 580X, or BTO the "Radeon Pro Vega 48 with 8GB of HBM2 memory".

I think they can handle a few products having an "Apple CPU".

Re:Apple's long processor journey by davnicwil on Sunday February 16, 2020 @01:42PM (#22343057)
> Once all developers have cross-compiled their apps

This is what I'm referring to specifically. If this were to happen, there would be a transition period where an obscure technical difference would mean they can do certain things on one mac model, and not on another.

And this won't even be like 'the entire new generation of macbooks can run this, the older ones can't' but 'this particular new model of macbook air can't run this, all the rest can, including all the other new ones' - Apple will never allow that to happen, it's completely antithetical to their product positioning strategy - simple computers that just work.

I concede that in the mac(book) line they do go into detail on some technical specs, but these are pretty much sliding scale numbers, bigger is better and more powerful and more expensive. It's very clear even to casual consumers (perhaps with a little explanation) why a bigger frequency number, more storage, more memory, is better. I.e. it's the same thing, just more powerful.

That's a very different thing than trying to explain to a consumer that the chip architecture is different, and why that means certain software doesn't work now, but will once the developer does this and that, etc etc. Again, Apple will simply not put themselves in that position.

To be honest I kind of hope I'm wrong - I'm interested in seeing what a macbook with Apple's own chips in it would look like, and if that's their plan then for me the sooner it happens the better. I just don't see it happening in any other way than all at once, though.

Re:Apple's long processor journey by sjwright on Sunday February 16, 2020 @11:21PM (#22345584)
We already have the evidence of how well it can work with the Intel transition. If anything, adding ARM to the Mac platform would be dramatically easier than the PPC-Intel transition because the ground work is already done:

— Unlike in 2006, a greater proportion of current Mac apps are developed with architecture independence, whether intentionally or not.

— Unlike in 2006, nearly all Mac developers are already using Apple's Xcode as their IDE.

— Unlike in 2006, many Mac app developers will already be familiar with the ARM CPUs, because they'll have already worked with them on the iPhone and iPad.

— Unlike in 2006, Apple has an additional motivating force called the Mac App Store. Apple would almost certainly require all new/updated apps in their store to be cross-compiled.

So no, you're wrong.

We've seen this before. We know how quickly it played out in 2006, despite that being objectively more difficult. This would be easy. All it would take is a 6 month transition period where ARM Macs are only marketed towards developers (and informed early adopters) combined with an x86 binary emulation layer to cater for straggling vertical/corporate apps.

Re:Apple's long processor journey by davnicwil on Monday February 17, 2020 @05:26AM (#22346671)
Yeah, those are some good points. You've brought me around to thinking this is more likely now!

I'm still just leaning towards them introducing these chips as an all in one product category, though - perhaps under a different brand of macbook model that is very clearly distinct from all the rest (looks different, etc) and a software strategy to match like a suite of ARM compatible software out of the gate that make it a useful standalone device whilst the ecosystem catches up. But yeah you're right, the transition looks like it'll be smoother than I'd assumed and it maybe wouldn't be a blocking obstacle from their point of view. Let's see!

Re:Apple's long processor journey by sjwright on Friday February 21, 2020 @07:48PM (#22388573)
If there's going to be a new product category, I imagine it would be an iPad Pro that runs iPadOS but can also run unmodified ARM-compiled Mac apps when attached to a keyboard and trackpad. (And the "files" app would look more like Finder.)
Re:Apple's long processor journey by zozbot234 on Sunday February 16, 2020 @08:00AM (#22341354)
Windows can run natively on ARM.
Re:Apple's long processor journey by sjwright on Sunday February 16, 2020 @10:20AM (#22341916)
You’re right, Windows can—but whatever app important enough to justify the effort of running within a virtual machine probably can’t.

(And you’re assuming that Microsoft will sell you a license for Windows on ARM in a VM, or that anyone will build that virtual machine software to support it.)

Re:Apple's long processor journey by michelb on Sunday February 16, 2020 @02:54AM (#22340455)
Some new AMD Ryzen processor identifiers seem to be present in the latest MacOS beta..Really curious..