Apple: No Macintosh Forks. But the iPad... • Hacker News Board

Re: Apple: No Macintosh Forks. But the iPad...

#141

Post by scarface74 » Sun, Jul 28, 2019, 4:27 PM UTC

mjg59 wrote: post #61

Moto7451 wrote: post #4

I don’t think the argument holds very well. Apple has made three processor architectural changes including one on the current OS. “Too complicated” doesn’t really align with the execution history Apple has. The fat binary support Apple has is a huge tool and the ability to add instructions and optimizations to their chips to help with x86 emulation is a big deal. I don’t know if Apple will ever actually do this, but…

Apple has made two transitions while retaining compatibility, in one case with emulation of the old architecture being around the speed of the previous (68k to PPC) and in the other with emulation being faster than the previous architecture (PPC to x86). There's no ARM that's fast enough to emulate an x86 in the same power envelope, so right now any transition would either require all performance sensitive apps to be…

From personal experience: the slowest PPC Mac the 6100/60 was about the speed of the LCIi (68030-16Mhz with a 16 bit bus) under emulation. It was much slower than my LCII with a 68030-40Mhz card. It wasn’t until Connectix came out with a better emulator that emulation approaches tte speed of my old accelerated LCII. It also didn’t help that parts of the operating system were still emulated.

Re: Apple: No Macintosh Forks. But the iPad...

#142

Post by scarface74 » Sun, Jul 28, 2019, 4:33 PM UTC

taneq wrote: post #28

ChuckMcM wrote: post #7

I see a lot of Surface Pro in the iPad[1]. That isn't a bad thing, it is great to have two design studios trying to out do each other. If you agree that these devices should work better on ARM chips rather than x86 chips, then the iPad has an advantage with an already ARM based ecosystem. Of course the Surface R/T tried that too, and stumbled. But I wonder if Apple saw that as a hint of where Microsoft might go. I fi…

Re. [3], there’s often a significant cost to maintaining a separate data plan for each device. I was recently quoted $15/mo to connect an $18/mo iPad. That’s a lot to pay for the privilege of not turning your wifi hotspot on.

Yes it is a lot - T-Mobile charges $20 a month for an iPad data plan. I do it anyway.

It’s convenient not to have to burn battery on your primary device and while T-mobile offers unlimited 512kbps tethering, for $20 a month getting unlimited high speed tethering for us (my wife has a cellular iPad also) even though rarely used, is worth it.

Also, the iPad is an excellent hot spot. They’ve done benchmarks showing the iPad can work as a hotspot for up to 36 hours.

Re: Apple: No Macintosh Forks. But the iPad...

#143

Post by colejohnson66 » Sun, Jul 28, 2019, 4:53 PM UTC

scarface74 wrote: post #121

ajconway wrote: post #88

Earlier quoted context omitted.

Apple sells iPad Pros which they call “computers”. Those are powerful devices, but there is not much productivity software available, and UI is very different from traditional desktop interfaces. Apple could offer an Air-class machine powered by ARM with a familiar macOS, and most developers would be able to support it in a matter of weeks, if not days.

There is Microsoft Office and Adobe has previewed full Photoshop on it. What other mainstream productivity software do most people need?

Visual Studio?

Re: Apple: No Macintosh Forks. But the iPad...

#144

Post by gridlockd » Sun, Jul 28, 2019, 4:53 PM UTC

imtringued wrote: post #115

gridlockd wrote: post #112

Earlier quoted context omitted.

> ...with emulation being faster than the previous architecture (PPC to x86). This is not the history that I remember, at least with contemporary hardware. In my recollection, PPC emulation was generally slower, but it didn't necessarily really matter. > There's no ARM that's fast enough to emulate an x86 in the same power envelope, so right now any transition would either require all performance sensitive apps to be…

>Emulation adds overhead of course, but it's worth noting that most ISAs are effectively emulated through micro-operations That's not even remotely the same thing because that micro-code is optimized to the ISA of the processor and it's obviously specific to the microarchitecture of the processor which is again optimized for a specific ISA. It's like translating a Wikipedia article from normal English to simple Engli…

I don't think it's that different. Microcode can work efficiently with multiple ISAs. In practice, x86 and amd64 are actually fairly different targets. With amd64 you have far more registers and no x87 weirdness, for instance. ARM chips also generally support multiple ISAs.

Of course you have trade offs regarding optimizations, but that's true at multiple levels. For example, many exotic x86 instructions (like BCD) aren't as optimized as they could be.

> If you had proposed adding hardware acceleration to make emulation of a specific architecture faster then maybe one could have squinted and said it's emulation instead of secretly implementing a x86 CPU in your ARM CPU.

Of course I'm talking about hardware-level support. I'm talking about the things that already exist.

Re: Apple: No Macintosh Forks. But the iPad...

#145

Post by _ph_ » Sun, Jul 28, 2019, 4:55 PM UTC

ken wrote: post #126

_ph_ wrote: post #74

Earlier quoted context omitted.

It isn't especially difficult, but is is expensive. The big challenge with CPU design is to make up for the costs and for that you need numbers. In the 90ies, there were plenty of high-performance CPU designs, Alpha, Sparc, Mips. They were alle killed by two mechanisms, that Intel had a lead in fab technology and that Intel had much higher numbers, consequentely could gain back much higher investments as the competit…

> The Mac Pro numbers certainly wouldn't pay for such a CPU development. Again, though, what exactly does "development" mean here? Apple is already fabless. TSMC makes 32-core chips for AMD, so that scale is not new to them.

Well, the process of designing the chip to fabricate. This means paying a lot of electrical engineers to design the chip, probably paying for several iterations of lithography masks. Yes, TSMC certainly can make any chip of the desired size - they are already making enough of those - but the development is very expensive. The Mac Pro by itself is certainly not selling in high enough numbers to pay for such a development and considering how long Apple neglected the pro, I am somewhat dubious they would be willing to spend a huge amount of effort on it.

Re: Apple: No Macintosh Forks. But the iPad...

#146

Post by wwright » Sun, Jul 28, 2019, 4:58 PM UTC

TheOtherHobbes wrote: post #82

c256 wrote: post #78

Earlier quoted context omitted.

The future of Pro machines is largely about VMs. Heck, the recent past of Pro machines is largely about VMs — that’s the reason I so often hear people complain about 16GB ram limits, for example. In that world, I wouldn’t be surprised to see a Mac Pro running a (few?) very high core-count cpus(s) underneath an Apple/ARM based software stack, even if the cpu comes from Intel or AMD. That would let a putative Mac Pro r…

You don't need a VM to run Photoshop. The whole point of the desktop Pro machines is high-performance computing for creative applications. VMs have no place in that. RAM is an issue because it's a limiting factor for many rendering and editing applications. Laptop Pro is arguably different, but I suspect content creators still outnumber developers by a significant ratio.

VMs do have a place for that now: many shops run thin clients into a cluster for workstation uses.

Re: Apple: No Macintosh Forks. But the iPad...

#147

Post by mehmetoguzderin » Sun, Jul 28, 2019, 5:05 PM UTC

brantonb wrote: post #38

flomo wrote: post #13

My take on the iPad form-factor hasn't really changed since the introduction. Its really great for certain casual use cases, but as soon as you sit down at a desk to get some work done, oh god does this fucking suck. And the keyboard cases actually make it worse because you delude yourself into thinking it makes it better, when it does not. So an iOS/iPadOS laptop with full KVM support always seemed like a no-brainer…

I love my iPad with the keyboard case. When I hook it up to an external monitor and my Kinesis keyboard, it’s even better. I’m looking forward to mouse support in iOS 13. One of my favorite apps when it comes to the keyboard is Blink. It’s an SSH/Mosh client with a limited local shell. I use it to build a Jekyll site on an EC2 instance. Blink supports multi-monitor, so I can have different shells on different screens…

The new Safari in iPadOS makes it possible to use Code Server (Visual Studio Code on browser) with keyboard. If you already spin an EC2 instance, it is definitely worth a try. This also gives hope about the upcoming Visual Studio Online and its compatibility with iPadOS.

Re: Apple: No Macintosh Forks. But the iPad...

#148

Post by ksec » Sun, Jul 28, 2019, 5:09 PM UTC

ken wrote: post #126

_ph_ wrote: post #74

Earlier quoted context omitted.

It isn't especially difficult, but is is expensive. The big challenge with CPU design is to make up for the costs and for that you need numbers. In the 90ies, there were plenty of high-performance CPU designs, Alpha, Sparc, Mips. They were alle killed by two mechanisms, that Intel had a lead in fab technology and that Intel had much higher numbers, consequentely could gain back much higher investments as the competit…

> The Mac Pro numbers certainly wouldn't pay for such a CPU development. Again, though, what exactly does "development" mean here? Apple is already fabless. TSMC makes 32-core chips for AMD, so that scale is not new to them.

You will need to buy different set of tools to work and design for TSMC 's node. And while it is still from TSMC, the node for Desktop ( High Performance ) will be different to Phone / Tablet ( Low Power ). The cost of designing and testing a 5nm chips is roughly a billion. For iPhone that is spread out over 200M unit over its life time, or roughly $5 per chip excluding the actual cost of wafer.

For Mac you are looking at 25M unit per year, with TDP going from 15W to 250W. Apple could follow the same path as AMD and make one die to fit all. But in reality it is waste of engineering recourse and focus for little benefits.

Re: Apple: No Macintosh Forks. But the iPad...

#149

Post by pjmlp » Sun, Jul 28, 2019, 5:20 PM UTC

yoz-y wrote: post #90

vlozko wrote: post #62

Earlier quoted context omitted.

There’s definitely some common threads with this and Apple’s push to have apps use bitcode. It would make this duality a lot easier from an app distribution perspective without the need to have an emulation layer. My only guess as to why Apple hasn’t required bitcode by now is the sheer number of 3rd party libraries out there that aren’t built with bitcode enabled.

Chris Lattner has stated several times that bitcode does not help with porting to other platforms though

Only when talking about standard bitcode that everyone has access to directly from LLVM.

Apple's toolchain uses a modified version of bitcode, making it more portable.

There is a session on WWDC 2019 on how using bitcode made the 64bit transition of watchOS apps relatively easy.

Re: Apple: No Macintosh Forks. But the iPad...

#150

Post by pjmlp » Sun, Jul 28, 2019, 5:22 PM UTC

TheOtherHobbes wrote: post #82

c256 wrote: post #78

Earlier quoted context omitted.

The future of Pro machines is largely about VMs. Heck, the recent past of Pro machines is largely about VMs — that’s the reason I so often hear people complain about 16GB ram limits, for example. In that world, I wouldn’t be surprised to see a Mac Pro running a (few?) very high core-count cpus(s) underneath an Apple/ARM based software stack, even if the cpu comes from Intel or AMD. That would let a putative Mac Pro r…

You don't need a VM to run Photoshop. The whole point of the desktop Pro machines is high-performance computing for creative applications. VMs have no place in that. RAM is an issue because it's a limiting factor for many rendering and editing applications. Laptop Pro is arguably different, but I suspect content creators still outnumber developers by a significant ratio.

Many OS instances nowadays run on top of a type 1 hypervisor, Photoshop doesn't even notice it.