Apple's A12Z Under Rosetta Outperforms Microsoft's Native Arm-Based Surface Pro X

So, Geekbench has to come out with a universal binary for MacOS in order to run native on Apple silicon? not that the native score would be far from what we already know about the A12Z in the iPad, right?
Well if the A12Z really only uses the four high-performance cores in macOS, we would know which difference the four energy saving cores make. Aside that, you're right.
 
let’s not get ahead of ourselves here. The Surface Pro X is a terrible machine with absolutely glacial performance. I sure hope the Macs will be faster than that.
You bet...again, Apple cannot afford to have a slower first 13" Mbp with arm that is slower than the current 13" intel
Since the current Intel 13" mbp is a lot faster than surface pro x...you get your answer
 
Who thinks we might see an official Microsoft Apple Silicon version of Windows? It’s not out of the question.
Windows on ARM does exist, but has really many compatibility problems (only runs 32-bit code for example), and most software doesn't exist for WoA. That's why it makes nearly no sense to port Boot Camp over, because the big pull for Windows (trizillion programs! millions of games!) is effectively void.
[automerge]1593494098[/automerge]
This should come as a surprise to absolutely no one.

As the owner of a Surface RT (refurbished), I should pull the old kit out and see if it benchmarks higher than the Pro X. Something tells me I might be surprised.
Did you do it? :)
[automerge]1593494536[/automerge]
I am gathering the answers and will post them in a new thread.
Just for fun (and I'm sure the haters won't give you exact answers anyways):

  1. What set of benchmarks will you consider as the basis for comparison between the released Apple Silicon Mac systems and competitive Intel/AMD machines?

    I'm benchmarking battery life in laptops. If the Apple Silicon implementation is better there, I'm good.

  2. When doing our comparisons between Apple Silicon-based hardware and AMD/Intel based hardware, how will you pick the AMD/Intel chip to compare?

    I would go with the number of threads on desktops, and battery life on laptops.

    What objective metric would you use to define equivalent systems for comparison? Machines at the same price point? Machines with the same max TDP? Something else? The point of this question is that since Apple will not be selling its SoCs to others, one cannot do it purely on price of the chip, one needs some other objective metric to decide what two items should be compared.

    I guess the same price point would be fair because that's the one thing it all boils down to, really.
  3. What objective criteria would Apple Silicon have to meet to be a successful product vs. Intel/AMD’s chips? (10% faster? 25%? 10% better battery life? 25%? Something else?) Once Apple starts to deliver high-end GPUs, what are your answers on those same metrics for those?

    I'd go with either "same performance at 30 % better battery life" or "30 % more performance at same battery life". As for GPU, I'd say the same for the ease of it.
  4. When did you purchase your most recent Mac from Apple or a third party reseller that was currently shipping at the time you purchased it?

    Typing this on my 2015 riMac with M395X :)
  5. What would be required for you to purchase an Apple Silicon-based system?

    Money :D Joking aside, I think it just really boils down when I replace my current iMac. I'd love to see more performance for BOINC for instance, but if my set of work apps (mostly out of the Mac App Store) runs great, I'm not really sure what I would additionally wish for. The state of gaming will be another state of affairs, then again, I'll be thrilled what the Mac App Store will be once the iOS apps can be used on Macs as well :)
 
Last edited:
Windows on ARM does exist, but has really many compatibility problems (
He referred that Microsoft to build its own silicon arm , not with QC. But this year or next i think its impossible...Microsoft has to collaborate with QC
 
He referred that Microsoft to build its own silicon arm , not with QC. But this year or next i think its impossible...Microsoft has to collaborate with QC
I think, MikeSmoke referred to "an official Microsoft Apple Silicon version of Windows" which is Windows on ARM. It's like you're saying Windows x86_64 has to be recompiled for AMD processors because there is an Intel version.
 
Microsoft SQ1 is 7W TDP. The A12Z in the Mac Mini desktop is probably 15W TDP or higher.
Is it in the iPad Pro 2020 as well? What I gathered from AnandTech (https://www.anandtech.com/show/13661/the-2018-apple-ipad-pro-11-inch-review/4) here: "I’m expecting figures not all too different to what we’ve published on the A12, meaning single-core active system power should be in the 3.6-4.3W range. Naturally this should be a bit higher on the A12X due to the doubled memory controller interfaces." So where do you get your 15W from?

EDIT: Logic is a thing as well. An iPad with the same chip (4 performance and 4 energy saving cores, really) has a 36.71 watt-hour battery, which would translate to 3.671 watt usage for the whole iPad in order to get to a 10-hour battery life. With 15 watts, the iPad would be dead in just over about two hours, and that's not factoring in the screen, cellular and anything. So I'm curious how you got to 15W, because it's not overclocked in the development kit and it seems to consist of only 4 performance cores, too.
 
Last edited:
Much as every apple fan likes to brag about their apple devices (l have a few myself) l wonder why my daughter prefers to work on my Pro X and not on her MacBook. I guess raw speed is not all that matters.
 
Much as every apple fan likes to brag about their apple devices (l have a few myself) l wonder why my daughter prefers to work on my Pro X and not on her MacBook. I guess raw speed is not all that matters.
Yeah, software is a factor too!
 
What objective criteria would Apple Silicon have to meet to be a successful product vs. Intel/AMD’s chips? (10% faster? 25%? 10% better battery life? 25%? Something else?) Once Apple starts to deliver high-end GPUs, what are your answers on those same metrics for those?

I'd go with either "same performance at 30 % better battery life" or "30 % more performance at same battery life". As for GPU, I'd say the same for the ease of it.

For CPU: 50 percent faster on single core. Twice the core count.
For GPU: competitive with RTX 3080Ti.
 
I'm sure Geekbench is writing a native app as we speak. Hopefully we see some more true numbers and some metal/open CL numbers too
 
that’s CPU-native but not OS-native. Needs to be both.
It will be recompiled, sure. But: What difference would it be? The hardware is almost the same (even weaker than in the iPad Pro), and we already know the numbers for it. So that's just fetishism to me - it's not relevant because the A12Z won't even show up in consumer hardware.
 
It will be recompiled, sure. But: What difference would it be? The hardware is almost the same (even weaker than in the iPad Pro), and we already know the numbers for it. So that's just fetishism to me - it's not relevant because the A12Z won't even show up in consumer hardware.
I agree with you 100%. I find this weird race to benchmark the machine to be silly. All it’s telling us is a rough estimate of the rosetta overhead (for one particular non-representative app), and some really rough information about the relative speed of MacOs vs. ipados running on the same hardware (which amounts to “they run at about the same speed.”)

arguably we see that *maybe* x86 apps only have access to half the cores (4 high speed? 2 high and 2 efficient - more likely given the multi core number is about half ipad), but that doesn’t really mean much given that there’s no reason for apple to actually rewrite its entire thread scheduler just to support the DTK.

So it’s all, as you say, fetishism.

- I was just being pedantic.
 


Apple's Developer Transition Kit equipped with an A12Z iPad Pro chip began arriving in the hands of developers this morning to help them get their apps ready for Macs running Apple Silicon, and though forbidden, the first thing some developers did was benchmark the machine.

developertransitionkit.jpg

Multiple Geekbench results have indicated that the Developer Transition Kit, which is a Mac mini with an iPad Pro chip, features average single-core and multi-core scores of 811 and 2,871, respectively.

rosetta-2-benchmarks-a12z-mac-mini.jpg

As developer Steve Troughton-Smith points out, the two-year-old A12Z in the Mac mini outperforms Microsoft's Arm-based Surface Pro X in Geekbench performance, running x86_64 code in emulation faster than the Surface Pro X can run an Arm version natively.


Averaging seven Geekbench 5 benchmarking results, Microsoft's Surface Pro X features a single-core score of 726 and a multi-core score of 2,831, meaning the A12Z outperforms the Surface Pro X in single-core testing and is on par or slightly better in multi-core performance.


The Surface Pro X features a Microsoft-designed 3GHz Arm processor based on the Qualcomm SQ1 chip.

Apple's DTK provided to developers is just a test machine using an older A12Z chip (it's the same as the A12X chip in the 2018 iPad Pro but with an extra GPU core unlocked). Apple's Arm-based Macs that run Apple Silicon will have new chips designed for the Mac and based on the A14 chip created for the 2020 iPhone lineup with a 5-nanometer process.

Apple says its Apple Silicon Macs will bring major improvements in performance and power efficiency, and the first Arm-based Mac is set to be released before the end of 2020.

Article Link: Apple's A12Z Under Rosetta Outperforms Microsoft's Native Arm-Based Surface Pro X

You realize AMD Zen 4 is on 5nm TSMC process, correct? Nothing Apple is doing will be new as they both are doing it.
 
You realize AMD Zen 4 is on 5nm TSMC process, correct? Nothing Apple is doing will be new as they both are doing it.
Apple is doing it without a microcode rom, a microcode state machine in the instruction decoder, and a butt-ton of pipe stages to deal with branch prediction misses that occur between micro-ops that are part of the same x86 op. So that’s new :)
 
If you watched the keynote, they mentioned that they will be making a specific line of processors for the Macintosh. It will share the same architecture, hence the DTK, but it may not even be called an A14. Could be called B14 or perhaps a A14M.. They aren’t just taking the chips from the iPad and slapping them into a computer going forward. That’s only for the DTK.
I was logging in to point this out, then I read your comment!
 
I think, MikeSmoke referred to "an official Microsoft Apple Silicon version of Windows" which is Windows on ARM. It's like you're saying Windows x86_64 has to be recompiled for AMD processors because there is an Intel version.
He referred for microsoft to build its own arm chip. The microsoft windows arm OS will be offer for sale starting in "fall"
You can ask the user in private
 
He referred for microsoft to build its own arm chip. The microsoft windows arm OS will be offer for sale starting in "fall"
You can ask the user in private
Well, I'm referring to the comment the user made. Microsoft is free to build its own ARM chip, just pay the licence fees and go. Windows for ARM already exists, but not for customers just yet. My point still stands: Who needs Windows for ARM when it's only running 32-bit-software? The big pull for Windows (all the games! all the compatibility! great software catalogue!) is next to 0 when talking about Windows on ARM as it is right now. Read the reviews...
 
Many years ago we had Ghz-war, then Apple started using intel so that ended. Now we will have Geekbench-war; which of the latest intel/ARM cpu gets the highest scores. Very excited about the switch and will hold on to my 2015 MacBook Pro for another year or so.
 
I own a Surface Pro X and I love it. Works amazingly good for the $850 I spent. I also own a ton on Apple stuff, but I’m using the X more and more.
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.
Back
Top