Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
3DMark Ice Storm Unlimited off screen 1280 x 720 from NotebookCheck
----

5500M = 210925

Radeon Pro 560X (2018, used in MBP) = 255217

A12Z (slight tweak on 2018 A12X) = 221182

Two year old tablet design = mid range laptop GPU in 2020. I think you are underestimating what Apple could do with a newer GPU design and a laptop sized battery.
The Polaris amd? The 3 year old entry level rebadge? Not a high hurdle.
 
In one benchmark Geekbench. No one has has done extensive back to back benchmarks on real apps like Lightroom/photoshop. I mean the real macos desktop versions, not the neutered iOS versions.
Apple wouldn’t be exploring this route if they couldn’t match or beat the performance of Intel’s roadmap. I’m sure we will see some promising benchmarks in the not too distance future
 
You guys will be fine - Us who were in the PowerPC to Intel transition feared the same thing, but survived :p
Survived badly, my last G5 was an awful machine, couldnt sell it 2 years after, and my first macintel was also a crap, but O know this will be different as latest macintel are awesome , though lets see what happens in software side
 
  • Like
Reactions: dysamoria
So you're saying if I can build from source on an Intel Mac, i'll be able to do the same on an Apple silicon Mac?
Yes, I think Craig federigi explained that you can build the same source on Apple Silicon and it should work barring some specific changes which is why he referred to it as "be able to run it in days". But I am talking about how the translation technology might be working. And it could very well be really good.
 
  • Like
Reactions: Nightfury326
Because I want you to understand that this is a transition. When Apple does something, they do it 100%.

And the transition is including both Intel and ARM, so why not allow at first the end-user to choose between ARM and Intel on all MacBooks/Macs, then slowly fade out Intel? You could lower the price of the ARM component to get more on-board with it.
 
I'm not getting sucked in to the Rosetta 2 ruse. Running old apps on the new architecture will actually be slower. It's only when the apps are re-written and native that they can take advantage of the new Apple Silicon architecture. Lot of frustration back when Apple switched to PowerPC, then again with Intel, with both Apple and developers bloviating about how great simulation mode works.
 
In one benchmark Geekbench. No one has has done extensive back to back benchmarks on real apps like Lightroom/photoshop. I mean the real macos desktop versions, not the neutered iOS versions.
I myself use my iPad for photo editing more than I do my iMac nowadays. iPad is faster using the same app.

iPads do run quite well under sustained loads. My only complaint that when they get too hot, screen is dimmed.
 
Ok, but I'm comparing Apple's to Apple's.

Today Apple's dGPU offerings are 5500M, 5600M, Vega 48, Vega 56, Vega 64, Vega II, Vega II Duo and 5700XT.

Apart from 5500M, all these are 5 to 10 times as fast as 12Z.

So yes, I also expect Apple to come up with a solution. But we haven't seen anything remotely close to the speeds of the GPU's from Apple yet.

Nothing will prevent you to put in a Nvidia or AMD discrete GPU into one of the PCIe slots of your ARM Mac Pro.
 
Initial reaction is that in 3-5 years Apple is going to have the best performance of anything out there. For those running Bootcamp and doing Hackintoshs it's probably time to consider something else (Windows or Linux I guess?). Personally I'd be more than happy for a iPad/iOS like interface for my Mac as long as I had the ability to do more developer type things.

This is going to make Hackintoshes even more popular and practical. I can imagine lots of people want to run Mac and Windows side by side and/or have a lot of legacy x86 stuff they still want to run natively. It's unlikely that Apple will stop having Intel OS builds for at least 5 years, maybe even longer.

The Hackintosh development community's purpose in life has been to work around Apple's hardware and software development choices. This is more of the same. It's just another challenge.
 
In one benchmark Geekbench. No one has has done extensive back to back benchmarks on real apps like Lightroom/photoshop. I mean the real macos desktop versions, not the neutered iOS versions.
Try running a SPEC CPU benchmark.
 
Tim said the transition will be another 2 years. Which means we could have a new high end iMac/iMac Pro or Mac Pro at 1.9 years from now. Which will be supported ~5 AFTER release. I think you are safe.

When Apple transitioned from PowerPC to Intel 10.5.8 was the last Mac OS that would run on PowerPC. The Power Mac (PowerPC) was discontinued in August 2006 and 10.6 (Intel only) was introduced in August 2009. I'd say you'll get 3 years support at best. Maybe less.
 
Ok, but I'm comparing Apple's to Apple's.

Today Apple's dGPU offerings are 5500M, 5600M, Vega 48, Vega 56, Vega 64, Vega II, Vega II Duo and 5700XT.

Apart from 5500M, all these are 5 to 10 times as fast as 12Z.

So yes, I also expect Apple to come up with a solution. But we haven't seen anything remotely close to the speeds of the GPU's from Apple yet.

Well yeah, but the 5600M is a $700 add on part to a $2400 laptop. Apple powered 13” laptops are probably going to start around $1300 and rival the performance of a 5500M. I’m just conjecturing, we’ll see!
 
  • Like
Reactions: BeatCrazy
Yes, I think Craig federigi explained that you can build the same source on Apple Silicon and it should work barring some specific changes which is why he referred to it as "be able to run it in days". But I am talking about how the translation technology might be working. And it could very well be really good.

Well - being able to 'run in days' is different from easily cross compiling for a different instruction set. I'm not as optimistic as you, but we should see how this shakes out with these DTKs.

(Again, I'm talking mostly about CLI apps/services that can run via linux and macos, say, like Redis)
 
I think we should wait to hear from them. Recall Microsoft did develop an ARM version of Windows 10 and as Bootcamp requires a new license they may still make it work.


First, Windows on ARM is almost worse than not having Windows at all. It doesn't work well at all, and it's not compatible with 64 bit apps.

Second, in the history of apple using ARM, when have they ever allowed another OS to be installed? I fully expect it to require signed OS updates like iOS does.
 
This will either turn into success or near bankruptcy like back in the 90's for apple. But there is no steven p jobs to come back and resurrect Apple.

#1 reason for their custom processors: Control and pricing. It's all about the $ - nothing more.
#2 monopoly over software and/or developer fees, again, all about about the benjimen's.

Aside from those two reasons, of course their marketing dept will tout you can't compare an apple device to anything else because technically you can't!

I will want to see apple fail badly because after owning an Ipad 1, 2, 3, 4, 5, 6, 7, and 8th iterations, I've come to believe iOS/iPad apps are just not good enough. At the end of the work day I finish off with a real computer and that $500 developer fee is just stupid for developers. Apple SHOULD BE PAYING developers to hop on board with free incentives. Arrogant company I have zero empathy for when they fail and fail hard. 90% of the world rely on software that runs on x86 and there's just no way a majority of legacy and mainstream apps they are going to port over to an ultra expensive starbuck's millenial computer just because it has an apple logo on it.

Nearly all the features you see today is catchup to the competition. I've waited 14 iterations of iOS just so I can put a photos icon taking up 4 icon spaces on the same exact screen. You guys think it's expensive now for iproducts just you wait; it's gonna be much more expensive and much less compatible!
 
The Wikipedia page on the topic would disagree.
the a13 is an arm 8.4a design, apparently. https://en.m.wikipedia.org/wiki/ARM_architecture#Cores
Doesn’t that just mean it complies to the 8.4a instruction set?

I’m trying to find a recent article I read about how Apple licenses the instruction set, and makes its chip compliant to that set, but the chip itself is not merely a modified reference design.

I’ll see if I can dig it up in my history.

In the meantime, can anyone with a CPU background (like cmaier) chime in on this?
 
  • Like
Reactions: MyopicPaideia
I just now saw on the homebrew docs that you can force it to build as opposed to using bottles (or casks). That's great - I'm going to opt for that on my Intel Macs.

Will all that code compile on "Apple Silicon"? That would be good to test out on the Dev Transition Kit

Apple silicon is just a Marketing name for apples arm chips.

the real question is whether the software you use, (a) can compile on arm and (b) if the “brew” for it needs/gets patches to make it compile on arm.

a is probably the bigger concern. If it can be compiled on arm, home brew will generally grab the patches from another distro if available. But if it can’t, don’t expect homebrew “developers” to port a program to arm.
 
This is going to make Hackintoshes even more popular and practical. I can imagine lots of people want to run Mac and Windows side by side and/or have a lot of legacy x86 stuff they still want to run natively. It's unlikely that Apple will stop having Intel OS builds for at least 5 years, maybe even longer.

The Hackintosh development community's purpose in life has been to work around Apple's hardware and software development choices. This is more of the same. It's just another challenge.
Lasta time was 3 years (snow leopard 2007, extra year for uodates, not counting 3rd party developers dropping sooner the support)
 
  • Like
Reactions: dysamoria
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.