Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
As a tech enthusiast but someone who doesn't necessarily understand the finer side of this kind of thing, can anyone confirm if my understanding is correct—the M1 in the lowest type of configuration (a MacBook Air), emulating Intel-based macOS applications, performs better than the best high-end Intel iMac running x86 natively?

Is there a way to see how the iMac Pro and Mac Pro perform compared to the computers in the graphic?
Yes, this is what the graph is inferring for single-threaded loads. However, we don't know how well they perform for multi-threaded loads, and whether the M1 will be thermally limited for long-running tasks (particularly in the Air). I suspect performance will depend on specific applications too, so we need to see real-world results for each application.
 
Ya know, your attitude is the worst.
Either that or you don't know what "doubt" means or, very likely can't simply handle criticism of Apple.

There's nothing wrong, at all, with doubting a company or someone. There's still plenty of doubt to be had.

Further, failing to virtualize x86 is not insignificant. Software, in the real world, isn't always $0.99 from the store on Macs. It can be very expensive. Asking people to pay for it twice? That's.. a tough pill to swallow and Apple needs to offer something huge in return. Or risk people jumping to Microsoft.

When you force people to jump into a new ecosystem -- then their options to jump into ANY ecosystem because possible and reasonable. It's a very risky move.

There’s legitimate doubt, and there’s irrational fearmongering along the lines of “Apple is doomed because”.

So by your logic, people won’t pay a few dollars for software, but will happily buy a windows PC for a few hundred dollars just because?

These are the entry level Macs we are talking about. Most people are not buying them to virtualise software; they are getting them for basic entry-level tasks. The kind of limitations you speak of are simply not going to apply to them.

The only valid criticism I can think of is that Apple may be overhyping the gains of moving to AS and the real-world benefits may not be as impressive as stated, but either way, I see no reason to doubt that these AS Macs will offer superior performance and better battery life compared to intel PCs.
 
It's not really that hard. All modern CPUs do out of order execution. If you're already executing stuff in the "wrong" order, then you can do it concurrently.

There’s a very big difference between reordering an instruction stream on the same core vs. splitting an thread into multiple threads on different cores. They don’t even share L1 memory caches, so the penalty of not doing it well is horrendous.

Not to mention that out of order execution units typically have a window of around 8 instructions that they look at. Finding contention in such a small window (especially since the ONLY contention you have to worry about is registers in that case) is *far* easier than splitting a thread. It’s a near NP problem.
 
Massive reorder buffer: UltraSparc V had that. I know, because I was the original designer of the reorder unit on that chip.

On die memory: there is no on die memory. It’s in the package, but not on the die. This is easy to see from the actual die photographs that have appeared on Ars (I addressed this claim in another thread and posted the picture). There are a number of LPDDR4X channels with off-chip drivers, so you can even see how the die connects to off-die RAM. Here’s the photo: https://images.anandtech.com/doci/16226/M1.png


”width”: what width are you referring to? There is nothing unusual about the execution width. It’s, in fact, identical to that used in, say Athlon-64 and Opteron. (I know, because I owned the integer execution unit for the first of those designs)

Dedicated units: most chips are now designed as SoC with on-chip encryption units, etc. AMD transitioned to that design methodology with Bulldozer. I know, because I left AMD right around when that started happening.

The CPU portion of the chip is very similar to every other CPU I ever designed. The SoC methodology is now a very common methodology.

What’s different here is competence, not some radical difference between M1 and x86 chips.
Yes, but the issue here is you are looking at the cpu only. Apple is delivering a package. Now you may or may not have experience in this field and as it’s the internet anyone can claim to be anything, but you are narrowing the focus onto the cpu design. The specific core. The fact of the matter is that a computer is the sum of its parts which you should well know. Apple packaging everything together applies efficiencies that other chips do not have and are outside the norms of computer design. Perhaps I should have said it that way rather than give the impression I was talking merely cpu core design. This influences benchmarks. Whether just the cpu is similar or not isn’t really the point, it’s the bigger picture.

Also not to be harsh, but ultrasparc v was cancelled. Are there shipping processors with that sort of design? It may have been planned to be similar but if it never shipped it doesn’t show that design shifted that way at all. Unless of course features of that were incorporated in other designs, for that I would have to defer to you.
 
  • Angry
Reactions: NetMage
This is all fake news until production units are in the hands of real users and YouTubers. Does anyone *actually* believe the gimped M1 with 8GB or 16GB of RAM is going to process video faster than an Intel blowtorch. Probably not. But the marketing is cute.
 
If you need windows, then you will eventually likely need a windows machine. Luckily for Apple, only 1% of users use bootcamp, and something like 5% use VMs, so even if they lose those customers, they will more than make up for it with new buyers who want to run iOS software on their laptop or desktop.
I expect that Microsoft will push its consumer "Cloud PC" service quite soon to address some of these limitations. Of course you can already run virtual desktops in MS Azure, AWS, Shadow and many more, but it's still more focussed on Enterprise (and gamers to a small extent), not "typical consumer PC users". Microsoft will want to capitalize on the increasing number of consumers who will not be running Wintel client machines (new Mac users, Chromebook & tablet users)
 
The single-core is still faster than 10-core i9-10910 3.6 GHz in iMac and the multi-core is on par with 6-core i5-10500 3.1 GHz in iMac 27". I was planning to buy an Intel iMac 3.1 GHz if Apple Silicon didn't impress but this blows my mind. Imagine how fast the iMac M1/2/X/Z will be next year. Now I only hope that the GPU in iMac M can deliver too. Then we could play all our Intel games at least as fast. There will be some graphical bugs for sure but this is very promising and just the beginning.
:D
 
How can you say “for seemingly no good reason?”

It’s got way more performance than any of the competition, and two or three times the battery life.

Aren’t those good reasons?
Well I think that all depends on whether or not you can do the things you want to do on it.

Having the fastest computer in the world, or a computer with 20 hours of battery life, doesn’t mean a damn thing if you cant run the programs you want/need to run on it.

I’m not in that camp; the M1 Macs run everything I need. That doesn’t mean I don’t empathize with those in the opposite camp.
 
I’m definitely not an apple hater and these M1s look genuinely amazing. But, I rely on an x86 windows app for work. Currently use Parallels for it. Something will have to give when I next need a new computer.
I anticipate that within the year we'll see either x86-64 processor emulation solutions that run Windows x64 (the return of SoftPC and Virtual PC!), and/or Microsoft will begin licensing Windows ARM to consumers (and by that time they should have their 64-bit emulation worked out). Though one possible hurdle with the latter is how much faster Windows ARM will run on Macs than on their Surface Pro X. 😬
 
No, we aren't sure, you are. And you're wrong by the way. No one said Rosetta 2 can't run on multiple cores. The article just emphasises the single core perf because that already exceeds all the Intels so it results in a funnier article. Reading comprehension, people.

There is a multi-core score on the benchmark site. It just happens to be beaten by Intel Macs, because apparently multi-core emulation doesn't nearly scale linearly as in a native run, where multi-core score for a proper multi-threaded executable with tasks that are easy to run in parallel is almost exactly single score times core number. Here the single core perf is 1313, so you'd expect a multi-core score of around 10504, yet in the real world it only scores 5888. So multi-core scalability isn't great, but it does exist.

Apple will work hard either to improve on that, or push ARM ports for the most important apps. Or both.
Good Lord, did we cross over a bridge today because the trolls are out in force.
 
Well I was waiting for this. Why on earth would you buy a 2020 Intel Macbook Air or Pro now?

If you need x86 virtualisation. Or if you need compatibility with macOS older than Big Sur (As M1 machines won't even run previous versions in a Virtual Machine).

That's pretty much the only reason.
 
This is all fake news until production units are in the hands of real users and YouTubers. Does anyone *actually* believe the gimped M1 with 8GB or 16GB of RAM is going to process video faster than an Intel blowtorch. Probably not. But the marketing is cute.

An ipad running LumaFusion on 4gb of ram is already exporting video faster than a windows workstation running premiere pro.

I believe. In Apple’s ability to integrate their hardware and software. In Intel’s inability to innovate meaningfully in this space, and in the competition’s lack of incentive to properly optimise their offerings for the windows platform.
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.