Discussion Apple Silicon SoC thread

[Eug]

M1
5 nm
Unified memory architecture - LP-DDR4
16 billion transistors

8-core CPU

4 high-performance cores
192 KB instruction cache
128 KB data cache
Shared 12 MB L2 cache

4 high-efficiency cores
128 KB instruction cache
64 KB data cache
Shared 4 MB L2 cache
(Apple claims the 4 high-effiency cores alone perform like a dual-core Intel MacBook Air)

8-core iGPU (but there is a 7-core variant, likely with one inactive core)
128 execution units
Up to 24576 concurrent threads
2.6 Teraflops
82 Gigatexels/s
41 gigapixels/s

16-core neural engine
Secure Enclave
USB 4

Products:
$999 ($899 edu) 13" MacBook Air (fanless) - 18 hour video playback battery life
$699 Mac mini (with fan)
$1299 ($1199 edu) 13" MacBook Pro (with fan) - 20 hour video playback battery life

Memory options 8 GB and 16 GB. No 32 GB option (unless you go Intel).

It should be noted that the M1 chip in these three Macs is the same (aside from GPU core number). Basically, Apple is taking the same approach which these chips as they do the iPhones and iPads. Just one SKU (excluding the X variants), which is the same across all iDevices (aside from maybe slight clock speed differences occasionally).

EDIT:



M1 Pro 8-core CPU (6+2), 14-core GPU
M1 Pro 10-core CPU (8+2), 14-core GPU
M1 Pro 10-core CPU (8+2), 16-core GPU
M1 Max 10-core CPU (8+2), 24-core GPU
M1 Max 10-core CPU (8+2), 32-core GPU

M1 Pro and M1 Max discussion here:

Page 78 - Discussion - Apple Silicon SoC thread

Page 78 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M1 Ultra discussion here:

Page 109 - Discussion - Apple Silicon SoC thread

Page 109 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M2 discussion here:

Page 127 - Discussion - Apple Silicon SoC thread

Page 127 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

Second Generation 5 nm
Unified memory architecture - LPDDR5, up to 24 GB and 100 GB/s
20 billion transistors

8-core CPU

4 high-performance cores
192 KB instruction cache
128 KB data cache
Shared 16 MB L2 cache

4 high-efficiency cores
128 KB instruction cache
64 KB data cache
Shared 4 MB L2 cache

10-core iGPU (but there is an 8-core variant)
3.6 Teraflops

16-core neural engine
Secure Enclave
USB 4

Hardware acceleration for 8K h.264, h.264, ProRes

M3 Family discussion here:

Page 215 - Discussion - Apple Silicon SoC thread

Page 215 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

 

[Doug S]

I am not impressed.

It's OK, if that's a MBA with it's limited power budget. But disappointing if that is the new Mac Mini with more power to use, especially with all Apples talk of massive performance increases.

What will be nice is we can finally get away from using Geekbench as a CPU bench...

That's obviously not an M1, look at the clock rate. It is more likely an A12Z in one of those developer boxes, though the clock rate shown is a little low even for that.

And unless there's a native version, it is also running a translated binary (FWIW GB5 got 70% of native performance running a translated x86 binary)

 

[Doug S]

Does someone have a list of differences between what we think M1 is, vs. what we think A14X will be?

I'll give my list of what I think the differences are:

 

[jpiniero]

One nice thing is that all the models have the full 4+4 CPU configuration, there's no cut CPU models. The base model on the Icelake MBA released this year was dual core (1000NG4). The M1 is going to be way faster than that.

 

[Heartbreaker]

That's obviously not an M1, look at the clock rate. It is more likely an A12Z in one of those developer boxes, though the clock rate shown is a little low even for that.

And unless there's a native version, it is also running a translated binary (FWIW GB5 got 70% of native performance running a translated x86 binary)

Looks like it probably is the Dev box, hopefully M1 is significantly better.

There is a native version:

Evaluate your computer's hardware capabilities | Cinebench from Maxon

Cinebench is a free cross-platform test suite that evaluates your computer's hardware capabilities. Get a more accurate measurement of Cinema 4D's ability to take advantage of multiple CPU cores and modern processor.

www.maxon.net

"Cinebench R23 now supports Apple’s M1-powered computing systems "

I'll give my list of what I think the differences are:

Agreed, it looks fairly certain it will be the same chip, it will just be configured different.

 

[AmericanLocomotive]

There is no logic in that. They aren't obligated to make the comparison you want to see.

These are Apples lowest end ARM Mac parts that will ever exist. They will have excellent performance better than the majority of the laptop market.

It's only up from here.

How is there no logic in that? In Apple's own presentation, they are DIRECTLY making comparisons to "High end Windows Laptops" and the "The latest competitor's processors". So please explain how there is no logic in Apple comparing their processor to Renoir, when Renoir is in the segment they're comparing.

Furthermore "having better performance than the majority of the laptop market" is not saying much. Especially considering a full 25% of all laptops sold this year were Chromebooks. On top of that, the average laptop sale price in the U.S. is less than $700, and most <$700 laptops have pretty miserable processors.

Realistically, Apple should have Renoir in their comparisons (and not the "latest" laptop CPUs, which are Intel, which are not nearly as performant or efficient as Renoir) AND they should be comparing against similarly priced machines. Not the "entire laptop" market, of which the majority of machines are at a very low price.

 

[Heartbreaker]

How is there no logic in that? In Apple's own presentation, they are DIRECTLY making comparisons to "High end Windows Laptops" and the "The latest competitor's processors". So please explain how there is no logic in Apple comparing their processor to Renoir, when Renoir is in the segment they're comparing.

I didn't say it was invalid to compare. I am just pointing out that expecting marketing to target the specific product, YOU want them to, is not logical.

Generally marketing comparisons are done against favorable targets, and here the direct comparisons were made against, Apples own previous generation Intel products, which makes a whole lot more sense, since this will be the replacement for those, and the upgrade path from those products.

You might like to see the Renoir comparison, but expecting it from Apple marketing doesn't make any sense.

Don't equate what you want, to be what makes sense for a company to do.

 

[Mopetar]

Who cares what they did at their event or what comparisons they made. Once it launches reviewers will be able to get their hands on the products and compare them however they want as well as against other products that might represent future Zen3 laptop parts.

 

[moinmoin]

Intel's had 8 core mobile parts for over a year now, even the 16" MBP offers the 9880H as the upgraded model's CPU. Now you'll notice that Apple didn't replace the 16" just yet.

That is a binned desktop chip, I did specifically exclude DTR. Maybe I should have said "ultrabook" instead mobile laptops? With the high TDP Intel's H-line can and will consume Apple will have a field day again showing off its more efficient ARM based M-line replacement for it once it's out.

 

[Leeea]

The Zen 3/Zen 2/10900k test setups were running at their manufacturer's official maximum supported DRAM frequency, how does that effectively "set" to DDR4-2400?

Your are mistaken.

The spec2006 results for the 5950x were identical to the results in this article:
https://www.anandtech.com/show/1621...e-review-5950x-5900x-5800x-and-5700x-tested/9
easily verified by looking at the graph.

In the same article, it states:
https://www.anandtech.com/show/1621...-review-5950x-5900x-5800x-and-5700x-tested/11

This is also typically run at JEDEC subtimings where possible. It is noted that some users are not keen on this policy, stating that sometimes the maximum supported frequency is quite low, or faster memory is available at a similar price, or that the JEDEC speeds can be prohibitive for performance.

2400 MHz is the JEDEC timing for the memory in question.

Your link points to a result using Intel-specific compilers which Anand doesn't use for the benches (Look at that libquantum test for why).

vs using an Apple specific compilier for the Apple chip?

of course, the quote from the articule:

Starting off with SPECint2006, we don’t see anything very unusual about the A14 scores, save the great improvement in 456.hmmer. Actually, this wasn’t due to a microarchitectural jump, but rather due to new optimisations on the part of the new LLVM version in Xcode 12.

 

[Eug]

No way... a Mac is way more capable than an iPad. I have a 5th gen iPad with bluetooth keyboard and mouse, and it's just not comparable.

Therein lies much of the problem.

Check out an iPad Pro 12.9" with Magic Keyboard and then report back.

Both the 10.5"/11" and 12.9" iPad Pros as well as the 10.2" iPads and 10.5"/11" iPad Air all have full sized non-Bluetooth keyboards available. The 10-11" devices have keyboards which have 18 mm key spacing, which is considered ergonomically full-sized, but which is still smaller than PC keyboards. The 12.9" devices have 19 mm key spacing, which is exactly the same as all Macs and most Windows PCs, and which is also considered ergonomically correct.

The 9.7" iPad keyboards are problematic for two reasons. 1) Most are Bluetooth. Pairing issues, lag to connect, etc. and just the general annoyance of having to charge the battery. This was fixed with the 9.7" iPad Pro, but all suffer a second problem: 2) The keyboard size is unergonomic. The keyboard for the 9.7" iPad Pro is spaced at roughly 17.5 mm IIRC, and that gives me problems. I also owned a Logitech Bluetooth model and it was at about 17 mm, and it actually made my wrists hurt when I typed on it. In contrast, the 18 mm on my iPad Pro 10.5" and my wife's iPad 7 10.2" is perfect for us. We have relatively small hands, so if you have bigger hands, then a 12.9" iPad Pro with 19 mm spacing (and trackpad if you get the Magic Keyboard) may be more appropriate for you.

The flexibility you get with macOS is leagues beyond what iPadOS offers. Multitasking is still hit or miss on iPad in terms of managing apps, support for more complex applications is basically non-existent unless you're a creative.

I have the same problem with some business applications, but it's a lot better in 2020 than it was say in 2017.

True external display support doesn't exist and there's no CLI. My iPad is MUCH better as a consumption machine than a productivity machine, but a Macbook Air can be both.

True external display would be nice, and for some people CLI too, but I would guess that less than 1% of computer users regularly use the CLI.

As for consumption on a Mac, one that that irritates me to no end on my MacBook is that I can't download Netflix episodes to it. It's not allowed. In fact, because of this, on business trips I had started taking BOTH my iPad Pro 10.5" (with Apple Smart Keyboard) and my 12" MacBook m3 (not M1 ) with me. BTW, one side bonus these days is that I can use the iPad Pro as an external monitor for my 12" MacBook, which can come in handy for MS Office on the road. (Mind you, these days I'm usually just stuck at home because of Covid.)

Even for a writing an internet post, it's inferior to a real laptop. Just because you don't need CPU power to write a post, doesn't make crappy keyboard and tiny screen good to use.

I don't even like using a laptop to post, when I can use desktop with big screen full size KB and mouse.

All currently shipping non-refurb iPads and iPad Pros have support for full-sized keyboards, as ergonomically defined by occupational health guidelines. However, if you want true Mac-sized full-sized keyboards, then the 12.9" iPad Pro with Apple Magic Keyboard, Apple Smart Keyboard Folio, or Logitech Folio Touch is the answer. See above.

 

[AmericanLocomotive]

I didn't say it was invalid to compare. I am just pointing out that expecting marketing to target the specific product, YOU want them to, is not logical.

Generally marketing comparisons are done against favorable targets, and here the direct comparisons were made against, Apples own previous generation Intel products, which makes a whole lot more sense, since this will be the replacement for those, and the upgrade path from those products.

I'm really not even sure what you're arguing? You keep ignoring the point that Apple compared their product to the entire notebook market - not just their own. My whole point of this starting this discussion was bring up the point that Apple's comparisons were heavily biased, untruthful and not really representative of how their chip competes with modern x86 chips.

Your only rebuttal so far has been "it's not logical for Apple to make those comparisons because it won't be as favorable to them" ...which literally backs up my original claim.

 

[Heartbreaker]

I'm really not even sure what you're arguing? You keep ignoring the point that Apple compared their product to the entire notebook market - not just their own. My whole point of this starting this discussion was bring up the point that Apple's comparisons were heavily biased, untruthful and not really representative of how their chip competes with modern x86 chips.

Your whole point seemed to be ranting that they MUST compare it to Renoir, and failure to do so was some kind of crime.

It's marketing. Get over it.

Unbiased third party comparison is what we all wait for, all the time, and the wait won't be long.

I expect Renoir laptops will be in the 2% that beat it. Will that make you feel better?

 

[defferoo]

Therein lies much of the problem.

Check out an iPad Pro 12.9" with Magic Keyboard and then report back.

Both the 10.5"/11" and 12.9" iPad Pros as well as the 10.2" iPads and 10.5"/11" iPad Air all have full sized non-Bluetooth keyboards available. The 10-11" devices have keyboards which have 18 mm key spacing, which is considered ergonomically full-sized, but which is still smaller than PC keyboards. The 12.9" devices have 19 mm key spacing, which is exactly the same as all Macs and most Windows PCs, and which is also considered ergonomically correct.

The 9.7" iPad keyboards are problematic for two reasons. 1) Most are Bluetooth. Pairing issues, lag to connect, etc. and just the general annoyance of having to charge the battery. This was fixed with the 9.7" iPad Pro, but all suffer a second problem: 2) The keyboard size is unergonomic. The keyboard for the 9.7" iPad Pro is spaced at roughly 17.5 mm IIRC, and that gives me problems. I also owned a Logitech Bluetooth model and it was at about 17 mm, and it actually made my wrists hurt when I typed on it. In contrast, the 18 mm on my iPad Pro 10.5" and my wife's iPad 7 10.2" is perfect for us. We have relatively small hands, so if you have bigger hands, then a 12.9" iPad Pro with 19 mm spacing (and trackpad if you get the Magic Keyboard) may be more appropriate for you.

I'm not talking about the ergonomics of the keyboard, I have a Logitech K380 which works great. All I'm saying is that the combination of iPad with keyboard and trackpad is still a subpar productivity experience relative to a Mac laptop, regardless of the type of keyboard and size of keyboard. (and it largely boils down to iPadOS)

True external display would be nice, and for some people CLI too, but I would guess that less than 1% of computer users regularly use the CLI.

Agreed with regards to the CLI, that's just my use-case, I'm sure it's different for others, but anything that involves heavy multitasking is just difficult on an iPad. Without true external monitor support and better multitasking capabilities (not referring to the speed, but the ergonomics of multitasking), I just don't see it as a serious solution for getting things done.

As for consumption on a Mac, one that that irritates me to no end on my MacBook is that I can't download Netflix episodes to it. It's not allowed. In fact, because of this, on business trips I had started taking BOTH my iPad Pro 10.5" (with Apple Smart Keyboard) and my 12" MacBook m3 (not M1 ) with me. BTW, one side bonus these days is that I can use the iPad Pro as an external monitor for my 12" MacBook, which can come in handy for MS Office on the road. (Mind you, these days I'm usually just stuck at home because of Covid.)

This is true, maybe Netflix will allow their iPadOS app to run on macOS which would have downloading enabled, but I'm not keeping my hopes up for that one. When I'm traveling and not looking to do work, I just bring my iPad. It can still get things done in a pinch, and has support for downloading Netflix content.

 

[AmericanLocomotive]

Your whole point seemed to be ranting that they MUST compare it to Renoir, and failure to do so was some kind of crime.

No. The point of my argument is that if they're going to make claims in reference to the entire PC ecosystem (which they did..), then they must include products like Renoir. Failing to do so is extremely misleading, and perhaps even false advertising (and false advertising is a crime, BTW).

Many here (including Apple) are talking like how M1 is this untouchable chip, and x86 is not even remotely close and will never be able to touch it in efficiency or perf/watt. But the reality is we already have x86 chips that are A LOT closer than Apple is letting on. My gut feeling is that Apple doesn't want to admit how close current x86 chips are. Why else would they work so hard to obscure what chips they are comparing to?

 

[Eug]

I'm hearing that Geekbench 5 is now universal with native support for M1. I can't seem to find a link for that though.

We'll have third party M1 test results in less than a week people, from at least two benchmarking applications, Cinebench R23 and Geekbench 5.

Are Apple's main apps like iMovie, Final Cut, Garageband, Logic Pro, Photos, etc. also now fat binaries? Or are they still pending release?

 

[Heartbreaker]

No. The point of my argument is that if they're going to make claims in reference to the entire PC ecosystem (which they did..), then they must include products like Renoir. Failing to do so is extremely misleading, and perhaps even false advertising (and false advertising is a crime, BTW).

They don't have to include it specifically any more than they have to include every other product on the market specifically.

You are just ranting nonsense here again.

 

[AmericanLocomotive]

They don't have to include it specifically any more than they have to include every other product on the market specifically.

You are just ranting nonsense here again.

"We built the fastest, and most powerful car in the world."*

"*When compared to the latest car released by a competitor."**

"**Of course, the latest car released by any competitor is a low-end economy car that costs 1/4 of what our car costs, but we are just going to conveniently leave that part out."

That is what Apple is doing. It is highly misleading advertising. Like I said, it's one thing if they were limiting it to only their own products, but they are not.

 

[jpiniero]

That is a binned desktop chip, I did specifically exclude DTR. Maybe I should have said "ultrabook" instead mobile laptops? With the high TDP Intel's H-line can and will consume Apple will have a field day again showing off its more efficient ARM based M-line replacement for it once it's out.

The 9880H's TDP is technically 45 W. I guess it would depend on what your definition of DTR is.

They may of course be talking about single thread performance.

 

[name99]

i would wait for third party benchmarks (and other than SPEC and geekbench)

Like what? What *CPU* benchmarks are more informative than these two.
Be very very careful with your answer if you want to retain my respect.

Let's see what exactly did the M1 Macs replace:

M1 MacBook Air
Core i3-1000NG4 1.1 GHz, Core i5-1030NG7 1.1 GHz, Core i7-1060NG7 1.2 GHz - 9-10 Watt Ice Lake (Geekbench 5 MC score ~ 3900)

M1 MacBook Pro
Core i5-8257U 1.4 GHz, Core i7-8557U 1.7 GHz - 15 Watt Coffee Lake (Geekbench 5 MC score ~ 4050)

M1 Mac mini
Core i3-8100B 3.6 GHz - 65 Watt (!) Coffee Lake (Geekbench 5 MC score ~ 3550)

Essentially what this means is that with the new M1 Macs, Apple has replaced all its Intel Macs in these form factors* that score in the GB5 MC range of about 4000 or less.

Even A12X from 2018 beats this 4000 threshold. And so does A14 non-X in the iPhone 12 Pro Max I'm getting this week. A14X/M1 should thoroughly trounce all these CPUs. Furthermore, this doesn't even touch on all the extra goodies on that SoC, that aren't measured by general benchmark tests like GB. GB isn't a good correlate to video editor scrubbing performance on iPadOS for example. iPadOS video editors often run much more smoothly than one might expect from those scores.

*There are still some entry level Intel iMacs that score in the ≤4000 range. Thus, I suspect that Apple will use M1 in the entry level iMacs as well.

BTW, how loud is that Core i3-8100B Mac mini?



As mentioned, Apple doesn't care about Renoir here, and quite frankly, I'd say the vast majority of their target market doesn't care either. In fact, I'd say 99% of them don't even know what Renoir is. It would be stupid for Apple to focus on that.

Much more interesting is the single threaded scores; they are what makes a machine feel "snappy".

The GB5 (single-threaded) numbers for all the Intel machines you listed are around 1150.
The iPad Pro (A12X/Z) is similar; A13 is about 1330, A14 (iPhone) about 1580.

Well think about who the audience for these Macs is - it is existing Mac owners looking to upgrade. They aren't going to think the numbers are a bunch of snake oil, even if they seem a bit overly optimistic. What they'll hear is "these new Macs are a lot faster than my current Air/MBP13/Mini" and that's true.

The wider potential audience of PC users some of whom might be induced to switch for significant performance bumps aren't going to listen to numbers in an Apple marketing event no matter how detailed they were. Those people will only potentially give Apple a look after they see unbiased reviews like the in-depth stuff Anandtech does.

Well, true story, I spoke to my builder today and he said that even though he has been a PC user all his life, he sees how fast his wife can edit an manipulate photos and video on her iPad while the same operation struggle on his PC. He's seriously considering getting one of these macs right away because it does well what his job requires -- video/photo editing at high speed. Not "professional" level, but a large part of his job at an amateur level. I suggested he wait as long as he can because the ARM low-end iMac is probably the best match to his needs, but he has work to do right now...

That's how this plays out in the real world; people who have no interest in belonging to the PC vs Apple tribe, they just have a job to do and want the tool that does it well.
Gamers are NEVER going to be on board because for most of them half the fun is building their own PC and dicking around with overclocking. That's not the experience Apple is selling and never will be, so there's zero point in Apple either try to appeal to them, or them complaining that Apple doesn't do what they want.

 

[chrisjames61]

I don't think they're going beyond Macbook with M1, but we'll see.

I find Apple events to be very cringe on multiple levels, I might stop watching and just wait for the reports, lol.

As a person who has purchased literally hundreds of Macs since 1984 because I own a print shop I would say that Apple is "very cringe" is an understatement of the highest order. The company as a whole repulses me on so many levels.

 

[name99]

We also have some issues here, in that almost all of Apple's recent Axx performance increase has come from clock speeds and leveraging TSMC processes.

This is not even close to true.
Last time I did the calculation, for the A12 I think, the A12 was about 4x as fast as the A7, evenly split between 2x IPC and 2x clock rate increase.
With A14 it's probably still about the same. Almost all the A13 boost was from better IPC, almost all the A14 boost is from clock rate.
It's still about half the performance is from a better designed chip, half is from running faster transistors.

 

[name99]

Interesting. I didn't know Cinebench R23 had gone native. It turns out the press release for that only came out an hour ago.

How good is Cinebench at determining clock speeds? It says 2.5 GHz single-core and 2.3 GHz multi-core.

It's benchmarking the A12Z, not the M1.

And Cinebench is a multicore benchmark. That's fine for adolescents who primarily care about boasting, but the hard problem in CPU design is single-threaded performance. As soon as someone prioritizes MT scores over ST scores I know they're a fool, someone who cares about these scores as a way to measure dick-length not a way to understand the engineering.
(Yes, there ARE important uses for MT scores. But believe me, I can tell from your tone whether or not you understand what they are...)

Long term, if Cinebench is especially important to you, what will matter is
- M1, along with every other improvement, has a 4th NEON unit
- I would expect Cinebench can make good use of SVE/2, when Apple finally gives it to us! How much do Cinebench numbers change as you disable AVX512, then AVX going to just SSE?
- Cinebench might (I honestly don't know) be able to make use of the AMX extensions. Those also still have not been activated in XCode. LLVM has been doing a lot of work over the past six months in the handling of matrices (work in which a lot of Apple people have been involved). So the hope is that fairly soon this will be released in XCode and AMX on both A13 and A14 will be available to developers.

Point is, once again, dick-measure if you must. But understanding-wise, even apart from future Apple chips, there's work to be done on getting maximum value from the existing chips, work that's still ongoing and not yet complete. It need to get into the compilers, then the apps need to be recompiled (and perhaps even restructured to make optimal use of new functionality). On the positive side this means that the M1 mac you buy today may grow 10% faster over the next two years or so with successive OS and app updates.

 

[Leeea]

Like what? What *CPU* benchmarks are more informative than these two.
Be very very careful with your answer if you want to retain my respect.

https://www.google.com/search?q=flaws+in+synthetic+benchmarks&oq=flaws+in+synthetic+benchmarks

https://www.spec.org/retired.html

I assume now you have lost all your respect for Spec.org? They decided spec2006 had "become to out-of-date" to be relevant and replaced it with spec2017. The last official spec2006 submission was 2018.

 

[Eug]

Much more interesting is the single threaded scores; they are what makes a machine feel "snappy".

The GB5 (single-threaded) numbers for all the Intel machines you listed are around 1150.
The iPad Pro (A12X/Z) is similar; A13 is about 1330, A14 (iPhone) about 1580.

People always say this, but I don’t think it’s that simple anymore, at least with 2020 OSes and software.

I find my iPad Pro 10.5 (A10X) feels snappier than my iPad 7 (A10). Actually the iPad 7 is surprisingly decent, but the iPad Pro 10.5 is better. Single-core performance is identical.

Also, for some basic OS navigation stuff and surfing, my Mac Pro with 8-core X5365 (GB SC 400 / MC 2200 tested under Windows) sometimes feels faster than my MacBook with 2-core m3-7Y32 (GB SC 750 / MC 1580).

Similarly my Windows 10 Phenom II 1055T 6-core 2.8 GHz feels noticeably faster after the upgrade from the original Athlon II 435 3-core 2.9 GHz, although part of that is related to turbo.

Well, true story, I spoke to my builder today and he said that even though he has been a PC user all his life, he sees how fast his wife can edit an manipulate photos and video on her iPad while the same operation struggle on his PC. He's seriously considering getting one of these macs right away because it does well what his job requires -- video/photo editing at high speed. Not "professional" level, but a large part of his job at an amateur level. I suggested he wait as long as he can because the ARM low-end iMac is probably the best match to his needs, but he has work to do right now...

That's how this plays out in the real world; people who have no interest in belonging to the PC vs Apple tribe, they just have a job to do and want the tool that does it well.
Gamers are NEVER going to be on board because for most of them half the fun is building their own PC and dicking around with overclocking. That's not the experience Apple is selling and never will be, so there's zero point in Apple either try to appeal to them, or them complaining that Apple doesn't do what they want.

Yes, I mentioned earlier about LumaFusion on iPad Pro doing way better for UI and scrubbing smoothness than the CPU performance benchmarks might suggest.

 

[name99]

"We built the fastest, and most powerful car in the world."*

"*When compared to the latest car released by a competitor."**

"**Of course, the latest car released by any competitor is a low-end economy car that costs 1/4 of what our car costs, but we are just going to conveniently leave that part out."

That is what Apple is doing. It is highly misleading advertising. Like I said, it's one thing if they were limiting it to only their own products, but they are not.

What EXACTLY are the statements that Apple made that have you so incensed?
You have never actually quoted any of them. All you do is insist that other people (not you, you are too smart) but other people will misinterpret them; but every time someone points out where your outrage is unjustified you keep insisting that something else is an outrage.

Here are the sorts of things Apple said:

• Uses 1/4 the power compared to the latest PC laptops running at full performance
• Uses 1/3 the power compared to the latest PC laptop GPUs running at full performance
• 
  
• MBA
• 3x faster than the best selling Windows laptop in its class
  • Faster than 98% of PC laptops
  • Up to 3.5x faster CPU than previous model
  • Up to 5x faster graphics than previous model
  • Up to 9x faster machine learning than previous model

Want to tell us where your objections lie?

Actually IMHO the most interesting/significant was a comparison against the previous model but not other machines, namely that MBP has 4x faster code compile than previous model.