Multiple comparisons such as those in this article are why tables and graphs were invented.
Yes but that results in two problems.
The author can't feel good about himself by writing a wall of text that really doesn't mean much.
We don''t actually have shipping Mac ARM chips so there would be plenty of blank space in any honest comparison chart.
What baffles the mind is that Apple has clearly stated that the development Macs, with ARM chips, sent out don't represent the coming Macs. In fact those development platforms are using an older ARM chip. For various reasons the currently shipping A series are not likely representative of the coming Macs either. Now I expect the Mac chips will inherit much from the A series and a Mac Book might even use an A series chip, but to address the competitive landscape they will need to implement a far more performant solution. So I'm at a loss to see the value in this article, I doubt that the Mac processors will even be in the A series lineup.
The value in this article is pretty simple: It compares today's and recent years' Intel Macs with today's and recent years' A-series devices -- iPhones, iPads and the Dev Kit Mac. Does that mean much? Perhaps if the performance of today's A-series devices was woeful, then no, it probably wouldn't mean much. But what this article does point out quite well across the board is that yesterday's and today's A-series devices - that aren't in the slightest optimized for what Macs are supposed to be - do in fact keep up quite well with at least the low and mid range Intel Macs of similar time periods.
What that tells me is that if we make the (I think very reasonable assumption) that Apple's rate of improvement remains similar to what it has been, then tomorrow's A-series Macs - with (a) more powerful silicon than today's A-series devices and (b) silicon optimized for the purpose of tomorrow's Macs - are going to do a perfectly good job of keeping up with, if not trouncing, what they might have been if they'd stayed with Intel for Macs.
There's concern about how much Apple's chips can keep with and/or exceed the performance of Intel's for the purpose of future Macs. This article provides pretty clearly what information we have on that topic so far, and gives us something we can work with for at least guesstimating some answers to those concerns. From (a) the current landscape and (b) the rate of recent growth - both of which are presented pretty nicely in this article - I think it's pretty reasonable to extrapolate what Apple likely has in their labs right now and based on all that, I'm willing to guess it's pretty fricking awesome.
It would have been more interesting to see a comparison between Ryzen 4000 Mobile and Apple A Processors.
Bashing Intel is no news. Apple needs to beat AMD now, not Intel and this is much less likely given how perfect the recent AMD Notebooks have been considering the relevant metrics.
Apple uses Intel processors not AMD. This article compares, not bashes current or relatively current Apple offerings to give an idea of how Apple Silicon is already doing an impressive work to keep up.
If Apple wanted to, they can take their Macs to 128bit or more. Imagine, for Mac Pros, multiple 256bit processors. Apple has now unleashed their potential. Software developers now can do apps that cover all the Apple hardware.
Apple SHOULD have been using AMD processors for a few years now. The exclusivity deal with Intel ended years ago, and in the last few years AMD gained the upper hand in processor speed. It might have even let us avoid this Apple silicon fiasco.
I fail to understand how Apple Silicon is a "fiasco". Huh? What on earth are you talking about? I think you've completely misunderstood why Apple is switching to their own Silicon. It's not all about performance. In fact I think performance is only secondary to what they're actually trying to achieve with ASi. They just waited till now to do it to ensure that they could do what they're actually trying to achieve, without sacrificing performance.
If we were to use the same logic you're expressing there, we'd be saying things like "Apple SHOULD have been using Windows for a few years now". Think of all the money they could have saved instead of pouring more resources into macOS.
It would have been more interesting to see a comparison between Ryzen 4000 Mobile and Apple A Processors.
Bashing Intel is no news. Apple needs to beat AMD now, not Intel and this is much less likely given how perfect the recent AMD Notebooks have been considering the relevant metrics.
Apple uses Intel processors not AMD. This article compares, not bashes current or relatively current Apple offerings to give an idea of how Apple Silicon is already doing an impressive work to keep up.
If Apple wanted to, they can take their Macs to 128bit or more. Imagine, for Mac Pros, multiple 256bit processors. Apple has now unleashed their potential. Software developers now can do apps that cover all the Apple hardware.
Apple SHOULD have been using AMD processors for a few years now. The exclusivity deal with Intel ended years ago, and in the last few years AMD gained the upper hand in processor speed. It might have even let us avoid this Apple silicon fiasco.
I fail to understand how Apple Silicon is a "fiasco". Huh? What on earth are you talking about? I think you've completely misunderstood why Apple is switching to their own Silicon. It's not all about performance. In fact I think performance is only secondary to what they're actually trying to achieve with ASi. They just waited till now to do it to ensure that they could do what they're actually trying to achieve, without sacrificing performance.
If we were to use the same logic you're expressing there, we'd be saying things like "Apple SHOULD have been using Windows for a few years now". Think of all the money they could have saved instead of pouring more resources into macOS.
Sigh. How do some people just so not get it?
This forum, like many other apple-based ones, consists a lot performance-driven and short-sighted individuals who only have a view of a regular PC builder.
I'm not saying DIY is bad, but you can't use that vision all the time.
My biggest complaint with my work-issued 2018 MBP15 is that it runs hot when I have it connected to an external monitor and using the builtin keyboard. The top surface gets hot, heating up the keyboard! I really like the butterfly keyboard a lot more than the work-issue Macally one, and my work from home setup is bit too space constrained for an external keyboard anyways.
Hopefully they can have a 25 W SoC that keeps the keyboard and top case cool while providing better performance than Intel systems. Actually, I think they can put the logic board behind the display by the hinge if it is long skinny like the iPad Pros. That'll remove the primary source of heat from the keyboard and keep it nice and cool at all times.
Same here, egg frying heat too on a 2019 MBP, plus battery life sucks. Just reading news sites in Safari is a pain with ads causing a very jumpy experience and the battery drains in a couple of hours whereas my iPad can go on forever on the same sites and stay cool and scroll smoothly. I can't wait for an MBP with Apple Silicon.
My biggest complaint with my work-issued 2018 MBP15 is that it runs hot when I have it connected to an external monitor and using the builtin keyboard. The top surface gets hot, heating up the keyboard! I really like the butterfly keyboard a lot more than the work-issue Macally one, and my work from home setup is bit too space constrained for an external keyboard anyways.
I have the same experience with temperature as you in my MBP 13" 2017. The keyboard gets hot when running some applications and doing video conference. Looking forward how the new Apple notebooks improve this issue.
Hopefully they can have a 25 W SoC that keeps the keyboard and top case cool while providing better performance than Intel systems. Actually, I think they can put the logic board behind the display by the hinge if it is long skinny like the iPad Pros. That'll remove the primary source of heat from the keyboard and keep it nice and cool at all times.
What you propose is was MS did with the Surface Book. You'll have to sacrifice some inches in the screen, with the benefit that you mentioned. I think it could be possible with the new, smaller SoC's.
I think it is possible to put in an active cooling system for a 6 mm thick device like an iPad, so 15W to 30W SoCs are possible. The display should be wedged shaped where is tapers to the thinness of Apple's current laptop displays. I'm also all in on have the front cams stick out like they do on phones. The logic board also needs to be as close to the hinge as possible so the laptop can stay balanced.
Not that I think they would do it. It's just the transition to Apple Silicon represents a big opportunity to redesign a laptop inside and outside, and I hope Apple takes it. Apple Silicon logic boards will be smaller than Intel boards by quite a bit, and with lower power, the batteries can get smaller too. This provides some opportunities for design. They can do some pretty wild things.
These low power chips enable all sorts of possibilities in both the laptops and the iPads to get a bit more performance with passive systems. For example they could simply machine the case into a more performant heat sink and mount the SoC directly to the optimized shell. The shell already impacts thermal performance but this would be a more direct usage of the shell as a traditional heat sink. The trick is to design in the fins so that they look acceptable. We might be only talking a few whats more capability for passive cooling but that could have a big impact. Other possibilities include carbon fiber heat sinks to spread the heat even faster. I don't ever see 15 to 30 watts. sustained, in an iPad though, it is just foo much no matter how good your heat sinking is. The real trick in these very compact or thin devices, like an iPad or Mac Book, is getting good sustained performance to avoid the machine crapping out from continuous use. You don't want frequency scalling to impact the feel of the machine like it did on the old Mac Books.
In any event yeah these ARM chips should make for some interesting new products from Apple. The question is will this be the first round of machines or will the real innovation come in round two. I'm actually holding off on buying an AMD laptop as I'm really interested in seeing ARM done right in the PC space. Unless Apple goes nuts with pricing or screws up Mac OS i could see getting back into the Mac laptops as secondary machines. If Mac OS gets locked down even more I can see myself rejecting based on that issue alone.
Probably a mix and match of keeping the existing form factors to debuting a new form factor. It's just going to depend on where the particular product is in the design cycle.
Yes, for an iPad, no more than 7 to 8 W. It's a handheld device and that should automatically limit it to passive cooling from the case without it being uncomfortable to touch. But on a laptop that only has about say 3 mm of height for a fan and heatsink, I think 15 W is definitely possible. Apple achieves 15 W with about 8 mm of height an one fan for the 2 port. A bigger fan, a bigger heat sink, more airflow could probably achieve double that. But Apple simply isn't going to do that or really doesn't want to so it. They want to get away from having to design around hot components in their machines. So, if they have a thin and light laptop, it is likely going to use a lower Watt SoC that outperforms Intel and AMD thin and light laptops, that use hotter components.
The decreased logic board area and decreased battery capacities does offer some interesting things though. If the board gets small enough, there may be enough room for a keyboard with 3 to 4 mm of travel. A nice clickity-clackity 4 mm travel laptop keyboard would be very very interesting. The dual display clamshell or folding display clamshell can be 6 mm thick unfolded, 12 mm closed. There are going to be a few Lakefield laptops like this, but Apple should be able to crush them in terms of performances and the number of touchscreen apps too.
Hopefully, one of their big priorities is to have none of their Apple silicon laptops be uncomfortable to the touch. No more than 85 °F or something like that. They'd rather use a 10 W SoC than a 20 W SoC in a MBP13, or a 25 W SoC than a 50 W SoC in a MPB16, if they can help it.
I can imagine all sorts of possibilities for low power but performant SoC. One idea that I really would love to see Apple do is to make a keyboard with a built in Mac! Considering how good keyboards are designed they should be able to do this either passively cooled or actively cooled without blowing out the size of the keyboard. Connect the keyboard to a monitor supporting USB power delivery and you have a complete computing solution. For some people the monitor would need to support additional I/O for others WiFi in the keyboard would be enough. The nice thing is this could be delivered as the new low cost Mac solution while the Mini gets reconfigured into a machine that more people would actually buy.
As for the laptops I'm with you at least partially, but honestly if the MBP don't get hot they are not getting max performance out of the platform and most users of these machines need all the performance they can get. A passively cooled Mac Book and even the Mac Book Airs though are not performance machines and as such should run cooler. I'd rather see real steeps in capability going from each class of machine - Mac Book = limited connectivity / performance; Mac Book Airs = more connectivity and 2X the performance; Mac Book Pros = max connectivity and at least 4x the performance. Frankly connectivity might mean bringing back some old features depending upon the class of machine. SD slots is a huge one and frankly it wouldn't hurt to see Ethernet on the Pros. Performance would come from clock rate increases in part but mostly by more cores. Cores are especially important for MBP users so when I say at least 4X I mean 4 times the number of cores in the Mac Book. I think this is very possible at 5 nm using some of the techniques common on the AMD side of the industry.
The story should have included a graph showing the performance increase in Apple silicon CPUs vs Intel CPUs since the original iPhone was released. The crossing of the curves explains what is really going on.
What Metriacanthosaurus said. While some new benchmarks on the 12Z chip running native apps suggests that even that chip has an impressive amount of barely-tapped potential, the real point here is that Apple has not yet released any member of the "family of SoCs" that are specifically designed for the Mac. Nor has it yet released any device that has all of its systems optimized for the (presumably redesigned) future Macs.
Recent stories here and elsewhere are kind of focused on the chips themselves because that's where the (tiny amount of available) information is right now, but there's really four keys to future Macs: first, the specially-designed Mac-centric SoC; second, the optimized motherboard and other mechanical components (we've been enjoying some of this part for years now, which is why we're so far ahead of PC makers on things like TB3/USB-C/USB4); third, software compiled specifically to take advantage of this custom hardware (in particular, I foresee much greater expansion on multi-tasking for all but the most basic software); and four, new chassis designs again fully in harmony with the chip, graphics, thermals, and support systems.
Intel has been great for Apple, and often very accommodating to Apple's specific desires (especially given the size of the Mac market, which is still small). But Apple Silicon (please note: not silicone!) is made not only with an awareness of hardware requirements but also the specific ways Mac users work with software, neither of which Intel can really design for. Because of the potential this opens up, I think Apple will continue to work on bringing more components in-house (like wireless/5G) and forming partnerships with third-parties where they can get custom-designed parts for its particular and in some cases unique needs.
Kudos to Mike P for the rundown, though this is really only the beginning of a tale mostly yet to be revealed. Specs and comparisons are fun, but at the end of the day the truly remarkable thing about all this is that Apple has been planning a brilliant revival of the Mac -- by far their least-popular "computer" product, let's not forget -- to keep it relevant and even exciting in the current age of mobile and wearable domination. I cannot wait to see what Apple Silicon running new Apple hardware can do, how much room for innovation they've opened up, and specifically (though I'm not the target for it) what high-end Apple Macs are going to be able to do. I'm with Jean-Louis Gassée in thinking that some major surprises are still ahead of us, including some that will benefit the entire industry, directly or indirectly.
I’ll address one point: you’re clearly not a developer, or at least not one with enough experience. If you make a faster CPU it doesn’t change a thing about what you can do regarding multitasking, regardless of single core or multicore performance, and adding more cores does nothing to change the nature of how you solve problems effectively by adding more threads in a process or more things in the system as a whole. In fact, adding more cores and more multitasking/threads slows down throughput for a process and often a system, when those related tasks aren’t embarrassingly parallel that don’t have memory conflicts. Look up Amdahl’s Law, and what’s important to understand is even the best system is constrained by main memory latency and speed, with the CPU waiting for data from main memory about 30-40% of the time, despite all the huge cache hierarchy: it’s made far worse if you quickly swap unique code in and out of the CPU for as many threads as possible, as quickly as possible.
There are no applications and domains that exist that don’t already work well on a high-end MacPro and not-quite-as-fast on an i9, but adding more cores doesn’t automatically enable the developer to accomplish anything, and it isn’t any different in how it is designed by the developer.
I don't really get the point of articles like this. It just feels like click bait until we know the details of what Apple will really release. The ONLY thing we need to know is whether Apple is capable of matching or exceeding Intel's performance... per core. They can. From there, it's simply a matter of what type of configuration Apple chooses to produce. The end. Comparing A10 fusion and A12x chips is absolutely meaningless as that's not what Apple is going to ship with their Apple Silicon Macs.
It would have been more interesting to see a comparison between Ryzen 4000 Mobile and Apple A Processors.
Bashing Intel is no news. Apple needs to beat AMD now, not Intel and this is much less likely given how perfect the recent AMD Notebooks have been considering the relevant metrics.
Apple uses Intel processors not AMD. This article compares, not bashes current or relatively current Apple offerings to give an idea of how Apple Silicon is already doing an impressive work to keep up.
If Apple wanted to, they can take their Macs to 128bit or more. Imagine, for Mac Pros, multiple 256bit processors. Apple has now unleashed their potential. Software developers now can do apps that cover all the Apple hardware.
While you seem to be randomly throwing bit count around without having the necessary technical understanding to do so, I would like to point out that Apple will not be competing against Intel based machines but AMD based ones. So it is well in the interest of the average reader to see how Apple can keep up with AMD.
AMD are just playing the Intel game; showing TDP for base clock. When that jumps 2.5x for turbo, the 4800U won’t be drawing 15W, it’ll be cooking x64 eggs. Perhaps Apple should do the same & release the small-core TDP only.
Obviously you haven't read any recent reviews. Beyond that AMD and Intel calculate their TDP numbers differently. In any event the AMD laptops are demonstrating an amazing ability to keep cool while under load. They might not do as well as intel at idle but for people that actually use their laptops AMD has proven to be far less demandign power wise while giving better performance on a number of work loads. Effectively you don't know what is actually going on with modern processors.
So you’re saying the stated 15W TDP is for full load? Or is it misleading (not identically misleading, just misleading) like Intel?
It would have been more interesting to see a comparison between Ryzen 4000 Mobile and Apple A Processors.
Bashing Intel is no news. Apple needs to beat AMD now, not Intel and this is much less likely given how perfect the recent AMD Notebooks have been considering the relevant metrics.
Apple uses Intel processors not AMD. This article compares, not bashes current or relatively current Apple offerings to give an idea of how Apple Silicon is already doing an impressive work to keep up.
If Apple wanted to, they can take their Macs to 128bit or more. Imagine, for Mac Pros, multiple 256bit processors. Apple has now unleashed their potential. Software developers now can do apps that cover all the Apple hardware.
Apple SHOULD have been using AMD processors for a few years now. The exclusivity deal with Intel ended years ago, and in the last few years AMD gained the upper hand in processor speed. It might have even let us avoid this Apple silicon fiasco.
So they’d just be at the mercy of AMD’s product strategy instead of Intel’s?
At least with ASi they can use a, predominantly, 1st-party ISA (with a little Aarch64 for marketing/ misinterpretation/ compatibility) on their own logic. Refreshing when they want, adding functionality when they want, implementing the OS as hardware when they want.
It would have been more interesting to see a comparison between Ryzen 4000 Mobile and Apple A Processors.
Bashing Intel is no news. Apple needs to beat AMD now, not Intel and this is much less likely given how perfect the recent AMD Notebooks have been considering the relevant metrics.
Apple uses Intel processors not AMD. This article compares, not bashes current or relatively current Apple offerings to give an idea of how Apple Silicon is already doing an impressive work to keep up.
If Apple wanted to, they can take their Macs to 128bit or more. Imagine, for Mac Pros, multiple 256bit processors. Apple has now unleashed their potential. Software developers now can do apps that cover all the Apple hardware.
While you seem to be randomly throwing bit count around without having the necessary technical understanding to do so, I would like to point out that Apple will not be competing against Intel based machines but AMD based ones. So it is well in the interest of the average reader to see how Apple can keep up with AMD.
AMD are just playing the Intel game; showing TDP for base clock. When that jumps 2.5x for turbo, the 4800U won’t be drawing 15W, it’ll be cooking x64 eggs. Perhaps Apple should do the same & release the small-core TDP only.
Obviously you haven't read any recent reviews. Beyond that AMD and Intel calculate their TDP numbers differently. In any event the AMD laptops are demonstrating an amazing ability to keep cool while under load. They might not do as well as intel at idle but for people that actually use their laptops AMD has proven to be far less demandign power wise while giving better performance on a number of work loads. Effectively you don't know what is actually going on with modern processors.
So you’re saying the stated 15W TDP is for full load? Or is it misleading (not identically misleading, just misleading) like Intel?
Pretty much. The whole load for an iPad Pro is probably around 15-20W. That is for everything, not just the SoC. I know my 11” iPad Pro never heats up much.
Comments
What that tells me is that if we make the (I think very reasonable assumption) that Apple's rate of improvement remains similar to what it has been, then tomorrow's A-series Macs - with (a) more powerful silicon than today's A-series devices and (b) silicon optimized for the purpose of tomorrow's Macs - are going to do a perfectly good job of keeping up with, if not trouncing, what they might have been if they'd stayed with Intel for Macs.
There's concern about how much Apple's chips can keep with and/or exceed the performance of Intel's for the purpose of future Macs. This article provides pretty clearly what information we have on that topic so far, and gives us something we can work with for at least guesstimating some answers to those concerns. From (a) the current landscape and (b) the rate of recent growth - both of which are presented pretty nicely in this article - I think it's pretty reasonable to extrapolate what Apple likely has in their labs right now and based on all that, I'm willing to guess it's pretty fricking awesome.
I fail to understand how Apple Silicon is a "fiasco". Huh? What on earth are you talking about? I think you've completely misunderstood why Apple is switching to their own Silicon. It's not all about performance. In fact I think performance is only secondary to what they're actually trying to achieve with ASi. They just waited till now to do it to ensure that they could do what they're actually trying to achieve, without sacrificing performance.
If we were to use the same logic you're expressing there, we'd be saying things like "Apple SHOULD have been using Windows for a few years now". Think of all the money they could have saved instead of pouring more resources into macOS.
Sigh. How do some people just so not get it?
I'm not saying DIY is bad, but you can't use that vision all the time.
There are no applications and domains that exist that don’t already work well on a high-end MacPro and not-quite-as-fast on an i9, but adding more cores doesn’t automatically enable the developer to accomplish anything, and it isn’t any different in how it is designed by the developer.