Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
Leaked Intel Roadmap Reveals More Efficient Chip Than M1 Pro and Max to Launch Within Two Years
- Thread starter MacRumors
- Start date
- Sort by reaction score
Apple Roadmap: "Skate to where the puck will be."
A leaked roadmap by Intel suggests that the company is developing a new lineup of CPUs that are targeted at outperforming Apple's 14-inch MacBook Pro with the M1 Pro and M1 Max chips by late 2023, or early 2024, which would be almost two years after the new chips and laptop made their debut.
The roadmap by Intel, initially leaked by AdoredTV and interpreted by Wccftech, explicitly states that Intel wants to compete with Apple's 14-inch MacBook Pro with its Arrow Lake series. According to the roadmap, Intel's 15th generation Arrow Lake processors could be ready to ship by late 2023, or early 2024 with a priority on delivering high-performance while using minimal energy.
The roadmap also says that Intel will utilize TSMC's 3nm process. Apple currently utilizes the 5nm process for its latest chips and is expected to adopt the 3nm chip architecture in 2023 with the "M3" Apple silicon chip and A17 chip in the iPhone 15.
Intel has already beaten Apple's M1 Max chip on paper if you ignore high-energy consumption and poor battery life. Benchmarks show that Intel's latest Core i9 processors received a higher score than Apple's M1 Max chip in tests, but that 4% increase in performance is offset by a marked reduction in battery life compared to Apple's chips. Tests show that a laptop with Intel's latest i9 Core chip only lasts six hours for video playback. In comparison, Apple advertises the latest 16-inch MacBook Pro as getting up to 21 hours of battery life for offline video playback.
Ever since Apple announced its transition away from Intel during the summer of 2020, it has been slowly transitioning its Macs to custom-made chips. So far, Apple has released four laptop computers with Apple silicon, alongside two desktop computers. In just a few weeks, Apple is expected to announce at least one new Mac with Apple silicon, with possibilities being a new high-end Mac mini and an update to the low-end 13-inch MacBook Pro.
Article Link: Leaked Intel Roadmap Reveals More Efficient Chip Than M1 Pro and Max to Launch Within Two Years
Intel Roadmap: "Be right there, just looking for my other skate."
https://www.zdnet.com/article/op-ed-windows-isnt-ready-for-arm-developers/
It's sad that Apple is the only company in the industry with any ability to execute on long-term plans. Kudos to Apple management though.
Debian have had support for ARM since 2000. As noted by @chucker23n1, Android is Linux on ARM and Amazon have their own ARM based Graviton CPU's that you can spin up VM's to run on top of as well. The ARM powered Chrome OS laptops are also Linux on ARM as well and platforms like the Raspberry Pi run Linux on ARM including desktop environments. Not to mention all of the smaller embedded use cases running Linux on ARM.
To put it another way, Linux on ARM is shipping more devices each year than Windows on x86.
Forget ARM, Microsoft only now are porting Visual Studio to 64-bit. In the time that Apple have moved from PPC (32-bit/64-bit) to Intel (32-bit/64-bit) and now Apple Silicon (64-bit), Microsoft haven't been able to port their own flagship IDE product to 64-bit. Of course they haven't supported ARM, they don't even fully support the 64-bit instruction set introduced over fifteen years ago! (Windows XP 64-bit came out in 2005)
Visual Studio 2022 just finally became a 64-bit app. It isn't just an ARM binary that is lagging. It is basically the whole stack. ( "Shoemaker's children have no shoes" kind of situation). Microsoft doesn't put loads of effort into moving Visual Studio forward as fast as possible with respect to the underlying foundations libraries it depends upon. It is partial just and editor with an enhanced GUI tools. The underlying non-GUI tools can be native.
That max backward compatibility focus stretches into the IDE itself. It is designed to deploy on oldest Windows versions also. [ Deep contrast to Apple and XCode
Xcode - Support - Apple Developer
XCode 13 can't run on anything older than macOS 11.3. XCode 12 10.15.4 . XCode 11 10.14.4 , but get this XCode 11.4 10.15.x ( a dot update to an app requires a whole operating system upgrade? )
Microsoft Studio for Mac 2019 goes all the way back to macOS 10.13 for minimal OS level. Farther back than Apple's support table goes.
Studio 2022 does cut off the non 32-bit operating systems. 64-only Windows 11 Arm isn't all that old. Eventually they probably will finish port since not dragging super long, 32-bit anchor behind them. Studio 2019 actually runs on Windows 7 (and 8.1 ). ]
The other issue that they have yet another coding environment. Visual Studio Code. That is where they throw most of their 'porting wide to multiple platform' resources at. It rides on top of Electron ( so mostly not native anywhere, but extremely portable. ).
They do have a Windows Arm version.
https://code.visualstudio.com/#alt-downloads
It isn't the exact same tool but it is a Microsoft IDE. There is lots of coding projects can do on Windows on Arm now. Intensely Win32 centric ones maybe not. But a wide variety of stuff is doable. That helps take the 'urgency' off getting the other tool over.
Revisionist history. Amazon shipped Graviton in 2018. Two years before Apple. Graviton2 2019 . One year before Apple.
A couple of major web servers vendors ( who do their own boxes ) made substantive moves off of Intel Server CPUs before Apple did.
x86 has been dumped out of tablets , embedded devices , and various systems for years.
Apple has done the biggest extravaganza about doing it. Biggest show doesn't mean first.
Translation of headline:
Competition is good, but I’ll believe it when I see it. Right now, it just sounds like Intel trying to get people to wait for their vaporware in two years instead of going with products Apple (and AMD) have on shelves now. And, of course, Apple won’t be standing still on Apple Silicon in the intervening two years.
I seem to recall that IBM, ages ago, had a known practice of announcing products that were much better – on paper – than competitors’ new products, with the hope of getting customers to stay with them rather than going to the competition.
Intel Leaks Roadmap Hoping People Will Believe That Intel Will Have Competitor For Then-Two-Year-Old Apple Chip Two Years From Now
Competition is good, but I’ll believe it when I see it. Right now, it just sounds like Intel trying to get people to wait for their vaporware in two years instead of going with products Apple (and AMD) have on shelves now. And, of course, Apple won’t be standing still on Apple Silicon in the intervening two years.
I seem to recall that IBM, ages ago, had a known practice of announcing products that were much better – on paper – than competitors’ new products, with the hope of getting customers to stay with them rather than going to the competition.
And Linux on ARM probably has a bigger install base than Linux on x86, come to think of it. (Though, yes, outside of Android and Chrome OS, the two least Linux like userlands and environments, most of those deployments are usually embedded devices and some Raspberry Pis.)
I’ve been developing (in my spare time) on Linux on ARM since 2016, in the form of Raspberry Pi’s (don't mistake them for toys, they can do quite a lot for their size, but they’re specifically aimed at being small and cheap). And Linux on ARM wasn’t some new experimental thing when I got there, it had been in wide use for years.
One of the great things about Linux (inherited from Unix) is that, unless you’re working on device drivers, it doesn’t really matter what the underlying hardware is - as long as you follow portability standards, the code will compile on any Linux box (or, if you’re careful, any Unix box). So there doesn’t have to be a strong line in the sand between ARM and x86-64 for Linux developers.
Xcode on iPad? Playgrounds took how long to show up on iPad? Apple has a gigantic cross platform development ecosystem set up. Pot calling kettle black. Apple spent well over a decade having folks on Intel Macs build apps to iPhones/iPads.
The to date Windows Arms systems have been powered by mainly smartphone targeted processors. Maximum mobility has been the primary; not massive sales to developers. Studio 2020 dumping the 32-bit anchor is extremely likely part of the long term plan for Windows Arm. It is much cleaner target to do a full port to at about the same time that around the same time the software+hardware platform is about to make a substantive move forward on Windows 11 on Qualcomm 8cx gen 3 . That actually is planning.
The reason it isn't ARM native don't matter. The fact that it took them more than 20 years just to get 64-bit does not bode well. If anything it proves my point- Wintel is all about backwards compatibility and its various pros and cons, Apple is about breaking with past to make the best possible product.
They should finish the port before they ship WoA systems to unsuspecting customers. Doubtless Apple has had macOS on ARM for years now. But they didn't ship it until it was ready.
It shows a lack of commitment on Microsoft's part. VScode is nor full blown IDE that the most important Windows devs are using.
Amazon is not abandoning x86. They are also using ARM. Tablets were never x86 only, there were a few Atom devices that flopped. Some embedded devices still use x86, but other ISAs have always been used. The Mac was a 100% x86 platform for 15 years, and now it will be a 0% x86 platform. Apple is not the first or only company to explore ARM, but they are the only company to embrace ARM and totally abandon x86. No revisionism. And Apple's never been about being first. They're about being best.
I still plan to buy a new Windows device in the near future. My Surface Pro 3 which is my only Windows device at the moment is running Windows 11 but is not fully supported. Intel and Microsoft’s problem is not necessarily performance, yeah, it’s great to have. But the advantage Apple has that’s superior is the ecosystem. My iPad, MacBook Pro, iPhone and Apple Watch all work together. Also, when you include accessories like AirPods/Beats and the services, it’s a hard sell once you join the Apple world to switch to disjointed and wonky alternatives.
Apple never pitched iPhone and iPad as a full-blown computer ("what's a computer" ad aside). Microsoft is shipping WoA systems that look like regular PCs on the outside, are sold as regular PC, yet can't run PC software. Also, developers wanted to make apps for iOS, Apple didn't have to tempt them over. What message does Microsoft send to devs when they won't do even the bare minimum for the new platform?
Which is what they completely miss. Users want to use a platform with apps. Contrast this with Apple, who first shipped the dev kit and then the system.
Then where is the announcement that VS for ARM is being worked on? You are assuming things with no evidence. Since it took two decades to get 64-bit, let's not be too optimistic here. Currently Microsoft's stance is that to develop for WoA, buy two devices.
Amazing how many just want to dunk on Intel..
Them getting it together and competing again, particularly with AMD, is a massive net win for customers.
Zoom out from the dunking folks
This story is good news.
Them getting it together and competing again, particularly with AMD, is a massive net win for customers.
Zoom out from the dunking folks
This story is good news.
The problem is that we've been on the Intel roadmap train before, we've seen them fail to deliver on their process improvements for the better part of a decade now and their roadmap is calling out that in a couple of years they want to be competitive with last years Apple chip.
This isn't a good news story, this is Intel desperately trying to convince the world they can do it and they're still relevant. They went from clear and dominant market leaders to a world where AMD has gotten ahead of them, Apple is moving away from them entirely and they're left with Microsoft, who have dabbled with ARM for a while and sell an AMD powered console, as really their last ally in the software space. Intel have spent the last year running attack ads on the Mac which is really awkward given most of the Macs out there run Intel chips, they've tried to smoke and mirror away the benefits of the M1 chip and now they're admitting they're at least two years away from being competitive in the mobile CPU space.
Okay, sure. In two years you'll have a chip that is faster than a 3 year old Apple chip. Good for competition? Sure, I suppose.
Coo Coo Coo Cool beans.
Cool beans?
Cool beans.
Honestly I hope it's true as this type of thing pushes the competition more and more.
Cool beans?
Cool beans.
Honestly I hope it's true as this type of thing pushes the competition more and more.
They already have CPUs that are faster than the fastest Apple CPU. Where they are still behind is power efficiency. This roadmap indicates that the "Arrow Lake" CPUs will use TSMC's 3nm process, which is the same that Apple will use then (currently Apple uses 5nm).
Well, making a CPU faster isn't that hard if you don't care about power efficiency.
Intel can not do that unless they have a time machine as they are not able to know what Apple will release until Apple release it.
intel ARE targeting what Apple have right now and that is just laughable!
Just like GM et al targeting to be as good as Tesla is right now but in 2025!
Sorry to rain on Macrumors' parade but here are a few things they missed.
1) There is a HUGE difference between what Intel says and what they deliver as they have a track record of missing their own projections ever since Skylake.
2) There is a HUGE difference between the actual time and Intel time as they have been so far behind since Skylake.
3) Intel are basically aiming to beat Apple's current offerings but in 2023 which by then Apple will have far better offerings.
4) Intel could beat AS in raw speed but that is absolutely useless when you trade off poor battery life and terrible inefficiency, which Apple have managed to pull off very well.
5) Intel would also need to deal with the insane amounts of heat that could cook an egg as otherwise as I am pretty sure that is not good for longevity.
I could go on but these are just a few of what I could be bothered to write down, plus even if Intel do somehow beat Apple that is just one part of the equation. Apple has more to offer professionals and customers than just raw speed etc. Apple transitioning to their own silicon was not about destroying Intel or taking away customers.
1) There is a HUGE difference between what Intel says and what they deliver as they have a track record of missing their own projections ever since Skylake.
2) There is a HUGE difference between the actual time and Intel time as they have been so far behind since Skylake.
3) Intel are basically aiming to beat Apple's current offerings but in 2023 which by then Apple will have far better offerings.
4) Intel could beat AS in raw speed but that is absolutely useless when you trade off poor battery life and terrible inefficiency, which Apple have managed to pull off very well.
5) Intel would also need to deal with the insane amounts of heat that could cook an egg as otherwise as I am pretty sure that is not good for longevity.
I could go on but these are just a few of what I could be bothered to write down, plus even if Intel do somehow beat Apple that is just one part of the equation. Apple has more to offer professionals and customers than just raw speed etc. Apple transitioning to their own silicon was not about destroying Intel or taking away customers.