Windows on ARM is up to MS. It could be a lot better, but go and blame MS for it. As far as Linux installations on Mac go, it doesn't matter. It's been known for a while, thanks to the hackintosh scene, that Apple's been working on their own virtualisation. So let's assume that Apple is shipping macOS with it's own (controlled) version of a T1 hypervisor that allows hardware pass through... problem solved. For reference, check out what you can do with Proxmox and GPU passthrough for a Hackintosh.
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.
Intel Restates Support for Apple During Transition to Apple Silicon
- Thread starter MacRumors
- Start date
- Sort by reaction score
Intel's mistake was that they were a bit too ambitious and tried to leapfrog the competition a few years ago. But they'll get there. Note how even with their old process Intel is still quite competitive with AMD using TSMC's currently more advanced process, and no ARM CPU has been publicly demonstrated yet that can keep up with their high-end chips on a per core basis. It remains to be seen what Apple can do in this space. But Intel isn't sleeping either. Their stock price hasn't been affected at all by Apple's announcement ...
A little under 10%, yes. Not a small chunk of business to lose.
More importantly, look how adamant people are on here that Arm cannot possibly compete. Decades of “intel inside” have people convinced.
But what happens once apple shows that it’s perfectly possible to be as fast as intel or faster, in thinner lighter cooler devices? What happens once the damn breaks?
Ask blackberry. Ask windows what happened in mobile. Ask Unix vendors about Linux.
Really the story is that Apple has unhitched itself from Intel's timetable and instead hitched itself to TSMC's and Samsung's. Pretty reasonable decision given how well TSMC in particular has done, but I wouldn't count out Intel yet. They have the resources to catch up.
He’s right. (I worked on PowerPC x704, x705, AMD K6-ii, k6-ii+, K6-iii, K6-iii+, athlon 64, opteron, UltrsaSparc v, f-risc/G)
I mostly use my laptop for light-duty stuff (web browsing, listening to music, etc.). I have a mid-2012 Macbook Air that still runs like a champ, but it will soon be 8 years old and I've been wanting a retina display, more speed and better battery life.
I knew the ARM laptops were likely to be announced at WWDC, but now I'm facing the actual purchase decision. I'm worried that if I buy an Intel Mac, it will be obsolete in 5 years or less. I also generally don't buy the first-gen of new Apple stuff, so if I wait for ARM, will me trusty Macbook Air make it to 9 or 10 years of age? My MB Air is on a second battery that's nearing 750 cycles, and the screen looks so low res...
I knew the ARM laptops were likely to be announced at WWDC, but now I'm facing the actual purchase decision. I'm worried that if I buy an Intel Mac, it will be obsolete in 5 years or less. I also generally don't buy the first-gen of new Apple stuff, so if I wait for ARM, will me trusty Macbook Air make it to 9 or 10 years of age? My MB Air is on a second battery that's nearing 750 cycles, and the screen looks so low res...
Well as somebody else pointed here - 5M Macs sold per quarter vs 60M PCs will not make much difference. But it is also question of prestige. On the other hand, I too eagerly await what Apple Silicon can do in real desktops and how can it rival high end Intels in terms of performance and stability. I guess that is why Apple will still release Intel Macs.
You're the target audience. Apple is again marketing to the "Shriners" those weirdos who own and collect ancient Apple products and have a little temple to Steve Jobs in their residence.
The Shriners will eat up the bogus tricked out presentations Apple releases on ARM performance.
There seems to be a lot of shrugging this off as "its just Apple", they just represent 1% of Intel's business.
But there are a few points I'd like to raise:
1) This is really high profile and embarrassing to Intel
2) If Microsoft got it together with their Windows on ARM ecosystem, Intel could be in huge trouble
3) Most of Intel's sales are to servers in the cloud. For 2 years, AWS has had both Graviton (their own ARM processors) and AMD processors in their offerings, whereas they were previously Intel exclusive.
No matter which way you look at it, Intel has been struggling and customers are beginning to move on. Its one thing to switch to AMD, but switching processor architectures is a long-term loss due to the work generally involved.
And of course these days, cloud-based software is usually agnostic to what the client is running (its usually javascript/html or cross-platform client development tools),and agnostic to what the servers are running because most developers don't write code in assembly or even C for that matter if they are writing for the cloud.
Intel losing their grip on the server market should be even more concerning to them. Its where all the money is for them.
But there are a few points I'd like to raise:
1) This is really high profile and embarrassing to Intel
2) If Microsoft got it together with their Windows on ARM ecosystem, Intel could be in huge trouble
3) Most of Intel's sales are to servers in the cloud. For 2 years, AWS has had both Graviton (their own ARM processors) and AMD processors in their offerings, whereas they were previously Intel exclusive.
No matter which way you look at it, Intel has been struggling and customers are beginning to move on. Its one thing to switch to AMD, but switching processor architectures is a long-term loss due to the work generally involved.
And of course these days, cloud-based software is usually agnostic to what the client is running (its usually javascript/html or cross-platform client development tools),and agnostic to what the servers are running because most developers don't write code in assembly or even C for that matter if they are writing for the cloud.
Intel losing their grip on the server market should be even more concerning to them. Its where all the money is for them.
I agree that losing Apple as a customer probably won't affect the bottom line too much...although it doesn't look particularly good!
I think the bigger potential problem for Intel is if the Apple Silicon proves to be very powerful ands great thermals/power consumption. Because if that's the case, and if leading apps such as MS Office and Adobe CC have been moved to Apple Silicon (Arm), then there is the potential for other manufacturers to start jumping ship and creating an explosion in the number of other device using an Arm platform...and that could be a big problem for Intel.
[automerge]1592924115[/automerge]
Seems like we both had the same idea at the same time!
Most binaries built for windows, and prebuilt linux binaries, are compiled to use only the most widely available instructions, though some software is compiled with feature tests and fallback code paths. On macOS, the default clang and swiftc configuration builds for all macs supported by the chosen API version, which allows it to assume the existence of intel-specific extensions not supported by AMD or older/cheaper intel chips, and so produce more efficient binaries.
OTOH, if you compile software yourself for your own specific machine a good configuration script can detect exactly which extensions you have and optimise accordingly. Linear algebra libraries are often configured like that.
This exactly why intel should be worried
[automerge]1592924647[/automerge]
Support will exist yes. But Apple will soon in the next 1 to 2 years stop purchasing from intel
We certainly hope and assume so.
However, call me a sceptic, but I do feel the need of actual proof.
I am sure Apple won't be doing such a move if the performance per watt (as it was called before, when Apple went from G5 -> Intel) wasn't better on Apple Solicon than the Intel I-series.
But I have seen this kind of marketing done before, when Apple is introducing a new CPU (G5 specifically) and claims to be the fastest desktop computer. In the real world, with real apps, these claims are usually dumbed down...
What we should all consider is that your knowledge and experience in designing computer chips is the same as mine in performing nano neurosurgery.
Zero.
I guess that will depend on how Apple's big experiment goes. Personally I'm torn. I kind of like the prospect of being able to run iOS apps on a Mac, but on the other hand I am concerned that they will turn their "pro" computers into iOS consumer toys. In any case I'll have to leave the Mac platform if they drop Intel entirely since I need to be able to run x86 Linux VMs for work (which is sad, since MacOS is my favorite OS). Anyway, it was nice to have a widely compatible compute platform across all major vendors that could run all major operating systems for the past 15 years ...
Can continue? They haven’t started yet. The main reason no benchmarks are allowed is to avoid showing how unscalable the A12z embedded SoC is in the full OS X and to halt the ensuing paranoia Apple knows will happen when disclosed.
The hardware teams have years to go before this vision is made reality, and neither AMD nor even Intel designs of today will be indicative of performance in designs two years from now.
Hell in 3 months, enthusiasts will be salivating at Zen 3, Big Navi and Nvidia’s latest GPUs and how far all three have upped the game in computing.
lOl, 95% HPC market belongs to Intel, 4.5% belongs to AMD & guess who has the other 0.5% market share? Despite Intel having downtimes, It's not ARM that's gaining market share in Exoscale computing (Datacenter, Scalable architecture, HPC), But AMD (another x86 vendor).
Before say Graviton, Watch STH( ServeTheHome) & Phoronix benchmarks of Graviton 2 & it's comparison with Epyc ROME. They are hilariously way behind. Their I/O performance is garbage, one of the major factor for Datacenters.
Maybe. Let's first wait how it actually goes ...
Actually Intel still makes more revenue on PCs than datacenter servers, although the latter has stronger growth (in Q1 2020, their PC division generated $9.8 billion, and their datacenter group $7 billion).
They actually had 43% growth YoY in this segment.
Thunderbolt 3 is available for others now. My son has an AMD based PC with a Thunderbolt 3 port. Also, Thunderbolt 3 is a subset of USB4 as well as an option.
You sound unhappy. Is COVID making you lonely?
[automerge]1592926690[/automerge]
Another angry post. We are seeing a theme here.
I do not like the Apple Shriners at all. Chairman Mao weaponized that type for his Cultural Revolution.
That's odd, when I last spoke to my contacts at Oracle, their intention was to try out AMD with no intention to really go there. We're talking data centers around the world. Already did a post on that a while back and explained why it won't happen in another thread, just do a search.