61–70 of 263 posts
This sounds weird. Are they going to have two versions of every executable? One arm and one intel? Or would this low power/power nap mode only support a tiny subset of functionality that apple chooses to include in their OS release?
The flagship ARM A72 and A73 are not adequate for true desktop class performance, somewhat catching up to Intel's low end core u laptop chips. It's increasingly looking like to get x86 level performance ARM would lose its low power advantages.
The AMD Zen on the other hand appears to be extremely efficient. I fiddled with ARM boards on and off for over 3 years excited by the possibilities of tiny form factor desktop class computing at laughably minimal costs with ARM SOCs. The reality is the extremely poor to non existent driver support and the 'effectively closed' ARM ecosystem is a deal breaker that left me disillusioned and strangely relieved with the the open PC ecosystem.
Apple should just buy AMD. It would only cost them about 15 Billion or so and they would get an x86 license. If they really want to control their own destiny this would be the way to go.
IIRC AMD's cross-licensing deals with Intel over certain key patents are null and void if AMD is bought, which puts a real damper on the main reason anyone would consider purchasing the company.
That really sounds like a winning proposition for Apple, given that Intel's own 64-bit arches historically sucked.
Totally expected, because they need to increase performance and lower battery consumption. Now the extent of taking job from main Intel's CPU and spectrum of possibilities of ARM coprocessors are yet to be seen. I can see it doing some hardware related tasks that do not interfere with actual higher stack of macOS and x86 space. But this is all pretty common. This title looks little clickbaity imho.
(1) - I can only imagine it with a virtualized ISA ala IBM. Still - even they didn't do that. The capabilities only exist in separation: eg. IBM TIMI allows to move applications across physical processor ISAs, while various clustered virtualization implementations can move live VMs across distinct hosts.
Apple should just buy AMD. It would only cost them about 15 Billion or so and they would get an x86 license. If they really want to control their own destiny this would be the way to go.
I believe the licensing deal would terminate if AMD is sold
>Advanced Micro Devices has clarified terms of the cross-license agreement with Intel Corp. on Thursday. As it appears, if either AMD or Intel change their control (i.e., gets acquired), the cross-license agreement between the two companies is automatically terminated for both parties.
Since AMD invented x64 this would leave Intel in quite a bind and the only solution would be to work with the new owner to reach an agreement.
Intel needs to sacrifice Microsoft and make x86 a legacy architecture. There are huge parts of their processor designs that no one at the company modifies (or even understands) from one generation to the next, but which they cannot remove for backwards compatibility purposes. It's time to start fresh with a new architecture if they want to maintain their reputation of having the most powerful technology.
As long as it's still x86/AMD64 we're good. I really don't want to see PPC/Intel fragmentation again.
I thought it was mostly painless. Vast majority of applications provided an Intel binary right away without many issues. Rosetta wasn't too terrible for simple tasks for the rest of them.
The overhead was mostly acceptable because the performance boost from the chip change hid a lot of it. Not to mention the CISC vs RISC thing worked in Apple's Favour. There are few PPC instructions that were required to be supported that couldn't be covered with a small number of x86 instructions.
There is not a publicly available ARM chip that has single thread performance anywhere near the i5 / i7 chips being used. Add to this the complexity of converting SSE to equivalent instructions and the overheads dealing with edge cases, I am not sure there is much chance of equivalent performance.
The one thing going for Apple with an intel -> arm switch is that almost all major apps a built using Xcode. When PPC -> x86 happened, the apps that lagged the most were the ones stuck on CodeWarrior and other 3rd party IDEs that apple never gave sufficient notice to port in advance of the general announcement (however I will concede that codewarrior was owned by Motorola so it may not have made the jump anyway).
I think if Apple does release ARM based macs, it will be with apps specifically recompiled, not using an emulation layer.
Earlier quoted context omitted.
There already are ARM chips in the new MBPRs, for example - the touchbar and touch ID with its secure enclave runs on ARM. I could easily foresee them putting in more powerful ARM chips and offloading some tasks to them.
Hope it's less crashy/buggy in the future than my current touchbar :/
>Is it IBM compatible though? Man, I hated hearing that question. It was so utterly retarded, but trying to explain to the person who asked why it was a retarded thing to say always came off as damage control. >Yep, not IBM compatible. Not interested. Maybe Apple can get away with their own chips now. It sounds like they just want to take more R&D away from Mac though. "Just stick an A10 in it."
macOS applications could similarly be built to run on multiple instruction sets with basically no effort from the developers.
Perhaps initially it might be restricted to first-party apps, or maybe AppStore apps, but having fat binaries is something macOS developers are used to doing ...
The difficult bit would be the runtime migration from x86 to ARM and back. For processes that can restarted, it's easy. For running, stateful applications it would be more difficult.
But I think things like Mail.app already use a backend daemon to manage their datastore: you could suspend the UI process and restart the backend daemon on the low-power CPU fairly simply ...
That being said, I've seen a number of comments about running iOS apps on Macs, or "convertible" Macs/iPads, and so on. I think those are off base given the supposed purity that Apple always talks about.
However, there is one thing I've never seen mentioned - a combined Mac/iOS binary. Similar to the old Universal binary for PPC/Intel, this could be a single app that just has different UX depending on the device it's run on.
I'm not sure why nobody has talked about that option, as it seems most likely to me, and gives more weight to the ARM everywhere strategy.
One "app", and it would be native, with native UI on whichever device it's running on (Mac/iOS/TV/Watch/etc.). Given Apple's investment into a streamlined complier that they rolled out with Watch, many if not most of the pieces are already in place for this.
It would not surprise me if that is the big announcement for this summer (or next at the latest).