From :
http://www.theinquirer.net/inquirer...d-arm-chip-architectures-in-project-skybridge
....
There's two kinds of cores on the motherboard, how code is run on each is up to the OS.
Not sure what article you are reading. You are confused. The same article highlights in the next paragraph.
" .. saying that it has licensed the ARMv8 chip architecture and will design its own
pin-compatible 64-bit x86 and ARM base system on chip (SoC) processors.. "
The cores are inside the chip package. The chip package pins fit into the same socket (and/or same ball grid array, BGA, if soldered directly to the board ). The commonality here is the same "socket". This enables folks can use the same base motherboard with different packaged cores. That doesn't say diddly squat about multiple sockets filled with heterogenous chip packages.
The heterogeneous cores inside the package are far more likely about the x86 or ARM core and the GPU cores . That what comprises what AMD calls a APU package. Is AMD going to license other folks GPU designs... not likely.
Similarly, Intel has been incrementally moving to make Itanium and high end Xeon E7 use the same chipset/motherboard. That also doesn't mean can mix and match.
What Skybridge will allow is the folks who are in the "build my own server data center" systems to do is standardize on a 1-2 motherboard designs and be able to deploy a wider set of servers on that core standard design by plugging in different CPU packages into different instantiations.
AMD doesn't have a huge footprint in the SoC x86 server market either. So this is a strategic move to allow them to market with two entries trying to "break into" the market with the same infrastructure.
Intel is also doing US no favours by their CPU choices in all their hardware. The Mac Airs are excused for their CPU choice due to power and heat restrictions.
But in the new Mac Mini, and even the lowest end the newer lowest end iMac, intel has decided to use the ULV intel part.
What Apple decides with Intel parts is Apple's decision. The entry iMac and Mac Mini are likely using MBA parts for the same reason the two MBA sub-models are using the exact same standard offering. Higher volume means lower prices so Apple can lower the price and still keep Apple's 30% target margins.
Same reason why Mac Mini has always used high number of Macbook/Macbook Pro parts.
If Apple pulls the MBA 12" 2014 away some that volume pile to move to the Core M then most likely the bundling of MBA 13" , Mac Mini entry , and iMac entry will stay the same while the MBA 12" 2014 price point moves up (at least for a couple design iterations/years ).
The ULV (ultra low voltage) components typically cost more for each watt of performance than the similarly priced Low Voltage (LV) and standard CPU.
Of late Apple has been offseting that by targeting the systems at lower price point to drive volume. Intel needs the volume sales so the discounts likely remove a substantial portion of that price difference. The rest not covered by the volume differences is covered in some combination of lower RAM , smaller SSD (or using HDD in Mini's case) , design kneecaping , and/or older tech ( non hiDPI and/or IPS screens in the current MBA's case ).
this is mostly noticable in latest mac Mini iteration where they opted to use the same intel ULV chip as the Mac Mini at 17w than the previous quad core 25w part, or even the larger faster quade core desktop 85w part. for that same $200, intel could be providing i3/i5 quadcores at 3.0ghz or faster.
Apple could easily provide cheaper products that give better performance than some of their newest ones, but are opting not too, likely in order to maximize profits by reducing the diversity of their internal components and build requirements. [/quote]
The "cheaper CPU and not quite as good CPU" rhetoric is rather weak because AMD has been in the position for a couple of years no and hasn't cracked a major Apple design win bake-off. Apple has very little interest in getting into a "race to the bottom" price war with rest of the classic PC industry.
thank you for the afternoon reading. sounds like I missed what AMD is currently working on (they've been mostly irrelevant in the desktop space for a bit now)
If actually read the material, Skybridge isn't for desktops. Skybridge doesn't bring you back into the loop on AMD's desktop strategy either.
" ... I don't expect we'll see standard socketed desktop boards that are compatible with both ARM and x86 SoCs, but a pin compatible design will have some benefits for embedded, BGA solutions. AMD expects to target embedded and client markets with these designs, not servers. ... "
http://www.anandtech.com/show/7989/...bridge-pincompatible-arm-and-x86-socs-in-2015
I think anandtech is a bit off here. The custom/embedded market is increasing what a decent fraction the server market is. Facebook, Google, MS , etc.. the jumbo big players in server consumption aren't buying servers systems "off the shelf " anymore. They are making their own custom systems .... which is largely what the embedded market is.
Can Apple easily keep a "Contingency Plan B: OS X on ARM" research (big 'R' , little 'd' R&d ) project going by taking AMD ( and/or other) embedded ARM server reference design boards and just porting OS X to that as a lab project? Yes. Does that mean there are ARM Mac's coming any time soon? Nope. Apple kept the Mac OS X on Intel Plan B in the background for years before flipping.
If Intel
and AMD stops delivering viable x86 solutions then sure ; Apple might pull the trigger. Intel may fail 3-4 years from now but there plan over next 1-2 is solid. They won't have a process tech issue with the upcoming "tick" . And frankly there is no good reason that all the other fab vendors aren't also going to have major issues when they get into the same process tech range as Intel. It is physics they all are running into .... not "lazy US workers" or "bloated Intel monopoly bureaucracy" .
