I guess I'll be switching back to pcs then. Cause I want a processor that's powerful and compatible with windows.
Stupid move IMO
I like ARM in phones Etc
Hopefully it's just be like a version of the MacBook Air and not all MacBooks
I really doubt Apple would move to ARM anytime soon on its Macs. ARM's biggest advantage is the chips use little power in relation to performance. However, Intel has a big advantage in terms of raw performance and it is working to improve where it is at a disadvantage. Moreover, Apple gained some big advantages when it went to Intel in terms of not having to compete on specs anymore, and bringing a lot of people into the fold who had to use Windows. Apple has sold a lot of Macs because the Mac could run Windows. I suspect we are hearing these rumors as a method of placing pressure on Intel to do something.
With all that said, Microsoft is bringing Windows to ARM. So eventually it is possible lots of Windows only software might make an ARM port. Microsoft will certainly port versions of its own software to ARM. So, at that point Windows will be able to run on Apple's ARM architecture as well. So a few years from now when ARM chips are capable of running OSX (and if Intel is still at a disadvantage), Apple can ditch Intel then and Windows would still likely run on Apple's Macs.
Let me explain: Switching to ARM completely has many problems. First it's several years off, before ARM-based chips will be powerful enough to match Intel chips. Second, a full switch would require another round of recoding and recompilations for software developers. This might be fairly easy for apps in the Mac app store, but not so much for the more 'serious' apps out there. Remember how long it took Adobe to port Photoshop&co to run native on Intel cpus?
Still, the idea is attractive, because ARM designs are much, much more power efficient than Intels right now and judging by the benchmarks from the A6-series, even the fairly slow Intel Atom chips still have a ways to go. But Apple really likes power efficiency. The more power efficient the system, the slimmer and lighter they can make their computers without sacrificing battery runtime.
How to get the best of both worlds? Use both.
Take the Intel based systems we have today and add an A-Series chip to it. Use the ARM chip to run (parts of) the kernel, APIs and non-time-sensitive background tasks to take load of the Intel-CPU. Maybe make GrandCentral architecture aware to maybe run less cpu-intensive and time-sensitive tasks automatically on the ARM chip for app store software as well. That way the Intel cpu can go into lower power modes more often, saving power for longer lasting batteries.
The more I think about this, the more I believe that this could be feasible. But then I'm not an engineer or OS programmer.
No way. A full x86 compatibility is a must. Besides power. Intel power. No toy-like ARM power.
a must for who? 100 million people get plenty done with ARM based iPads and their 2048-by-1536 display. Why wouldn't' the A7 be powerful enough for a $799 11" MacBook Air, 8 hour battery, retina display, under 2 lbs? No windows support, office or adobe. And no thunderbolt. But runs everything in the mac app store within a couple of months of launch. Optional 4G LTE version. Apple would sell millions of them.
a must for who? 100 million people get plenty done with ARM based iPads and their 2048-by-1536 display. Why wouldn't' the A7 be powerful enough for a $799 11" MacBook Air, 8 hour battery, retina display, under 2 lbs? No windows support, office or adobe. And no thunderbolt. But runs everything in the mac app store within a couple of months of launch. Optional 4G LTE version. Apple would sell millions of them.
If CPU performance didn't matter, why weren't the MacBook Airs running Intel Atom chips. They could have been cheaper, lighter weight, cooler, with longer battery life. Win, Win, Win, Win....
It seems that performance does matter. What you are arguing for is the Apple netbook.
That's seems to be in direct contradiction with the ARM 64bit Cortex A57 roadmap (up to 3GHz)
Those chips that aren't on the market yet. It's also ARM's first major push into 64-bit and positioning itself toward the server market which are going to have a constant power source so you aren't dealing with power consumption and heat in the same way as a handheld device. Don't get me wrong, power efficiency and low heat in servers chips is a huge drive but it doesn't have the same limitations as it does with handheld devices which is why Intel is just now getting any foothold in this area.
This is what the danger of "a little knowledge" looks like. There is a small theoretical advantage to ARM simpler instruction set.
But this is swamped by execution. The real reason ARM was historically so much better at mobile, is because that is what they have been building for, for years, while Intel OTOH concentrated on high performance.
In case you haven't noticed, Intel is waking up. Check out the Motorola Razr i, with an Intel Atom inside. It was the only phone to regularly beat the new A6 iPhone on benchmarks, and it is still gets good battery life.
Next year, Intel is releasing a brand new Atom Architecture (first in 5 years) it will be arriving on Intels mature 22nm process and coming in varieties ranging from 1 core to 4 core.
After that Intel is planning to start doing Tic-Toc iterations in mobile, like they do on desktops (where the obliterated AMD).
In three years most new Android phones could be running Intel Atoms and making iPhones looks slow in comparison and all the talk will be about how Apple is going to switch iOS to Intel and ditch non competetive ARM.
The truth is we don't know, but anyone writing off Intel in Mobile or saying an Apple switch of OSX to ARM is inevitable, is clueless.
Thank you oh wise one for clearing that up. Regardless, Apple's future lies in ARM, you may know not, but I do. Apple has put it's weight behind it, it fits Apple's business model, therefore it's a given. Moving to Intel was just a temporary move after the IBM/Moto/Apple PPC treo went separate ways. Right now Apple can be dictated to by Intel, and it sure as hell aint happy about that because it has been burnt before.
Thank you oh wise one for clearing that up. Regardless, Apple's future lies in ARM, you may know not, but I do. Apple has put it's weight behind it, it fits Apple's business model, therefore it's a given. Moving to Intel was just a temporary move after the IBM/Moto/Apple PPC treo went separate ways. Right now Apple can be dictated to by Intel, and it sure as hell aint happy about that because it has been burnt before.
You do realize that if Apple gets rid of Intel it has to get rid of Thunderbolt(Light Peak), right? I simply don't see this happening anytime soon.
You do realize that if Apple gets rid of Intel it has to get rid of Thunderbolt(Light Peak), right? I simply don't see this happening anytime soon.
This is a good point, but it begs the question: What IS Lightning, then? A "fully Apple" implementation of Thunderbolt tech with a different connector?
Thank you oh wise one for clearing that up. Regardless, Apple's future lies in ARM, you may know not, but I do. Apple has put it's weight behind it, it fits Apple's business model, therefore it's a given. Moving to Intel was just a temporary move after the IBM/Moto/Apple PPC treo went separate ways. Right now Apple can be dictated to by Intel, and it sure as hell aint happy about that because it has been burnt before.
Apple fanboys tend to see the world as a place where companies need to fight to survive. Can't they just coexist?
You do realize that if Apple gets rid of Intel it has to get rid of Thunderbolt(Light Peak), right? I simply don't see this happening anytime soon.
Thunderbolt doesn't seem to be gaining much widespread support and although the port is called Thunderbolt, the DisplayPort aspect of the protocol is the only part that most Mac users are utilizing. High bandwidth data transfer might be a luxury that 4K video editors enjoy but the majority of regular Mac users can get by with USB 3 or even WiFi for data transfers. Thunderbolt is a professional feature and we have seen how focused Apple is on professionals. When we hear reports of post PC computing being the future of the industry I can easily see Apple dropping Intel and Thunderbolt. If they decide to burn more bridges, that bridge is not too far.
Surface as already prove how bad the idea of merging Desktop OS with Mobile device cpu is wrong.
I think desktop computing will remain with x86 architecture until the end, Mac or WinTel common usage depend too much of running legacy softwares and hardwares to switch to an incompatible platform while keeping the Desktop PC as it is. Steve Jobs vision about a near future Post-PC era was right, Desktop PC will still be around for a long time, but I think Apple and other tech company will focus more on other platform beside the aging Desktop PC paradigm.
Thunderbolt doesn't seem to be gaining much widespread support and although the port is called Thunderbolt, the DisplayPort aspect of the protocol is the only part that most Mac users are utilizing. High bandwidth data transfer might be a luxury that 4K video editors enjoy but the majority of regular Mac users can get by with USB 3 or even WiFi for data transfers. Thunderbolt is a professional feature and we have seen how focused Apple is on professionals. When we hear reports of post PC computing being the future of the industry I can easily see Apple dropping Intel and Thunderbolt. If they decide to burn more bridges, that bridge is not too far.
It seems like I read about Thunderbolt capable gear on AnandTech every week even though it's only been out of Apple exclusivity for a little over 6 months now. I don't think anyone should expect for widespread adoption of a high-end feature to solidify overnight. Come January if we don't see a lot more Thunderbolt stuff at CES then I think we can start making reasonable predictions about its longevity.
I have always had a Mac on my desk at my law office, but until Apple switched to Intel, I had my staff using PCs and had to always have access to a Windows PC because some of the software we have to use is Windows only. Now, I have a Mac on every desk in my office with Parallels installed for the programs that require Windows. A switch to ARM would be a huge problem for me and likely force me to switch back to Windoze PCs.
Apple achieved a great deal of market respectability when they switched to Intel, and it did drive sales for awhile. Intel spends a lot of money on marketing. But today, I'm not sure if it matters all that much what's under the hood. If anything, the graphics will improve making a switch away from Intel.
What I'm most concerned about is the gradual and seemingly inevitable rush towards the melding of OS X and iOS. Some functional overlap and interoperability can be a good thing when you own multiple Apple devices and a Mac but by and large, I do not want my $3500 Mac acting, behaving and operating like a $200 cell phone.
I'd like to save my finger gestures for when somebody cuts me off in traffic
Comments
Quote:
Originally Posted by Seankill
I guess I'll be switching back to pcs then. Cause I want a processor that's powerful and compatible with windows.
Stupid move IMO
I like ARM in phones Etc
Hopefully it's just be like a version of the MacBook Air and not all MacBooks
I really doubt Apple would move to ARM anytime soon on its Macs. ARM's biggest advantage is the chips use little power in relation to performance. However, Intel has a big advantage in terms of raw performance and it is working to improve where it is at a disadvantage. Moreover, Apple gained some big advantages when it went to Intel in terms of not having to compete on specs anymore, and bringing a lot of people into the fold who had to use Windows. Apple has sold a lot of Macs because the Mac could run Windows. I suspect we are hearing these rumors as a method of placing pressure on Intel to do something.
With all that said, Microsoft is bringing Windows to ARM. So eventually it is possible lots of Windows only software might make an ARM port. Microsoft will certainly port versions of its own software to ARM. So, at that point Windows will be able to run on Apple's ARM architecture as well. So a few years from now when ARM chips are capable of running OSX (and if Intel is still at a disadvantage), Apple can ditch Intel then and Windows would still likely run on Apple's Macs.
Ok, here is a theory: Intel/ARM-hybrid-Macs
Let me explain: Switching to ARM completely has many problems. First it's several years off, before ARM-based chips will be powerful enough to match Intel chips. Second, a full switch would require another round of recoding and recompilations for software developers. This might be fairly easy for apps in the Mac app store, but not so much for the more 'serious' apps out there. Remember how long it took Adobe to port Photoshop&co to run native on Intel cpus?
Still, the idea is attractive, because ARM designs are much, much more power efficient than Intels right now and judging by the benchmarks from the A6-series, even the fairly slow Intel Atom chips still have a ways to go. But Apple really likes power efficiency. The more power efficient the system, the slimmer and lighter they can make their computers without sacrificing battery runtime.
How to get the best of both worlds? Use both.
Take the Intel based systems we have today and add an A-Series chip to it. Use the ARM chip to run (parts of) the kernel, APIs and non-time-sensitive background tasks to take load of the Intel-CPU. Maybe make GrandCentral architecture aware to maybe run less cpu-intensive and time-sensitive tasks automatically on the ARM chip for app store software as well. That way the Intel cpu can go into lower power modes more often, saving power for longer lasting batteries.
The more I think about this, the more I believe that this could be feasible. But then I'm not an engineer or OS programmer.
Quote:
Originally Posted by Snowdog65
Nothing more than last years recycled nonsense rumor.
Top end ARM chips are totally outclassed, even by the PowerPC chips Apple transitioned away from in 2005.
ARM may be getting faster, but it doesn't come close to catching Intel in the foreseeable future.
Ironically enough all those Power PC chips are being used to power every major game system on the market, the X-Box included.
Quote:
Originally Posted by zunx
No way. A full x86 compatibility is a must. Besides power. Intel power. No toy-like ARM power.
a must for who? 100 million people get plenty done with ARM based iPads and their 2048-by-1536 display. Why wouldn't' the A7 be powerful enough for a $799 11" MacBook Air, 8 hour battery, retina display, under 2 lbs? No windows support, office or adobe. And no thunderbolt. But runs everything in the mac app store within a couple of months of launch. Optional 4G LTE version. Apple would sell millions of them.
Quote:
Originally Posted by alandail
a must for who? 100 million people get plenty done with ARM based iPads and their 2048-by-1536 display. Why wouldn't' the A7 be powerful enough for a $799 11" MacBook Air, 8 hour battery, retina display, under 2 lbs? No windows support, office or adobe. And no thunderbolt. But runs everything in the mac app store within a couple of months of launch. Optional 4G LTE version. Apple would sell millions of them.
If CPU performance didn't matter, why weren't the MacBook Airs running Intel Atom chips. They could have been cheaper, lighter weight, cooler, with longer battery life. Win, Win, Win, Win....
It seems that performance does matter. What you are arguing for is the Apple netbook.
Those chips that aren't on the market yet. It's also ARM's first major push into 64-bit and positioning itself toward the server market which are going to have a constant power source so you aren't dealing with power consumption and heat in the same way as a handheld device. Don't get me wrong, power efficiency and low heat in servers chips is a huge drive but it doesn't have the same limitations as it does with handheld devices which is why Intel is just now getting any foothold in this area.
Quote:
Originally Posted by Snowdog65
This is what the danger of "a little knowledge" looks like. There is a small theoretical advantage to ARM simpler instruction set.
But this is swamped by execution. The real reason ARM was historically so much better at mobile, is because that is what they have been building for, for years, while Intel OTOH concentrated on high performance.
In case you haven't noticed, Intel is waking up. Check out the Motorola Razr i, with an Intel Atom inside. It was the only phone to regularly beat the new A6 iPhone on benchmarks, and it is still gets good battery life.
Next year, Intel is releasing a brand new Atom Architecture (first in 5 years) it will be arriving on Intels mature 22nm process and coming in varieties ranging from 1 core to 4 core.
After that Intel is planning to start doing Tic-Toc iterations in mobile, like they do on desktops (where the obliterated AMD).
In three years most new Android phones could be running Intel Atoms and making iPhones looks slow in comparison and all the talk will be about how Apple is going to switch iOS to Intel and ditch non competetive ARM.
The truth is we don't know, but anyone writing off Intel in Mobile or saying an Apple switch of OSX to ARM is inevitable, is clueless.
Thank you oh wise one for clearing that up. Regardless, Apple's future lies in ARM, you may know not, but I do. Apple has put it's weight behind it, it fits Apple's business model, therefore it's a given. Moving to Intel was just a temporary move after the IBM/Moto/Apple PPC treo went separate ways. Right now Apple can be dictated to by Intel, and it sure as hell aint happy about that because it has been burnt before.
You do realize that if Apple gets rid of Intel it has to get rid of Thunderbolt(Light Peak), right? I simply don't see this happening anytime soon.
Originally Posted by SolipsismX
You do realize that if Apple gets rid of Intel it has to get rid of Thunderbolt(Light Peak), right? I simply don't see this happening anytime soon.
This is a good point, but it begs the question: What IS Lightning, then? A "fully Apple" implementation of Thunderbolt tech with a different connector?
Quote:
Originally Posted by monstrosity
Thank you oh wise one for clearing that up. Regardless, Apple's future lies in ARM, you may know not, but I do. Apple has put it's weight behind it, it fits Apple's business model, therefore it's a given. Moving to Intel was just a temporary move after the IBM/Moto/Apple PPC treo went separate ways. Right now Apple can be dictated to by Intel, and it sure as hell aint happy about that because it has been burnt before.
Apple fanboys tend to see the world as a place where companies need to fight to survive. Can't they just coexist?
Quote:
Originally Posted by SolipsismX
You do realize that if Apple gets rid of Intel it has to get rid of Thunderbolt(Light Peak), right? I simply don't see this happening anytime soon.
Thunderbolt doesn't seem to be gaining much widespread support and although the port is called Thunderbolt, the DisplayPort aspect of the protocol is the only part that most Mac users are utilizing. High bandwidth data transfer might be a luxury that 4K video editors enjoy but the majority of regular Mac users can get by with USB 3 or even WiFi for data transfers. Thunderbolt is a professional feature and we have seen how focused Apple is on professionals. When we hear reports of post PC computing being the future of the industry I can easily see Apple dropping Intel and Thunderbolt. If they decide to burn more bridges, that bridge is not too far.
Surface as already prove how bad the idea of merging Desktop OS with Mobile device cpu is wrong.
I think desktop computing will remain with x86 architecture until the end, Mac or WinTel common usage depend too much of running legacy softwares and hardwares to switch to an incompatible platform while keeping the Desktop PC as it is. Steve Jobs vision about a near future Post-PC era was right, Desktop PC will still be around for a long time, but I think Apple and other tech company will focus more on other platform beside the aging Desktop PC paradigm.
Originally Posted by mstone
Thunderbolt doesn't seem to be gaining much widespread support…
That would be due to exclusivity on Apple's part. It's directly integrated into Haswell, so we'll see what happens when that's launched.
If Intel has any sense and actually wants their own port to be adopted, they'll only make boards that include it.
Quote:
Originally Posted by Tallest Skil
That would be due to exclusivity on Apple's part. It's directly integrated into Haswell, so we'll see what happens when that's launched.
If Intel has any sense and actually wants their own port to be adopted, they'll only make boards that include it.
I thought the exclusivity agreement ended already.
It seems like I read about Thunderbolt capable gear on AnandTech every week even though it's only been out of Apple exclusivity for a little over 6 months now. I don't think anyone should expect for widespread adoption of a high-end feature to solidify overnight. Come January if we don't see a lot more Thunderbolt stuff at CES then I think we can start making reasonable predictions about its longevity.
Originally Posted by mstone
I thought the exclusivity agreement ended already.
So did I…
Guess Intel gets to shove it down their throats.
Apple achieved a great deal of market respectability when they switched to Intel, and it did drive sales for awhile. Intel spends a lot of money on marketing. But today, I'm not sure if it matters all that much what's under the hood. If anything, the graphics will improve making a switch away from Intel.
What I'm most concerned about is the gradual and seemingly inevitable rush towards the melding of OS X and iOS. Some functional overlap and interoperability can be a good thing when you own multiple Apple devices and a Mac but by and large, I do not want my $3500 Mac acting, behaving and operating like a $200 cell phone.
I'd like to save my finger gestures for when somebody cuts me off in traffic