Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
I would like ARM to displace the x86 instruction set. Early in my career I found myself writing x86 assembler. It was a pretty ugly architecture compared to 68000 (in the original Mac & Amiga) or the 6502 (Apple II, Commodore 64 & BBC Micro).

Hopefully Apple inspires Microsoft and PC manufactures to get serious about Windows on ARM. Linux on ARM is already in wide use on Chrome Books, Android phones and the Raspberry Pi and available on Cloud providers like AWS. I think once ARM Macs are common and Docker for the ARM Macs is production ready, more companies will deploy their cloud workloads on ARM VMs and Docker clusters.
 
I am different, in that I like to watch empires rise and fall. What I am hoping is that Apple provides the roadmap and inspiration for other companies to create integrated chip offerings of their own.

Resulting in fewer companies ordering processors from Intel, and leaving them in the annals of history.

In the end, you reap what you have sown.
 
Not really sure about Intel's future at the moment. They're looking at outsourcing their manufacturing. I suppose if they can't improve their process, may as well fab chips from others that may not require it. But thankfully for Intel, Apple isn't selling chips to others, nor are they licensing any of their IP for others to incorporate into their products. That means everyone else is stuck with them for the moment.

It will be interesting to see what Nvidia does with ARM, provided they're allowed to make the purchase. ARM on server will be interesting to watch as well. Still, this predicament is primarily Intel's fault. If they do go under, they should be allowed to do so, others can buy up their assets and hopefully fare better. But they've got enough momentum to carry them along for at least another decade or so.
 
  • Like
Reactions: AxiomaticRubric
I hope Intel continues marinating in their own failures for a while longer since for the last decade they've relied entirely on their pride and brand recognition and stopped innovating and kept overcharging people for basically the same barely improved tech year after year. Meanwhile AMD and Apple have passed them up at a laughable pace while Intel continues to stagnate. I'm not rooting for Intel, but I do want them to catch up to AMD and Apple for the sole reason that competition is good and promotes innovation. But they are in dire need of dislodging their heads from their nether regions.
 
AMD has the same problem Intel has in this arena - they have both stated clearly that their architectures and the ISA pretty much cap them at a 4 wide pipe. Apple has an 8 wide pipe and if they had a reason to go higher they could. So Apple is going to continue to murder everyone on PPW for the foreseeable future; and when we get M1X in a few weeks where they take this super efficient microarchitecture and scale it up the performance is going to be ridiculous.
 
I was there for the switch to intel. I owned many intel machines. I think healthy competition to drive these companies forward is in our best interest. The hype for intel then is similar to the AS hype.


may the best man win....just shame we don’t have Steve here, to show us one more thing.
 
The perceived need to keep backward compatibility is probably what's holding Intel and also AMD back. The only way to increase performance is to keep cranking up the CPU frequencies. With the world moving to an increasingly mobile workflow, and battery tech. is not advancing fast enough, this will be a huge challenge for both Intel and AMD to overcome.

If they could clean up their ISA over time, like what Apple is doing, they probably have a chance.
 
The ARM group is set to make 32-bit compatibility optional next year. Already the Apple chips have shed that, several years ago. In a few years, Qualcomm, Broadcom and others will start to close the gap with Apple. Really, I wish Apple would offer an almost-as-good SoC for sale, to raise more interest in ARM systems. Intel x86 is destined to collapse under the weight of its legacy design, and ARM's strongest competition will become RISC-V.
 
Intel x86 is destined to collapse under the weight of its legacy design, and ARM's strongest competition will become RISC-V.
IMHO, unless big industry player starts adopting RISC-V and makes SoCs/CPUs for sale and commit to supporting it, it'll end up like Linux, where it's relegated to niche status. The main priority in the business world is support. Equipment designers like Apple, HP, Dell, etc. need very high level of support for the components they adopt for their products. If the SoCs/CPUs are not well supported, it'll not get used for product design.
 
I was there for the switch to intel. I owned many intel machines. I think healthy competition to drive these companies forward is in our best interest. The hype for intel then is similar to the AS hype.
Seems like a lot of similarities to that transition. Apple had a hard time getting PowerPC processors for their planned line. Just like the delays they have suffered from Intel not delivering. It may be the kick Intel needs to get their mojo back.
 
AMD has the same problem Intel has in this arena - they have both stated clearly that their architectures and the ISA pretty much cap them at a 4 wide pipe. Apple has an 8 wide pipe and if they had a reason to go higher they could. So Apple is going to continue to murder everyone on PPW for the foreseeable future; and when we get M1X in a few weeks where they take this super efficient microarchitecture and scale it up the performance is going to be ridiculous.

I was a designer on some of AMDs CPUs, and at one point i owned the integer execution units and dispatch. Not much reason x86 can’t go wider, other than the fact that code wouldn’t probably benefit too much from it, due to too much instruction interdependency, I suppose. Microcode is a disadvantage - when you send a complex instruction to the instruction decoder and it replaces it with a sequence of N microops, those microops will tend to have interdependencies which require them to be at least partially sequenced. If, instead, you have Arm, you can let the compiler do some of the work of ordering the instruction stream to take advantage of multiple pipelines, and the instruction stream that reaches the instruction decoder will tend to have fewer clumps of interdependent instructions.
 
The perceived need to keep backward compatibility is probably what's holding Intel and also AMD back. The only way to increase performance is to keep cranking up the CPU frequencies. With the world moving to an increasingly mobile workflow, and battery tech. is not advancing fast enough, this will be a huge challenge for both Intel and AMD to overcome.

If they could clean up their ISA over time, like what Apple is doing, they probably have a chance.
It's more than perceived need, backwards compatibility trumps raw performance for businesses, and Intel would die a quick death if they lost it.

Performance isn't the most important thing, does it run what I need it to run, is.

As for having a chance, someone would have to start selling more than them for them to be worried.
 
It's more than perceived need, backwards compatibility trumps raw performance for businesses, and Intel would die a quick death if they lost it.
I have to admit that I do not have much experience of such needs for backward compatibility. The organisation I worked for are switching mainly to cloud based solutions for work. I could theoretically get my job done with a M1 Mac, tho. I'm assigned a Dell Windows 10 notebook. How big is this need for backward compatibility, I really don't know, but I kind of suspect it's not big, compared to the big scheme of things.

In theory, Intel/AMD could maintain a legacy line of CPUs and keep it on life support for such backward compatibility and move forward with a cleaner x86 ISA for their latest and greatest. Really depends on how creative their architects wants to get.
 
I was a designer on some of AMDs CPUs, and at one point i owned the integer execution units and dispatch. Not much reason x86 can’t go wider, other than the fact that code wouldn’t probably benefit too much from it, due to too much instruction interdependency, I suppose. Microcode is a disadvantage - when you send a complex instruction to the instruction decoder and it replaces it with a sequence of N microops, those microops will tend to have interdependencies which require them to be at least partially sequenced. If, instead, you have Arm, you can let the compiler do some of the work of ordering the instruction stream to take advantage of multiple pipelines, and the instruction stream that reaches the instruction decoder will tend to have fewer clumps of interdependent instructions.
Which leads to the question of why did they state they could not go beyond 4 decoders?
 
  • Like
Reactions: pmccumber
The perceived need to keep backward compatibility is probably what's holding Intel and also AMD back. The only way to increase performance is to keep cranking up the CPU frequencies. With the world moving to an increasingly mobile workflow, and battery tech. is not advancing fast enough, this will be a huge challenge for both Intel and AMD to overcome.
Gaming is one of the biggest reasons for backward compatibility. People often return to games from 10-15 years ago, just like they may want to rewatch "old" movies from the 2000s. And while some popular games get "enhanced editions" or "remastered versions", playing old games usually requires running software that has not received updates for a long time.
 
I am different, in that I like to watch empires rise and fall. What I am hoping is that Apple provides the roadmap and inspiration for other companies to create integrated chip offerings of their own.

Resulting in fewer companies ordering processors from Intel, and leaving them in the annals of history.

In the end, you reap what you have sown.
And what has Intel sown?
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.