Microsoft has no choice.
Arm has been dominating the biggest growing market mobile (everything from phones to tablets and now). Intel is fighting a three front war now. While one battlefront is the mobile market where ARM essentially is the only choice, another battlefront is dominated by Nvidia with the processors for graphics and ML/AI. If that wasn’t bad enough, AMD is attacking hard on Intel’s home arena: PC CPUs.
When Apple dropped Intel for M1 they showed that Arm wasn’t just some niche processor technology for less powerful devices, such as mobile devices.
So not only is AMD taking market shares in the PC market, ARM is on the rise and doesn’t look very good for Intel right now.
Is Intel really capable of innovating their way out of their current path to extinction?
Longer term it’s going to be interesting to see what if anything RISC-V changes. Right now they’re filling a role that ARM occupied about 20 years ago being primarily an alternative for cheap and medium power devices, but just like ARM they’ve got the potential to duke it out in the desktop space with the right backing. It would for instance be an interesting move if Microsoft partnered with a company like HiFive to produce a truly high end RISC-V CPU similar to Apples M1/M2.
Producing a really high end CPU just be muscle flexing. Anybody can do that. Having apps run on it is a whole another story.
What Apple done right with M1 was not producing a powerful Arm CPU, but having old apps run on it so everyday people won’t be thrown into an unknown territory.
I’m too, looking forward to RISCV’s expansion though. MS could just skip ARM and adopt the better platform.
Producing a really high end CPU just be muscle flexing. Anybody can do that. Having apps run on it is a whole another story.
You say that, but nobody has actually done so. HiFive has produced some CPUs that would qualify as extremely low end desktop CPUs, but nothing that can compete with even middle of the road processors like an i5 or a Ryzen 5. As for apps, it would be pretty trivial to get a huge swath of Linux apps running on it, and if there was enough of a base and demand you’d see companies producing RISC-V binaries as well (much like they’re starting to for ARM). For emulation layers I’m sure something could be done, QEMU if nothing else could probably be used.
Does RISC-V have the better power/heat management that ARM has? Would be interesting in intel goes all in RISC
Yes, technically speaking ARM is RISC, just a different flavor of it from RISC-V. They’re effectively siblings. x86 on the other hand (and AMD64) are CISC processors. CISC provides compact programs at the cost of a more complicated (and therefore more power hungry) CPU. That said this is a gross oversimplification and no modern CPU is entirely RISC or CISC under the covers. Both ARM and x86 end up looking quite similar to each other when you dig into them, with x86 producing microcode from its instruction set that is effectively RISC, and ARM introducing some decidedly CISC looking instructions.
The reality is the relative power hungry-ness of the architectures doesn’t really come down to RISC vs. CISC as much as it does x86 providing backwards compatibility to literally decades of bad decisions. If x86 could jettison backwards compatibility and ditch all but the latest and greatest of its instruction set it would be able to compete watt for watt with ARM easily, but that’s a tradeoff customers are unwilling to engage with as it would render large swaths of software incompatible.
Intel is fine. The fact that they are somewhat competetive on their dinosaur fabrication node is crazy by itsself.
Intel is not fine on servers - ARM servers are about 20% faster for outright performance and 40% faster for performance-per-dollar. Since it’s literally just selecting a different option in a dropdown menu (assuming your software runs well on ARM, which it probably does these days), why would anyone choose Intel on a server?
And they’re not fine no a laptops either - unplugged my ARM Mac from the charger seven hours ago… and I’m at 80% charge right now. Try that with an Intel laptop with an i9 Processor and a discrete NVIDIA GPU (those two would be needed to have similar performance).
They’re only really doing well on desktop PCs, which is a small market, and people who can’t be bothered changing to a new architecture — a big market but one that is going away.
You are forgetting cloud computing - all my workloads have moved to Graviton or will do very shortly.
ARM is limited by licensing greed. RISC-V or its successors is the future.
Lol. Microsoft will never beat apple when in comes to how well their system runs on ARM hardware. simply because Apple has 3 chips to support that they know perfectly. Microsoft Windows would need to support whatever ARM chip comes out which will be an overgrowing number. This fact alone makes it extremely hard.
On the other hand Microsoft has already won in some way. Even with Apple silicon, Apple computers are still way less used then Windows PCs. So it’s not like windows is the underdog here. They are only fighting to stay in their monopoly.
The primary reason for people to use windows is still gaming and specialized software like CAD. Windows on ARM will not be used by anyone unless AAA games or AutoCAD software is build for ARM and Nvidia and AMD GPUs can be easily coupled with it.
I don’t see this coming at all. The only area where cheap, low power ARM PCs with windows would make sense, Linux or ChromeOS would be the way better and cheaper option. I don’t see any market for high performy ARM PCs with windows on them until demanding software and hardware supports it.
Microsoft will never beat apple when in comes to how well their system runs on ARM hardware
I dunno - cellular networking, touch screen, detachable keyboard… Apple is pretty easy to beat if you ask me. All Microsoft needs is an ARM chip that is “fast enough” and also has competitive battery life. Something Intel can’t deliver on.
Windows on ARM will not be used by anyone unless AAA games or AutoCAD software is build for ARM
That’s not how the transition went on a Mac. Software compiled for Intel is generally faster on ARM than it ever was on Intel Macs… not because the CPU is faster (it’s not), but rather Apple Silicon Macs have faster SSDs, faster RAM, more L2/L3 cache, etc. Those aren’t proprietary secrets, they’re just expensive. Anyone can do the same. Intel has caught up but only on their expensive desktop processors. If Qualcomm can do it on with a reasonably priced laptop chipset, that could be pretty special.
Games aren’t limited by compute performance, they’re mostly limited by how fast textures can be read. And it’s the same with AutoCAD.
Also you missed a massive use case - browsing the web. Chrome/etc is already optimised for ARM, since nobody uses x86 on a smartphone.
Microsoft Windows would need to support whatever ARM chip comes out which will be an overgrowing number.
Or they can do with producing, say, HaloPhones and HaloPads and only supporting what’s used in them.
Windows on ARM will not be used by anyone unless AAA games or AutoCAD software is build for ARM and Nvidia and AMD GPUs can be easily coupled with it.
I suspect this is like weapons trade or big commercial integrations. There will be ARM versions of those when there will be a strategy of MS and its partners profiting from it. Same with hardware.
It’s not that something happening naturally didn’t happen, it’s that there’s no such strategy to turn in that direction. This market is so oligopolized that it even looks this way.
I’m still waiting for ARM compatible drivers for the Dymo label printers we use. It’s been 4 years now.
Fuuuuuuuck Dymo.
It would be nice to have the option of buying a printer which just accepts PostScript via ulpt. I mean, some Brother models do, I even had one working before it melted (don’t ask me how).
Benchmarks or real applications?
Bridging the gap with Rosetta was a huge part of why Apple Silicon worked, and Windows is way more reliant on closed source legacy software than Mac is.
