It has taken them that long to make arm be a thing on windows and that’s building on people porting stuff to arm for Mac to finally get momentum.
RISC-V with windows will be an eternity to be feasible.
Windows branding is now forever tied with x86/x64 Win32 legacy compatibility, meanwhile WSL had captured back a lot of webdevs from Mac. Google continues to push Chrome, but Electron continues to grow side by side. Lots of stuff happening with AI on Linux too, with both Windows and Mac remaining to be consumer deployment targets. Phone CPUs are fast enough to run some games on WINE+Bochs.
At this point, would it not make sense for MS to make its own ChromeOS and bolt-on an "LSW"?
I think you’re over estimating what percentage of users use WSL. They’re an insignificant fraction of the user base.
And with games, I think you’re also overestimating how good the translation layers like Proton are, and how rapidly Microsoft advance DX as well.
Will it now?
Microsoft was already deeply involved in 2021 as per that years' summit RISC-V Foundation's technical talks. Ztso was pushed by them.
Windows for arm hails back to 2011. They’re only just now getting native arm ports for several major packages. That’s ~13 years for a well established architecture that’s used much more universally than RISC-V. They don’t even have arm ports for lots of software that has arm ports on macOS.
RISC-V will take an aeon longer to get a respectable amount of the windows ecosystem ported over.
Absolutely agree.
The key development Microsoft has demonstrated recently is the ability to run x86 Windows software in non-x86 Windows systems.
Now that this is in place -and will only get better-, there is no longer a chicken and egg situation.
Instead, what we have is a clearly defined path to migrate away from x86.
It is evident to anybody paying attention that Microsoft has RISC-V support well underway.
But even if they had to start from scratch, it would be much easier, thanks to ARM having paved the way.
Without the ISVs, it’s a flop for consumers.
MS has had an abysmal time getting them to join in on ARM, only starting to have a little success now. Saying “Ha ha, just kidding, it’s RISC-V now” would be a disaster. That’s the kind of rug pull that helped kill Windows Mobile.
Emulators aren’t good enough. They’re a stop gap. Unless the new chip is so much better than the old it’s faster with emulation then the old one was native no one will accept it long. Apple’s been there, but that’s not where MS sits today.
And if your emulator is too good, what stops ISVs from saying “you did it for us, we don’t have to care”? So once again they don’t have to do it at all and you have no native software.
MS can’t drop their ARM push unless they want to drop all non-x86 initiatives for a long time.
x86 emulation enables adoption.
Adoption means having an user base.
Having an user base means developers will consider making the platform a target.
>Saying “Ha ha, just kidding, it’s RISC-V now” would be a disaster.
Would it now? If anything, offering RISC-V support as well would further reinforce the idea that Windows is ISA-independent, and not tied to x86 anymore.
In case this translation was needed at all. The point is the point is not a "-riscv" compilation option.
Anymore? It’s been independent since the 90s. It’s only ISVs that have been an issue.
And a rug pull is a fantastic way to scare all the ISVs far far away.
But, as an example, Windows Phone 8 and later were based on the NT kernel. You already mentioned the 360.
The competition isn’t sitting still either and QC already hit this with Intel stealing their thunder with Lunar Lake. They’re efficient enough that the difference in efficiency is far overshadowed by their compatibility story.
Ecosystem support will always go to the incumbent and this would place RISC-V third behind x86 and ARM. macOS did this right by saying there’s only one true way forward. It forces adoption.
For native apps, you need users. For users, you need emulation.
It cannot be overstated how important successful x86 emulation is for the migration to anything else to be feasible.
The incumbent is the only two companies -Intel and AMD- that can make x86 hardware.
The alternative is the rest of the industry.
Thus having a migration path should be plenty on its own.
Intel and AMD can both join by making RISC-V or ARM hardware themselves. My take is that they will too, eventually, come around. Or they'll just disappear from relevance.
You have to think in network effects. You mention “the rest of the industry” yet ignore that it’s mostly arm , which would make arm the incumbent.
x86 is the king for windows. But ARM has massive inroads with mobile, and now desktop with macOS, and servers with Amazon/Nvidia etc
There’s a lot better incentive to support ARM than RISC-V for software developers. It isn’t one or the other , but it is a question of resources.
Intel and AMD seem fine turning x86 around when threatened as can be seen by Lunar Lake and Stryx Point. Both have been good enough to steal QC’s thunder. You don’t think ARM manufacturers will do the same to RISC-V?
TBH most of your arguments for RISC-V adoption seem to start from the position that it’s inevitable AND that competing platforms won’t also improve.
Why do you think they’d take RISC-V any more seriously than their previous attempts at ARM?
There are two fallacies to overcome here.