Yeah, but it seems unlikely that many of them are learning in languages or environments where the arch really makes any difference. If the dominant OS on RPi was RiscOS (a man can dream...) it might be a different story.
And where does it? Almost nothing I write will get compiled down to native code. Linus is forgetting the immense volume of code that's written in Java, PHP, Python, C#, Ruby and dozens of other languages that rely on runtime interpreters.
I agree I will not even think of optimizing my code to run on POWER, SPARC, or ARM and that I won't care where my software runs enough to create a market for these, but I don't care enough to keep an x86 market either.
Having said that, it would be good for those who propose new architectures to ensure there is a ready supply of entry level machines for enthusiasts and early adopters. Seeding these groups will ensure their architectures and software is more thoroughly used and tested.
Are all these kids learning C or assembly? Because if they are learning Javascript, Python, etc. it doesn't matter in which processor their code is running.
Exactly. That's what I don't get about this whole architecture argument. If I write a mess of Python and deploy on a local ARM SBC or drop it into a remote x86 webserver, what's the difference?
Are they really? RPi is cool and all, but I doubt the market share of ARM development is that big. As I was kid I got interested in programming because I wanted to develop games, and I would guess that still most yungsters want. For that RPi is shitty choice.
It is pretty big for smartphones and tablets. And embedded devices.
Games on smartphones are perfectly viable - RPi is not good enough but oDroid or Google Pixel is.
The only problem is developing on same machine as you use. For that, you need a full fledged, quite powerful ARM laptop. Hacked Chromebook for example.
Otherwise, the emulator is way too slow.
That's probably the strongest counter-argument. New generations will learn programming on Arm and RISC-V (whether it's something like an iPad or a Raspberry Pi).
Linus very much sounds like a grumpy old man saying "get off of my lawn!" (as he usually does).
Well, it's difficult to not get grumpy when you hear the same promises for many years. It's not like "ARM for servers" is something new. The exact same things were already promised over a decade ago, and somehow, it never really came to pass. And I think his reasons are spot on: aside from very specific workloads, it just did not make sense to buy ARM-based servers. They were usually not much cheaper, and they usually did not save much power, compared to x86-based machines. Combine that with cross-development, and you have a loser.
Exactly. Modern X86-64 chips got improved power saving, more cores to increase density at reduced power cost, much more powerful GPU for running compute.
Plus, server space buyers are conservative, they want support of a big company behind their hardware. Someone the size of Cisco, Dell or HP. Or hardware that is used by Google or Microsoft.
Combine that with anticompetitive long term agreements and you get the picture.
Somehow network routers have a variety of architectures inside and nobody has a problem - because they have a bunch of reputable companies behind each of them. (Variants of MIPS, ARM, ARM64 and x86 are in the wild.)
