This blog comes in as a response to multiple media outlets
First of all, STFU with all the clickbait-y title BS.
Coming to the actual point, here is the forum post where Linus stated that x86 won.
The forum thread started with people discussing the newly released Arm Ares aka Neoverse N1 for the server space. In the thread, the first post by Linus(a reply to OP) he states, “We’ll see if it actually delivers, but ARM is certainly looking a whole lot better than it used to.”
To which ‘anon’ replies that “They (arm) have no market for an 8 core design. They would have to not just match but beat x86 in single threaded performance for there to be any reason to use such a thing.”
> The plot thickens
Then comes Linus’s much-hyped post where he argues that “performance” is not really the reason. The main reason is that Arm still heavily relies on cross-platform development. Whether its a server/cloud or mobile target, for the most part, the majority of the development is done on an x86 PC, cross-compiled and finally deployed on Arm.
He proceeds to state that the reason x86 is so successful is that developers have direct access to an x86 machine in their homes in the form of their desktops and workstation.
Now, I do agree with what he said in that thread, about having a Arm desktop to directly develop for Arm on Arm.
I just don’t really agree with his last statement “It’s why x86 won.”.
If there was ever a war between Arm and x86, and believe me we ARE at war. The Arm ecosystem is just getting started.
We already have desktop/laptop specific chipsets from the like of Qualcomm with the SD850 and SD8cx, and even some of the mobile chipsets like the
So that’s performance sorted, we even have development boards from the likes of 96Boards with above mentioned SoCs.
So what is really missing then?
Two things specifically:
– A Desktop friendly form factor: Like a NUC.
– Standardization: Now since we are aiming for a developer platform, rather than a development platform. Stuff needs to “Just Work”. Generic Arm distro images need to “Just Boot”. No more board specific images, board-specific kernel, board-specific needs to stop being a thing. And this is something the community has been begging for ages.
SBBR and SBSA implementation need to happen, Tianocore and Linux kernel upstreaming efforts need to happen and stop being something “optional”. And I am literally just repeating the words of the Arm community, its time vendors step up big time.
As for me, I’ll be at Linaro Connect BKK19 talking about this exact Arm DUC along with a few more link-minded members of the Arm community. Our session is titled “BKK19-302 Designing a
And that’s why stuff needs to happen NOW.