By: Linus Torvalds (torvalds.delete@this.linux-foundation.org), May 19, 2013 12:19 pm
Room: Moderated Discussions
Michael S (already5chosen.delete@this.yahoo.com) on May 19, 2013 11:39 am wrote:
>
> Sounds very LRB. Not at all like a Silverthorne.
So I have no real inside information, and I may have exaggerated things a bit, and it was all complete conjecture anyway (but conjecture that explains what we saw with Atom).
But I'm interested: why do you think the original Atom core is a much better core than LRB?
Yes, yes, LRB had the magical vector extensions and obviously the whole "lots of cores" thing, so it was very different and much more ambitious than Atom was, but I think they are similar in the sense that they started out as small projects by a couple of people, and took a lot of shortcuts due to that.
And my real argument was that the reason the original Atom was in-order wasn't that it was a better and more power-efficient design, it was because it was a short-cut for a project that didn't have the resources to do anything more. Then it kind of stayed that way (much too long).
Linus
>
> Sounds very LRB. Not at all like a Silverthorne.
So I have no real inside information, and I may have exaggerated things a bit, and it was all complete conjecture anyway (but conjecture that explains what we saw with Atom).
But I'm interested: why do you think the original Atom core is a much better core than LRB?
Yes, yes, LRB had the magical vector extensions and obviously the whole "lots of cores" thing, so it was very different and much more ambitious than Atom was, but I think they are similar in the sense that they started out as small projects by a couple of people, and took a lot of shortcuts due to that.
And my real argument was that the reason the original Atom was in-order wasn't that it was a better and more power-efficient design, it was because it was a short-cut for a project that didn't have the resources to do anything more. Then it kind of stayed that way (much too long).
Linus