On Thu, Feb 14, 2019 at 9:51 AM Linus Torvalds
<torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
>
> The arm64 numbers scaled horribly even before, and that's because
> there is too much ping-pong, and it's probably because there is no
> "stickiness" to the cacheline to the core, and thus adding the extra
> loop can make the ping-pong issue even worse because now there is more
> of it.
Actually, if it's using the ll/sc, then I don't see why arm64 should
even change. It doesn't really even change the pattern: the initial
load of the value is just replaced with a "ll" that gets a non-zero
value, and then we re-try without even doing the "sc" part.
End result: exact same "load once, then do ll/sc to update". Just
using a slightly different instruction pattern.
But maybe "ll" does something different to the cacheline than a regular "ld"?
Alternatively, the machine you used is using LSE, and the "swp" thing
has some horrid behavior when it fails.
So I take it back. I'm actually surprised that arm64 performs worse. I
don't think it should. But numbers walk, bullshit talks, and it
clearly does make for worse numbers on arm64.
Linus
