By: Travis (travis.downs.delete@this.gmail.com), December 20, 2017 5:54 pm
Room: Moderated Discussions
Linus Torvalds (torvalds.delete@this.linux-foundation.org) on December 20, 2017 5:18 pm wrote:
> Wild guess: it's about store ordering guarantees, and the L1 hit store being done concurrently
> with (or perhaps even instead of) the store buffer for some efficiency reason.
This part I don't understand - do you mean these stores skip the store buffer? That would definitely be interesting. I think we have lots of evidence that L1 stores don't in fact usually skip the store buffer (for example, load-forwarding behaviors are very visible for stores that fit in cache).
> Wild guess: it's about store ordering guarantees, and the L1 hit store being done concurrently
> with (or perhaps even instead of) the store buffer for some efficiency reason.
This part I don't understand - do you mean these stores skip the store buffer? That would definitely be interesting. I think we have lots of evidence that L1 stores don't in fact usually skip the store buffer (for example, load-forwarding behaviors are very visible for stores that fit in cache).