This was to make the initial implementation simpler, but I was *considering* making it just like… a rule. It's not a terrible rule. One of the main reasons I want dynamic typing is when I'm prototyping anyhow.
I trust you, but I don’t understand how that works on Intel unless you’re calling the same method over and over… RIP is always the same, should always miss?
-
-
Intel’s contemporary predictors also use branch history AIUI.
-
@mattgodbolt suggests otherwise for the BTB: https://xania.org/201602/bpu-part-three … Unless it’s changed since 2016.
End of conversation
New conversation -
-
-
Also sure, but that’s what speculative devirtualization is for, right? :) Guess what the library you’re linking to is, fall back if not… I’m not saying you *should* do this—you shouldn’t :) Just saying it’s theoretically possible and e.g. HotSpot gets a ton of mileage from it
-
Like you said, I think it only really pays off if you have a tracing JIT or high quality PGO info.
End of conversation
New conversation -
-
Show additional replies, including those that may contain offensive content
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.