Interesting. I thought modern CPU optimisation required avoiding branches, but here adding the branch allows the branch pediction to parallelise what it otherwise couldn't.
That would be great, if only it worked as intended! From the perspective of an optimizing compiler, `a == b ? a : b` is worse than `b` regardless of the probability you assign to `a == b`.
This is really surprising! I've never considered the possibility that using an equality test to skip a write that would be a no-op could break a dependency and thus lead to higher perf overall if the "equal" outcome occurs often enough. This might be applicable in many situations where you "edit" some data in-place, but most of the time there are few or no changes.
Interesting. I thought modern CPU optimisation required avoiding branches, but here adding the branch allows the branch pediction to parallelise what it otherwise couldn't.
I think this call for something similar to "__builtin_expect" or linux' likely()/unlikely().
Not very clean, but better than inserting obscure optimisations in the source.
That would be great, if only it worked as intended! From the perspective of an optimizing compiler, `a == b ? a : b` is worse than `b` regardless of the probability you assign to `a == b`.
Assuming compilers are smart enough to insert an unnecessary branch to break the dependency.
I was wondering the same thing. Also, could profile-guided optimisation help here?
Brilliant! Hadn't seen this technique before.
latency optimization is a skill. I liked how you went till CSE pass. I myself wrote several passes to go to lowest latency possible
This is really surprising! I've never considered the possibility that using an equality test to skip a write that would be a no-op could break a dependency and thus lead to higher perf overall if the "equal" outcome occurs often enough. This might be applicable in many situations where you "edit" some data in-place, but most of the time there are few or no changes.