New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Speed up iota (filling array with consecutive numbers) #58271
Conversation
This is an automated comment for commit ff90f64 with description of existing statuses. It's updated for the latest CI running ❌ Click here to open a full report in a separate page Successful checks
|
Turns out that when working on min for non numeric types I noticed that |
a6b4044
to
96da2f5
Compare
96da2f5
to
ed6b970
Compare
To check:
|
@Algunenano, Mac OS defines size_t as unsigned long long instead of unsigned long. |
Fixed the OSX build and verified locally that indeed a couple of tests were slower with the changes. I couldn't see why and it went away as soon as I rebased the branch with master, so let's see what it says now. |
Test diffs in |
Changelog category (leave one):
Changelog entry (a user-readable short description of the changes that goes to CHANGELOG.md):
Affects many places where we need this kind of function.
I decided to only implement SSE42 (which was the default/baseline in official builds) and AVX2 (which gives 1.4x as much performance as SSE42) as I didn't see any improvement in introducing AVX512F or AVX512BW.
Here are the benchmarks I did:
Other affected functions are:
rowNumberInBlock
arraySort
ORDER BY
)