-
Notifications
You must be signed in to change notification settings - Fork 152
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
Make ST_distance core kernels (point-point, point-linestring, linestring-linestring) perfectly load balanced. #1061
Labels
Comments
isVoid
changed the title
Make core kernels (point-point, point-linestring, linestring-linestring) perfectly load balanced.
Make ST_distance core kernels (point-point, point-linestring, linestring-linestring) perfectly load balanced.
Apr 8, 2023
3 tasks
This work require further investigation on the performance for load-balanced kernel. According to a recent benchmark , the "loop-segment" kernels performs better than load-balanced kernel if the dataset is not skewed. However, there exists some ground for optimization for load balanced kernel. Benchmark: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Currently, distance computation kernels are not perfectly load balanced. Most kernels follow this pattern: launch the number of threads on one operand and for each thread loop over points/segments of the correponding pair in the other. This can slow down the operation if the data are unbalanced/skewed.
Instead, the kernels should launch the number of thread that's makes one thread computes one pair of point-point/point-segment/segment-segment, then uses atomic operation to aggregate the result. This avoids slow down if the data is skewed.
The text was updated successfully, but these errors were encountered: