This repository was archived by the owner on Jul 28, 2025. It is now read-only.
Adds load balanced kernel for point-point, point-linestring and linestring-linestring#1144
Draft
isVoid wants to merge 33 commits intorapidsai:branch-23.08from
Draft
Adds load balanced kernel for point-point, point-linestring and linestring-linestring#1144isVoid wants to merge 33 commits intorapidsai:branch-23.08from
isVoid wants to merge 33 commits intorapidsai:branch-23.08from
Conversation
…ti-geometry based
…y multigeometry test case.
…to fix/segment_iterator
…into improvement/load_balanced_distance_kernel
…m:isVoid/cuspatial into improvement/load_balanced_distance_kernel
harrism
reviewed
May 30, 2023
| auto aggregate = BlockReduce(temp_storage).Reduce(partial, cub::Min()); | ||
|
|
||
| // atmomic with leading thread | ||
| if (cooperative_groups::this_thread_block().thread_rank() == 0) |
Member
There was a problem hiding this comment.
Is there any advantage to this over if (threadIdx.x == 0)? What code does this produce? It's impossible for threadIdx.x == 0 to have exited before any other threads in its block in this code.
Contributor
Author
There was a problem hiding this comment.
Cannot think of any advantage comparing to threadIdx.x == 0. I originally had hopped writing modularized kernel with cg but but later regressed. This is probably a remnant from prototyping.
harrism
reviewed
May 30, 2023
| std::size_t constexpr threads_per_block = 256; | ||
| std::size_t const num_blocks = | ||
| (multilinestrings1.num_points() + threads_per_block - 1) / threads_per_block; | ||
| std::size_t num_threads = 1e8; |
Member
There was a problem hiding this comment.
Rather than hard coding, this may be a job for the occupancy API...
https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__OCCUPANCY.html
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Place holder for PRs to close during burndown period.
Closes #1061
Checklist