Replace custom size kernel with cub::DeviceReduce::TransformReduce#811
Open
PointKernel wants to merge 1 commit intoNVIDIA:devfrom
Open
Replace custom size kernel with cub::DeviceReduce::TransformReduce#811PointKernel wants to merge 1 commit intoNVIDIA:devfrom
PointKernel wants to merge 1 commit intoNVIDIA:devfrom
Conversation
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR replaces the custom size kernel with the corresponding cub util and the performance has been improved significantly with large capacities.
Microbenchmark timing of
static_map::size()only. NVIDIA GH200 480GB, CUDA 13.1 / GCC 14.3. Map populated withNumInputsunique I64 keys at 0.5 occupancy (so capacity = 2 × NumInputs).cub::DeviceReduce::TransformReduce)