Change descending from template parameter to an argument #1883
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
…eter The intent is to reduce the build time, build memory footprint, and binary size of the sorting_impl module. With this change it stands at 46MB, before it was 72MB.
…x_impl With this change, _tensor_sorting_impl goes back to 17MB, and _tensor_sorting_radix_impl is 30MB. The memory footprint of linking should be greatly reduced, speeding up the building process, reducing the required memory footprint, and providing better parallelisation opportunities for the build job. The build time on my Core i7 reduced from 45 minutes to 33 minutes.
|
Deleted rendered PR docs from intelpython.github.com/dpctl, latest should be updated shortly. 🤞 |
|
On GPU Max 1100, sorting an array of |
ndgrigorian
approved these changes
Oct 29, 2024
oleksandr-pavlyk
deleted the
change-descending-from-template-parameter-to-an-argument
branch
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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 removes template parameter
is_ascendingfrom radix sort functions and introduces it as function call argument instead.This halves the binary size due to reduction in device code portion. Furthermore, radix sorting functions are singled out into a dedicated Python module
_tensor_sorting_radix_implfurther reducing the build time and memory footprint and provide increased parallelization opportunities to the linker.The overall build time drops from 45 minutes to 33 minutes on my Core i7 laptop.