Split the CUDA CKF into different TUs #742
Merged
Conversation
This file contains 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
stephenswat
added
refactor
stephenswat
force-pushed
the
refactor/ckf_tus
branch
2 times, most recently
from
bbeb4f7 to
30aebf1
Compare
|
My plan to finally get rid of those .ipp files has failed. 🫡 Anyway, updated. |
stephenswat
force-pushed
the
refactor/ckf_tus
branch
4 times, most recently
from
24a9c9e to
4ec0290
Compare
krasznaa
requested changes
Oct 23, 2024
krasznaa
requested changes
Oct 23, 2024
There was a problem hiding this comment.
Okay, let's go with this general setup at the moment. As we discussed in person, I have some further ideas for how to tweak the code later on even further, but these changes do not make those future changes any more difficult. (The general direction of my idea is very similar.)
device/common/include/traccc/finding/device/apply_interaction.hpp
Outdated
Show resolved
Hide resolved
stephenswat
force-pushed
the
refactor/ckf_tus
branch
from
4ec0290 to
54e7489
Compare
|
Great! I've rebased and incorporated the change requests |
stephenswat
force-pushed
the
refactor/ckf_tus
branch
from
54e7489 to
bf45c83
Compare
This commit splits the monstrously large CUDA track finding translation unit up into smaller ones, one for each of the kernels. This should speed up compilation times and decrease memory usage. Also groups the payloads for each of the functions into convenient structs, so we don't need to pass 20+ arguments for some of the kernel calls. Does not change the functionality of the code.
|
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Outdated suggestions cannot be applied.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 commit splits the monstrously large CUDA track finding (and some CCL) translation unit up into smaller ones, one for each of the kernels. This should speed up compilation times and decrease memory usage.
Also groups the payloads for each of the functions into convenient structs, so we don't need to pass 20+ arguments for some of the kernel calls.
Does not change the functionality of the code.