feat: taskparallel propagation (producer-consumer model) #1070
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
niermann999
force-pushed
the
feat-taskparallel-prop
branch
from
2dd726a to
2c4c673
Compare
niermann999
changed the title
niermann999
force-pushed
the
feat-taskparallel-prop
branch
2 times, most recently
from
995cbf5 to
87b4a50
Compare
|
niermann999
added
enhancement
niermann999
force-pushed
the
feat-taskparallel-prop
branch
from
87b4a50 to
f1c7cf5
Compare
|
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Outdated suggestions cannot be applied.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.
Use warp specialization to reduce branching in the propagation: Assign a number of warps to work on different queues for stepping and navigation to different surface types, so that the thread divergence is reduced to the branching in the given step. Since warps are assigned to queues instead of tracks, this will (hopefully) open up possibilities for better load balancing in the case where a different number of sensitives have to be resolved in a given volume, followed by gap volume propagation