Split relocation kernels #408
Open
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
|
Can one of the admins verify this patch? |
JuanGonzalezCaminero
force-pushed
the
split_relocation
branch
from
7ecc190 to
c4a039c
Compare
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Outdated suggestions cannot be applied.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.
Separate the Relocation kernels for Electrons and gammas into a setup kernel which decides whether a track will relocate, do an interaction, or continue to the next step, and a relocation kernel in which the actual geometry calls are performed.
The reason for this split is that the current relocation kernels, specially in the case of electrons and positrons are very divergent. Only a small portion of the tracks in a warp will do a relocation, but the geometry calls involved are costly, which can slow down the rest of the threads in that warp.
These changes haven't shown a speedup so far in runs without a B-field, but the split should improve profiling results by isolating the relocation code.