Speed up SH backward camera-gradient reduction - #751
Merged
Conversation
Launch the spherical harmonics backward kernel with one grid row per camera and simplify the resulting indexing. Performance was verified to be unchanged. Signed-off-by: Matthew Cong <mcong@nvidia.com>
Signed-off-by: Matthew Cong <mcong@nvidia.com>
matthewdcong
force-pushed
the
improve_sh_bwd_reduce
branch
from
August 22, 2026 04:00
f83a90b to
1c87f56
Compare
Signed-off-by: Matthew Cong <mcong@nvidia.com>
matthewdcong
force-pushed
the
improve_sh_bwd_reduce
branch
from
August 23, 2026 20:38
2f578ad to
c4849d9
Compare
swahtz
added
the
Gaussian Splatting
swahtz
requested changes
Aug 24, 2026
swahtz
left a comment
swahtz
left a comment
Contributor
There was a problem hiding this comment.
Overall looks good to me, just a few minor checks/fixes.
Signed-off-by: Matthew Cong <mcong@nvidia.com>
matthewdcong
force-pushed
the
improve_sh_bwd_reduce
branch
from
August 24, 2026 05:34
3b9c00d to
bb087ca
Compare
matthewdcong
enabled auto-merge (squash)
August 24, 2026 05:34
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Instead of allocating a full view-direction gradient intermediate in unified memory, we instead allocate more compact device-local per-block sums. The per-block sums are written to after a block reduce in the SH kernel followed by a CUB
DeviceSegmentedReduce. On dual RTX 3090s: