This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
[v1.4.x] Fix launch bounds in spatial transformer #13898
Closed
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
KellenSunderland
changed the title
|
@mxnet-label-bot add [pr-awaiting-review] |
larroy
approved these changes
Jan 17, 2019
|
@mxnet-label-bot update [pr-awaiting-merge] |
marcoabreu
added
pr-awaiting-merge
* Fix launch bounds in spatial transformer * Adding explanation in comment.
KellenSunderland
force-pushed
the
pr_bilinear_backward_launch_bounds_1_4
branch
from
cb0d731
to
0cd3cde
Compare
|
Yeah I also read this as limiting to a single thread, but it's actually limiting to 1024 threads and setting a minimum number of block launches to 1. See correspondence in the original PR: #13188 |
|
Didn't get a committer review by deadline so I'm closing this one off. Fix is already in master and should be available if we have many user reports for this error. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Description
Without launch_bounds compiler is not required to use small enough number of registers to fit 1024 threads per block. Our internal CI with CUDA 10 build was failing on V100 because of this.
Original PR: #13188
Checklist
Essentials
Please feel free to remove inapplicable items for your PR:
Changes
Comments