[CK] Fix divide-by-zero crash for grouped conv kernels - #6132
Merged
Conversation
Details: Detected in ROCM-20764 during run pytorch unit tests for conv3d with 0 padding. Signed-off-by: Artem Kuzmitckii <artem.kuzmitckii@amd.com>
Contributor
Author
|
@ROCm/ck-reviewers please have a look |
bartekxk
approved these changes
Apr 23, 2026
assistant-librarian Bot
pushed a commit
to ROCm/composable_kernel
that referenced
this pull request
Apr 23, 2026
[CK] Fix divide-by-zero crash for grouped conv kernels (#6132) ## Motivation During run pytorch unit tests for conv3d: `test_dtypes_nn_functional_conv3d_cuda`, `test_fake_crossref_backward_amp_nn_functional_conv3d_cuda_float32` found divide-by-zero crash during CK kernel selection. Refs ROCM-20764 ## Technical Details Add assert for K0PerBlock equal 0, also covered other potential places related with k_batch calculation. ## Test Plan Run miopen command extracted from mentioned test: `MIOpenDriver convfp16 --spatial_dim 3 -I NCDHW -O NCDHW -f NCDHW -n 1 -c 1 -k 1 -g 1 --in_d 4 -H 4 -W 4 --fil_d 4 -y 4 -x 4 --pad_d 0 -p 0 -q 0 --conv_stride_d 2 -u 2 -v 2 --dilation_d 1 -l 1 -j 1 -m conv -F 4 -t 1` ## Test Result Passed ## Submission Checklist - [X] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests. Signed-off-by: Artem Kuzmitckii <artem.kuzmitckii@amd.com>
1 task
aledudek
pushed a commit
that referenced
this pull request
May 20, 2026
## Motivation During run pytorch unit tests for conv3d: `test_dtypes_nn_functional_conv3d_cuda`, `test_fake_crossref_backward_amp_nn_functional_conv3d_cuda_float32` found divide-by-zero crash during CK kernel selection. Refs ROCM-20764 ## Technical Details Add assert for K0PerBlock equal 0, also covered other potential places related with k_batch calculation. ## Test Plan Run miopen command extracted from mentioned test: `MIOpenDriver convfp16 --spatial_dim 3 -I NCDHW -O NCDHW -f NCDHW -n 1 -c 1 -k 1 -g 1 --in_d 4 -H 4 -W 4 --fil_d 4 -y 4 -x 4 --pad_d 0 -p 0 -q 0 --conv_stride_d 2 -u 2 -v 2 --dilation_d 1 -l 1 -j 1 -m conv -F 4 -t 1` ## Test Result Passed ## Submission Checklist - [X] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests. Signed-off-by: Artem Kuzmitckii <artem.kuzmitckii@amd.com>
shumway
pushed a commit
to ROCm/composable_kernel
that referenced
this pull request
May 27, 2026
[CK] Fix divide-by-zero crash for grouped conv kernels (#6132) ## Motivation During run pytorch unit tests for conv3d: `test_dtypes_nn_functional_conv3d_cuda`, `test_fake_crossref_backward_amp_nn_functional_conv3d_cuda_float32` found divide-by-zero crash during CK kernel selection. Refs ROCM-20764 ## Technical Details Add assert for K0PerBlock equal 0, also covered other potential places related with k_batch calculation. ## Test Plan Run miopen command extracted from mentioned test: `MIOpenDriver convfp16 --spatial_dim 3 -I NCDHW -O NCDHW -f NCDHW -n 1 -c 1 -k 1 -g 1 --in_d 4 -H 4 -W 4 --fil_d 4 -y 4 -x 4 --pad_d 0 -p 0 -q 0 --conv_stride_d 2 -u 2 -v 2 --dilation_d 1 -l 1 -j 1 -m conv -F 4 -t 1` ## Test Result Passed ## Submission Checklist - [X] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests. Signed-off-by: Artem Kuzmitckii <artem.kuzmitckii@amd.com>
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.
Motivation
During run pytorch unit tests for conv3d:
test_dtypes_nn_functional_conv3d_cuda,test_fake_crossref_backward_amp_nn_functional_conv3d_cuda_float32found divide-by-zero crash during CK kernel selection.
Refs ROCM-20764
Technical Details
Add assert for K0PerBlock equal 0, also covered other potential places related with k_batch calculation.
Test Plan
Run miopen command extracted from mentioned test:
MIOpenDriver convfp16 --spatial_dim 3 -I NCDHW -O NCDHW -f NCDHW -n 1 -c 1 -k 1 -g 1 --in_d 4 -H 4 -W 4 --fil_d 4 -y 4 -x 4 --pad_d 0 -p 0 -q 0 --conv_stride_d 2 -u 2 -v 2 --dilation_d 1 -l 1 -j 1 -m conv -F 4 -t 1Test Result
Passed
Submission Checklist