Artem Kuzmitckii 281d1bf50b [rocm-libraries] ROCm/rocm-libraries#6132 (commit e97065d) ...

[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>

2026-04-23 20:12:40 +00:00

..

ck

[rocm-libraries] ROCm/rocm-libraries#6132 (commit e97065d)

2026-04-23 20:12:40 +00:00

ck_tile

[rocm-libraries] ROCm/rocm-libraries#6611 (commit 5375c0f)

2026-04-22 10:52:59 +00:00

rapidjson

…