ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 02:02:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK Conv] Add bwd weight instance for large-k shape (#4266)

Browse Source 
## Proposed changes

This instance improves the shape used in `./bin/ckProfiler
grouped_conv_bwd_weight 1 2 0 2 0 1 2 1 32 2376 256 3 3 100 100 1 1 1 1
1 1 1 1 all` from 10.3 ms to 6.6 ms.

## Checklist

Please put an `x` into the boxes that apply. You can also fill these out
after creating the PR. If you're not sure, please don't hesitate to ask.

- [ ] I have added tests relevant to the introduced functionality, and
the unit tests are passing locally
- [ ] I have added the test to REGRESSION_TESTS list defined at the top
of CMakeLists.txt in tests/CMakeLists.txt, **IF** the test takes more
than 30 seconds to run.
- [ ] I have added inline documentation which enables the maintainers
with understanding the motivation
- [ ] I have removed the stale documentation which is no longer relevant
after this pull request
- [ ] (If this change is user-facing) I have added release notes which
provide the end users with a brief summary of the improvement from this
pull request
- [ ] I have run `clang-format` on all changed files
- [ ] Any dependent changes have been merged

## Discussion

If this is a relatively large or complex change, feel free to start a
discussion by explaining why you chose the solution you did and what
alternatives you considered



---
🔁 Imported from
[ROCm/composable_kernel#3692](https://github.com/ROCm/composable_kernel/pull/3692)
🧑‍💻 Originally authored by @johannes-graner

Co-authored-by: Graner, Johannes <johannes.graner@amd.com>
Co-authored-by: systems-assistant[bot] <systems-assistant[bot]@users.noreply.github.com>
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>
This commit is contained in:
assistant-librarian[bot]
2026-02-10 16:56:59 +00:00
committed by GitHub
parent f6bb48458d
commit 333816f842
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_v3_xdl_instance.hpp
View File

@@ -123,7 +123,8 @@ using device_grouped_conv_bwd_weight_v3_xdl_c_shuffle_f16_direct_load_instances
DeviceGroupedConvBwdWeight_Xdl_CShuffleV3< NDimSpatial, ALayout, BLayout, ELayout, F16, F16, F16, F32, PassThrough, PassThrough, PassThrough, ConvSpec, 256, 64, 128, 64, 8, 32, 32, 1, 2, S<4, 8, 8>, S<0, 2, 1>,S<0, 2, 1>, 1, 8, 8, 0, S<4, 16, 4>, S<0, 2, 1>,S<0, 2, 1>, 1, 8, 8, 0, 1, 1, S<1, 32, 1, 8>, 8, Scheduler, PipelineVersion, F16, F16, true, 2>,
DeviceGroupedConvBwdWeight_Xdl_CShuffleV3< NDimSpatial, ALayout, BLayout, ELayout, F16, F16, F16, F32, PassThrough, PassThrough, PassThrough, ConvSpec, 256, 64, 64, 64, 8, 16, 16, 2, 2, S<4, 8, 8>, S<0, 2, 1>,S<0, 2, 1>, 1, 8, 8, 0, S<4, 8, 8>, S<0, 2, 1>,S<0, 2, 1>, 1, 8, 8, 0, 1, 1, S<1, 32, 1, 4>, 8, Scheduler, PipelineVersion, F16, F16, true>,
DeviceGroupedConvBwdWeight_Xdl_CShuffleV3< NDimSpatial, ALayout, BLayout, ELayout, F16, F16, F16, F32, PassThrough, PassThrough, PassThrough, ConvSpec, 256, 64, 64, 64, 8, 16, 16, 2, 2, S<4, 8, 8>, S<0, 2, 1>,S<0, 2, 1>, 1, 8, 8, 0, S<4, 8, 8>, S<0, 2, 1>,S<0, 2, 1>, 1, 8, 8, 0, 1, 1, S<1, 32, 1, 4>, 2, Scheduler, PipelineVersion, F16, F16, true>,
DeviceGroupedConvBwdWeight_Xdl_CShuffleV3< NDimSpatial, ALayout, BLayout, ELayout, F16, F16, F16, F32, PassThrough, PassThrough, PassThrough, ConvSpec, 256, 64, 64, 64, 8, 16, 16, 2, 2, S<4, 32, 2>, S<0, 2, 1>,S<0, 2, 1>, 1, 2, 1, 0, S<4, 32, 2>, S<0, 2, 1>,S<0, 2, 1>, 1, 2, 1, 0, 1, 1, S<1, 32, 1, 4>, 4, Scheduler, PipelineVersion, F16, F16, true>
DeviceGroupedConvBwdWeight_Xdl_CShuffleV3< NDimSpatial, ALayout, BLayout, ELayout, F16, F16, F16, F32, PassThrough, PassThrough, PassThrough, ConvSpec, 256, 64, 64, 64, 8, 16, 16, 2, 2, S<4, 32, 2>, S<0, 2, 1>,S<0, 2, 1>, 1, 2, 1, 0, S<4, 32, 2>, S<0, 2, 1>,S<0, 2, 1>, 1, 2, 1, 0, 1, 1, S<1, 32, 1, 4>, 4, Scheduler, PipelineVersion, F16, F16, true>,
DeviceGroupedConvBwdWeight_Xdl_CShuffleV3< NDimSpatial, ALayout, BLayout, ELayout, F16, F16, F16, F32, PassThrough, PassThrough, PassThrough, ConvSpec, 256, 128, 64, 32, 8, 32, 32, 2, 1, S<2, 16, 8>, S<0, 2, 1>,S<0, 2, 1>, 1, 8, 8, 0, S<2, 8, 16>, S<0, 2, 1>,S<0, 2, 1>, 1, 8, 8, 0, 1, 1, S<1, 32, 1, 8>, 8, Scheduler, PipelineVersion, F16, F16, true>
// clang-format on
>;