Skip to content

[WIP] Investigate bf16 support in MIOpen pooling#2974

Closed
Copilot wants to merge 1 commit intodevelopfrom
copilot/investigate-bf16-support
Closed

[WIP] Investigate bf16 support in MIOpen pooling#2974
Copilot wants to merge 1 commit intodevelopfrom
copilot/investigate-bf16-support

Conversation

Copy link

Copilot AI commented Nov 27, 2025

No description provided.

Copilot AI requested a review from MiloLurati November 27, 2025 18:34
@MiloLurati MiloLurati closed this Nov 27, 2025
@MiloLurati MiloLurati deleted the copilot/investigate-bf16-support branch November 27, 2025 18:36
COrruDXC pushed a commit to COrruDXC/rocm-libraries that referenced this pull request Nov 28, 2025
* Add initial fp16_mem_128x128x32_2x2x1_32x32x16_NonPersistent test suite

* Account for stride when computing K offsets for A and B tensor

This change ensures that the correct stride is used when computing the K
offsets into the A and B tensors in the Stream-K Kernel's operator()
function. This ensures that the kernel executes correct regardless of
whether A and B are row or column major.

* Move helper code to test_gemm_streamk_util.hpp

* Separate tests into smoke/regression/extended. Add bf16 datatype

* Run clang-format

* Refactor combinatorial macro expansion and naming

* Adjust the initialization values to account for better tolerance on bf16

* Correct BF16 datatypes in comments

* Move the extended tests under the REGRESSION_TESTS label

* Apply suggestions from code review

Co-authored-by: Copilot <[email protected]>

---------

Co-authored-by: Emily Martins <[email protected]>
Co-authored-by: Copilot <[email protected]>
ammallya pushed a commit that referenced this pull request Feb 3, 2026
* Add initial fp16_mem_128x128x32_2x2x1_32x32x16_NonPersistent test suite

* Account for stride when computing K offsets for A and B tensor

This change ensures that the correct stride is used when computing the K
offsets into the A and B tensors in the Stream-K Kernel's operator()
function. This ensures that the kernel executes correct regardless of
whether A and B are row or column major.

* Move helper code to test_gemm_streamk_util.hpp

* Separate tests into smoke/regression/extended. Add bf16 datatype

* Run clang-format

* Refactor combinatorial macro expansion and naming

* Adjust the initialization values to account for better tolerance on bf16

* Correct BF16 datatypes in comments

* Move the extended tests under the REGRESSION_TESTS label

* Apply suggestions from code review

Co-authored-by: Copilot <[email protected]>

---------

Co-authored-by: Emily Martins <[email protected]>
Co-authored-by: Copilot <[email protected]>

[ROCm/composable_kernel commit: f570888]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants