Skip to content

[hipblaslt] Add Origami Libs for Major GEMMs#598

Merged
davidd-amd merged 1 commit into
release-staging/rocm-rel-7.0from
users/AlexBrownAMD/rocm-rel-7.0-cp10
Jul 13, 2025
Merged

[hipblaslt] Add Origami Libs for Major GEMMs#598
davidd-amd merged 1 commit into
release-staging/rocm-rel-7.0from
users/AlexBrownAMD/rocm-rel-7.0-cp10

Conversation

@davidd-amd
Copy link
Copy Markdown
Contributor

Replaces #502 to enable azure tests.

This PR (only affects gfx950):

  • removes all major GEMMs from the GridBased folder
  • adds major GEMMs for Origami libraries in gfx950
  • adds fallback kernels for all GEMMs
  • adds the latest custom kernels for BBS_TN/HHS_TN
  • some modifications to file names, kernel names, bias datatypes
[----------] Global test environment tear-down
[==========] 19961 tests from 12 test suites ran. (664140 ms total)
[  PASSED  ] 19961 tests.
hipBLASLt version: 100100
hipBLASLt git version: 6e7cadecf4
command line: ./hipblaslt-test

---------

This PR (only affects gfx950):

- removes all major GEMMs from the GridBased folder
- adds major GEMMs for Origami libraries in gfx950
- adds fallback kernels for all GEMMs
- adds the latest custom kernels for BBS_TN/HHS_TN
- some modifications to file names, kernel names, bias datatypes

```
[----------] Global test environment tear-down
[==========] 19961 tests from 12 test suites ran. (664140 ms total)
[  PASSED  ] 19961 tests.
hipBLASLt version: 100100
hipBLASLt git version: 6e7cade
command line: ./hipblaslt-test

---------

Co-authored-by: b-shi <brianshi@amd.com>
@davidd-amd davidd-amd merged commit 4ef8214 into release-staging/rocm-rel-7.0 Jul 13, 2025
7 of 9 checks passed
@davidd-amd davidd-amd deleted the users/AlexBrownAMD/rocm-rel-7.0-cp10 branch July 13, 2025 19:34
b-shi added a commit that referenced this pull request Jul 15, 2025
- removes all major GEMMs from the GridBased folder
- adds major GEMMs for Origami libraries in gfx950
- adds fallback kernels for all GEMMs
- adds the latest custom kernels for BBS_TN/HHS_TN
- some modifications to file names, kernel names, bias datatypes

---------

Co-authored-by: aliry95amd <ayazdani@amd.com>
Co-authored-by: b-shi <brianshi@amd.com>
AlexBrownAMD pushed a commit that referenced this pull request Jul 15, 2025
- removes all major GEMMs from the GridBased folder
- adds major GEMMs for Origami libraries in gfx950
- adds fallback kernels for all GEMMs
- adds the latest custom kernels for BBS_TN/HHS_TN
- some modifications to file names, kernel names, bias datatypes

---------

Co-authored-by: aliry95amd <ayazdani@amd.com>
Co-authored-by: b-shi <brianshi@amd.com>
SathiyarajRam pushed a commit that referenced this pull request Jul 15, 2025
- removes all major GEMMs from the GridBased folder
- adds major GEMMs for Origami libraries in gfx950
- adds fallback kernels for all GEMMs
- adds the latest custom kernels for BBS_TN/HHS_TN
- some modifications to file names, kernel names, bias datatypes

---------

Co-authored-by: aliry95amd <ayazdani@amd.com>
Co-authored-by: b-shi <brianshi@amd.com>
ammallya pushed a commit that referenced this pull request Jul 22, 2025
ammallya pushed a commit that referenced this pull request Oct 27, 2025
Ensure transform functions in samples are only available on the device
ammallya pushed a commit that referenced this pull request Oct 28, 2025
Ensure transform functions in samples are only available on the device

[ROCm/rocwmma commit: 414dcf0]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants