Skip to content

[AMD] Add Gluon GEMM tutorial#930

Merged
mengfei-jiang merged 0 commit intoROCm:gluon_extfrom
mengfei-jiang:gluon_ext_tutorial
Mar 13, 2026
Merged

[AMD] Add Gluon GEMM tutorial#930
mengfei-jiang merged 0 commit intoROCm:gluon_extfrom
mengfei-jiang:gluon_ext_tutorial

Conversation

@mengfei-jiang
Copy link
Copy Markdown

The core Triton is a small number of people, and we receive many PRs (thank
you!). To help us review your code more quickly, if you are a new
contributor (less than 3 PRs merged) we ask that you complete the following
tasks and include the filled-out checklist in your PR description.

Complete the following tasks before sending your PR, and replace [ ] with
[x] to indicate you have done them.

  • I am not making a trivial change, such as fixing a typo in a comment.

  • I have written a PR description following these
    rules.

  • I have run pre-commit run --from-ref origin/main --to-ref HEAD.

  • Select one of the following.

    • I have added tests.
      • /test for lit tests
      • /unittest for C++ tests
      • /python/test for end-to-end tests
    • This PR does not need a test because this is a tutorial.
  • Select one of the following.

    • I have not added any lit tests.
    • The lit tests I have added follow these best practices,
      including the "tests should be minimal" section. (Usually running Python code
      and using the instructions it generates is not minimal.)

@mengfei-jiang mengfei-jiang force-pushed the gluon_ext_tutorial branch 2 times, most recently from 73d7cb2 to 51c5544 Compare March 11, 2026 10:05
2. using the amd extensions, mostly gl.amd.cdna3/4.xxx

### extensions
1. instruction scheduling related
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

since they are all not fully respect, we cover it here


shared_a: gl.constexpr = gl.PaddedSharedLayout(
interval_padding_pairs=[[512, 16]],
offset_bases=[
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

make the bases short instead of multiple lines to ease user.

# Two sched_barrier(0x0) calls define a hard scheduling region:
# no instructions may move in or out.
#
# Mask values (combinable via bitwise OR):
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

better to have it in triton _init.py or readme,



## Triton prepare
1. git cherry-pick tip commits from [gluon_ext](https://github.com/ROCm/triton/tree/gluon_ext).
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

also need to rebase it, so we can make gluon_ext clean.

@mengfei-jiang mengfei-jiang force-pushed the gluon_ext_tutorial branch 5 times, most recently from 5f507d5 to e563ef2 Compare March 12, 2026 02:00
@mengfei-jiang mengfei-jiang force-pushed the gluon_ext_tutorial branch 2 times, most recently from 2bfd3e3 to b14a6fd Compare March 13, 2026 03:36
@mengfei-jiang mengfei-jiang merged commit b14a6fd into ROCm:gluon_ext Mar 13, 2026
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