Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add TMA support for circular buffering pass #2833

Open
wants to merge 16 commits into
base: main
Choose a base branch
from
Open

Add TMA support for circular buffering pass #2833

wants to merge 16 commits into from
+1,579 −10

Commits on Aug 22, 2024

  1. Add allocation changes

    @rdspring1
    rdspring1 committed Aug 22, 2024
    Configuration menu
    Copy the full SHA
    12db3ee View commit details
    Browse the repository at this point in the history

  2. Add Indexing changes

    @rdspring1
    rdspring1 committed Aug 22, 2024
    Configuration menu
    Copy the full SHA
    2491171 View commit details
    Browse the repository at this point in the history

Commits on Aug 23, 2024

  1. Add circular buffering pass and testing

    @rdspring1
    rdspring1 committed Aug 23, 2024
    Configuration menu
    Copy the full SHA
    6d8ad5f View commit details
    Browse the repository at this point in the history

Commits on Sep 8, 2024

  1. Merge branch 'main' of https://github.com/nvidia/fuser into tma_cb

    @rdspring1
    rdspring1 committed Sep 8, 2024
    Configuration menu
    Copy the full SHA
    25c482d View commit details
    Browse the repository at this point in the history

  2. predicate and mbarrier changes 

    * Add support for Hopper::electSync
* Create ElectSync PredicateType
* Make mbarrier synchronous
  * mbarrier waits for all threads in CTA
  * All threads issues arriveExpectTx to get mbarrier_token
    @rdspring1
    rdspring1 committed Sep 8, 2024
    Configuration menu
    Copy the full SHA
    2f8d9e9 View commit details
    Browse the repository at this point in the history

  3. add mbarrier_wait immediately

    @rdspring1
    rdspring1 committed Sep 8, 2024
    Configuration menu
    Copy the full SHA
    2a06157 View commit details
    Browse the repository at this point in the history

  4. skip expressions_allocated_in_main_loop

    @rdspring1
    rdspring1 committed Sep 8, 2024
    Configuration menu
    Copy the full SHA
    0c8858f View commit details
    Browse the repository at this point in the history

Commits on Sep 9, 2024

  1. Ensure a full warp exists if there is elect sync predicate

    @rdspring1
    rdspring1 committed Sep 9, 2024
    Configuration menu
    Copy the full SHA
    f8123af View commit details
    Browse the repository at this point in the history

  2. comments≈

    @rdspring1
    rdspring1 committed Sep 9, 2024
    Configuration menu
    Copy the full SHA
    508d674 View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' of https://github.com/nvidia/fuser into tma_cb

    @rdspring1
    rdspring1 committed Sep 9, 2024
    Configuration menu
    Copy the full SHA
    d4c7938 View commit details
    Browse the repository at this point in the history

Commits on Sep 16, 2024

  1. Add compatibility check for elect sync

    @rdspring1
    rdspring1 committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    ccfedfc View commit details
    Browse the repository at this point in the history

  2. add test for elect sync compatibility

    @rdspring1
    rdspring1 committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    f29aa22 View commit details
    Browse the repository at this point in the history

  3. Use MBarrierArrive

    @rdspring1
    rdspring1 committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    f685a9b View commit details
    Browse the repository at this point in the history

Commits on Sep 17, 2024

  1. comments

    @rdspring1
    rdspring1 committed Sep 17, 2024
    Configuration menu
    Copy the full SHA
    b84eb96 View commit details
    Browse the repository at this point in the history

  2. Add has_elect_sync_predicate to kernel_summary

    @rdspring1
    rdspring1 committed Sep 17, 2024
    Configuration menu
    Copy the full SHA
    c1fdec5 View commit details
    Browse the repository at this point in the history

Commits on Sep 18, 2024

  1. Merge branch 'main' of https://github.com/nvidia/fuser into tma_cb

    @rdspring1
    rdspring1 committed Sep 18, 2024
    Configuration menu
    Copy the full SHA
    4f011b5 View commit details
    Browse the repository at this point in the history