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 atomic_ref support for 8 and 16b types. #2255

Merged
merged 34 commits into from
Oct 16, 2024
Merged

Add atomic_ref support for 8 and 16b types. #2255

merged 34 commits into from
Oct 16, 2024

Commits on Aug 16, 2024

  1. Support fetch_add and CAS on 8/16b

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    9941a44 View commit details
    Browse the repository at this point in the history

  2. Add 16b test

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    bfd97ee View commit details
    Browse the repository at this point in the history

  3. Fix issues found when enabling 8/16b in a heterogeneous test, PTX see… 

    …ms to be invalid though
    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    24bb639 View commit details
    Browse the repository at this point in the history

  4. Remove 16b cas and use only 32b cas.

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    f93e690 View commit details
    Browse the repository at this point in the history

  5. Get several tests passing for 8/16b atomics

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    ae24c8e View commit details
    Browse the repository at this point in the history

  6. Remove todo and ifdefs from tests covering 8b/16b atomics

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    1af8667 View commit details
    Browse the repository at this point in the history

  7. Fix bug in 16b atomic load

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    ff06fa1 View commit details
    Browse the repository at this point in the history

  8. Move store close to fetch_update since it is a derived primitive

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    8daaad1 View commit details
    Browse the repository at this point in the history

  9. Fix bug in minmax due to s64 overload missing for arithmetic types

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    f588332 View commit details
    Browse the repository at this point in the history

  10. Add more 8/16b tests for atomic_ref

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    60e8c25 View commit details
    Browse the repository at this point in the history

  11. Fixup remove debug prints

    @wmaxey
    wmaxey committed Aug 16, 2024
    Configuration menu
    Copy the full SHA
    e9a79f4 View commit details
    Browse the repository at this point in the history

Commits on Aug 17, 2024

  1. Cleanup bitmask hell, fix bug where lower mask was ignored

    @wmaxey
    wmaxey committed Aug 17, 2024
    Configuration menu
    Copy the full SHA
    b713109 View commit details
    Browse the repository at this point in the history

  2. Add test covering interleaved CAS onto same atomic window

    @wmaxey
    wmaxey committed Aug 17, 2024
    Configuration menu
    Copy the full SHA
    1c2627d View commit details
    Browse the repository at this point in the history

  3. Fixup documentation mistake.

    @wmaxey
    wmaxey authored Aug 17, 2024
    Configuration menu
    Copy the full SHA
    c0f52c8 View commit details
    Browse the repository at this point in the history

Commits on Aug 19, 2024

  1. Make atomics enable_if uses match rest of libcudacxx.

    @wmaxey
    wmaxey committed Aug 19, 2024
    Configuration menu
    Copy the full SHA
    6d1beec View commit details
    Browse the repository at this point in the history

  2. Verify fetch_add sequential load behavior in 8b/16b atomics

    @wmaxey
    wmaxey committed Aug 19, 2024
    Configuration menu
    Copy the full SHA
    d5f8928 View commit details
    Browse the repository at this point in the history

Commits on Aug 20, 2024

  1. Remove 8b/16b add PTX tests

    @wmaxey
    wmaxey committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    c9ca506 View commit details
    Browse the repository at this point in the history

Commits on Aug 21, 2024

  1. Optimize fetch_update CAS loops

    @wmaxey
    wmaxey committed Aug 21, 2024
    Configuration menu
    Copy the full SHA
    6f5d0b8 View commit details
    Browse the repository at this point in the history

  2. Fix name of preset for PTX codegen test

    @wmaxey
    wmaxey committed Aug 21, 2024
    Configuration menu
    Copy the full SHA
    b7b944e View commit details
    Browse the repository at this point in the history

  3. Fix signed/unsigned comparison

    @wmaxey
    wmaxey committed Aug 21, 2024
    Configuration menu
    Copy the full SHA
    2381c42 View commit details
    Browse the repository at this point in the history

  4. Fix atomics codegen tests not being built

    @wmaxey
    wmaxey committed Aug 21, 2024
    Configuration menu
    Copy the full SHA
    07d1077 View commit details
    Browse the repository at this point in the history

  5. Fix CMake target for libcudacxx ptx tests.

    @wmaxey
    wmaxey committed Aug 21, 2024
    Configuration menu
    Copy the full SHA
    a2d19d1 View commit details
    Browse the repository at this point in the history

Commits on Aug 27, 2024

  1. Make dump_and_check executable again

    @wmaxey
    wmaxey committed Aug 27, 2024
    Configuration menu
    Copy the full SHA
    70aa4a3 View commit details
    Browse the repository at this point in the history

Commits on Aug 28, 2024

  1. Work around inconsistent parsing of [[[ in FileCheck versions

    @wmaxey
    wmaxey committed Aug 28, 2024
    Configuration menu
    Copy the full SHA
    e08ed80 View commit details
    Browse the repository at this point in the history

Commits on Sep 4, 2024

  1. Make min/max match algorith.min/max.

    @wmaxey
    wmaxey authored Sep 4, 2024
    Configuration menu
    Copy the full SHA
    1000597 View commit details
    Browse the repository at this point in the history

Commits on Sep 10, 2024

  1. Merge branch 'main' into fea/atomic_ref_8_16_bit_support

    @wmaxey
    wmaxey authored Sep 10, 2024
    Configuration menu
    Copy the full SHA
    f48a49b View commit details
    Browse the repository at this point in the history

Commits on Sep 11, 2024

  1. Work around NVCC 11.X using different syntax for inline ptx

    @wmaxey
    wmaxey committed Sep 11, 2024
    Configuration menu
    Copy the full SHA
    b7baeef View commit details
    Browse the repository at this point in the history

  2. Fix warnings in the codegen tests.

    @wmaxey
    wmaxey committed Sep 11, 2024
    Configuration menu
    Copy the full SHA
    c59b3ab View commit details
    Browse the repository at this point in the history

  3. Use PTX 16b ld/st instead of 32b CAS

    @wmaxey
    wmaxey committed Sep 11, 2024
    Configuration menu
    Copy the full SHA
    642b487 View commit details
    Browse the repository at this point in the history

  4. Switch 8b ld/st to 16b ld

    @wmaxey
    wmaxey committed Sep 11, 2024
    Configuration menu
    Copy the full SHA
    b1901a2 View commit details
    Browse the repository at this point in the history

Commits on Oct 7, 2024

  1. Merge branch 'main' into fea/atomic_ref_8_16_bit_support

    @wmaxey
    wmaxey committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    8612403 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into fea/atomic_ref_8_16_bit_support

    @wmaxey
    wmaxey committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    928465f View commit details
    Browse the repository at this point in the history

  3. Make atomic min/max match std::min/max behavior

    @wmaxey
    wmaxey committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    71376e9 View commit details
    Browse the repository at this point in the history

  4. Atomic codegen tests: clang-cuda reorders some arguments, include the… 

    …m in the DAG to fix CI failures
    @wmaxey
    wmaxey committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    0479ebd View commit details
    Browse the repository at this point in the history