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

[TL] Adapt TL Hardware-aware Search Space with Roller #207

Merged
merged 26 commits into from
Oct 2, 2024
Merged

[TL] Adapt TL Hardware-aware Search Space with Roller #207

merged 26 commits into from
Oct 2, 2024

Commits on Sep 28, 2024

  1. Refactor tilelang dequantize module and add matmul_blocked_weight_onl… 

    …y function
    @LeiWang1999
    LeiWang1999 committed Sep 28, 2024
    Configuration menu
    Copy the full SHA
    f3b1eb9 View commit details
    Browse the repository at this point in the history

  2. remove un-implemented code.

    @LeiWang1999
    LeiWang1999 committed Sep 28, 2024
    Configuration menu
    Copy the full SHA
    730d13e View commit details
    Browse the repository at this point in the history

  3. Implement BaseScheduler to wrap some related items.

    @LeiWang1999
    LeiWang1999 committed Sep 28, 2024
    Configuration menu
    Copy the full SHA
    8047ee7 View commit details
    Browse the repository at this point in the history

  4. lint fix

    @LeiWang1999
    LeiWang1999 committed Sep 28, 2024
    Configuration menu
    Copy the full SHA
    64db065 View commit details
    Browse the repository at this point in the history

  5. test skip

    @LeiWang1999
    LeiWang1999 committed Sep 28, 2024
    Configuration menu
    Copy the full SHA
    cef04a8 View commit details
    Browse the repository at this point in the history

Commits on Sep 29, 2024

  1. Refactor tilelang dequantize module and add matmul_blocked_weight_onl… 

    …y function
    @LeiWang1999
    LeiWang1999 committed Sep 29, 2024
    Configuration menu
    Copy the full SHA
    f1652e9 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' of https://github.com/microsoft/BitBLAS into tl_o… 

    …ps_dynamic
    @LeiWang1999
    LeiWang1999 committed Sep 29, 2024
    Configuration menu
    Copy the full SHA
    4f6c545 View commit details
    Browse the repository at this point in the history

  3. test fix

    @LeiWang1999
    LeiWang1999 committed Sep 29, 2024
    Configuration menu
    Copy the full SHA
    c485b68 View commit details
    Browse the repository at this point in the history

  4. hardware tuning demo

    @LeiWang1999
    LeiWang1999 committed Sep 29, 2024
    Configuration menu
    Copy the full SHA
    ebe42a6 View commit details
    Browse the repository at this point in the history

  5. Merge branch 'main' of https://github.com/microsoft/BitBLAS into tl_o… 

    …ps_dynamic
    @LeiWang1999
    LeiWang1999 committed Sep 29, 2024
    Configuration menu
    Copy the full SHA
    88230ec View commit details
    Browse the repository at this point in the history

Commits on Sep 30, 2024

  1. remove debug related items.

    @LeiWang1999
    LeiWang1999 committed Sep 30, 2024
    Configuration menu
    Copy the full SHA
    44246a1 View commit details
    Browse the repository at this point in the history

Commits on Oct 1, 2024

  1. imlement tuner and cache fix

    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    bb51e15 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' of https://github.com/microsoft/BitBLAS into tl_o… 

    …ps_dynamic
    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    f42a3b9 View commit details
    Browse the repository at this point in the history

  3. lint fix

    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    de7ae18 View commit details
    Browse the repository at this point in the history

  4. test case fix.

    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    ef40bd8 View commit details
    Browse the repository at this point in the history

  5. Adapt Tuning Space generation with Roller

    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    85f0a5f View commit details
    Browse the repository at this point in the history

  6. Merge branch 'main' of https://github.com/microsoft/BitBLAS into tl_o… 

    …ps_dynamic
    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    e9f7db3 View commit details
    Browse the repository at this point in the history

  7. lint fix

    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    9e31336 View commit details
    Browse the repository at this point in the history

  8. Refactor select_scheduler function for fine-grained interface 

    The select_scheduler function in the dense/__init__.py module has been refactored to use a fine-grained interface. This change provides more flexibility and enables the implementation of high-performance kernels.

Update MatmulScheduler class in matmul_tensorcore.py

The MatmulScheduler class in the matmul_tensorcore.py module has been updated to calculate the number of threads based on the block size and warp size. This ensures optimal GPU warp configuration for NVIDIA GPUs.

Improve test_general_matmul_tilelang_kernel.py

The test_general_matmul_tilelang_kernel.py module has been improved to include additional test cases and assertions for correctness.
    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    2f1a260 View commit details
    Browse the repository at this point in the history

  9. Refactor select_scheduler function for fine-grained interface

    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    f1378d4 View commit details
    Browse the repository at this point in the history

  10. Refactor NotImplementedError message in BaseTLHint class

    @LeiWang1999
    LeiWang1999 committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    137cce3 View commit details
    Browse the repository at this point in the history

Commits on Oct 2, 2024

  1. Update submodule reference in 3rdparty/tvm

    @LeiWang1999
    LeiWang1999 committed Oct 2, 2024
    Configuration menu
    Copy the full SHA
    fc19fa2 View commit details
    Browse the repository at this point in the history

  2. Refactor matmul_finetune function to use topk=20 for hardware-aware f… 

    …inetuning
    @LeiWang1999
    LeiWang1999 committed Oct 2, 2024
    Configuration menu
    Copy the full SHA
    fe51bb1 View commit details
    Browse the repository at this point in the history

  3. Refactor submodule reference in 3rdparty/tvm

    @LeiWang1999
    LeiWang1999 committed Oct 2, 2024
    Configuration menu
    Copy the full SHA
    79878cb View commit details
    Browse the repository at this point in the history

  4. lint fix

    @LeiWang1999
    LeiWang1999 committed Oct 2, 2024
    Configuration menu
    Copy the full SHA
    0fc7ab9 View commit details
    Browse the repository at this point in the history

  5. Refactor test_general_matmul_tilelang_impl.py and test_tilelang_gemm.py

    @LeiWang1999
    LeiWang1999 committed Oct 2, 2024
    Configuration menu
    Copy the full SHA
    255e925 View commit details
    Browse the repository at this point in the history