mirror of
https://github.com/tile-ai/tilelang.git
synced 2026-10-21 06:40:23 +08:00
fe5bf3569d
* enhance `T.alloc_barrier` and let `T.wait/arrive` only accept buffers * lint * Refactor mbarrier handling and update related documentation - Updated the `T.alloc_barrier` function to accept an array of arrive counts instead of individual thread counts. - Modified the `get_mbarrier` function documentation to clarify its purpose and usage. - Enhanced the `CreateMBarrierBuffer` function to create mbarrier buffers with shared storage scope. - Updated tests to reflect changes in mbarrier allocation and usage. - Adjusted comments in various files to improve clarity regarding mbarrier functionality. * lint * fix test * tcgen5 check input * lint * fix name conflict * add name check * apply ai suggestions * fix shared mem disalignment and missing fence for mbarrier init * fix cutedsl codegen * bugfix * add test for cutedsl codegen * Update testing/python/jit/test_tilelang_jit_cutedsl.py Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * Remove tilelang.disable_cache() call Remove cache disabling from the test file. --------- Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Co-authored-by: Lei Wang <34334180+LeiWang1999@users.noreply.github.com>