mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-19 22:39:03 +00:00

Files

Mateusz Ozga 30ab1d6a71 [CK_TILE] Multiple-ABD GEMM example (#2788 )

* Multi ABD - initial commit

* Clang-foramt fix

* block gemm, unify the name of CDataType

* Apply chnages to mem-pipeline

* Rollback prefix for DType and Layout

* Gemm Kernel Basic, rename

* WMMA config

* Grouped GEMM

* Clang-format

* Dropout, name

* Review v2

* Move element_wise fn to unnary, remov old ones fn

* clang-format

* Fix issue review

* WP operator adjust to universal gemm

* v2 prepare

* Remove unused comment

* Remove vectorsize

* Rollback

* Adjust pipeline for abd

* Shuffle argument

* CI-fail fix quant

* Fix ag_br pipeline

* Failing tests

* Typo

* Single argument support

2025-09-19 01:14:11 +02:00

algorithm

refactor: use snake_case naming in ck_tile/core components (#2766 )

2025-09-03 09:34:11 +02:00

arch

Extend XDL kernel to Support RDNA3/4 - Part 5 (#2725 )

2025-09-15 10:59:25 -07:00

container

[CK_TILE] Add permuteN optimization to remove lds operation in c_shuffle (#2764 )

2025-09-08 22:02:48 -07:00

numeric

[CK_TILE] Refine pk_fp4's fill, pack, and unpack (#2845 )

2025-09-17 10:54:06 +08:00

tensor

[CK_TILE] Multiple-ABD GEMM example (#2788 )

2025-09-19 01:14:11 +02:00

utility

Fix UB caused by reinterpret_cast (#2849 )

2025-09-18 07:12:37 -07:00

config.hpp

Fix formatting problem (#2768 )

2025-09-02 14:14:10 +03:00

README.md

introducing ck_tile! (#1216 )

2024-04-15 19:27:12 -05:00

README.md

ck_tile/core

ck_tile/core contains every basic functions and structures to create a GPU kernel using ck_tile. User should only include ck_tile/core.hpp this single header to use all the functionality. Everything is under ck_tile namespace. The coding style under this folder should be similar to std (snake_case for structure/function, Camel for template types...)

algorithm/
    coordinate transform and some other reusable algorithm
arch/
    contains some basic device building block like mma, buffer addressing, etc...
container/
    contains basic container data structure, array/sequence/tuple/...
numeric/
    data type, and data type related math
tensor/
    tensor descriptors and tile level API
utility/
    other utility function for both host/device