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

Files

Max Podkorytov 2570462ecf [CK_TILE] Fix transpose_vectors for 2x2 8-bit tiles (#3042 )

fix transpose_vectors logic for 2x2 8-bit tiles

    add a test which goes through this code path.

    factor out constexpr'd cases into smaller functions.

    add inline docs about the data movement

    impact: gemms with 8-bit non-rcr inputs on gfx942

2025-10-20 13:40:44 -07:00

algorithm

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

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

arch

[CK_TILE] Patch for pk_fp4 ref check and buffer load. (#3044 )

2025-10-20 14:47:04 +08:00

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] fix pk_fp4 compilation for non-gfx950 GPUs (#2983 )

2025-10-09 07:43:41 -07:00

tensor

Fix for Add the API to load SGPR (#2913 )

2025-09-25 10:32:42 -07:00

utility

[CK_TILE] Fix transpose_vectors for 2x2 8-bit tiles (#3042 )

2025-10-20 13:40:44 -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