mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 18:17:44 +00:00

Files

Yi DING ef32abc4cc [CK_TILE] FMHA BWD Optimization For GFX950 (#2628 )

* simplify fmha_bwd_kernel MakeKargs & dq_dram_window

* simply duplicate

* trload pipeline

* Try two-stage

* add prefetch

* optimize & iglp

[ROCm/composable_kernel commit: 4fde1646e5]

2025-08-12 11:11:55 +08:00

algorithm

[CK_TILE] Enable printing more structures in CK-Tile (#2443 )

2025-08-07 15:45:27 +03:00

arch

[CK_TILE] Enable printing more structures in CK-Tile (#2443 )

2025-08-07 15:45:27 +03:00

container

[CK_TILE] Enable printing more structures in CK-Tile (#2443 )

2025-08-07 15:45:27 +03:00

numeric

[CK_TILE] FMHA BWD Optimization For GFX950 (#2628 )

2025-08-12 11:11:55 +08:00

tensor

[CK_TILE] FMHA BWD Optimization For GFX950 (#2628 )

2025-08-12 11:11:55 +08:00

utility

Fixes to "General 2D Reduction Kernel" (#2535 ) (#2656 )

2025-08-11 15:01:33 +02:00

config.hpp

update the switch condition for buffer built-ins (#2602 )

2025-08-01 14:30:07 -07:00

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