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

Files

Yi DING f0702c1636 [CK_TILE] Refine FP32 => FP16/BF16 Conversion (#3215 )

* [CK_TILE] Refine FP32 => FP16/BF16 Conversion

* Thank you Copilot

* Rename fix

* Fix example

* Fix accu checking

* Fix

* Fix

[ROCm/composable_kernel commit: 8b284a63a4]

2025-11-20 10:50:26 -08:00

algorithm

[CK_Tile] Merge multiple convolution groups into a single GEMM batch (#2986 )

2025-10-29 16:49:28 +02:00

arch

[CK_BUILDER] Add grouped conv fwd ck tile traits (#3183 )

2025-11-11 13:55:33 -08:00

container

[CK_TILE] Share partition index across threads and specify offset in load_tile()/async_load_tile()/load_tile_transpose() (#2905 )

2025-11-12 10:26:14 +08:00

numeric

[CK_TILE] Refine FP32 => FP16/BF16 Conversion (#3215 )

2025-11-20 10:50:26 -08:00

tensor

[CK_TILE] Refine FP32 => FP16/BF16 Conversion (#3215 )

2025-11-20 10:50:26 -08:00

utility

[CK_TILE] Improve device printing (#3198 )

2025-11-14 09:46:06 +08:00

config.hpp

Add support for RDNA1 GPUs (#3220 )

2025-11-20 10:45:57 -08:00

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