ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-19 22:39:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

General 2D Reduction Kernel (#2535)

Browse Source 
* General 2D Reduction Kernel

* Move the reduction kernel from the example
* Split the code and add the necessary policy, problem, shape files as
per ck_tile convention
* Add/modify the headers
* Modified the example to work with the 'new' kernel
* Added tests for the kernel
* N-D refernce reduce
* Added support for N-D input with transform to 2D
* Added padding to support various input sized tensors
* Bug fix in the thread buffer constructor
* Some comments to explain the reduce2d block kernel

* comments resolution

* clang-format

* comments resolution

* clang-format

* clang-format

* comments resolution

* clang-format
This commit is contained in:
Yashvardhan Agarwal
2025-08-06 16:36:59 +03:00
committed by GitHub
parent 2622ff06cb
commit 4750b293fe
14 changed files with 905 additions and 199 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
include/ck_tile/core/container/thread_buffer.hpp
View File

@@ -42,7 +42,11 @@ struct thread_buffer {
// TODO: this ctor can't ignore
CK_TILE_HOST_DEVICE constexpr thread_buffer() : data{} {}
CK_TILE_HOST_DEVICE constexpr thread_buffer(const value_type & o) : data{o} {}
CK_TILE_HOST_DEVICE constexpr thread_buffer(const value_type & o) : data{} {
static_for<0, N, 1>{}(
[&](auto i) { data[i] = o; }
);
}
CK_TILE_HOST_DEVICE static constexpr auto size() { return N; }
CK_TILE_HOST_DEVICE auto & get() {return data; }