mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 08:50:17 +00:00
4750b293fe
* 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
24 lines
783 B
CMake
24 lines
783 B
CMake
add_subdirectory(image_to_column)
|
|
add_subdirectory(gemm)
|
|
add_subdirectory(gemm_weight_preshuffle)
|
|
add_subdirectory(batched_gemm)
|
|
add_subdirectory(grouped_gemm)
|
|
add_subdirectory(gemm_multi_d)
|
|
add_subdirectory(data_type)
|
|
add_subdirectory(container)
|
|
add_subdirectory(elementwise)
|
|
# Not including these tests as there is a bug on gfx90a and gfx942
|
|
# resulting in "GPU core dump"
|
|
#add_subdirectory(moe_smoothquant)
|
|
add_subdirectory(permute)
|
|
add_subdirectory(moe_sorting)
|
|
add_subdirectory(slice_tile)
|
|
add_subdirectory(memory_copy)
|
|
add_subdirectory(batched_transpose)
|
|
add_subdirectory(smoothquant)
|
|
add_subdirectory(topk_softmax)
|
|
add_subdirectory(add_rmsnorm2d_rdquant)
|
|
# add_subdirectory(layernorm2d)
|
|
# add_subdirectory(rmsnorm2d)
|
|
add_subdirectory(gemm_block_scale)
|
|
add_subdirectory(reduce) |