ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-05 06:01:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Tensile-style block to C tile map (#239)

Browse Source 
* fix build

* Revert "fix build"

This reverts commit d73102384b.

* post PR #235 merge fix

* amend

* adds tensile-stype c-tile map

* make it dynamic version

* add k-split flavor tile map

* apply tensile-style tile map to all xdl gridwise gemms

* remove dead code

Co-authored-by: Chao Liu <chao.liu2@amd.com>
This commit is contained in:
Anthony Chang
2022-05-25 10:55:22 +08:00
committed by GitHub
parent 61851ae2b9
commit e579c9e5c6
11 changed files with 481 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
include/ck/tensor_operation/gpu/device/device_grouped_gemm_xdl.hpp
View File

@@ -346,7 +346,6 @@ struct DeviceGroupedGemmXdl
return block_2_ctile_map_.CheckValidity(c_grid_desc_m_n);
}
private:
typename GridwiseGemm::DefaultBlock2CTileMap block_2_ctile_map_;
ck::index_t BlockStart_;
};
@@ -418,9 +417,8 @@ struct DeviceGroupedGemmXdl
DeviceGroupedGemmXdl::MakeCGridDescriptor_M_N(M, N, StrideC);
const index_t grid_size_grp =
typename GroupedGemmBlock2CTileMap::UnderlyingBlock2CTileMap(
c_grid_desc_m_n_, M01, N01)
.CalculateGridSize(c_grid_desc_m_n_);
GroupedGemmBlock2CTileMap(c_grid_desc_m_n_, M01, N01, 0)
.block_2_ctile_map_.CalculateGridSize(c_grid_desc_m_n_);
const index_t BlockStart = grid_size_;
const index_t BlockEnd = grid_size_ + grid_size_grp;