ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-24 14:54:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add host lib (#1134)

Browse Source 
* Format

* Format

* Format

* Remove const

* Use the right template

* Format

* Format

* add row/col instances

* Add missing file

* fixed

* Format

* Updates

* Format

* fixed rrr layout

* Format

* Update test and embed modules

* Restore older version

* Update year

* Set -fPIC

* Format

* Use double for isnan

* rename host folder to codegen + minor fix

* add codegen CI test

* add option to build components without building CK

* fix the groovy syntax

* fix typo

* use the correct function for the codegen stage

---------

Co-authored-by: Jing Zhang <jizha@amd.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>

[ROCm/composable_kernel commit: 8eff4d62b6]
This commit is contained in:
Paul Fultz II
2024-03-05 19:08:43 -06:00
committed by GitHub
parent 7241d5ad6a
commit 871810b885
33 changed files with 3170 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
codegen/include/ck/host/operation/gemm.hpp Normal file
View File

@@ -0,0 +1,49 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
#include <string>
namespace ck {
namespace host {
namespace operation {
struct TileDesc
{
int block_size = 0;
int m_per_block = 0;
int n_per_block = 0;
int k_per_block = 0;
int ak1 = 0;
int bk1 = 0;
int m_per_XDL = 0;
int n_per_XDL = 0;
int m_Xdl_per_wave = 0;
int n_Xdl_per_wave = 0;
int num_gemmk_prefetch_stage = 0;
};
struct BlockTransferDesc
{
std::string thread_cluster_length = "";
std::string thread_cluster_arrange_order = "";
std::string src_access_order = "";
int src_vec_dim = 0;
int src_scalar_per_vector = 0;
int dst_scalar_per_vector_k1 = 0;
int lds_add_extra_dim = 0;
};
struct CShuffleDesc
{
int m_Xdl_per_wave_per_shuffle = 0;
int n_Xdl_per_wave_per_shuffle = 0;
};
struct CBlockTransferDesc
{
std::string cluster_lengths_m_block_m_wave_m_per_Xdl_n_block_n_wave_n_per_Xdl = "";
int scalar_per_vector_n_wave_n_per_Xdl = 0;
};
} // namespace operation
} // namespace host
} // namespace ck