Refactor the design of DeviceGemmMultipleDMultipleR_Xdl_CShuffle (#378)

This commit is contained in:
Po Yen Chen
2022-08-24 23:12:54 +08:00
committed by GitHub
parent fa2d894be1
commit 88e43744d8
7 changed files with 123 additions and 261 deletions

View File

@@ -4,6 +4,8 @@
#pragma once
#include <cstdlib>
#include <memory>
#include <vector>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"