[CK_TILE] Multiple-D GEMM example (#2219)

* Multiple d, initial commit

* Check Ds Layout

* Readme and clang format

* Update branch & conflicts

* Multiple D - fix clang-formatter

* Rename elemetwise_op

* Fix CI

* Code review part1

* Remove printf

* Remove unnecessary comment

* Add new tests with Col layout

* Review part 2

* Added support for Multiple D GEMM

* Update comment

* Remove maybe_unused

* Clang-format

* Review part 3

* Add comment to function

* Add comment to function: another

* Take number of params for a refrence function

* Remove additional d param for 0 tensor

* Change name of function

* Fix CI fails

example/ck_tile/17_grouped_gemm/grouped_gemm.hpp

@@ -7,7 +7,8 @@
 
 #include "ck_tile/core.hpp"
 #include "ck_tile/host/kernel_launch.hpp"
-#include "ck_tile/ops/gemm/kernel/grouped_gemm_kernel.hpp"
+#include "ck_tile/ops/gemm.hpp"
+#include "ck_tile/ops/elementwise/unary_element_wise_operation.hpp"
 
 #define CK_TILE_PIPELINE_COMPUTE_V3 1
 #define CK_TILE_PIPELINE_MEMORY 2
@@ -53,7 +54,7 @@ using BDataType   = Types::BDataType;
 using AccDataType = Types::AccDataType;
 using CDataType   = Types::CDataType;
 
-using grouped_gemm_kargs = ck_tile::GemmHostArgs;
+using grouped_gemm_kargs = ck_tile::GemmHostArgs</*NumDTensor = 0*/>;
 
 auto create_args(int argc, char* argv[])
 {
@@ -82,7 +83,17 @@ inline std::size_t get_workspace_size(const std::vector<grouped_gemm_kargs>& gem
     return gemm_descs.size() * sizeof(ck_tile::GemmTransKernelArg);
 }
 
-template <typename ALayout, typename BLayout, typename CLayout>
+template <typename ADataType,
+          typename BDataType,
+          typename DsDataType,
+          typename AccDataType,
+          typename CDataType,
+          typename ALayout,
+          typename BLayout,
+          typename DsLayout,
+          typename CLayout,
+          bool Persistent,
+          typename CDEElementWise>
 float grouped_gemm(const std::vector<grouped_gemm_kargs>& gemm_descs,
                    const ck_tile::stream_config& s,
                    void* kargs_ptr);