reorganize example 2

example/01_gemm/gemm_xdl_fp64.cpp

@@ -25,6 +25,11 @@ using F64 = double;
 using F32 = float;
 using F16 = ck::half_t;
 
+using ADataType   = double;
+using BDataType   = double;
+using CDataType   = double;
+using AccDataType = double;
+
 using Row = ck::tensor_layout::gemm::RowMajor;
 using Col = ck::tensor_layout::gemm::ColumnMajor;
 
@@ -46,28 +51,11 @@ using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemmXdl
 //##########|  Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise|Spacialization|  Size| Block| Block| Block|   |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| SrcDstVectorDim|       DstScalar|
 //##########|      |      |      |        |        |        |        |   Operation|   Operation|   Operation|              |      |      |      |      |   |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |                |       PerVector|
 //##########|      |      |      |        |        |        |        |            |            |            |              |      |      |      |      |   |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |                |                |
-#if 0
              <  F64,   F64,   F64,     F64,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   64,    32,    32,     4,  1,   16,   16,    2,    2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              1,      true,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              1,      true,               7,               1>;
-using ADataType   = double;
-using BDataType   = double;
-using CDataType   = double;
-using AccDataType = double;
-#else
-            <   F32,   F32,   F32,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   64,    32,    32,     4,  1,   16,   16,    2,    2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              1,      true,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              1,      true,               7,               1>;
-using ADataType   = float;
-using BDataType   = float;
-using CDataType   = float;
-using AccDataType = float;
-#endif
-    // clang-format on
-
-    using ReferenceGemmInstance = ck::tensor_operation::host::ReferenceGemm<ADataType,
-                                                                            BDataType,
-                                                                            CDataType,
-                                                                            AccDataType,
-                                                                            AElementOp,
-                                                                            BElementOp,
-                                                                            CElementOp>;
+// clang-format on
+
+using ReferenceGemmInstance = ck::tensor_operation::host::
+    ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>;
 
 template <typename DataType>
 std::ostream& show_2d_matrix(std::ostream& os, Tensor<DataType>& matrix)