add moegemm in device and grid

example/65_gemm_multiply_multiply/moe_gemm_fp16.cpp

@@ -8,7 +8,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_v3_b_preshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_moe_gemm.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_v3.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 #include "ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp"
@@ -125,7 +125,7 @@ static constexpr ck::index_t AK1 = 16 / sizeof(A0DataType);
 static constexpr ck::index_t BK1 = 16 / sizeof(B0DataType);
 static constexpr ck::index_t EVec = 16 / sizeof(EDataType);
 // using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShuffle_V3
-using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShuffle_V3_BPreshuffle
+using DeviceOpInstance = ck::tensor_operation::device::DeviceMoeGemm
     // clang-format off
 ///######|  ALayout|  BLayout| DsLayout| ELayout|      AData|      BData|     DsData|     EData|     AccData|         CShuffle|           A|           B|          CDE|           GEMM| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
 ///######|         |         |         |        |       Type|       Type|       Type|      Type|        Type|         DataType| 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| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
@@ -154,7 +154,7 @@ using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShu
                //    MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
                 //  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
                1,    1,   S<1, 32, 1, 8>, S<EVec, EVec, 1>,
-               ck::BlockGemmPipelineScheduler::Intrawave, ck::BlockGemmPipelineVersion::v1, A0DataType>;
+               ck::BlockGemmPipelineScheduler::Intrawave, ck::BlockGemmPipelineVersion::v1, true, A0DataType>;
         // kernel 2: 128->32x128x128
         //  <      Row,      Col, DsLayout, ELayout, A0DataType, B0DataType, DsDataType, EDataType, AccDataType, CShuffleDataType,  AElementOp,  BElementOp, CDEElementOp,       GemmSpec,   128,   32,   128,    128,  16,  16,  32,   32,    1,    2,     S<8, 16, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,          0,     S<8, 16, 1>,    S<1, 0, 2>,     S<1, 0, 2>,             2,              16,             16,          0,          1,           1,               S<1, 16, 1, 8>,      S<8, 8, 1>,  ck::BlockGemmPipelineScheduler::Interwave, ck::BlockGemmPipelineVersion::v1, EDataType>;