Change GridwiseOp nam

include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp

@@ -526,7 +526,7 @@ struct DeviceBatchedContractionMultipleD_Wmma_CShuffle
     using BGridDesc = decltype(DeviceOp::MakeBGridDescriptor({}, {}));
 
     // GridwiseOp
-    using GridwiseOp = GridwiseGemmMultipleD_k0mk1_k0nk1_mn_wmma_cshuffle<
+    using GridwiseOp = GridwiseGemmMultipleD_Wmma<
         // DataType Family
         ADataType,
         BDataType,

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_wmma_cshuffle.hpp

@@ -286,7 +286,7 @@ struct DeviceBatchedGemmSoftmaxGemmPermute_Wmma_CShuffle
     };
 
     // GridwiseOp
-    using GridwiseOp = GridwiseBatchedGemmSoftmaxGemm_Wmma_CShuffle<
+    using GridwiseOp = GridwiseBatchedGemmSoftmaxGemm_Wmma<
         // DataType Family
         ADataType,
         B0DataType,

include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp

@@ -263,7 +263,7 @@ struct DeviceGemmMultipleD_Wmma_CShuffle : public DeviceGemmMultipleD<ALayout,
     using EGridDesc_M_N  = decltype(MakeEGridDescriptor_M_N<ELayout>(1, 1, 1));
 
     // GridwiseOp
-    using GridwiseOp = GridwiseGemmMultipleD_k0mk1_k0nk1_mn_wmma_cshuffle<
+    using GridwiseOp = GridwiseGemmMultipleD_Wmma<
         // DataType Family
         ADataType,
         BDataType,

include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp

@@ -222,7 +222,7 @@ struct DeviceGemmWmma_CShuffle : public DeviceGemm<ALayout,
     using CGridDesc_M_N = decltype(MakeCGridDescriptor_M_N(1, 1, 1));
 
     // GridwiseGemm
-    using GridwiseGemm = GridwiseGemm_k0mk1_k0nk1_mn_wmma<
+    using GridwiseGemm = GridwiseGemm_Wmma<
         BlockSize,
         ADataType,
         BDataType,

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp

@@ -323,7 +323,7 @@ struct DeviceGroupedConvFwdMultipleD_Wmma_CShuffle
     using BGridDesc = decltype(DeviceOp::MakeBGridDescriptor<BLayout>({}, {}));
 
     // GridwiseOp
-    using GridwiseOp = GridwiseGemmMultipleD_k0mk1_k0nk1_mn_wmma_cshuffle<
+    using GridwiseOp = GridwiseGemmMultipleD_Wmma<
         // DataType Family
         ADataType,
         BDataType,

include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_wmma_cshuffle.hpp

@@ -182,7 +182,7 @@ template <typename ADataType,
           index_t NumGemmKPrefetchStage = 1,
           LoopScheduler LoopSched       = make_default_loop_scheduler(),
           PipelineVersion PipelineVer   = PipelineVersion::v1>
-struct GridwiseBatchedGemmSoftmaxGemm_Wmma_CShuffle
+struct GridwiseBatchedGemmSoftmaxGemm_Wmma
 {
     static constexpr auto I0 = Number<0>{};
     static constexpr auto I1 = Number<1>{};

include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp

@@ -321,7 +321,7 @@ template < // DataType Family
     index_t NumGemmKPrefetchStage = 1,
     LoopScheduler LoopSched       = make_default_loop_scheduler(),
     PipelineVersion PipelineVer   = PipelineVersion::v1>
-struct GridwiseGemmMultipleD_k0mk1_k0nk1_mn_wmma_cshuffle
+struct GridwiseGemmMultipleD_Wmma
 {
     static constexpr index_t NumDTensor = DsDataType::Size();
 

include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp

@@ -119,7 +119,7 @@ template <index_t BlockSize,
           index_t NumGemmKPrefetchStage = 1,
           LoopScheduler LoopSched       = make_default_loop_scheduler(),
           PipelineVersion PipelineVer   = PipelineVersion::v1>
-struct GridwiseGemm_k0mk1_k0nk1_mn_wmma
+struct GridwiseGemm_Wmma
 {
     static constexpr auto I0 = Number<0>{};
     static constexpr auto I1 = Number<1>{};