pre-commited missing files

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

@@ -34,8 +34,7 @@ __global__ void
 #if CK_USE_LAUNCH_BOUNDS
     __launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
 #endif
-        kernel_grouped_gemm_xdl_splitk(
-            const void CK_CONSTANT_ADDRESS_SPACE* gemm_descs_const,
+        kernel_grouped_gemm_xdl_splitk(const void CK_CONSTANT_ADDRESS_SPACE* gemm_descs_const,
                                        const index_t group_count,
                                        const AElementwiseOperation a_element_op,
                                        const BElementwiseOperation b_element_op,

profiler/include/profiler/profile_grouped_gemm_two_stage_impl.hpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -226,7 +226,8 @@ bool profile_grouped_gemm_two_stage_impl(int do_verification,
 
         std::string gemm_name = gemm_ptr->GetTypeString();
 
-        using DeviceOpSplitK = ck::tensor_operation::device::DeviceGroupedGemmMultipleDSplitK<ALayout,
+        using DeviceOpSplitK =
+            ck::tensor_operation::device::DeviceGroupedGemmMultipleDSplitK<ALayout,
                                                                            BLayout,
                                                                            ck::Tuple<>,
                                                                            CLayout,
@@ -258,8 +259,10 @@ bool profile_grouped_gemm_two_stage_impl(int do_verification,
             dynamic_cast<DeviceOpSplitK*>(gemm_ptr.get())
                 ->SetKBatchSize(argument_ptr.get(), kbatch_curr);
 
-            DeviceMem gemm_arg_dev_mem(dynamic_cast<DeviceOpSplitK*>(gemm_ptr.get())->GetDeviceKernelArgSize(argument_ptr.get()));
-            dynamic_cast<DeviceOpSplitK*>(gemm_ptr.get())->SetDeviceKernelArgs(argument_ptr.get(), gemm_arg_dev_mem.GetDeviceBuffer());
+            DeviceMem gemm_arg_dev_mem(dynamic_cast<DeviceOpSplitK*>(gemm_ptr.get())
+                                           ->GetDeviceKernelArgSize(argument_ptr.get()));
+            dynamic_cast<DeviceOpSplitK*>(gemm_ptr.get())
+                ->SetDeviceKernelArgs(argument_ptr.get(), gemm_arg_dev_mem.GetDeviceBuffer());
 
             if(gemm_ptr->IsSupportedArgument(argument_ptr.get()))
             {