fix clang format (#740)

include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp

@@ -611,7 +611,8 @@ struct DeviceGroupedGemmSoftmaxGemmPermute_Xdl_CShuffle
                 some_has_main_k_block_loop |= y;
             }
 
-            hipGetErrorString(hipMemcpyWithStream(arg.p_workspace_,
+            hipGetErrorString(
+                hipMemcpyWithStream(arg.p_workspace_,
                                     arg.group_kernel_args_.data(),
                                     arg.group_kernel_args_.size() * sizeof(GroupKernelArg),
                                     hipMemcpyHostToDevice,

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

@@ -597,7 +597,8 @@ struct DeviceGroupedGemmMultipleD_Dl : public DeviceGroupedGemm<ALayout,
                 }
             }
 
-            hipGetErrorString(hipMemcpyWithStream(arg.p_workspace_,
+            hipGetErrorString(
+                hipMemcpyWithStream(arg.p_workspace_,
                                     arg.gemm_desc_kernel_arg_.data(),
                                     arg.gemm_desc_kernel_arg_.size() * sizeof(GemmKernelArg),
                                     hipMemcpyHostToDevice,

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

@@ -548,10 +548,10 @@ struct DeviceGroupedGemm_Xdl : public DeviceGroupedGemm<ALayout,
                 }
             }
 
-            hipGetErrorString(
-                hipMemcpyWithStream(arg.p_workspace_,
+            hipGetErrorString(hipMemcpyWithStream(arg.p_workspace_,
                                                   arg.gemm_desc_kernel_arg_.data(),
-                                    arg.gemm_desc_kernel_arg_.size() * sizeof(GemmBiasTransKernelArg),
+                                                  arg.gemm_desc_kernel_arg_.size() *
+                                                      sizeof(GemmBiasTransKernelArg),
                                                   hipMemcpyHostToDevice,
                                                   stream_config.stream_id_));
 

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

@@ -406,7 +406,8 @@ struct DeviceGroupedGemmXdlSplitKCShuffle : public DeviceGroupedGemmSplitK<ALayo
                 }
             }
 
-            hip_check_error(hipMemcpyWithStream(arg.p_workspace_,
+            hip_check_error(
+                hipMemcpyWithStream(arg.p_workspace_,
                                     arg.gemm_kernel_args_.data(),
                                     arg.gemm_kernel_args_.size() * sizeof(GemmTransKernelArg),
                                     hipMemcpyHostToDevice,