remove unnecessary changes

include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -944,5 +941,3 @@ struct DeviceConv2dFwdXdl_C_Shuffle_Bias_Activation_Input_N_Hi_Wi_C_Weight_K_Y_X
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -910,5 +907,3 @@ struct DeviceConv2dFwdXdl_C_Shuffle_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_W
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -681,5 +678,3 @@ struct DeviceConv2dFwdXdl_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -270,5 +267,3 @@ struct DeviceConv3dFwdNaive_Input_N_Di_Hi_Wi_C_Weight_K_Z_Y_X_C_Output_N_Do_Ho_W
 } // namespace tensor_operation
 } // namespace ck
 #endif
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -40,7 +37,7 @@ template <typename GridwiseGemm,
           bool HasMainKBlockLoop>
 __global__ void
 #if CK_USE_LAUNCH_BOUNDS
-    __launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
+__launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
 #endif
     kernel_gemm_xdlops_v2r3_for_conv3d(
         const FloatAB* __restrict__ p_a_grid,
@@ -664,5 +661,3 @@ struct DeviceConv3dFwdXdl_Input_N_Di_Hi_Wi_C_Weight_K_Z_Y_X_C_Output_N_Do_Ho_Wo_
 } // namespace tensor_operation
 } // namespace ck
 #endif
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -1590,5 +1587,3 @@ struct DeviceConvNdBwdDataNwcKxcNwk_Dl
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -1477,5 +1474,3 @@ struct DeviceConvNdBwdDataNwcKxcNwk_Xdl
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_elementwise_2d_impl.hpp

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -340,5 +337,3 @@ struct DeviceElementwise2dImpl : public DeviceElementwise<InDataTypeTuple,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -305,5 +302,3 @@ struct DeviceElementwiseImpl
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -598,5 +595,3 @@ struct DeviceElementwiseNormalizationImpl
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -890,5 +887,3 @@ struct DeviceGemmBiasAddReduce_Xdl_CShuffle : public DeviceGemmReduce<1, ReduceO
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -615,5 +612,3 @@ struct DeviceGemmDl : public DeviceGemm<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -37,7 +34,7 @@ template <typename GridwiseGemm,
           bool HasDoubleTailKBlockLoop>
 __global__ void
 #if CK_USE_LAUNCH_BOUNDS
-    __launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
+__launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
 #endif
     kernel_gemm_dl_multiple_d(
         const ABDataType* __restrict__ p_a_grid,
@@ -675,5 +672,3 @@ struct DeviceGemmMultipleD_Dl : public DeviceGemmMultipleD<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -40,7 +37,7 @@ template <typename GridwiseGemmWelford,
           bool HasMainKBlockLoop>
 __global__ void
 #if CK_USE_LAUNCH_BOUNDS
-    __launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
+__launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
 #endif
     kernel_gemm_multiple_d_welford_first_half_xdl_cshuffle(
         const ABDataType* __restrict__ p_a_grid,
@@ -61,8 +58,7 @@ __global__ void
             e_grid_desc_mblock_mperblock_nblock_nperblock,
         const MeanVarGridDescriptor_MBlock_MPerBlock_NBlock
             mean_var_grid_desc_mblock_mperblock_nblock,
-            const CountGridDescriptor_MBlock_MPerBlock_NBlock
-                count_grid_desc_mblock_mperblock_nblock,
+        const CountGridDescriptor_MBlock_MPerBlock_NBlock count_grid_desc_mblock_mperblock_nblock,
         const Block2ETileMap block_2_etile_map,
         index_t NRaw)
 {
@@ -125,7 +121,7 @@ template <typename GridwiseWelfordLayernorm,
           typename HElementwiseOperation>
 __global__ void
 #if CK_USE_LAUNCH_BOUNDS
-    __launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
+__launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
 #endif
     kernel_welford_layernorm2d_second_half(
         const EMeanVarDataType* __restrict__ p_e_grid,
@@ -1089,5 +1085,3 @@ struct DeviceGemmMultipleDLayernorm_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -41,7 +38,7 @@ template <typename GridwiseGemm,
           bool HasMainKBlockLoop>
 __global__ void
 #if CK_USE_LAUNCH_BOUNDS
-    __launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
+__launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
 #endif
     kernel_gemm_multiple_d_multiple_r_xdl_cshuffle(
         const FloatAB* __restrict__ p_a_grid,
@@ -695,5 +692,3 @@ struct DeviceGemmMultipleDMultipleR_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -708,5 +705,3 @@ struct DeviceGemmMultipleD_Wmma_CShuffle : public DeviceGemmMultipleD<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -818,7 +815,7 @@ struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout,
     }
 
     template <class Desc, class DsPointer>
-    __device__ static void Run(Desc desc,
+    __device__ static void Run(const Desc& desc,
                                const ADataType* __restrict__ p_a_grid,
                                const BDataType* __restrict__ p_b_grid,
                                DsPointer p_ds_grid,
@@ -866,5 +863,3 @@ struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -850,5 +847,3 @@ struct DeviceGemmReduce_Xdl_CShuffle : public DeviceGemmReduce<0, ReduceOperatio
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -608,5 +605,3 @@ struct DeviceGemmWmma_CShuffle : public DeviceGemm<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
@@ -307,5 +304,3 @@ struct DeviceGemmXdl : public DeviceGemm<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop