remove unnecessary changes

include/ck/tensor_operation/gpu/device/impl/device_gemm_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.
 
@@ -308,5 +305,3 @@ struct DeviceGemm_Xdl_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_layernorm_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.
 
@@ -783,5 +780,3 @@ struct DeviceGemmLayerNorm_Xdl_CShuffle : public BaseOperator
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_skip_b_lds.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.
 
@@ -532,5 +529,3 @@ struct DeviceGemmXdlSkipBLds : public DeviceGemm<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.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.
 
@@ -331,5 +328,3 @@ struct DeviceGemmXdlSplitKCShuffle : public DeviceGemmSplitK<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_waveletmodel_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.
 
@@ -37,10 +34,9 @@ template <typename GridwiseGemm,
           bool HasMainKBlockLoop>
 __global__ void
 #if CK_USE_LAUNCH_BOUNDS
-    __launch_bounds__(CK_WAVELET_MAX_THREAD_PER_BLOCK, CK_WAVELET_MIN_BLOCK_PER_CU)
+__launch_bounds__(CK_WAVELET_MAX_THREAD_PER_BLOCK, CK_WAVELET_MIN_BLOCK_PER_CU)
 #endif
-        kernel_gemm_xdl_waveletmodel_cshuffle(
-            const ABDataType* __restrict__ p_a_grid,
+    kernel_gemm_xdl_waveletmodel_cshuffle(const ABDataType* __restrict__ p_a_grid,
                                           const ABDataType* __restrict__ p_b_grid,
                                           EDataType* __restrict__ p_e_grid,
                                           const AElementwiseOperation a_element_op,
@@ -533,5 +529,3 @@ struct DeviceGemm_Xdl_WaveletModel_CShuffle : public DeviceGemm<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_contraction_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.
 
@@ -31,7 +28,7 @@ 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_grouped_contraction_multiple_d_xdl_cshuffle(
         const void CK_CONSTANT_ADDRESS_SPACE* contraction_args,
@@ -915,5 +912,3 @@ struct DeviceGroupedContractionMultipleD_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.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.
 
@@ -113,7 +110,7 @@ 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_grouped_conv_bwd_data_multiple_d_xdl_cshuffle(
         const ABDataType* __restrict__ p_a_grid,
@@ -1080,5 +1077,3 @@ struct DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_gnwc_gkxc_gnwk_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.
 
@@ -62,7 +59,7 @@ 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_batched_gemm_dlops_bwd_weight(
         const FloatAB* __restrict__ p_a_grid,
@@ -1228,5 +1225,3 @@ struct DeviceGroupedConvBwdWeightGnwcGkxcGnwk_Dl
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_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.
 
@@ -64,10 +61,9 @@ 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_batched_gemm_xdlops_bwd_weight(
-            const FloatAB* __restrict__ p_a_grid,
+    kernel_batched_gemm_xdlops_bwd_weight(const FloatAB* __restrict__ p_a_grid,
                                           const FloatAB* __restrict__ p_b_grid,
                                           FloatC* __restrict__ p_c_grid,
                                           const AElementwiseOperation a_element_op,
@@ -1526,5 +1522,3 @@ struct DeviceGroupedConvBwdWeight_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_multiple_d_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.
 
@@ -16,7 +13,6 @@
 #include "ck/host_utility/io.hpp"
 #endif
 
-
 #include "ck/utility/common_header.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
@@ -121,7 +117,7 @@ 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_grouped_conv_fwd_dl_multiple_d(
         const ABDataType* __restrict__ p_a_grid,
@@ -970,5 +966,3 @@ struct DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_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.
 
@@ -96,7 +93,7 @@ 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_grouped_conv_fwd_dl(
         const ABDataType* __restrict__ p_a_grid,
@@ -780,7 +777,6 @@ struct DeviceGroupedConvFwdDl_NHWC_KYXC_NHWK : public DeviceGroupedConvFwd<NDimS
     static auto MakeInvoker() { return Invoker{}; }
 #endif
 
-
     std::unique_ptr<BaseArgument>
     MakeArgumentPointer(const void* p_a,
                         const void* p_b,
@@ -856,5 +852,3 @@ struct DeviceGroupedConvFwdDl_NHWC_KYXC_NHWK : public DeviceGroupedConvFwd<NDimS
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r.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.
 
@@ -78,5 +75,3 @@ struct DeviceGroupedConvFwdMultipleDMultipleR : public BaseOperator
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_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.
 
@@ -134,7 +131,7 @@ 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_batch_gemm_multiple_d_xdl_cshuffle(
         const ABDataType* __restrict__ p_a_grid,
@@ -1119,5 +1116,3 @@ struct DeviceGroupedConvFwdMultipleDMultipleR_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_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.
 
@@ -856,5 +853,3 @@ struct DeviceGroupedConvFwdMultipleD_Wmma_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_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.
 
@@ -118,7 +115,7 @@ 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_grouped_conv_fwd_multiple_d_xdl_cshuffle(
         const ABDataType* __restrict__ p_a_grid,
@@ -968,5 +965,3 @@ struct DeviceGroupedConvFwdMultipleD_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 #pragma once
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
@@ -34,7 +31,7 @@ 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_grouped_gemm_multiple_d_dl(const void CK_CONSTANT_ADDRESS_SPACE* gemm_descs_const,
                                       const index_t group_count,
@@ -768,5 +765,3 @@ struct DeviceGroupedGemmMultipleD_Dl : public DeviceGroupedGemm<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_softmax_gemm_permute_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.
 
@@ -35,7 +32,7 @@ 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_grouped_gemm_softmax_gemm_xdl_cshuffle_v1(
         const void CK_CONSTANT_ADDRESS_SPACE* group_kernel_args,
@@ -897,5 +894,3 @@ struct DeviceGroupedGemmSoftmaxGemmPermute_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 #pragma once
 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
@@ -33,7 +30,7 @@ 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_grouped_gemm_xdl(const void CK_CONSTANT_ADDRESS_SPACE* gemm_descs_const,
                             const index_t group_count,
@@ -723,5 +720,3 @@ struct DeviceGroupedGemm_Xdl : public DeviceGroupedGemm<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_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.
 
@@ -32,7 +29,7 @@ template <typename GridwiseGemm,
           InMemoryDataOperationEnum CGlobalMemoryDataOperation>
 __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_grouped_gemm_xdl_splitk(const void CK_CONSTANT_ADDRESS_SPACE* gemm_descs_const,
                                    const index_t group_count)
@@ -634,5 +631,3 @@ struct DeviceGroupedGemmXdlSplitKCShuffle : public DeviceGroupedGemmSplitK<ALayo
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.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.
 
@@ -596,5 +593,3 @@ struct DeviceMultipleReduceMultiBlock : public DeviceMultipleReduce<Rank,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop