remove unnecessary changes

include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.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.
 
@@ -423,5 +420,3 @@ struct DeviceMultipleReduceThreadWise : public DeviceMultipleReduce<Rank,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_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.
 
@@ -403,5 +400,3 @@ struct DeviceNormalizationImpl : public DeviceNormalization<XDataType,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_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.
 
@@ -659,5 +656,3 @@ struct DeviceNormalizationSplitKImpl : public DeviceNormalization<XDataType,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_permute_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.
 
@@ -284,5 +281,3 @@ struct DevicePermuteImpl : DevicePermute<NumDim, InDataType, OutDataType, Elemen
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.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.
 
@@ -114,5 +111,3 @@ struct DevicePool2dFwd_NHWC_NHWC : public DevicePool3dFwd_NDHWC_NDHWC<InDataType
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.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.
 
@@ -412,5 +409,3 @@ struct DevicePool3dFwd_NDHWC_NDHWC : public DevicePoolFwd<5,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_reduce_common.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.
 
@@ -143,5 +140,3 @@ shuffle_tensor_dimensions(const std::array<index_t, Rank>& origLengthsStrides,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_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.
 
@@ -552,5 +549,3 @@ struct DeviceReduceMultiBlock : public DeviceReduce<InDataType,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.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.
 
@@ -394,5 +391,3 @@ struct DeviceReduceThreadWise : public DeviceReduce<InDataType,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_softmax_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.
 
@@ -390,7 +387,7 @@ struct DeviceSoftmaxImpl : public DeviceSoftmax<InDataType,
                                           acc_elementwise_op);
     };
 #ifndef __HIPCC_RTC__
-  static auto MakeInvoker() { return Invoker{}; }
+    static auto MakeInvoker() { return Invoker{}; }
 #endif
 
     std::unique_ptr<BaseInvoker> MakeInvokerPointer() override
@@ -419,5 +416,3 @@ struct DeviceSoftmaxImpl : public DeviceSoftmax<InDataType,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.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.
 
@@ -194,5 +191,3 @@ struct DeviceSparseEmbeddingsForwardLayernorm : public BaseOperator
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_splitk_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.
 
@@ -39,25 +36,25 @@ 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_contraction_multiple_d_xdl_cshuffle(
-            const FloatAB* __restrict__ p_a_grid,
-            const FloatAB* __restrict__ p_b_grid,
-            FloatDsPointer p_ds_grid,
-            FloatE* __restrict__ p_e_grid,
-            const index_t batch_count,
-            const AElementwiseOperation a_element_op,
-            const BElementwiseOperation b_element_op,
-            const CDEElementwiseOperation cde_element_op,
-            const AGridDesc_AKB_AK0_M_AK1 a_grid_desc_akb_ak0_m_ak1,
-            const BGridDesc_BKB_BK0_N_BK1 b_grid_desc_bkb_bk0_n_bk1,
-            const DsGridDescriptor_MBlock_MPerBlock_NBlock_NPerBlock
-                ds_grid_desc_mblock_mperblock_nblock_nperblock,
-            const EGridDescriptor_MBlock_MPerBlock_NBlock_NPerBlock
-                e_grid_desc_mblock_mperblock_nblock_nperblock,
-            const ComputePtrOffsetOfBatch compute_ptr_offset_of_batch,
-            const Block2ETileMap block_2_etile_map)
+    kernel_contraction_multiple_d_xdl_cshuffle(
+        const FloatAB* __restrict__ p_a_grid,
+        const FloatAB* __restrict__ p_b_grid,
+        FloatDsPointer p_ds_grid,
+        FloatE* __restrict__ p_e_grid,
+        const index_t batch_count,
+        const AElementwiseOperation a_element_op,
+        const BElementwiseOperation b_element_op,
+        const CDEElementwiseOperation cde_element_op,
+        const AGridDesc_AKB_AK0_M_AK1 a_grid_desc_akb_ak0_m_ak1,
+        const BGridDesc_BKB_BK0_N_BK1 b_grid_desc_bkb_bk0_n_bk1,
+        const DsGridDescriptor_MBlock_MPerBlock_NBlock_NPerBlock
+            ds_grid_desc_mblock_mperblock_nblock_nperblock,
+        const EGridDescriptor_MBlock_MPerBlock_NBlock_NPerBlock
+            e_grid_desc_mblock_mperblock_nblock_nperblock,
+        const ComputePtrOffsetOfBatch compute_ptr_offset_of_batch,
+        const Block2ETileMap block_2_etile_map)
 {
 #if(!defined(__HIP_DEVICE_COMPILE__) || defined(__gfx908__) || defined(__gfx90a__) || \
     defined(__gfx940__) || defined(__gfx941__) || defined(__gfx942__))
@@ -1078,7 +1075,7 @@ struct DeviceSplitKContractionMultipleD_Xdl_CShuffle
     }
 
 #ifndef __HIPCC_RTC__
-  static auto MakeInvoker() { return Invoker{}; }
+    static auto MakeInvoker() { return Invoker{}; }
 #endif
     // polymorphic
     std::unique_ptr<BaseArgument>
@@ -1153,5 +1150,3 @@ struct DeviceSplitKContractionMultipleD_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/masking_specialization.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.
 
@@ -83,5 +80,3 @@ struct C0MatrixMask_impl
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/matrix_padder.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.
 
@@ -383,5 +380,3 @@ struct MatrixPadder_v2
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/reduction_operator_mapping.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.
 
@@ -187,5 +184,3 @@ struct reduce_unary_operator<ReduceTensorOp::NORM2, false, true>
 };
 
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/tensor_layout.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.
 
@@ -418,5 +415,3 @@ std::ostream& operator<<(std::ostream& os, const Layout&)
 
 } // namespace tensor_layout
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/tensor_specialization.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.
 
@@ -29,5 +26,3 @@ inline std::string getTensorSpecializationString(const TensorSpecialization& s)
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/welford_helper.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.
 
@@ -90,5 +87,3 @@ struct GetReduceCountPerThreadForMultiblockWelford
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/element/binary_element_wise_operation.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.
 
@@ -326,5 +323,3 @@ struct AddFastGelu
 } // namespace element_wise
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/element/element_wise_operation.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.
 
@@ -395,5 +392,3 @@ struct UnaryTypeConvert<ck::bhalf_t, float>
 } // namespace element_wise
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop