remove unnecessary changes

include/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d.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.
 
@@ -66,5 +63,3 @@ struct DeviceSplitKContractionMultipleD : public BaseOperator
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/gemm_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.
 
@@ -60,5 +57,3 @@ inline std::string getGemmSpecializationString(const GemmSpecialization& s)
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_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.
 
@@ -13,7 +10,6 @@
 #include "ck/host_utility/kernel_launch.hpp"
 #endif
 
-
 #include "ck/utility/common_header.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
@@ -999,5 +995,3 @@ struct DeviceBatchedContractionMultipleD_Wmma_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_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.
 
@@ -13,7 +10,6 @@
 #include "ck/host_utility/kernel_launch.hpp"
 #endif
 
-
 #include "ck/utility/common_header.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
@@ -42,7 +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_contraction_multiple_d_xdl_cshuffle(
         const FloatAB* __restrict__ p_a_grid,
@@ -980,7 +976,6 @@ struct DeviceBatchedContractionMultipleD_Xdl_CShuffle
     static auto MakeInvoker() { return Invoker{}; }
 #endif
 
-
     // polymorphic
     std::unique_ptr<BaseArgument>
     MakeArgumentPointer(const void* p_a,
@@ -1053,5 +1048,3 @@ struct DeviceBatchedContractionMultipleD_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

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

-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Weverything"
 #pragma once
 
 #ifndef __HIPCC_RTC__
@@ -10,7 +7,6 @@
 #include "ck/host_utility/kernel_launch.hpp"
 #endif
 
-
 #include "ck/utility/common_header.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
@@ -64,7 +60,7 @@ 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_batched_gemm_e_permute_xdl(const ABDataType* __restrict__ p_a_grid,
                                       const ABDataType* __restrict__ p_b_grid,
@@ -637,7 +633,6 @@ struct DeviceBatchedGemmEPermuteXdl : public DeviceBatchedGemmEPermute<ALayout,
     static auto MakeInvoker() { return Invoker{}; }
 #endif
 
-
     // polymorphic
     std::unique_ptr<BaseArgument>
     MakeArgumentPointer(const void* p_a,
@@ -703,5 +698,3 @@ struct DeviceBatchedGemmEPermuteXdl : public DeviceBatchedGemmEPermute<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_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.
 
@@ -14,7 +11,6 @@
 #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"
@@ -45,10 +41,9 @@ 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_gemm_gemm_xdl_cshuffle_v1(
-            const FloatAB* __restrict__ p_a_grid,
+    kernel_gemm_gemm_xdl_cshuffle_v1(const FloatAB* __restrict__ p_a_grid,
                                      const FloatAB* __restrict__ p_b_grid,
                                      const FloatAB* __restrict__ p_b1_grid,
                                      FloatC* __restrict__ p_c_grid,
@@ -676,7 +671,6 @@ struct DeviceBatchedGemmGemm_Xdl_CShuffle : public DeviceBatchedGemmGemm<ALayout
     static auto MakeInvoker() { return Invoker{}; }
 #endif
 
-
     // polymorphic
     std::unique_ptr<BaseArgument> MakeArgumentPointer(const void* p_a,
                                                       const void* p_b,
@@ -761,5 +755,3 @@ struct DeviceBatchedGemmGemm_Xdl_CShuffle : public DeviceBatchedGemmGemm<ALayout
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_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.
 
@@ -66,7 +63,7 @@ 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_batched_gemm_xdl(const ABDataType* __restrict__ p_a_grid,
                             const ABDataType* __restrict__ p_b_grid,
@@ -723,5 +720,3 @@ struct DeviceBatchedGemmMultiD_Xdl : public DeviceBatchedGemmMultiD<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_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.
 
@@ -55,7 +52,7 @@ 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,
@@ -797,5 +794,3 @@ struct DeviceBatchedGemmMultipleD_Dl : public DeviceBatchedGemmMultiD<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_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.
 
@@ -44,7 +41,7 @@ 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_batched_gemm_gemm_xdl_cshuffle_v1(
         const A0B0B1DataType* __restrict__ p_a0_grid,
@@ -997,5 +994,3 @@ struct DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_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.
 
@@ -41,7 +38,7 @@ template <typename GridwiseGemm,
           bool HasMainK0BlockLoop>
 __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_reduce_xdl_cshuffle_v1(
         const FloatAB* __restrict__ p_a_grid,
@@ -1009,5 +1006,3 @@ struct DeviceBatchedGemmReduce_Xdl_CShuffle : public DeviceGemmReduce<0, ReduceO
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_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.
 
@@ -45,7 +42,7 @@ 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_batched_gemm_softmax_gemm_xdl_cshuffle_v1(
         const FloatAB* __restrict__ p_a_grid,
@@ -956,5 +953,3 @@ struct DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_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.
 
@@ -43,7 +40,7 @@ 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_batched_gemm_softmax_gemm_xdl_cshuffle_v1(
         const FloatAB* __restrict__ p_a_grid,
@@ -774,5 +771,3 @@ struct DeviceBatchedGemmSoftmaxGemm_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batched_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.
 
@@ -51,7 +48,7 @@ namespace device {
 template <typename DeviceOp, 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_v2r3(const typename DeviceOp::Argument karg)
 {
@@ -437,5 +434,3 @@ struct DeviceBatchedGemmXdl : public DeviceBatchedGemm<ALayout,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batchnorm_backward_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.
 
@@ -875,5 +872,3 @@ struct DeviceBatchNormBwdImpl : public DeviceBatchNormBwd<XDataType,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_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.
 
@@ -823,5 +820,3 @@ struct DeviceBatchNormFwdImpl : public DeviceBatchNormFwd<XDataType,
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_cgemm_4gemm_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.
 
@@ -589,5 +586,3 @@ struct DeviceCGemm_4Gemm_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_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.
 
@@ -37,7 +34,7 @@ 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_contraction_multiple_d_xdl_cshuffle(
         const FloatAB* __restrict__ p_a_grid,
@@ -791,5 +788,3 @@ struct DeviceContractionMultipleD_Xdl_CShuffle
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_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.
 
@@ -809,5 +806,3 @@ struct DeviceConv2dBwdWeightXdl_C_Shuffle_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop

include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_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.
 
@@ -767,5 +764,3 @@ struct DeviceConv2dBwdDataXdl_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_conv2d_fwd_xdl_c_shuffle_bias_activation_add_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.
 
@@ -987,5 +984,3 @@ struct
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-
-#pragma clang diagnostic pop