Absolute include path (#281)

* ad gelu and fast_gelu

* added GeLU and fast GeLU

* clean up

* add gemm+fastgelu example

* add gemm+gelu instances

* update profiler

* clean up

* clean up

* adding gemm+bias+activation

* clean

* adding bias

* clean

* adding gemm multiple d

* debugging

* add gemm bias add fastgelu

* rename, clean

* refactoring; add readme

* refactor

* refactor

* refactor

* refactor

* refactor

* refactor

* fix

* fix

* update example

* update example

* rename

* update example

* add ckProfiler

* clean

* clean

* clean

* clean

* add client app example

* update readme

* delete obselete files

* remove old client app

* delete old file

* cleaning

* clean

* remove half

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path for all examples

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* revert client app example

* clean build

* fix build

* temporary disable client test on Jenkins

* clean

* clean

* clean

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

-#ifndef DEVICE_REDUCE_HPP
-#define DEVICE_REDUCE_HPP
+#pragma once
 
 #include <vector>
 #include <memory>
 #include <iostream>
 
-#include "common_header.hpp"
-#include "device_base.hpp"
-#include "reduction_enums.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/utility/reduction_enums.hpp"
+#include "ck/tensor_operation/gpu/device/device_base.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -41,4 +40,3 @@ using DeviceReducePtr =
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-#endif

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

-#ifndef DEVICE_REDUCE_COMMON_HPP
-#define DEVICE_REDUCE_COMMON_HPP
+#pragma once
 
 #include <vector>
 #include <cassert>
 
-#include "common_header.hpp"
-#include "reduction_enums.hpp"
-#include "reduction_operator.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/utility/reduction_enums.hpp"
+#include "ck/utility/reduction_operator.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -85,6 +84,4 @@ std::vector<index_t> shuffle_tensor_dimensions(const std::vector<index_t>& origL
 
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-#endif

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

-#ifndef DEVICE_REDUCE_MULTIBLOCK_HPP
-#define DEVICE_REDUCE_MULTIBLOCK_HPP
+#pragma once
 
 #include <iostream>
 #include <sstream>
-#include "device.hpp"
-#include "device_base.hpp"
-#include "device_reduce.hpp"
-#include "device_reduce_common.hpp"
-#include "gridwise_2d_reduction_multiblock.hpp"
-#include "gridwise_set_buffer_value.hpp"
-#include "reduction_operator.hpp"
+
+#include "ck/utility/common_header.hpp"
+#include "ck/utility/reduction_operator.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce_common.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp"
+#include "ck/device_utility/device_prop.hpp"
+#include "ck/device_utility/kernel_launch.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -505,4 +508,3 @@ struct DeviceReduceMultiBlock : public DeviceReduce<InElementwiseOperation, AccE
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-#endif

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

-#ifndef DEVICE_REDUCE_THREADWISE_HPP
-#define DEVICE_REDUCE_THREADWISE_HPP
+#pragma once
 
 #include <iostream>
 #include <sstream>
-#include "device.hpp"
-#include "device_reduce.hpp"
-#include "device_reduce_common.hpp"
-#include "gridwise_2d_reduction_multiblock.hpp"
-#include "gridwise_2d_reduction_threadwise.hpp"
+
+#include "ck/device_utility/device_prop.hpp"
+#include "ck/device_utility/kernel_launch.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce_common.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -370,4 +371,3 @@ struct DeviceReduceThreadWise : public DeviceReduce<InElementwiseOperation, AccE
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-#endif

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

-#ifndef DEVICE_SOFTMAX_HPP
-#define DEVICE_SOFTMAX_HPP
+#pragma once
 
 #include <iostream>
 #include <sstream>
-#include "device.hpp"
-#include "device_base.hpp"
-#include "device_reduce.hpp"
-#include "device_reduce_multiblock.hpp"
-#include "device_reduce_common.hpp"
-#include "gridwise_softmax.hpp"
-#include "gridwise_set_buffer_value.hpp"
-#include "reduction_operator.hpp"
+
+#include "ck/utility/reduction_operator.hpp"
+#include "ck/tensor_operation/gpu/device/device_base.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce_common.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_softmax.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp"
+#include "ck/device_utility/device_prop.hpp"
+#include "ck/device_utility/kernel_launch.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -200,4 +201,3 @@ struct DeviceSoftmax : public BaseOperator
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-#endif // DEVICE_SOFTMAX_HPP

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

 #pragma once
+
 #include <iostream>
 #include <vector>
 
-#include "device.hpp"
-#include "device_base.hpp"
-#include "gridwise_unary_elementwise_1d.hpp"
+#include "ck/device_utility/device_prop.hpp"
+#include "ck/device_utility/kernel_launch.hpp"
+#include "ck/tensor_operation/gpu/device/device_base.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_unary_elementwise_1d.hpp"
 
 namespace ck {
 namespace tensor_operation {

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

-#ifndef GEMM_SPECIALIZATION
-#define GEMM_SPECIALIZATION
+#pragma once
 
 namespace ck {
 namespace tensor_operation {
@@ -20,4 +19,3 @@ enum struct GemmSpecialization
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-#endif

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

-/*******************************************************************************
- *
- * MIT License
- *
- * Copyright (c) 2020 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- *******************************************************************************/
-#ifndef CK_REDUCTION_OPERATOR_MAPPING_HPP
-#define CK_REDUCTION_OPERATOR_MAPPING_HPP
-
-#include "reduction_operator.hpp"
-#include "reduction_enums.hpp"
-#include "element_wise_operation.hpp"
+#pragma once
+
+#include "ck/utility/reduction_operator.hpp"
+#include "ck/utility/reduction_enums.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+// FIXME: can it be replaced with ck::Tuple?
 #include <tuple>
 
 namespace ck {
@@ -205,6 +180,4 @@ struct reduce_unary_operator<ReduceTensorOp::NORM2, false, true>
     };
 };
 
-} // end of namespace ck
-
-#endif
+} // namespace ck

include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp

-/*******************************************************************************
- *
- * MIT License
- *
- * Copyright (c) 2022 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- *******************************************************************************/
 #pragma once
 
-#include "data_type.hpp"
+#include "ck/utility/data_type.hpp"
 
 namespace ck {
 namespace tensor_operation {

include/ck/tensor_operation/gpu/element/element_wise_operation.hpp

 #pragma once
 
-#include "data_type.hpp"
-#include "math_v2.hpp"
-#include "unary_element_wise_operation.hpp"
-#include "binary_element_wise_operation.hpp"
+#include "ck/utility/data_type.hpp"
+#include "ck/utility/math_v2.hpp"
+#include "ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp"
 
 namespace ck {
 namespace tensor_operation {

include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp

 #pragma once
 
-#include "data_type.hpp"
-#include "math_v2.hpp"
+#include "ck/utility/data_type.hpp"
+#include "ck/utility/math_v2.hpp"
 
 namespace ck {
 namespace tensor_operation {

include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp

-#ifndef UTILITY_BLOCK_TO_CTILE_MAP
-#define UTILITY_BLOCK_TO_CTILE_MAP
+#pragma once
 
-#include "utility/math.hpp"
-#include "utility/number.hpp"
-#include "tensor_description/tensor_adaptor.hpp"
-#include "tensor_description/multi_index_transform_helper.hpp"
+#include "ck/utility/math.hpp"
+#include "ck/utility/number.hpp"
+#include "ck/tensor_description/tensor_adaptor.hpp"
+#include "ck/tensor_description/multi_index_transform_helper.hpp"
 
 namespace ck {
 
@@ -485,5 +484,3 @@ __host__ __device__ bool DefaultValidCTileIndex(const CTileIdx& c_tile_idx,
 }
 
 } // namespace ck
-
-#endif // UTILITY_BLOCK_TO_CTILE_MAP

include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp

-/*******************************************************************************
- *
- * MIT License
- *
- * Copyright (c) 2020 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- *******************************************************************************/
-#ifndef CK_GRIDWISE_2D_REDUCTION_MULTIBLOCK_HPP
-#define CK_GRIDWISE_2D_REDUCTION_MULTIBLOCK_HPP
-
-#include "reduction_common.hpp"
-#include "reduction_operator.hpp"
-#include "reduction_functions_accumulate.hpp"
-#include "reduction_functions_blockwise.hpp"
-#include "reduction_functions_threadwise.hpp"
-
-#include "threadwise_tensor_slice_transfer.hpp"
-#include "element_wise_operation.hpp"
+#pragma once
+
+#include "ck/utility/reduction_common.hpp"
+#include "ck/utility/reduction_operator.hpp"
+#include "ck/utility/reduction_functions_accumulate.hpp"
+#include "ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp"
+#include "ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 namespace ck {
 
@@ -635,4 +608,3 @@ struct GridwiseReduction_mk_to_m_multiblock
 };
 
 } // namespace ck
-#endif

include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp

-/*******************************************************************************
- *
- * MIT License
- *
- * Copyright (c) 2021 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- *******************************************************************************/
-#ifndef CK_GRIDWISE_2D_REDUCTION_THREADWISE_HPP
-#define CK_GRIDWISE_2D_REDUCTION_THREADWISE_HPP
-
-#include "data_type.hpp"
-#include "reduction_common.hpp"
-#include "reduction_operator.hpp"
-#include "reduction_functions_accumulate.hpp"
-#include "reduction_functions_threadwise.hpp"
-#include "threadwise_tensor_slice_transfer.hpp"
-#include "element_wise_operation.hpp"
+#pragma once
+
+#include "ck/utility/data_type.hpp"
+#include "ck/utility/reduction_common.hpp"
+#include "ck/utility/reduction_operator.hpp"
+#include "ck/utility/reduction_functions_accumulate.hpp"
+#include "ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 namespace ck {
 
@@ -495,4 +469,3 @@ struct GridwiseReduction_mk_to_m_threadwise
 };
 
 } // namespace ck
-#endif

include/ck/tensor_operation/gpu/grid/gridwise_5ary_Elementwise_1d.hpp

 #pragma once
 
-#include "cluster_descriptor.hpp"
-#include "data_type.hpp"
-#include "element_wise_operation.hpp"
-#include "threadwise_tensor_slice_transfer.hpp"
+#include "ck/tensor_description/cluster_descriptor.hpp"
+#include "ck/utility/data_type.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
 
 namespace ck {
 

include/ck/tensor_operation/gpu/grid/gridwise_binary_elementwise_1d.hpp

 #pragma once
 
-#include "cluster_descriptor.hpp"
-#include "data_type.hpp"
-#include "element_wise_operation.hpp"
-#include "threadwise_tensor_slice_transfer.hpp"
+#include "ck/utility/data_type.hpp"
+#include "ck/tensor_description/cluster_descriptor.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
 
 namespace ck {
 

include/ck/tensor_operation/gpu/grid/gridwise_gemm_bias_add_reduce_xdl_cshuffle_v1.hpp

 #pragma once
-#include "multi_index_transform_helper.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
-#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp"
-#include "blockwise_gemm_xdlops.hpp"
-#include "thread_group_tensor_slice_transfer_v4r1.hpp"
-#include "thread_group_tensor_slice_transfer_v6r1.hpp"
-#include "threadwise_tensor_slice_transfer.hpp"
-#include "gridwise_gemm_pipeline_v1.hpp"
-#include "reduction_functions_threadwise.hpp"
+
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/multi_index_transform_helper.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
+#include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
+#include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
+#include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
+#include "ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 namespace ck {
 

include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_v1r3.hpp

 #pragma once
 
-#include "common_header.hpp"
-#include "multi_index_transform_helper.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
-#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp"
-#include "blockwise_gemm_dl_v2r3.hpp"
-#include "blockwise_tensor_slice_transfer_v5r1.hpp"
-#include "threadwise_tensor_slice_transfer.hpp"
-#include "threadwise_tensor_slice_set.hpp"
-#include "element_wise_operation.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/multi_index_transform_helper.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
+#include "ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp"
+#include "ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 namespace ck {
 

include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp

 #pragma once
 
-#include "common_header.hpp"
-#include "multi_index_transform_helper.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
-#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp"
-#include "blockwise_gemm_xdlops.hpp"
-#include "thread_group_tensor_slice_transfer_v4r1.hpp"
-#include "thread_group_tensor_slice_transfer_v7.hpp"
-#include "threadwise_tensor_slice_transfer.hpp"
-#include "gridwise_gemm_pipeline_v1.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/multi_index_transform_helper.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
+#include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
+#include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
+#include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 namespace ck {
 

include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp

 #pragma once
-#include "common_header.hpp"
-#include "tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
+
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
 
 namespace ck {