Skip to content

GitLab

Unverified Commit d1db6a0c authored by Chao Liu's avatar Chao Liu Committed by GitHub
Browse files

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
parent a49115b9
Hide whitespace changes
Inline Side-by-side
Showing with 161 additions and 242 deletions
include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
View file @ d1db6a0c
#pragma once #pragma once
#include "common_header.hpp"
#include "multi_index_transform_helper.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "blockwise_gemm_xdlops.hpp" #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "thread_group_tensor_slice_transfer_v4r1.hpp" #include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
#include "thread_group_tensor_slice_transfer_v6r1.hpp" #include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "gridwise_gemm_pipeline_v1.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp"
#include "reduction_functions_threadwise.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 { namespace ck {
......
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp
View file @ d1db6a0c
#pragma once #pragma once
#include "common_header.hpp"
#include "multi_index_transform_helper.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "blockwise_gemm_xdlops.hpp" #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "thread_group_tensor_slice_transfer_v4r1.hpp" #include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
#include "thread_group_tensor_slice_transfer_v6r1.hpp" #include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "gridwise_gemm_pipeline_v1.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/element/element_wise_operation.hpp"
namespace ck { namespace ck {
......
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp
View file @ d1db6a0c
#pragma once #pragma once
#include "common_header.hpp" #include "ck/utility/common_header.hpp"
#include "multi_index_transform_helper.hpp" #include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp" #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "blockwise_gemm_xdlops.hpp" #include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
#include "thread_group_tensor_slice_transfer_v4r1.hpp" #include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "thread_group_tensor_slice_transfer_v6r1.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp"
#include "gridwise_gemm_pipeline_v1.hpp" #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
namespace ck { namespace ck {
......
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
View file @ d1db6a0c
#pragma once #pragma once
#include "common_header.hpp" #include "ck/utility/common_header.hpp"
#include "multi_index_transform_helper.hpp" #include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp" #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "blockwise_gemm_xdlops.hpp" #include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
#include "thread_group_tensor_slice_transfer_v4r1.hpp" #include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "gridwise_gemm_pipeline_v1.hpp" #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
namespace ck { namespace ck {
......
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp
View file @ d1db6a0c
#ifndef CK_GRIDWISE_GEMM_XDLOPS_V2R4_HPP #pragma once
#define CK_GRIDWISE_GEMM_XDLOPS_V2R4_HPP
#include "ck/utility/common_header.hpp"
#include "common_header.hpp" #include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "multi_index_transform_helper.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp" #include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
#include "blockwise_gemm_xdlops.hpp" #include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "thread_group_tensor_slice_transfer_v4r1.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
namespace ck { namespace ck {
...@@ -607,7 +608,6 @@ struct GridwiseGemm_bk0mk1_bk0nk1_mn_xdlops_v2r4 ...@@ -607,7 +608,6 @@ struct GridwiseGemm_bk0mk1_bk0nk1_mn_xdlops_v2r4
c_grid_buf); c_grid_buf);
} }
} }
}; // namespace ck };
} // namespace ck } // namespace ck
#endif
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
View file @ d1db6a0c
#ifndef CK_GRIDWISE_GEMM_XDLOPS_V2R4R2_HPP #pragma once
#define CK_GRIDWISE_GEMM_XDLOPS_V2R4R2_HPP
#include "ck/utility/common_header.hpp"
#include "common_header.hpp" #include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "multi_index_transform_helper.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp" #include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
#include "blockwise_gemm_xdlops.hpp" #include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "thread_group_tensor_slice_transfer_v4r1.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "thread_group_tensor_slice_transfer_v6r1.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
namespace ck { namespace ck {
...@@ -717,7 +718,6 @@ struct GridwiseGemm_bk0mk1_bk0nk1_mn_xdlops_v2r4r2 ...@@ -717,7 +718,6 @@ struct GridwiseGemm_bk0mk1_bk0nk1_mn_xdlops_v2r4r2
}); });
} }
} }
}; // namespace ck };
} // namespace ck } // namespace ck
#endif
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
View file @ d1db6a0c
#pragma once #pragma once
#include "common_header.hpp"
#include "multi_index_transform_helper.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_space_filling_curve.hpp"
#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "blockwise_gemm_xdlops.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "thread_group_tensor_slice_transfer_v4r1.hpp" #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "thread_group_tensor_slice_transfer_v6r1.hpp" #include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "gridwise_gemm_pipeline_v1.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "tensor_space_filling_curve.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/element/element_wise_operation.hpp"
namespace ck { namespace ck {
......
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
View file @ d1db6a0c
#ifndef CK_GRIDWISE_GEMM_XDLOPS_V3R2_HPP #pragma once
#define CK_GRIDWISE_GEMM_XDLOPS_V3R2_HPP
#include "ck/utility/common_header.hpp"
#include "common_header.hpp" #include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "multi_index_transform_helper.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp" #include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
#include "blockwise_gemm_xdlops.hpp" #include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "thread_group_tensor_slice_transfer_v4r1.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "thread_group_tensor_slice_transfer_v6r2.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
#include "gridwise_gemm_pipeline_v1.hpp" #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
namespace ck { namespace ck {
...@@ -755,4 +755,3 @@ struct GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v3r2 ...@@ -755,4 +755,3 @@ struct GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v3r2
}; };
} // namespace ck } // namespace ck
#endif
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
View file @ d1db6a0c
#pragma once #pragma once
#include "common_header.hpp"
#include "multi_index_transform_helper.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_operation/gpu/grid/block_to_ctile_map.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "blockwise_gemm_xdlops.hpp" #include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "thread_group_tensor_slice_transfer_v4r1.hpp" #include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp"
#include "thread_group_tensor_slice_transfer_v6r3.hpp" #include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "gridwise_gemm_pipeline_v1.hpp" #include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp"
#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
namespace ck { namespace ck {
......
include/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp
View file @ d1db6a0c
/******************************************************************************* #pragma once
*
* 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_SET_BUFFER_VALUE_HPP
#define CK_GRIDWISE_SET_BUFFER_VALUE_HPP
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
namespace ck { namespace ck {
...@@ -77,4 +51,3 @@ __global__ void kernel_buffer_set_value(const Grid1dBufferDescType grid_1d_buffe ...@@ -77,4 +51,3 @@ __global__ void kernel_buffer_set_value(const Grid1dBufferDescType grid_1d_buffe
}; };
} // namespace ck } // namespace ck
#endif
include/ck/tensor_operation/gpu/grid/gridwise_softmax.hpp
View file @ d1db6a0c
/******************************************************************************* #pragma once
*
* MIT License #include "ck/utility/data_type.hpp"
* #include "ck/utility/reduction_common.hpp"
* Copyright (c) 2022 Advanced Micro Devices, Inc. #include "ck/utility/reduction_operator.hpp"
* #include "ck/utility/reduction_functions_accumulate.hpp"
* Permission is hereby granted, free of charge, to any person obtaining a copy #include "ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp"
* of this software and associated documentation files (the "Software"), to deal #include "ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp"
* in the Software without restriction, including without limitation the rights #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
* 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 GRIDWISE_SOFTMAX_HPP
#define GRIDWISE_SOFTMAX_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"
namespace ck { namespace ck {
...@@ -404,4 +378,3 @@ struct GridwiseSoftmax_mk_to_mk ...@@ -404,4 +378,3 @@ struct GridwiseSoftmax_mk_to_mk
}; };
} // namespace ck } // namespace ck
#endif // GRIDWISE_SOFTMAX_HPP
include/ck/tensor_operation/gpu/grid/gridwise_unary_elementwise_1d.hpp
View file @ d1db6a0c
#pragma once #pragma once
#include "cluster_descriptor.hpp" #include "ck/utility/data_type.hpp"
#include "data_type.hpp" #include "ck/tensor_description/cluster_descriptor.hpp"
#include "element_wise_operation.hpp" #include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
#include "threadwise_tensor_slice_transfer.hpp" #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
namespace ck { namespace ck {
......
include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
View file @ d1db6a0c
/******************************************************************************* #pragma once
*
* 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_FUNCTIONS_THREADWISE_HPP
#define CK_REDUCTION_FUNCTIONS_THREADWISE_HPP
#include "reduction_functions_accumulate.hpp" #include "ck/utility/reduction_functions_accumulate.hpp"
namespace ck { namespace ck {
...@@ -117,6 +91,4 @@ struct ThreadwiseReductionWithIndex ...@@ -117,6 +91,4 @@ struct ThreadwiseReductionWithIndex
}; };
}; };
}; // end of namespace ck } // namespace ck
#endif
include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp
View file @ d1db6a0c
#pragma once #pragma once
#include "common_header.hpp"
#include "math.hpp" #include "ck/utility/common_header.hpp"
#include "ck/utility/math.hpp"
namespace ck { namespace ck {
......
include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp
View file @ d1db6a0c
#ifndef CK_THREADWISE_TENSOR_SET_HPP #pragma once
#define CK_THREADWISE_TENSOR_SET_HPP
#include "common_header.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
namespace ck { namespace ck {
...@@ -56,4 +55,3 @@ struct ThreadwiseTensorSliceSet_v1 ...@@ -56,4 +55,3 @@ struct ThreadwiseTensorSliceSet_v1
}; };
} // namespace ck } // namespace ck
#endif
include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
View file @ d1db6a0c
#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_HPP #pragma once
#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_HPP
#include "common_header.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_space_filling_curve.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_space_filling_curve.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
namespace ck { namespace ck {
...@@ -1168,4 +1167,3 @@ struct ThreadwiseTensorSliceTransfer_v4 ...@@ -1168,4 +1167,3 @@ struct ThreadwiseTensorSliceTransfer_v4
}; };
} // namespace ck } // namespace ck
#endif
include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
View file @ d1db6a0c
#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_V3R1_HPP #pragma once
#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_V3R1_HPP
#include "common_header.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "static_tensor.hpp" #include "ck/tensor/static_tensor.hpp"
namespace ck { namespace ck {
...@@ -789,4 +788,3 @@ struct ThreadwiseTensorSliceTransfer_v3r1 ...@@ -789,4 +788,3 @@ struct ThreadwiseTensorSliceTransfer_v3r1
}; };
} // namespace ck } // namespace ck
#endif
include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.hpp
View file @ d1db6a0c
#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_V4R1_HPP #pragma once
#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_V4R1_HPP
#include "common_header.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
namespace ck { namespace ck {
// Assume: // Assume:
...@@ -171,4 +170,3 @@ struct ThreadwiseTensorSliceTransfer_v4r1 ...@@ -171,4 +170,3 @@ struct ThreadwiseTensorSliceTransfer_v4r1
}; };
} // namespace ck } // namespace ck
#endif
include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
View file @ d1db6a0c
#pragma once #pragma once
#include "common_header.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "ck/tensor_description/tensor_space_filling_curve.hpp"
namespace ck { namespace ck {
......
include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp
View file @ d1db6a0c
#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_V6R1_HPP #pragma once
#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_V6R1_HPP
#include "common_header.hpp" #include "ck/utility/common_header.hpp"
#include "tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "tensor_space_filling_curve.hpp" #include "ck/tensor_description/tensor_space_filling_curve.hpp"
namespace ck { namespace ck {
...@@ -206,7 +205,6 @@ struct ThreadwiseTensorSliceTransfer_v6r1 ...@@ -206,7 +205,6 @@ struct ThreadwiseTensorSliceTransfer_v6r1
SrcCoord src_coord_; SrcCoord src_coord_;
DstCoord dst_coord_; DstCoord dst_coord_;
const ElementwiseOperation element_op_; const ElementwiseOperation element_op_;
}; // namespace ck };
} // namespace ck } // namespace ck
#endif
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment