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
2026-05-02 04:31:25 +00:00 · 2022-06-24 20:51:04 -05:00
parent a49115b95e
commit d1db6a0c3e
499 changed files with 3000 additions and 24130 deletions
--- a/include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
@@ -1,32 +1,6 @@
-/*******************************************************************************
- *
- * 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
+#pragma once

-#include "reduction_functions_accumulate.hpp"
+#include "ck/utility/reduction_functions_accumulate.hpp"

 namespace ck {

@@ -117,6 +91,4 @@ struct ThreadwiseReductionWithIndex
    };
 };

-}; // end of namespace ck
-
-#endif
+} // namespace ck
--- a/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp
@@ -1,6 +1,7 @@
 #pragma once
-#include "common_header.hpp"
-#include "math.hpp"
+
+#include "ck/utility/common_header.hpp"
+#include "ck/utility/math.hpp"

 namespace ck {

--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp
@@ -1,9 +1,8 @@
-#ifndef CK_THREADWISE_TENSOR_SET_HPP
-#define CK_THREADWISE_TENSOR_SET_HPP
+#pragma once

-#include "common_header.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"

 namespace ck {

@@ -56,4 +55,3 @@ struct ThreadwiseTensorSliceSet_v1
 };

 } // namespace ck
-#endif
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
@@ -1,10 +1,9 @@
-#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_HPP
-#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_HPP
+#pragma once

-#include "common_header.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
-#include "tensor_space_filling_curve.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_space_filling_curve.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"

 namespace ck {

@@ -1168,4 +1167,3 @@ struct ThreadwiseTensorSliceTransfer_v4
 };

 } // namespace ck
-#endif
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
@@ -1,10 +1,9 @@
-#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_V3R1_HPP
-#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_V3R1_HPP
+#pragma once

-#include "common_header.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
-#include "static_tensor.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor/static_tensor.hpp"

 namespace ck {

@@ -789,4 +788,3 @@ struct ThreadwiseTensorSliceTransfer_v3r1
 };

 } // namespace ck
-#endif
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.hpp
@@ -1,9 +1,8 @@
-#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_V4R1_HPP
-#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_V4R1_HPP
+#pragma once

-#include "common_header.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"

 namespace ck {
 // Assume:
@@ -171,4 +170,3 @@ struct ThreadwiseTensorSliceTransfer_v4r1
 };

 } // namespace ck
-#endif
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
@@ -1,8 +1,9 @@
 #pragma once

-#include "common_header.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_description/tensor_space_filling_curve.hpp"

 namespace ck {

--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp
@@ -1,10 +1,9 @@
-#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_V6R1_HPP
-#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_V6R1_HPP
+#pragma once

-#include "common_header.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
-#include "tensor_space_filling_curve.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_description/tensor_space_filling_curve.hpp"

 namespace ck {

@@ -206,7 +205,6 @@ struct ThreadwiseTensorSliceTransfer_v6r1
    SrcCoord src_coord_;
    DstCoord dst_coord_;
    const ElementwiseOperation element_op_;
-}; // namespace ck
+};

 } // namespace ck
-#endif
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r2.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r2.hpp
@@ -1,10 +1,9 @@
-#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_V6R2_HPP
-#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_V6R2_HPP
+#pragma once

-#include "common_header.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
-#include "tensor_space_filling_curve.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_description/tensor_space_filling_curve.hpp"

 namespace ck {

@@ -256,4 +255,3 @@ struct ThreadwiseTensorSliceTransfer_v6r2
 };

 } // namespace ck
-#endif
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r3.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r3.hpp
@@ -1,10 +1,9 @@
-#ifndef CK_THREADWISE_TENSOR_SLICE_TRANSFER_V6R3_HPP
-#define CK_THREADWISE_TENSOR_SLICE_TRANSFER_V6R3_HPP
+#pragma once

-#include "common_header.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
-#include "tensor_space_filling_curve.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_description/tensor_space_filling_curve.hpp"

 namespace ck {

@@ -306,4 +305,3 @@ struct ThreadwiseTensorSliceTransfer_v6r3
 };

 } // namespace ck
-#endif
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7.hpp
@@ -1,9 +1,9 @@
 #pragma once

-#include "common_header.hpp"
-#include "tensor_descriptor.hpp"
-#include "tensor_descriptor_helper.hpp"
-#include "tensor_space_filling_curve.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_descriptor.hpp"
+#include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_description/tensor_space_filling_curve.hpp"

 namespace ck {