Merge remote-tracking branch 'origin/develop' into batched_gemm_c_permute

include/ck/tensor_operation/gpu/device/device_cgemm.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.
- *
- *******************************************************************************/
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 #include "device_base.hpp"
 

include/ck/tensor_operation/gpu/device/device_cgemm_4gemm_xdl_cshuffle.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

include/ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

include/ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

include/ck/tensor_operation/gpu/device/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #ifndef DEVICE_CONV3D_FWD_NAIVE_HPP
 #define DEVICE_CONV3D_FWD_NAIVE_HPP
 

include/ck/tensor_operation/gpu/device/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #ifndef DEVICE_CONV3D_FWD_XDL_HPP
 #define DEVICE_CONV3D_FWD_XDL_HPP
 

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <vector>

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <vector>

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <vector>

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <vector>

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <iostream>

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 
 #include <functional>

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+#include <iostream>
+#include <vector>
+
+#include "device_base.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+
+template <ck::index_t NumInputTensor,
+          ck::index_t NumOutputTensor,
+          index_t NDim,
+          typename ElementwiseFunctor>
+struct DeviceElementwise : public BaseOperator
+{
+    virtual std::unique_ptr<BaseArgument>
+    MakeArgumentPointer(std::array<const void*, NumInputTensor> p_inputs,
+                        std::array<void*, NumOutputTensor> p_outputs,
+                        std::vector<index_t> lengths,
+                        std::vector<std::vector<index_t>> input_strides,
+                        std::vector<std::vector<index_t>> output_strides,
+                        ElementwiseFunctor functor) = 0;
+
+    virtual std::unique_ptr<BaseInvoker> MakeInvokerPointer() = 0;
+};
+
+template <ck::index_t NumInputTensor,
+          ck::index_t NumOutputTensor,
+          index_t NDim,
+          typename ElementwiseFunctor>
+using DeviceElementwisePtr =
+    std::unique_ptr<DeviceElementwise<NumInputTensor, NumOutputTensor, NDim, ElementwiseFunctor>>;
+
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 #include <iostream>
 #include <vector>