// Copyright (c) 2024 PaddlePaddle Authors. All Rights Reserved. // // Licensed under the Apache License, Version 2.0 (the "License"); // you may not use this file except in compliance with the License. // You may obtain a copy of the License at // // http://www.apache.org/licenses/LICENSE-2.0 // // Unless required by applicable law or agreed to in writing, software // distributed under the License is distributed on an "AS IS" BASIS, // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. // See the License for the specific language governing permissions and // limitations under the License. #pragma once #include "paddle/phi/core/dense_tensor.h" // only can include the headers in paddle/top/api dirs #include "paddle/phi/kernels/funcs/broadcast_function.h" namespace phi { namespace funcs { template void LaunchSameDimsElementwiseCudaKernel( const KPDevice &dev_ctx, const std::vector &ins, std::vector *outs, Functor func) { std::vector pt_inputs; std::vector pt_outputs; // TODO(YuanRisheng) *_tmp for cache DenseTensor, because the temporary // DenseTensor obj // generated by MakePhiDenseTensor can be destroyed when exits loop. *_tmp // can be deleted // when DenseTensor support copy constructor. std::vector> pt_inputs_tmp; std::vector> pt_outputs_tmp; for (auto in : ins) { pt_inputs_tmp.emplace_back(std::move(std::make_unique(*in))); } for (auto out : *outs) { pt_outputs_tmp.emplace_back(std::move(std::make_unique(*out))); } for (int i = 0; i < pt_inputs_tmp.size(); i++) { pt_inputs.push_back(pt_inputs_tmp[i].get()); } for (int i = 0; i < pt_outputs_tmp.size(); i++) { pt_outputs.push_back(pt_outputs_tmp[i].get()); } funcs::ElementwiseKernel( dev_ctx, pt_inputs, &pt_outputs, func); } } // namespace funcs } // namespace phi