未验证 提交 d61d6d75 编写于 作者: Z zhupengyang 提交者: GitHub

add .part to speed up compile (#27044) (#27099)

上级 a6ee3bcc
......@@ -12,7 +12,6 @@
// See the License for the specific language governing permissions and
// limitations under the License.
#include "paddle/fluid/operators/reduce_ops/cub_reduce.h"
#include "paddle/fluid/operators/reduce_ops/logsumexp_op.h"
REGISTER_OP_CUDA_KERNEL(logsumexp,
......@@ -20,8 +19,3 @@ REGISTER_OP_CUDA_KERNEL(logsumexp,
float, ops::LogsumexpFunctor>,
ops::ReduceKernel<paddle::platform::CUDADeviceContext,
double, ops::LogsumexpFunctor>);
REGISTER_OP_CUDA_KERNEL(
logsumexp_grad, ops::ReduceGradKernel<paddle::platform::CUDADeviceContext,
float, ops::LogsumexpGradFunctor>,
ops::ReduceGradKernel<paddle::platform::CUDADeviceContext, double,
ops::LogsumexpGradFunctor>);
// Copyright (c) 2018 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.
// .part used to speed up nvcc compile
#include "paddle/fluid/operators/reduce_ops/logsumexp_op.h"
REGISTER_OP_CUDA_KERNEL(
logsumexp_grad, ops::ReduceGradKernel<paddle::platform::CUDADeviceContext,
float, ops::LogsumexpGradFunctor>,
ops::ReduceGradKernel<paddle::platform::CUDADeviceContext, double,
ops::LogsumexpGradFunctor>);
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册