You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
71 lines
2.8 KiB
71 lines
2.8 KiB
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.
|
|
|
|
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. */
|
|
|
|
#include "paddle/memory/memcpy.h"
|
|
|
|
#include <cstring> // for memcpy
|
|
|
|
#include "paddle/platform/device_context.h"
|
|
|
|
namespace paddle {
|
|
namespace memory {
|
|
|
|
template <>
|
|
void Copy<platform::CPUPlace, platform::CPUPlace>(platform::CPUPlace, void* dst,
|
|
platform::CPUPlace,
|
|
const void* src, size_t num) {
|
|
std::memcpy(dst, src, num);
|
|
}
|
|
|
|
#ifndef PADDLE_ONLY_CPU
|
|
template <>
|
|
void Copy<platform::CPUPlace, platform::GPUPlace>(platform::CPUPlace dst_place,
|
|
void* dst,
|
|
platform::GPUPlace src_place,
|
|
const void* src, size_t num,
|
|
cudaStream_t stream) {
|
|
platform::GPUPlaceGuard g(src_place.device);
|
|
platform::GpuMemcpyAsync(dst, src, num, cudaMemcpyDeviceToHost, stream);
|
|
}
|
|
|
|
template <>
|
|
void Copy<platform::GPUPlace, platform::CPUPlace>(platform::GPUPlace dst_place,
|
|
void* dst,
|
|
platform::CPUPlace src_place,
|
|
const void* src, size_t num,
|
|
cudaStream_t stream) {
|
|
platform::GPUPlaceGuard g(dst_place.device);
|
|
platform::GpuMemcpyAsync(dst, src, num, cudaMemcpyHostToDevice, stream);
|
|
}
|
|
|
|
template <>
|
|
void Copy<platform::GPUPlace, platform::GPUPlace>(platform::GPUPlace dst_place,
|
|
void* dst,
|
|
platform::GPUPlace src_place,
|
|
const void* src, size_t num,
|
|
cudaStream_t stream) {
|
|
if (dst_place == src_place) {
|
|
platform::GPUPlaceGuard g(src_place.device);
|
|
platform::GpuMemcpyAsync(dst, src, num, cudaMemcpyDeviceToDevice, stream);
|
|
} else {
|
|
platform::GpuMemcpyPeer(dst, dst_place.device, src, src_place.device, num,
|
|
stream);
|
|
}
|
|
}
|
|
|
|
#endif // PADDLE_ONLY_CPU
|
|
|
|
} // namespace memory
|
|
} // namespace paddle
|