Ginkgo
Generated from pipelines/1589998975 branch based on develop. Ginkgo version 1.10.0
A numerical linear algebra library targeting many-core architectures
|
An RAII wrapper for a custom CUDA stream. More...
#include <ginkgo/core/base/stream.hpp>
Public Member Functions | |
cuda_stream () | |
Creates an empty stream wrapper, representing the default stream. | |
cuda_stream (int device_id) | |
Creates a new custom CUDA stream on the given device. More... | |
~cuda_stream () | |
Destroys the custom CUDA stream, if it isn't empty. | |
cuda_stream (const cuda_stream &)=delete | |
cuda_stream (cuda_stream &&) | |
Move-constructs from an existing stream, which will be emptied. | |
cuda_stream & | operator= (const cuda_stream &)=delete |
cuda_stream & | operator= (cuda_stream &&)=delete |
Move-assigns from an existing stream, which will be emptied. | |
CUstream_st * | get () const |
Returns the native CUDA stream handle. More... | |
An RAII wrapper for a custom CUDA stream.
The stream will be created on construction and destroyed when the lifetime of the wrapper ends.
gko::cuda_stream::cuda_stream | ( | int | device_id | ) |
Creates a new custom CUDA stream on the given device.
device_id | the device ID to create the stream on. |
CUstream_st* gko::cuda_stream::get | ( | ) | const |
Returns the native CUDA stream handle.
In an empty cuda_stream, this will return nullptr.