Ginkgo
Generated from pipelines/1554403166 branch based on develop. Ginkgo version 1.9.0
A numerical linear algebra library targeting many-core architectures
|
Public Member Functions | |
void * | allocate (size_type num_bytes) override |
void | deallocate (void *ptr) override |
CudaAsyncAllocator (CUstream_st *stream) | |
bool | check_environment (int device_id, CUstream_st *stream) const override |
Checks if the allocator can be used safely with the provided device ID and stream. More... | |
|
overridevirtual |
Checks if the allocator can be used safely with the provided device ID and stream.
The check is necessary to ensure safe usage of stream-ordered allocators and unified shared memory allocators.
device_id | the device ID the allocator will be used in. |
stream | the stream the allocator will be used with. |
Reimplemented from gko::CudaAllocatorBase.