Memory resource that wraps managed CUDA allocation. More...
#include <vecmem/memory/cuda/managed_memory_resource.hpp>
Inheritance diagram for vecmem::cuda::managed_memory_resource:
Public Member Functions | |
| VECMEM_CUDA_EXPORT | managed_memory_resource () |
| Default constructor. | |
| VECMEM_CUDA_EXPORT | ~managed_memory_resource () |
| Destructor. | |
Private Member Functions | |
Function(s) implementing @c vecmem::memory_resource | |
| virtual VECMEM_CUDA_EXPORT void * | do_allocate (std::size_t, std::size_t) override final |
| Allocate CUDA managed memory. | |
| virtual VECMEM_CUDA_EXPORT void | do_deallocate (void *p, std::size_t, std::size_t) override final |
| De-allocate a previously allocated managed memory block. | |
| virtual VECMEM_CUDA_EXPORT bool | do_is_equal (const memory_resource &other) const noexcept override final |
Compares *this for equality with other. | |
Detailed Description
Memory resource that wraps managed CUDA allocation.
This is an allocator-type memory resource that allocates managed CUDA memory, which is accessible directly to devices as well as to the host.
The documentation for this class was generated from the following files:
- cuda/include/vecmem/memory/cuda/managed_memory_resource.hpp
- cuda/src/memory/managed_memory_resource.cpp
