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 () override |
| Destructor. | |
Private Member Functions | |
Function(s) implementing @c vecmem::memory_resource | |
| VECMEM_CUDA_EXPORT void * | do_allocate (std::size_t, std::size_t) override |
| Allocate CUDA managed memory. | |
| VECMEM_CUDA_EXPORT void | do_deallocate (void *p, std::size_t, std::size_t) override |
| De-allocate a previously allocated managed memory block. | |
| VECMEM_CUDA_EXPORT bool | do_is_equal (const memory_resource &other) const noexcept override |
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
