kvikio::CudaPinnedAllocator Class Reference

Allocator for CUDA pinned host memory. More...

#include <bounce_buffer.hpp>

Public Member Functions
void *	allocate (std::size_t size)
	Allocate CUDA pinned host memory. More...
void	deallocate (void *buffer, std::size_t size)
	Deallocate memory previously allocated by this allocator. More...

Detailed Description

Allocator for CUDA pinned host memory.

Uses cudaMemHostAlloc to allocate pinned (page-locked) host memory that can be efficiently transferred to/from GPU device memory. The allocation is only guaranteed to be aligned to "at least 256 bytes". It is NOT guaranteed to be page aligned.

Note

Do NOT use with Direct I/O - lacks page alignment guarantee

Definition at line 48 of file bounce_buffer.hpp.

Member Function Documentation

allocate()

void* kvikio::CudaPinnedAllocator::allocate

(

std::size_t

size

)

Allocate CUDA pinned host memory.

Parameters

size	Requested size in bytes

Returns

Pointer to allocated pinned memory

deallocate()

void kvikio::CudaPinnedAllocator::deallocate	(	void *	buffer,
		std::size_t	size
	)

Deallocate memory previously allocated by this allocator.

Parameters

buffer	Pointer to memory to deallocate
size	Size of the allocation (unused, for interface consistency)

---

The documentation for this class was generated from the following file:

• bounce_buffer.hpp