Memory Management

Allocation of CUDA mapped zero-copy memory. More...

Functions
bool	cudaAllocMapped (void **cpuPtr, void **gpuPtr, size_t size)
	Allocate ZeroCopy mapped memory, shared between CUDA and CPU. More...
bool	cudaAllocMapped (void **ptr, size_t size)
	Allocate ZeroCopy mapped memory, shared between CUDA and CPU. More...
bool	cudaAllocMapped (void **ptr, size_t width, size_t height, imageFormat format)
	Allocate ZeroCopy mapped memory, shared between CUDA and CPU. More...
bool	cudaAllocMapped (void **ptr, const int2 &dims, imageFormat format)
	Allocate ZeroCopy mapped memory, shared between CUDA and CPU. More...
template<typename T >
bool	cudaAllocMapped (T **ptr, size_t width, size_t height)
	Allocate ZeroCopy mapped memory, shared between CUDA and CPU. More...
template<typename T >
bool	cudaAllocMapped (T **ptr, const int2 &dims)
	Allocate ZeroCopy mapped memory, shared between CUDA and CPU. More...
template<typename T >
bool	cudaAllocMapped (T **ptr, size_t size)
	Allocate ZeroCopy mapped memory, shared between CUDA and CPU. More...

Detailed Description

Allocation of CUDA mapped zero-copy memory.

Function Documentation

cudaAllocMapped() [1/7]

template<typename T >

bool cudaAllocMapped ( T **  ptr, const int2 &  dims  )

inline

Allocate ZeroCopy mapped memory, shared between CUDA and CPU.

This is a templated version for allocating images from vector types like uchar3, uchar4, float3, float4, ect. The overall size of the allocation will be calculated as dims.x * dims.y * sizeof(T).

Parameters

[out]	ptr	Returned pointer to the shared CPU/GPU memory.
[in]	dims	int2 vector where width=dims.x and height=dims.y

Returns

true if the allocation succeeded, false otherwise.

cudaAllocMapped() [2/7]

template<typename T >

bool cudaAllocMapped ( T **  ptr, size_t  size  )

inline

Allocate ZeroCopy mapped memory, shared between CUDA and CPU.

This is a templated version for allocating images from vector types like uchar3, uchar4, float3, float4, ect. The overall size of the allocation is specified by the size parameter.

Parameters

[out]	ptr	Returned pointer to the shared CPU/GPU memory.
[in]	size	size of the allocation, in bytes.

Returns

true if the allocation succeeded, false otherwise.

cudaAllocMapped() [3/7]

template<typename T >

bool cudaAllocMapped ( T **  ptr, size_t  width, size_t  height  )

inline

Allocate ZeroCopy mapped memory, shared between CUDA and CPU.

This is a templated version for allocating images from vector types like uchar3, uchar4, float3, float4, ect. The overall size of the allocation will be calculated as width * height * sizeof(T).

Parameters

[out]	ptr	Returned pointer to the shared CPU/GPU memory.
[in]	width	Width (in pixels) to allocate.
[in]	height	Height (in pixels) to allocate.

Returns

true if the allocation succeeded, false otherwise.

cudaAllocMapped() [4/7]

bool cudaAllocMapped ( void **  cpuPtr, void **  gpuPtr, size_t  size  )

inline

Allocate ZeroCopy mapped memory, shared between CUDA and CPU.

Note

although two pointers are returned, one for CPU and GPU, they both resolve to the same physical memory.

Parameters

[out]	cpuPtr	Returned CPU pointer to the shared memory.
[out]	gpuPtr	Returned GPU pointer to the shared memory.
[in]	size	Size (in bytes) of the shared memory to allocate.

Returns

true if the allocation succeeded, false otherwise.

cudaAllocMapped() [5/7]

bool cudaAllocMapped ( void **  ptr, const int2 &  dims, imageFormat  format  )

inline

Allocate ZeroCopy mapped memory, shared between CUDA and CPU.

This overload is for allocating images from an imageFormat type and the image dimensions. The overall size of the allocation will be calculated with the imageFormatSize() function.

Parameters

[out]	ptr	Returned pointer to the shared CPU/GPU memory.
[in]	dims	int2 vector where width=dims.x and height=dims.y
[in]	format	Format of the image.

Returns

true if the allocation succeeded, false otherwise.

cudaAllocMapped() [6/7]

bool cudaAllocMapped ( void **  ptr, size_t  size  )

inline

Allocate ZeroCopy mapped memory, shared between CUDA and CPU.

Note

this overload of cudaAllocMapped returns one pointer, assumes that the CPU and GPU addresses will match (as is the case with any recent CUDA version).

Parameters

[out]	ptr	Returned pointer to the shared CPU/GPU memory.
[in]	size	Size (in bytes) of the shared memory to allocate.

Returns

true if the allocation succeeded, false otherwise.

cudaAllocMapped() [7/7]

bool cudaAllocMapped ( void **  ptr, size_t  width, size_t  height, imageFormat  format  )

inline

Allocate ZeroCopy mapped memory, shared between CUDA and CPU.

This overload is for allocating images from an imageFormat type and the image dimensions. The overall size of the allocation will be calculated with the imageFormatSize() function.

Parameters

[out]	ptr	Returned pointer to the shared CPU/GPU memory.
[in]	width	Width (in pixels) to allocate.
[in]	height	Height (in pixels) to allocate.
[in]	format	Format of the image.

Returns

true if the allocation succeeded, false otherwise.