Movatterモバイル変換

This section describes the graphics interoperability functions of the CUDA runtime application programming interface.

Functions

__host__ ​cudaError_t cudaGraphicsMapResources ( int count,cudaGraphicsResource_t* resources,cudaStream_t stream =0 )

Map graphics resources for access by CUDA.

Parameters

count

- Number of resources to map

resources

- Resources to map for CUDA

stream

- Stream for synchronization

Returns

cudaSuccess,cudaErrorInvalidResourceHandle,cudaErrorUnknown

Description

Maps thecount graphics resources inresources for access by CUDA.

The resources inresources may be accessed by CUDA until they are unmapped. The graphics API from whichresources were registered should not access any resources while they are mapped by CUDA. If an application does so, the results are undefined.

This function provides the synchronization guarantee that any graphics calls issued beforecudaGraphicsMapResources() will complete before any subsequent CUDA work issued instream begins.

Ifresources contains any duplicate entries thencudaErrorInvalidResourceHandle is returned. If any ofresources are presently mapped for access by CUDA thencudaErrorUnknown is returned.

Note:

• This function uses standarddefault stream semantics.

• Note that this function may also return error codes from previous, asynchronous launches.

• Note that this function may also returncudaErrorInitializationError,cudaErrorInsufficientDriver orcudaErrorNoDevice if this call tries to initialize internal CUDA RT state.

• Note that as specified bycudaStreamAddCallback no CUDA function may be called from callback.cudaErrorNotPermitted may, but is not guaranteed to, be returned as a diagnostic in such case.

See also:

cudaGraphicsResourceGetMappedPointer,cudaGraphicsSubResourceGetMappedArray,cudaGraphicsUnmapResources,cuGraphicsMapResources

__host__ ​cudaError_t cudaGraphicsResourceGetMappedMipmappedArray (cudaMipmappedArray_t* mipmappedArray,cudaGraphicsResource_t resource )

Get a mipmapped array through which to access a mapped graphics resource.

Parameters

mipmappedArray

- Returned mipmapped array through whichresource may be accessed

resource

- Mapped resource to access

Returns

cudaSuccess,cudaErrorInvalidValue,cudaErrorInvalidResourceHandle,cudaErrorUnknown

Description

Returns in*mipmappedArray a mipmapped array through which the mapped graphics resourceresource may be accessed. The value set inmipmappedArray may change every time thatresource is mapped.

Ifresource is not a texture then it cannot be accessed via an array andcudaErrorUnknown is returned. Ifresource is not mapped thencudaErrorUnknown is returned.

Note:

• Note that this function may also return error codes from previous, asynchronous launches.

• Note that this function may also returncudaErrorInitializationError,cudaErrorInsufficientDriver orcudaErrorNoDevice if this call tries to initialize internal CUDA RT state.

• Note that as specified bycudaStreamAddCallback no CUDA function may be called from callback.cudaErrorNotPermitted may, but is not guaranteed to, be returned as a diagnostic in such case.

See also:

cudaGraphicsResourceGetMappedPointer,cuGraphicsResourceGetMappedMipmappedArray

__host__ ​cudaError_t cudaGraphicsResourceGetMappedPointer ( void** devPtr, size_t* size,cudaGraphicsResource_t resource )

Get an device pointer through which to access a mapped graphics resource.

Parameters

devPtr

- Returned pointer through whichresource may be accessed

size

- Returned size of the buffer accessible starting at*devPtr

resource

- Mapped resource to access

Returns

cudaSuccess,cudaErrorInvalidValue,cudaErrorInvalidResourceHandle,cudaErrorUnknown

Description

Returns in*devPtr a pointer through which the mapped graphics resourceresource may be accessed. Returns in*size the size of the memory in bytes which may be accessed from that pointer. The value set indevPtr may change every time thatresource is mapped.

Ifresource is not a buffer then it cannot be accessed via a pointer andcudaErrorUnknown is returned. Ifresource is not mapped thencudaErrorUnknown is returned. *

Note:

• Note that this function may also return error codes from previous, asynchronous launches.

• Note that this function may also returncudaErrorInitializationError,cudaErrorInsufficientDriver orcudaErrorNoDevice if this call tries to initialize internal CUDA RT state.

• Note that as specified bycudaStreamAddCallback no CUDA function may be called from callback.cudaErrorNotPermitted may, but is not guaranteed to, be returned as a diagnostic in such case.

See also:

cudaGraphicsMapResources,cudaGraphicsSubResourceGetMappedArray,cuGraphicsResourceGetMappedPointer

__host__ ​cudaError_t cudaGraphicsResourceSetMapFlags (cudaGraphicsResource_t resource, unsigned int flags )

Set usage flags for mapping a graphics resource.

Parameters

resource

- Registered resource to set flags for

flags

- Parameters for resource mapping

Returns

cudaSuccess,cudaErrorInvalidValue,cudaErrorInvalidResourceHandle,cudaErrorUnknown,

Description

Setflags for mapping the graphics resourceresource.

Changes toflags will take effect the next timeresource is mapped. Theflags argument may be any of the following:

• cudaGraphicsMapFlagsNone: Specifies no hints about howresource will be used. It is therefore assumed that CUDA may read from or write toresource.

• cudaGraphicsMapFlagsReadOnly: Specifies that CUDA will not write toresource.

• cudaGraphicsMapFlagsWriteDiscard: Specifies CUDA will not read fromresource and will write over the entire contents ofresource, so none of the data previously stored inresource will be preserved.

Ifresource is presently mapped for access by CUDA thencudaErrorUnknown is returned. Ifflags is not one of the above values thencudaErrorInvalidValue is returned.

Note:

• Note that this function may also return error codes from previous, asynchronous launches.

• Note that this function may also returncudaErrorInitializationError,cudaErrorInsufficientDriver orcudaErrorNoDevice if this call tries to initialize internal CUDA RT state.

• Note that as specified bycudaStreamAddCallback no CUDA function may be called from callback.cudaErrorNotPermitted may, but is not guaranteed to, be returned as a diagnostic in such case.

See also:

cudaGraphicsMapResources,cuGraphicsResourceSetMapFlags

__host__ ​cudaError_t cudaGraphicsSubResourceGetMappedArray (cudaArray_t* array,cudaGraphicsResource_t resource, unsigned int arrayIndex, unsigned int mipLevel )

Get an array through which to access a subresource of a mapped graphics resource.

Parameters

array

- Returned array through which a subresource ofresource may be accessed

resource

- Mapped resource to access

arrayIndex

- Array index for array textures or cubemap face index as defined bycudaGraphicsCubeFace for cubemap textures for the subresource to access

mipLevel

- Mipmap level for the subresource to access

Returns

cudaSuccess,cudaErrorInvalidValue,cudaErrorInvalidResourceHandle,cudaErrorUnknown

Description

Returns in*array an array through which the subresource of the mapped graphics resourceresource which corresponds to array indexarrayIndex and mipmap levelmipLevel may be accessed. The value set inarray may change every time thatresource is mapped.

Ifresource is not a texture then it cannot be accessed via an array andcudaErrorUnknown is returned. IfarrayIndex is not a valid array index forresource thencudaErrorInvalidValue is returned. IfmipLevel is not a valid mipmap level forresource thencudaErrorInvalidValue is returned. Ifresource is not mapped thencudaErrorUnknown is returned.

Note:

• Note that this function may also return error codes from previous, asynchronous launches.

• Note that this function may also returncudaErrorInitializationError,cudaErrorInsufficientDriver orcudaErrorNoDevice if this call tries to initialize internal CUDA RT state.

• Note that as specified bycudaStreamAddCallback no CUDA function may be called from callback.cudaErrorNotPermitted may, but is not guaranteed to, be returned as a diagnostic in such case.

See also:

cudaGraphicsResourceGetMappedPointer,cuGraphicsSubResourceGetMappedArray

__host__ ​cudaError_t cudaGraphicsUnmapResources ( int count,cudaGraphicsResource_t* resources,cudaStream_t stream =0 )

Unmap graphics resources.

Parameters

count

- Number of resources to unmap

resources

- Resources to unmap

stream

- Stream for synchronization

Returns

cudaSuccess,cudaErrorInvalidResourceHandle,cudaErrorUnknown

Description

Unmaps thecount graphics resources inresources.

Once unmapped, the resources inresources may not be accessed by CUDA until they are mapped again.

This function provides the synchronization guarantee that any CUDA work issued instream beforecudaGraphicsUnmapResources() will complete before any subsequently issued graphics work begins.

Ifresources contains any duplicate entries thencudaErrorInvalidResourceHandle is returned. If any ofresources are not presently mapped for access by CUDA thencudaErrorUnknown is returned.

Note:

• This function uses standarddefault stream semantics.

• Note that this function may also return error codes from previous, asynchronous launches.

• Note that this function may also returncudaErrorInitializationError,cudaErrorInsufficientDriver orcudaErrorNoDevice if this call tries to initialize internal CUDA RT state.

• Note that as specified bycudaStreamAddCallback no CUDA function may be called from callback.cudaErrorNotPermitted may, but is not guaranteed to, be returned as a diagnostic in such case.

See also:

cudaGraphicsMapResources,cuGraphicsUnmapResources

__host__ ​cudaError_t cudaGraphicsUnregisterResource (cudaGraphicsResource_t resource )

Unregisters a graphics resource for access by CUDA.

Parameters

resource

- Resource to unregister

Returns

cudaSuccess,cudaErrorInvalidResourceHandle,cudaErrorUnknown

Description

Unregisters the graphics resourceresource so it is not accessible by CUDA unless registered again.

Ifresource is invalid thencudaErrorInvalidResourceHandle is returned.

Note:

• Note that this function may also return error codes from previous, asynchronous launches.

• Note that this function may also returncudaErrorInitializationError,cudaErrorInsufficientDriver orcudaErrorNoDevice if this call tries to initialize internal CUDA RT state.

• Note that as specified bycudaStreamAddCallback no CUDA function may be called from callback.cudaErrorNotPermitted may, but is not guaranteed to, be returned as a diagnostic in such case.

• Use of the handle after this call is undefined behavior.

See also:

cudaGraphicsD3D9RegisterResource,cudaGraphicsD3D10RegisterResource,cudaGraphicsD3D11RegisterResource,cudaGraphicsGLRegisterBuffer,cudaGraphicsGLRegisterImage,cuGraphicsUnregisterResource