Provided by: nvidia-cuda-dev_10.1.243-3_amd64 
NAME
C++ API Routines - C++-style interface built on top of CUDA runtime API.
Data Structures
class __cudaOccupancyB2DHelper
Functions
template<class T , int dim> __CUDA_DEPRECATED cudaError_t cudaBindSurfaceToArray (const struct surface<
T, dim > &surf, cudaArray_const_t array)
[C++ API] Binds an array to a surface
template<class T , int dim> __CUDA_DEPRECATED cudaError_t cudaBindSurfaceToArray (const struct surface<
T, dim > &surf, cudaArray_const_t array, const struct cudaChannelFormatDesc &desc)
[C++ API] Binds an array to a surface
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTexture (size_t
*offset, const struct texture< T, dim, readMode > &tex, const void *devPtr, size_t size=UINT_MAX)
[C++ API] Binds a memory area to a texture
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTexture (size_t
*offset, const struct texture< T, dim, readMode > &tex, const void *devPtr, const struct
cudaChannelFormatDesc &desc, size_t size=UINT_MAX)
[C++ API] Binds a memory area to a texture
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTexture2D (size_t
*offset, const struct texture< T, dim, readMode > &tex, const void *devPtr, size_t width, size_t
height, size_t pitch)
[C++ API] Binds a 2D memory area to a texture
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTexture2D (size_t
*offset, const struct texture< T, dim, readMode > &tex, const void *devPtr, const struct
cudaChannelFormatDesc &desc, size_t width, size_t height, size_t pitch)
[C++ API] Binds a 2D memory area to a texture
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTextureToArray (const
struct texture< T, dim, readMode > &tex, cudaArray_const_t array)
[C++ API] Binds an array to a texture
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTextureToArray (const
struct texture< T, dim, readMode > &tex, cudaArray_const_t array, const struct cudaChannelFormatDesc
&desc)
[C++ API] Binds an array to a texture
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t
cudaBindTextureToMipmappedArray (const struct texture< T, dim, readMode > &tex,
cudaMipmappedArray_const_t mipmappedArray)
[C++ API] Binds a mipmapped array to a texture
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t
cudaBindTextureToMipmappedArray (const struct texture< T, dim, readMode > &tex,
cudaMipmappedArray_const_t mipmappedArray, const struct cudaChannelFormatDesc &desc)
[C++ API] Binds a mipmapped array to a texture
template<class T > cudaChannelFormatDesc cudaCreateChannelDesc (void)
[C++ API] Returns a channel descriptor using the specified format
cudaError_t cudaEventCreate (cudaEvent_t *event, unsigned int flags)
[C++ API] Creates an event object with the specified flags
template<class T > cudaError_t cudaFuncGetAttributes (struct cudaFuncAttributes *attr, T *entry)
[C++ API] Find out attributes for a given function
template<class T > cudaError_t cudaFuncSetAttribute (T *entry, enum cudaFuncAttribute attr, int value)
[C++ API] Set attributes for a given function
template<class T > cudaError_t cudaFuncSetCacheConfig (T *func, enum cudaFuncCache cacheConfig)
[C++ API] Sets the preferred cache configuration for a device function
template<class T > cudaError_t cudaGetSymbolAddress (void **devPtr, const T &symbol)
[C++ API] Finds the address associated with a CUDA symbol
template<class T > cudaError_t cudaGetSymbolSize (size_t *size, const T &symbol)
[C++ API] Finds the size of the object associated with a CUDA symbol
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaGetTextureAlignmentOffset
(size_t *offset, const struct texture< T, dim, readMode > &tex)
[C++ API] Get the alignment offset of a texture
template<class T > cudaError_t cudaLaunchCooperativeKernel (const T *func, dim3 gridDim, dim3 blockDim,
void **args, size_t sharedMem=0, cudaStream_t stream=0)
Launches a device function.
template<class T > cudaError_t cudaLaunchKernel (const T *func, dim3 gridDim, dim3 blockDim, void **args,
size_t sharedMem=0, cudaStream_t stream=0)
Launches a device function.
cudaError_t cudaMallocHost (void **ptr, size_t size, unsigned int flags)
[C++ API] Allocates page-locked memory on the host
template<class T > cudaError_t cudaMallocManaged (T **devPtr, size_t size, unsigned int
flags=cudaMemAttachGlobal)
Allocates memory that will be automatically managed by the Unified Memory system.
template<class T > cudaError_t cudaMemcpyFromSymbol (void *dst, const T &symbol, size_t count, size_t
offset=0, enum cudaMemcpyKind kind=cudaMemcpyDeviceToHost)
[C++ API] Copies data from the given symbol on the device
template<class T > cudaError_t cudaMemcpyFromSymbolAsync (void *dst, const T &symbol, size_t count,
size_t offset=0, enum cudaMemcpyKind kind=cudaMemcpyDeviceToHost, cudaStream_t stream=0)
[C++ API] Copies data from the given symbol on the device
template<class T > cudaError_t cudaMemcpyToSymbol (const T &symbol, const void *src, size_t count, size_t
offset=0, enum cudaMemcpyKind kind=cudaMemcpyHostToDevice)
[C++ API] Copies data to the given symbol on the device
template<class T > cudaError_t cudaMemcpyToSymbolAsync (const T &symbol, const void *src, size_t count,
size_t offset=0, enum cudaMemcpyKind kind=cudaMemcpyHostToDevice, cudaStream_t stream=0)
[C++ API] Copies data to the given symbol on the device
template<class T > cudaError_t cudaOccupancyMaxActiveBlocksPerMultiprocessor (int *numBlocks, T func, int
blockSize, size_t dynamicSMemSize)
Returns occupancy for a device function.
template<class T > cudaError_t cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags (int *numBlocks, T
func, int blockSize, size_t dynamicSMemSize, unsigned int flags)
Returns occupancy for a device function with the specified flags.
template<class T > CUDART_DEVICE cudaError_t cudaOccupancyMaxPotentialBlockSize (int *minGridSize, int
*blockSize, T func, size_t dynamicSMemSize=0, int blockSizeLimit=0)
Returns grid and block size that achieves maximum potential occupancy for a device function.
template<typename UnaryFunction , class T > CUDART_DEVICE cudaError_t
cudaOccupancyMaxPotentialBlockSizeVariableSMem (int *minGridSize, int *blockSize, T func,
UnaryFunction blockSizeToDynamicSMemSize, int blockSizeLimit=0)
Returns grid and block size that achieves maximum potential occupancy for a device function.
template<typename UnaryFunction , class T > CUDART_DEVICE cudaError_t
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags (int *minGridSize, int *blockSize, T func,
UnaryFunction blockSizeToDynamicSMemSize, int blockSizeLimit=0, unsigned int flags=0)
Returns grid and block size that achieves maximum potential occupancy for a device function.
template<class T > CUDART_DEVICE cudaError_t cudaOccupancyMaxPotentialBlockSizeWithFlags (int
*minGridSize, int *blockSize, T func, size_t dynamicSMemSize=0, int blockSizeLimit=0, unsigned int
flags=0)
Returns grid and block size that achieved maximum potential occupancy for a device function with the
specified flags.
template<class T > cudaError_t cudaStreamAttachMemAsync (cudaStream_t stream, T *devPtr, size_t length=0,
unsigned int flags=cudaMemAttachSingle)
Attach memory to a stream asynchronously.
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaUnbindTexture (const
struct texture< T, dim, readMode > &tex)
[C++ API] Unbinds a texture
Detailed Description
\brief C++ high level API functions of the CUDA runtime API (cuda_runtime_api.h)
This section describes the C++ high level API functions of the CUDA runtime application programming
interface. To use these functions, your application needs to be compiled with the nvcc compiler.
Function Documentation
template<class T , int dim> __CUDA_DEPRECATED cudaError_t cudaBindSurfaceToArray (const struct surface< T,
dim > & surf, cudaArray_const_t array)
Binds the CUDA array array to the surface reference surf. The channel descriptor is inherited from the
CUDA array. Any CUDA array previously bound to surf is unbound.
Parameters:
surf - Surface to bind
array - Memory array on device
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidSurface
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaBindSurfaceToArray (C API), cudaBindSurfaceToArray (C++ API)
template<class T , int dim> __CUDA_DEPRECATED cudaError_t cudaBindSurfaceToArray (const struct surface< T,
dim > & surf, cudaArray_const_t array, const struct cudaChannelFormatDesc & desc)
Binds the CUDA array array to the surface reference surf. desc describes how the memory is interpreted
when dealing with the surface. Any CUDA array previously bound to surf is unbound.
Parameters:
surf - Surface to bind
array - Memory array on device
desc - Channel format
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidSurface
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaBindSurfaceToArray (C API), cudaBindSurfaceToArray (C++ API, inherited channel descriptor)
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTexture (size_t * offset,
const struct texture< T, dim, readMode > & tex, const void * devPtr, size_t size = UINT_MAX)
Binds size bytes of the memory area pointed to by devPtr to texture reference tex. The channel descriptor
is inherited from the texture reference type. The offset parameter is an optional byte offset as with the
low-level cudaBindTexture(size_t*, const struct textureReference*, const void*, const struct
cudaChannelFormatDesc*, size_t) function. Any memory previously bound to tex is unbound.
Parameters:
offset - Offset in bytes
tex - Texture to bind
devPtr - Memory area on device
size - Size of the memory area pointed to by devPtr
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidTexture
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C
API), cudaBindTexture (C++ API), cudaBindTexture2D (C++ API), cudaBindTexture2D (C++ API, inherited
channel descriptor), cudaBindTextureToArray (C++ API), cudaBindTextureToArray (C++ API, inherited
channel descriptor), cudaUnbindTexture (C++ API), cudaGetTextureAlignmentOffset (C++ API)
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTexture (size_t * offset,
const struct texture< T, dim, readMode > & tex, const void * devPtr, const struct cudaChannelFormatDesc &
desc, size_t size = UINT_MAX)
Binds size bytes of the memory area pointed to by devPtr to texture reference tex. desc describes how the
memory is interpreted when fetching values from the texture. The offset parameter is an optional byte
offset as with the low-level cudaBindTexture() function. Any memory previously bound to tex is unbound.
Parameters:
offset - Offset in bytes
tex - Texture to bind
devPtr - Memory area on device
desc - Channel format
size - Size of the memory area pointed to by devPtr
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidTexture
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C
API), cudaBindTexture (C++ API, inherited channel descriptor), cudaBindTexture2D (C++ API),
cudaBindTexture2D (C++ API, inherited channel descriptor), cudaBindTextureToArray (C++ API),
cudaBindTextureToArray (C++ API, inherited channel descriptor), cudaUnbindTexture (C++ API),
cudaGetTextureAlignmentOffset (C++ API)
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTexture2D (size_t *
offset, const struct texture< T, dim, readMode > & tex, const void * devPtr, size_t width, size_t height,
size_t pitch)
Binds the 2D memory area pointed to by devPtr to the texture reference tex. The size of the area is
constrained by width in texel units, height in texel units, and pitch in byte units. The channel
descriptor is inherited from the texture reference type. Any memory previously bound to tex is unbound.
Since the hardware enforces an alignment requirement on texture base addresses, cudaBindTexture2D()
returns in *offset a byte offset that must be applied to texture fetches in order to read from the
desired memory. This offset must be divided by the texel size and passed to kernels that read from the
texture so they can be applied to the tex2D() function. If the device memory pointer was returned from
cudaMalloc(), the offset is guaranteed to be 0 and NULL may be passed as the offset parameter.
Parameters:
offset - Offset in bytes
tex - Texture reference to bind
devPtr - 2D memory area on device
width - Width in texel units
height - Height in texel units
pitch - Pitch in bytes
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidTexture
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C++
API), cudaBindTexture (C++ API, inherited channel descriptor), cudaBindTexture2D (C API),
cudaBindTexture2D (C++ API), cudaBindTextureToArray (C++ API), cudaBindTextureToArray (C++ API,
inherited channel descriptor), cudaUnbindTexture (C++ API), cudaGetTextureAlignmentOffset (C++ API)
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTexture2D (size_t *
offset, const struct texture< T, dim, readMode > & tex, const void * devPtr, const struct
cudaChannelFormatDesc & desc, size_t width, size_t height, size_t pitch)
Binds the 2D memory area pointed to by devPtr to the texture reference tex. The size of the area is
constrained by width in texel units, height in texel units, and pitch in byte units. desc describes how
the memory is interpreted when fetching values from the texture. Any memory previously bound to tex is
unbound.
Since the hardware enforces an alignment requirement on texture base addresses, cudaBindTexture2D()
returns in *offset a byte offset that must be applied to texture fetches in order to read from the
desired memory. This offset must be divided by the texel size and passed to kernels that read from the
texture so they can be applied to the tex2D() function. If the device memory pointer was returned from
cudaMalloc(), the offset is guaranteed to be 0 and NULL may be passed as the offset parameter.
Parameters:
offset - Offset in bytes
tex - Texture reference to bind
devPtr - 2D memory area on device
desc - Channel format
width - Width in texel units
height - Height in texel units
pitch - Pitch in bytes
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidTexture
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C++
API), cudaBindTexture (C++ API, inherited channel descriptor), cudaBindTexture2D (C API),
cudaBindTexture2D (C++ API, inherited channel descriptor), cudaBindTextureToArray (C++ API),
cudaBindTextureToArray (C++ API, inherited channel descriptor), cudaUnbindTexture (C++ API),
cudaGetTextureAlignmentOffset (C++ API)
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTextureToArray (const
struct texture< T, dim, readMode > & tex, cudaArray_const_t array)
Binds the CUDA array array to the texture reference tex. The channel descriptor is inherited from the
CUDA array. Any CUDA array previously bound to tex is unbound.
Parameters:
tex - Texture to bind
array - Memory array on device
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidTexture
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C++
API), cudaBindTexture (C++ API, inherited channel descriptor), cudaBindTexture2D (C++ API),
cudaBindTexture2D (C++ API, inherited channel descriptor), cudaBindTextureToArray (C API),
cudaBindTextureToArray (C++ API), cudaUnbindTexture (C++ API), cudaGetTextureAlignmentOffset (C++
API)
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTextureToArray (const
struct texture< T, dim, readMode > & tex, cudaArray_const_t array, const struct cudaChannelFormatDesc &
desc)
Binds the CUDA array array to the texture reference tex. desc describes how the memory is interpreted
when fetching values from the texture. Any CUDA array previously bound to tex is unbound.
Parameters:
tex - Texture to bind
array - Memory array on device
desc - Channel format
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidTexture
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C++
API), cudaBindTexture (C++ API, inherited channel descriptor), cudaBindTexture2D (C++ API),
cudaBindTexture2D (C++ API, inherited channel descriptor), cudaBindTextureToArray (C API),
cudaBindTextureToArray (C++ API, inherited channel descriptor), cudaUnbindTexture (C++ API),
cudaGetTextureAlignmentOffset (C++ API)
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTextureToMipmappedArray
(const struct texture< T, dim, readMode > & tex, cudaMipmappedArray_const_t mipmappedArray)
Binds the CUDA mipmapped array mipmappedArray to the texture reference tex. The channel descriptor is
inherited from the CUDA array. Any CUDA mipmapped array previously bound to tex is unbound.
Parameters:
tex - Texture to bind
mipmappedArray - Memory mipmapped array on device
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidTexture
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C++
API), cudaBindTexture (C++ API, inherited channel descriptor), cudaBindTexture2D (C++ API),
cudaBindTexture2D (C++ API, inherited channel descriptor), cudaBindTextureToArray (C API),
cudaBindTextureToArray (C++ API), cudaUnbindTexture (C++ API), cudaGetTextureAlignmentOffset (C++
API)
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaBindTextureToMipmappedArray
(const struct texture< T, dim, readMode > & tex, cudaMipmappedArray_const_t mipmappedArray, const struct
cudaChannelFormatDesc & desc)
Binds the CUDA mipmapped array mipmappedArray to the texture reference tex. desc describes how the memory
is interpreted when fetching values from the texture. Any CUDA mipmapped array previously bound to tex is
unbound.
Parameters:
tex - Texture to bind
mipmappedArray - Memory mipmapped array on device
desc - Channel format
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidTexture
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C++
API), cudaBindTexture (C++ API, inherited channel descriptor), cudaBindTexture2D (C++ API),
cudaBindTexture2D (C++ API, inherited channel descriptor), cudaBindTextureToArray (C API),
cudaBindTextureToArray (C++ API, inherited channel descriptor), cudaUnbindTexture (C++ API),
cudaGetTextureAlignmentOffset (C++ API)
template<class T > cudaChannelFormatDesc cudaCreateChannelDesc (void)
Returns a channel descriptor with format f and number of bits of each component x, y, z, and w. The
cudaChannelFormatDesc is defined as:
struct cudaChannelFormatDesc {
int x, y, z, w;
enum cudaChannelFormatKind f;
};
where cudaChannelFormatKind is one of cudaChannelFormatKindSigned, cudaChannelFormatKindUnsigned, or
cudaChannelFormatKindFloat.
Returns:
Channel descriptor with format f
See also:
cudaCreateChannelDesc (Low level), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (High
level), cudaBindTexture (High level, inherited channel descriptor), cudaBindTexture2D (High level),
cudaBindTextureToArray (High level), cudaBindTextureToArray (High level, inherited channel
descriptor), cudaUnbindTexture (High level), cudaGetTextureAlignmentOffset (High level)
cudaError_t cudaEventCreate (cudaEvent_t * event, unsigned int flags)
Creates an event object with the specified flags. Valid flags include:
• cudaEventDefault: Default event creation flag.
• cudaEventBlockingSync: Specifies that event should use blocking synchronization. A host thread that
uses cudaEventSynchronize() to wait on an event created with this flag will block until the event
actually completes.
• cudaEventDisableTiming: Specifies that the created event does not need to record timing data. Events
created with this flag specified and the cudaEventBlockingSync flag not specified will provide the best
performance when used with cudaStreamWaitEvent() and cudaEventQuery().
Parameters:
event - Newly created event
flags - Flags for new event
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorLaunchFailure, cudaErrorMemoryAllocation
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaEventCreate (C API), cudaEventCreateWithFlags, cudaEventRecord, cudaEventQuery,
cudaEventSynchronize, cudaEventDestroy, cudaEventElapsedTime, cudaStreamWaitEvent
template<class T > cudaError_t cudaFuncGetAttributes (struct cudaFuncAttributes * attr, T * entry)
This function obtains the attributes of a function specified via entry. The parameter entry must be a
pointer to a function that executes on the device. The parameter specified by entry must be declared as a
__global__ function. The fetched attributes are placed in attr. If the specified function does not exist,
then cudaErrorInvalidDeviceFunction is returned.
Note that some function attributes such as maxThreadsPerBlock may vary based on the device that is
currently being used.
Parameters:
attr - Return pointer to function's attributes
entry - Function to get attributes of
Returns:
cudaSuccess, cudaErrorInvalidDeviceFunction
Note:
Note that this function may also return error codes from previous, asynchronous launches.
cudaLaunchKernel (C++ API), cudaFuncSetCacheConfig (C++ API), cudaFuncGetAttributes (C API),
cudaSetDoubleForDevice, cudaSetDoubleForHost
template<class T > cudaError_t cudaFuncSetAttribute (T * entry, enum cudaFuncAttribute attr, int value)
This function sets the attributes of a function specified via entry. The parameter entry must be a
pointer to a function that executes on the device. The parameter specified by entry must be declared as a
__global__ function. The enumeration defined by attr is set to the value defined by value. If the
specified function does not exist, then cudaErrorInvalidDeviceFunction is returned. If the specified
attribute cannot be written, or if the value is incorrect, then cudaErrorInvalidValue is returned.
Valid values for attr are:
• cudaFuncAttributeMaxDynamicSharedMemorySize - The requested maximum size in bytes of dynamically-
allocated shared memory. The sum of this value and the function attribute sharedSizeBytes cannot exceed
the device attribute cudaDevAttrMaxSharedMemoryPerBlockOptin. The maximal size of requestable dynamic
shared memory may differ by GPU architecture.
• cudaFuncAttributePreferredSharedMemoryCarveout - On devices where the L1 cache and shared memory use
the same hardware resources, this sets the shared memory carveout preference, in percent of the total
shared memory. See cudaDevAttrMaxSharedMemoryPerMultiprocessor. This is only a hint, and the driver can
choose a different ratio if required to execute the function.
Parameters:
entry - Function to get attributes of
attr - Attribute to set
value - Value to set
Returns:
cudaSuccess, cudaErrorInvalidDeviceFunction, cudaErrorInvalidValue
Note:
Note that this function may also return error codes from previous, asynchronous launches.
cudaLaunchKernel (C++ API), cudaFuncSetCacheConfig (C++ API), cudaFuncGetAttributes (C API),
cudaSetDoubleForDevice, cudaSetDoubleForHost
template<class T > cudaError_t cudaFuncSetCacheConfig (T * func, enum cudaFuncCache cacheConfig)
On devices where the L1 cache and shared memory use the same hardware resources, this sets through
cacheConfig the preferred cache configuration for the function specified via func. This is only a
preference. The runtime will use the requested configuration if possible, but it is free to choose a
different configuration if required to execute func.
func must be a pointer to a function that executes on the device. The parameter specified by func must be
declared as a __global__ function. If the specified function does not exist, then
cudaErrorInvalidDeviceFunction is returned.
This setting does nothing on devices where the size of the L1 cache and shared memory are fixed.
Launching a kernel with a different preference than the most recent preference setting may insert a
device-side synchronization point.
The supported cache configurations are:
• cudaFuncCachePreferNone: no preference for shared memory or L1 (default)
• cudaFuncCachePreferShared: prefer larger shared memory and smaller L1 cache
• cudaFuncCachePreferL1: prefer larger L1 cache and smaller shared memory
Parameters:
func - device function pointer
cacheConfig - Requested cache configuration
Returns:
cudaSuccess, cudaErrorInvalidDeviceFunction
Note:
Note that this function may also return error codes from previous, asynchronous launches.
cudaLaunchKernel (C++ API), cudaFuncSetCacheConfig (C API), cudaFuncGetAttributes (C++ API),
cudaSetDoubleForDevice, cudaSetDoubleForHost, cudaThreadGetCacheConfig, cudaThreadSetCacheConfig
template<class T > cudaError_t cudaGetSymbolAddress (void ** devPtr, const T & symbol)
Returns in *devPtr the address of symbol symbol on the device. symbol can either be a variable that
resides in global or constant memory space. If symbol cannot be found, or if symbol is not declared in
the global or constant memory space, *devPtr is unchanged and the error cudaErrorInvalidSymbol is
returned.
Parameters:
devPtr - Return device pointer associated with symbol
symbol - Device symbol reference
Returns:
cudaSuccess, cudaErrorInvalidSymbol, cudaErrorNoKernelImageForDevice
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaGetSymbolAddress (C API), cudaGetSymbolSize (C++ API)
template<class T > cudaError_t cudaGetSymbolSize (size_t * size, const T & symbol)
Returns in *size the size of symbol symbol. symbol must be a variable that resides in global or constant
memory space. If symbol cannot be found, or if symbol is not declared in global or constant memory space,
*size is unchanged and the error cudaErrorInvalidSymbol is returned.
Parameters:
size - Size of object associated with symbol
symbol - Device symbol reference
Returns:
cudaSuccess, cudaErrorInvalidSymbol, cudaErrorNoKernelImageForDevice
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaGetSymbolAddress (C++ API), cudaGetSymbolSize (C API)
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaGetTextureAlignmentOffset
(size_t * offset, const struct texture< T, dim, readMode > & tex)
Returns in *offset the offset that was returned when texture reference tex was bound.
Parameters:
offset - Offset of texture reference in bytes
tex - Texture to get offset of
Returns:
cudaSuccess, cudaErrorInvalidTexture, cudaErrorInvalidTextureBinding
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C++
API), cudaBindTexture (C++ API, inherited channel descriptor), cudaBindTexture2D (C++ API),
cudaBindTexture2D (C++ API, inherited channel descriptor), cudaBindTextureToArray (C++ API),
cudaBindTextureToArray (C++ API, inherited channel descriptor), cudaUnbindTexture (C++ API),
cudaGetTextureAlignmentOffset (C API)
template<class T > cudaError_t cudaLaunchCooperativeKernel (const T * func, dim3 gridDim, dim3 blockDim, void
** args, size_t sharedMem = 0, cudaStream_t stream = 0)
The function invokes kernel func on gridDim (gridDim.x × gridDim.y × gridDim.z) grid of blocks. Each
block contains blockDim (blockDim.x × blockDim.y × blockDim.z) threads.
The device on which this kernel is invoked must have a non-zero value for the device attribute
cudaDevAttrCooperativeLaunch.
The total number of blocks launched cannot exceed the maximum number of blocks per multiprocessor as
returned by cudaOccupancyMaxActiveBlocksPerMultiprocessor (or
cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags) times the number of multiprocessors as specified
by the device attribute cudaDevAttrMultiProcessorCount.
The kernel cannot make use of CUDA dynamic parallelism.
If the kernel has N parameters the args should point to array of N pointers. Each pointer, from args[0]
to args[N - 1], point to the region of memory from which the actual parameter will be copied.
sharedMem sets the amount of dynamic shared memory that will be available to each thread block.
stream specifies a stream the invocation is associated to.
Parameters:
func - Device function symbol
gridDim - Grid dimensions
blockDim - Block dimensions
args - Arguments
sharedMem - Shared memory (defaults to 0)
stream - Stream identifier (defaults to NULL)
Returns:
cudaSuccess, cudaErrorInvalidDeviceFunction, cudaErrorInvalidConfiguration, cudaErrorLaunchFailure,
cudaErrorLaunchTimeout, cudaErrorLaunchOutOfResources, cudaErrorSharedObjectInitFailed
Note:
Note that this function may also return error codes from previous, asynchronous launches.
This function exhibits behavior for most use cases.
This function uses standard semantics.
cudaLaunchCooperativeKernel (C API)
template<class T > cudaError_t cudaLaunchKernel (const T * func, dim3 gridDim, dim3 blockDim, void ** args,
size_t sharedMem = 0, cudaStream_t stream = 0)
The function invokes kernel func on gridDim (gridDim.x × gridDim.y × gridDim.z) grid of blocks. Each
block contains blockDim (blockDim.x × blockDim.y × blockDim.z) threads.
If the kernel has N parameters the args should point to array of N pointers. Each pointer, from args[0]
to args[N - 1], point to the region of memory from which the actual parameter will be copied.
sharedMem sets the amount of dynamic shared memory that will be available to each thread block.
stream specifies a stream the invocation is associated to.
Parameters:
func - Device function symbol
gridDim - Grid dimensions
blockDim - Block dimensions
args - Arguments
sharedMem - Shared memory (defaults to 0)
stream - Stream identifier (defaults to NULL)
Returns:
cudaSuccess, cudaErrorInvalidDeviceFunction, cudaErrorInvalidConfiguration, cudaErrorLaunchFailure,
cudaErrorLaunchTimeout, cudaErrorLaunchOutOfResources, cudaErrorSharedObjectInitFailed,
cudaErrorInvalidPtx, cudaErrorNoKernelImageForDevice, cudaErrorJitCompilerNotFound
Note:
Note that this function may also return error codes from previous, asynchronous launches.
This function exhibits behavior for most use cases.
This function uses standard semantics.
cudaLaunchKernel (C API)
cudaError_t cudaMallocHost (void ** ptr, size_t size, unsigned int flags)
Allocates size bytes of host memory that is page-locked and accessible to the device. The driver tracks
the virtual memory ranges allocated with this function and automatically accelerates calls to functions
such as cudaMemcpy(). Since the memory can be accessed directly by the device, it can be read or written
with much higher bandwidth than pageable memory obtained with functions such as malloc(). Allocating
excessive amounts of pinned memory may degrade system performance, since it reduces the amount of memory
available to the system for paging. As a result, this function is best used sparingly to allocate staging
areas for data exchange between host and device.
The flags parameter enables different options to be specified that affect the allocation, as follows.
• cudaHostAllocDefault: This flag's value is defined to be 0.
• cudaHostAllocPortable: The memory returned by this call will be considered as pinned memory by all CUDA
contexts, not just the one that performed the allocation.
• cudaHostAllocMapped: Maps the allocation into the CUDA address space. The device pointer to the memory
may be obtained by calling cudaHostGetDevicePointer().
• cudaHostAllocWriteCombined: Allocates the memory as write-combined (WC). WC memory can be transferred
across the PCI Express bus more quickly on some system configurations, but cannot be read efficiently
by most CPUs. WC memory is a good option for buffers that will be written by the CPU and read by the
device via mapped pinned memory or host->device transfers.
All of these flags are orthogonal to one another: a developer may allocate memory that is portable,
mapped and/or write-combined with no restrictions.
cudaSetDeviceFlags() must have been called with the cudaDeviceMapHost flag in order for the
cudaHostAllocMapped flag to have any effect.
The cudaHostAllocMapped flag may be specified on CUDA contexts for devices that do not support mapped
pinned memory. The failure is deferred to cudaHostGetDevicePointer() because the memory may be mapped
into other CUDA contexts via the cudaHostAllocPortable flag.
Memory allocated by this function must be freed with cudaFreeHost().
Parameters:
ptr - Device pointer to allocated memory
size - Requested allocation size in bytes
flags - Requested properties of allocated memory
Returns:
cudaSuccess, cudaErrorMemoryAllocation
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaSetDeviceFlags, cudaMallocHost (C API), cudaFreeHost, cudaHostAlloc
template<class T > cudaError_t cudaMallocManaged (T ** devPtr, size_t size, unsigned int flags =
cudaMemAttachGlobal)
Allocates size bytes of managed memory on the device and returns in *devPtr a pointer to the allocated
memory. If the device doesn't support allocating managed memory, cudaErrorNotSupported is returned.
Support for managed memory can be queried using the device attribute cudaDevAttrManagedMemory. The
allocated memory is suitably aligned for any kind of variable. The memory is not cleared. If size is 0,
cudaMallocManaged returns cudaErrorInvalidValue. The pointer is valid on the CPU and on all GPUs in the
system that support managed memory. All accesses to this pointer must obey the Unified Memory programming
model.
flags specifies the default stream association for this allocation. flags must be one of
cudaMemAttachGlobal or cudaMemAttachHost. The default value for flags is cudaMemAttachGlobal. If
cudaMemAttachGlobal is specified, then this memory is accessible from any stream on any device. If
cudaMemAttachHost is specified, then the allocation should not be accessed from devices that have a zero
value for the device attribute cudaDevAttrConcurrentManagedAccess; an explicit call to
cudaStreamAttachMemAsync will be required to enable access on such devices.
If the association is later changed via cudaStreamAttachMemAsync to a single stream, the default
association, as specified during cudaMallocManaged, is restored when that stream is destroyed. For
__managed__ variables, the default association is always cudaMemAttachGlobal. Note that destroying a
stream is an asynchronous operation, and as a result, the change to default association won't happen
until all work in the stream has completed.
Memory allocated with cudaMallocManaged should be released with cudaFree.
Device memory oversubscription is possible for GPUs that have a non-zero value for the device attribute
cudaDevAttrConcurrentManagedAccess. Managed memory on such GPUs may be evicted from device memory to host
memory at any time by the Unified Memory driver in order to make room for other allocations.
In a multi-GPU system where all GPUs have a non-zero value for the device attribute
cudaDevAttrConcurrentManagedAccess, managed memory may not be populated when this API returns and instead
may be populated on access. In such systems, managed memory can migrate to any processor's memory at any
time. The Unified Memory driver will employ heuristics to maintain data locality and prevent excessive
page faults to the extent possible. The application can also guide the driver about memory usage patterns
via cudaMemAdvise. The application can also explicitly migrate memory to a desired processor's memory via
cudaMemPrefetchAsync.
In a multi-GPU system where all of the GPUs have a zero value for the device attribute
cudaDevAttrConcurrentManagedAccess and all the GPUs have peer-to-peer support with each other, the
physical storage for managed memory is created on the GPU which is active at the time cudaMallocManaged
is called. All other GPUs will reference the data at reduced bandwidth via peer mappings over the PCIe
bus. The Unified Memory driver does not migrate memory among such GPUs.
In a multi-GPU system where not all GPUs have peer-to-peer support with each other and where the value of
the device attribute cudaDevAttrConcurrentManagedAccess is zero for at least one of those GPUs, the
location chosen for physical storage of managed memory is system-dependent.
• On Linux, the location chosen will be device memory as long as the current set of active contexts are
on devices that either have peer-to-peer support with each other or have a non-zero value for the
device attribute cudaDevAttrConcurrentManagedAccess. If there is an active context on a GPU that does
not have a non-zero value for that device attribute and it does not have peer-to-peer support with the
other devices that have active contexts on them, then the location for physical storage will be 'zero-
copy' or host memory. Note that this means that managed memory that is located in device memory is
migrated to host memory if a new context is created on a GPU that doesn't have a non-zero value for the
device attribute and does not support peer-to-peer with at least one of the other devices that has an
active context. This in turn implies that context creation may fail if there is insufficient host
memory to migrate all managed allocations.
• On Windows, the physical storage is always created in 'zero-copy' or host memory. All GPUs will
reference the data at reduced bandwidth over the PCIe bus. In these circumstances, use of the
environment variable CUDA_VISIBLE_DEVICES is recommended to restrict CUDA to only use those GPUs that
have peer-to-peer support. Alternatively, users can also set CUDA_MANAGED_FORCE_DEVICE_ALLOC to a non-
zero value to force the driver to always use device memory for physical storage. When this environment
variable is set to a non-zero value, all devices used in that process that support managed memory have
to be peer-to-peer compatible with each other. The error cudaErrorInvalidDevice will be returned if a
device that supports managed memory is used and it is not peer-to-peer compatible with any of the other
managed memory supporting devices that were previously used in that process, even if cudaDeviceReset
has been called on those devices. These environment variables are described in the CUDA programming
guide under the 'CUDA environment variables' section.
• On ARM, managed memory is not available on discrete gpu with Drive PX-2.
Parameters:
devPtr - Pointer to allocated device memory
size - Requested allocation size in bytes
flags - Must be either cudaMemAttachGlobal or cudaMemAttachHost (defaults to cudaMemAttachGlobal)
Returns:
cudaSuccess, cudaErrorMemoryAllocation, cudaErrorNotSupported, cudaErrorInvalidValue
See also:
cudaMallocPitch, cudaFree, cudaMallocArray, cudaFreeArray, cudaMalloc3D, cudaMalloc3DArray,
cudaMallocHost (C API), cudaFreeHost, cudaHostAlloc, cudaDeviceGetAttribute, cudaStreamAttachMemAsync
template<class T > cudaError_t cudaMemcpyFromSymbol (void * dst, const T & symbol, size_t count, size_t
offset = 0, enum cudaMemcpyKind kind = cudaMemcpyDeviceToHost)
Copies count bytes from the memory area offset bytes from the start of symbol symbol to the memory area
pointed to by dst. The memory areas may not overlap. symbol is a variable that resides in global or
constant memory space. kind can be either cudaMemcpyDeviceToHost or cudaMemcpyDeviceToDevice.
Parameters:
dst - Destination memory address
symbol - Device symbol reference
count - Size in bytes to copy
offset - Offset from start of symbol in bytes
kind - Type of transfer
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidSymbol, cudaErrorInvalidMemcpyDirection,
cudaErrorNoKernelImageForDevice
Note:
Note that this function may also return error codes from previous, asynchronous launches.
This function exhibits behavior for most use cases.
Use of a string naming a variable as the symbol parameter was deprecated in CUDA 4.1 and removed in
CUDA 5.0.
See also:
cudaMemcpy, cudaMemcpy2D, cudaMemcpy2DToArray, cudaMemcpy2DFromArray, cudaMemcpy2DArrayToArray,
cudaMemcpyToSymbol, cudaMemcpyAsync, cudaMemcpy2DAsync, cudaMemcpy2DToArrayAsync,
cudaMemcpy2DFromArrayAsync, cudaMemcpyToSymbolAsync, cudaMemcpyFromSymbolAsync
template<class T > cudaError_t cudaMemcpyFromSymbolAsync (void * dst, const T & symbol, size_t count, size_t
offset = 0, enum cudaMemcpyKind kind = cudaMemcpyDeviceToHost, cudaStream_t stream = 0)
Copies count bytes from the memory area offset bytes from the start of symbol symbol to the memory area
pointed to by dst. The memory areas may not overlap. symbol is a variable that resides in global or
constant memory space. kind can be either cudaMemcpyDeviceToHost or cudaMemcpyDeviceToDevice.
cudaMemcpyFromSymbolAsync() is asynchronous with respect to the host, so the call may return before the
copy is complete. The copy can optionally be associated to a stream by passing a non-zero stream
argument. If kind is cudaMemcpyDeviceToHost and stream is non-zero, the copy may overlap with operations
in other streams.
Parameters:
dst - Destination memory address
symbol - Device symbol reference
count - Size in bytes to copy
offset - Offset from start of symbol in bytes
kind - Type of transfer
stream - Stream identifier
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidSymbol, cudaErrorInvalidMemcpyDirection,
cudaErrorNoKernelImageForDevice
Note:
Note that this function may also return error codes from previous, asynchronous launches.
This function exhibits behavior for most use cases.
Use of a string naming a variable as the symbol parameter was deprecated in CUDA 4.1 and removed in
CUDA 5.0.
See also:
cudaMemcpy, cudaMemcpy2D, cudaMemcpy2DToArray, cudaMemcpy2DFromArray, cudaMemcpy2DArrayToArray,
cudaMemcpyToSymbol, cudaMemcpyFromSymbol, cudaMemcpyAsync, cudaMemcpy2DAsync,
cudaMemcpy2DToArrayAsync, cudaMemcpy2DFromArrayAsync, cudaMemcpyToSymbolAsync
template<class T > cudaError_t cudaMemcpyToSymbol (const T & symbol, const void * src, size_t count, size_t
offset = 0, enum cudaMemcpyKind kind = cudaMemcpyHostToDevice)
Copies count bytes from the memory area pointed to by src to the memory area offset bytes from the start
of symbol symbol. The memory areas may not overlap. symbol is a variable that resides in global or
constant memory space. kind can be either cudaMemcpyHostToDevice or cudaMemcpyDeviceToDevice.
Parameters:
symbol - Device symbol reference
src - Source memory address
count - Size in bytes to copy
offset - Offset from start of symbol in bytes
kind - Type of transfer
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidSymbol, cudaErrorInvalidMemcpyDirection,
cudaErrorNoKernelImageForDevice
Note:
Note that this function may also return error codes from previous, asynchronous launches.
This function exhibits behavior for most use cases.
Use of a string naming a variable as the symbol parameter was deprecated in CUDA 4.1 and removed in
CUDA 5.0.
See also:
cudaMemcpy, cudaMemcpy2D, cudaMemcpy2DToArray, cudaMemcpy2DFromArray, cudaMemcpy2DArrayToArray,
cudaMemcpyFromSymbol, cudaMemcpyAsync, cudaMemcpy2DAsync, cudaMemcpy2DToArrayAsync,
cudaMemcpy2DFromArrayAsync, cudaMemcpyToSymbolAsync, cudaMemcpyFromSymbolAsync
template<class T > cudaError_t cudaMemcpyToSymbolAsync (const T & symbol, const void * src, size_t count,
size_t offset = 0, enum cudaMemcpyKind kind = cudaMemcpyHostToDevice, cudaStream_t stream = 0)
Copies count bytes from the memory area pointed to by src to the memory area offset bytes from the start
of symbol symbol. The memory areas may not overlap. symbol is a variable that resides in global or
constant memory space. kind can be either cudaMemcpyHostToDevice or cudaMemcpyDeviceToDevice.
cudaMemcpyToSymbolAsync() is asynchronous with respect to the host, so the call may return before the
copy is complete. The copy can optionally be associated to a stream by passing a non-zero stream
argument. If kind is cudaMemcpyHostToDevice and stream is non-zero, the copy may overlap with operations
in other streams.
Parameters:
symbol - Device symbol reference
src - Source memory address
count - Size in bytes to copy
offset - Offset from start of symbol in bytes
kind - Type of transfer
stream - Stream identifier
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidSymbol, cudaErrorInvalidMemcpyDirection,
cudaErrorNoKernelImageForDevice
Note:
Note that this function may also return error codes from previous, asynchronous launches.
This function exhibits behavior for most use cases.
Use of a string naming a variable as the symbol parameter was deprecated in CUDA 4.1 and removed in
CUDA 5.0.
See also:
cudaMemcpy, cudaMemcpy2D, cudaMemcpy2DToArray, cudaMemcpy2DFromArray, cudaMemcpy2DArrayToArray,
cudaMemcpyToSymbol, cudaMemcpyFromSymbol, cudaMemcpyAsync, cudaMemcpy2DAsync,
cudaMemcpy2DToArrayAsync, cudaMemcpy2DFromArrayAsync, cudaMemcpyFromSymbolAsync
template<class T > cudaError_t cudaOccupancyMaxActiveBlocksPerMultiprocessor (int * numBlocks, T func, int
blockSize, size_t dynamicSMemSize)
Returns in *numBlocks the maximum number of active blocks per streaming multiprocessor for the device
function.
Parameters:
numBlocks - Returned occupancy
func - Kernel function for which occupancy is calculated
blockSize - Block size the kernel is intended to be launched with
dynamicSMemSize - Per-block dynamic shared memory usage intended, in bytes
Returns:
cudaSuccess, cudaErrorInvalidDevice, cudaErrorInvalidDeviceFunction, cudaErrorInvalidValue,
cudaErrorUnknown,
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
cudaOccupancyMaxPotentialBlockSize
cudaOccupancyMaxPotentialBlockSizeWithFlags
cudaOccupancyMaxPotentialBlockSizeVariableSMem
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags
template<class T > cudaError_t cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags (int * numBlocks, T
func, int blockSize, size_t dynamicSMemSize, unsigned int flags)
Returns in *numBlocks the maximum number of active blocks per streaming multiprocessor for the device
function.
The flags parameter controls how special cases are handled. Valid flags include:
• cudaOccupancyDefault: keeps the default behavior as cudaOccupancyMaxActiveBlocksPerMultiprocessor
• cudaOccupancyDisableCachingOverride: suppresses the default behavior on platform where global caching
affects occupancy. On such platforms, if caching is enabled, but per-block SM resource usage would
result in zero occupancy, the occupancy calculator will calculate the occupancy as if caching is
disabled. Setting this flag makes the occupancy calculator to return 0 in such cases. More information
can be found about this feature in the 'Unified L1/Texture Cache' section of the Maxwell tuning guide.
Parameters:
numBlocks - Returned occupancy
func - Kernel function for which occupancy is calculated
blockSize - Block size the kernel is intended to be launched with
dynamicSMemSize - Per-block dynamic shared memory usage intended, in bytes
flags - Requested behavior for the occupancy calculator
Returns:
cudaSuccess, cudaErrorInvalidDevice, cudaErrorInvalidDeviceFunction, cudaErrorInvalidValue,
cudaErrorUnknown,
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaOccupancyMaxActiveBlocksPerMultiprocessor
cudaOccupancyMaxPotentialBlockSize
cudaOccupancyMaxPotentialBlockSizeWithFlags
cudaOccupancyMaxPotentialBlockSizeVariableSMem
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags
template<class T > CUDART_DEVICE cudaError_t cudaOccupancyMaxPotentialBlockSize (int * minGridSize, int *
blockSize, T func, size_t dynamicSMemSize = 0, int blockSizeLimit = 0)
Returns in *minGridSize and *blocksize a suggested grid / block size pair that achieves the best
potential occupancy (i.e. the maximum number of active warps with the smallest number of blocks).
Use
See also:
cudaOccupancyMaxPotentialBlockSizeVariableSMem if the amount of per-block dynamic shared memory
changes with different block sizes.
Parameters:
minGridSize - Returned minimum grid size needed to achieve the best potential occupancy
blockSize - Returned block size
func - Device function symbol
dynamicSMemSize - Per-block dynamic shared memory usage intended, in bytes
blockSizeLimit - The maximum block size func is designed to work with. 0 means no limit.
Returns:
cudaSuccess, cudaErrorInvalidDevice, cudaErrorInvalidDeviceFunction, cudaErrorInvalidValue,
cudaErrorUnknown,
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaOccupancyMaxPotentialBlockSizeWithFlags
cudaOccupancyMaxActiveBlocksPerMultiprocessor
cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
cudaOccupancyMaxPotentialBlockSizeVariableSMem
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags
template<typename UnaryFunction , class T > CUDART_DEVICE cudaError_t
cudaOccupancyMaxPotentialBlockSizeVariableSMem (int * minGridSize, int * blockSize, T func, UnaryFunction
blockSizeToDynamicSMemSize, int blockSizeLimit = 0)
Returns in *minGridSize and *blocksize a suggested grid / block size pair that achieves the best
potential occupancy (i.e. the maximum number of active warps with the smallest number of blocks).
Parameters:
minGridSize - Returned minimum grid size needed to achieve the best potential occupancy
blockSize - Returned block size
func - Device function symbol
blockSizeToDynamicSMemSize - A unary function / functor that takes block size, and returns the size,
in bytes, of dynamic shared memory needed for a block
blockSizeLimit - The maximum block size func is designed to work with. 0 means no limit.
Returns:
cudaSuccess, cudaErrorInvalidDevice, cudaErrorInvalidDeviceFunction, cudaErrorInvalidValue,
cudaErrorUnknown,
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags
cudaOccupancyMaxActiveBlocksPerMultiprocessor
cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
cudaOccupancyMaxPotentialBlockSize
cudaOccupancyMaxPotentialBlockSizeWithFlags
template<typename UnaryFunction , class T > CUDART_DEVICE cudaError_t
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags (int * minGridSize, int * blockSize, T func,
UnaryFunction blockSizeToDynamicSMemSize, int blockSizeLimit = 0, unsigned int flags = 0)
Returns in *minGridSize and *blocksize a suggested grid / block size pair that achieves the best
potential occupancy (i.e. the maximum number of active warps with the smallest number of blocks).
The flags parameter controls how special cases are handled. Valid flags include:
• cudaOccupancyDefault: keeps the default behavior as
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags
• cudaOccupancyDisableCachingOverride: This flag suppresses the default behavior on platform where global
caching affects occupancy. On such platforms, if caching is enabled, but per-block SM resource usage
would result in zero occupancy, the occupancy calculator will calculate the occupancy as if caching is
disabled. Setting this flag makes the occupancy calculator to return 0 in such cases. More information
can be found about this feature in the 'Unified L1/Texture Cache' section of the Maxwell tuning guide.
Parameters:
minGridSize - Returned minimum grid size needed to achieve the best potential occupancy
blockSize - Returned block size
func - Device function symbol
blockSizeToDynamicSMemSize - A unary function / functor that takes block size, and returns the size,
in bytes, of dynamic shared memory needed for a block
blockSizeLimit - The maximum block size func is designed to work with. 0 means no limit.
flags - Requested behavior for the occupancy calculator
Returns:
cudaSuccess, cudaErrorInvalidDevice, cudaErrorInvalidDeviceFunction, cudaErrorInvalidValue,
cudaErrorUnknown,
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaOccupancyMaxPotentialBlockSizeVariableSMem
cudaOccupancyMaxActiveBlocksPerMultiprocessor
cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
cudaOccupancyMaxPotentialBlockSize
cudaOccupancyMaxPotentialBlockSizeWithFlags
template<class T > CUDART_DEVICE cudaError_t cudaOccupancyMaxPotentialBlockSizeWithFlags (int * minGridSize,
int * blockSize, T func, size_t dynamicSMemSize = 0, int blockSizeLimit = 0, unsigned int flags = 0)
Returns in *minGridSize and *blocksize a suggested grid / block size pair that achieves the best
potential occupancy (i.e. the maximum number of active warps with the smallest number of blocks).
The flags parameter controls how special cases are handle. Valid flags include:
• cudaOccupancyDefault: keeps the default behavior as cudaOccupancyMaxPotentialBlockSize
• cudaOccupancyDisableCachingOverride: This flag suppresses the default behavior on platform where global
caching affects occupancy. On such platforms, if caching is enabled, but per-block SM resource usage
would result in zero occupancy, the occupancy calculator will calculate the occupancy as if caching is
disabled. Setting this flag makes the occupancy calculator to return 0 in such cases. More information
can be found about this feature in the 'Unified L1/Texture Cache' section of the Maxwell tuning guide.
Use
See also:
cudaOccupancyMaxPotentialBlockSizeVariableSMem if the amount of per-block dynamic shared memory
changes with different block sizes.
Parameters:
minGridSize - Returned minimum grid size needed to achieve the best potential occupancy
blockSize - Returned block size
func - Device function symbol
dynamicSMemSize - Per-block dynamic shared memory usage intended, in bytes
blockSizeLimit - The maximum block size func is designed to work with. 0 means no limit.
flags - Requested behavior for the occupancy calculator
Returns:
cudaSuccess, cudaErrorInvalidDevice, cudaErrorInvalidDeviceFunction, cudaErrorInvalidValue,
cudaErrorUnknown,
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaOccupancyMaxPotentialBlockSize
cudaOccupancyMaxActiveBlocksPerMultiprocessor
cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
cudaOccupancyMaxPotentialBlockSizeVariableSMem
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags
template<class T > cudaError_t cudaStreamAttachMemAsync (cudaStream_t stream, T * devPtr, size_t length = 0,
unsigned int flags = cudaMemAttachSingle)
Enqueues an operation in stream to specify stream association of length bytes of memory starting from
devPtr. This function is a stream-ordered operation, meaning that it is dependent on, and will only take
effect when, previous work in stream has completed. Any previous association is automatically replaced.
devPtr must point to an one of the following types of memories:
• managed memory declared using the __managed__ keyword or allocated with cudaMallocManaged.
• a valid host-accessible region of system-allocated pageable memory. This type of memory may only be
specified if the device associated with the stream reports a non-zero value for the device attribute
cudaDevAttrPageableMemoryAccess.
For managed allocations, length must be either zero or the entire allocation's size. Both indicate that
the entire allocation's stream association is being changed. Currently, it is not possible to change
stream association for a portion of a managed allocation.
For pageable allocations, length must be non-zero.
The stream association is specified using flags which must be one of cudaMemAttachGlobal,
cudaMemAttachHost or cudaMemAttachSingle. The default value for flags is cudaMemAttachSingle If the
cudaMemAttachGlobal flag is specified, the memory can be accessed by any stream on any device. If the
cudaMemAttachHost flag is specified, the program makes a guarantee that it won't access the memory on the
device from any stream on a device that has a zero value for the device attribute
cudaDevAttrConcurrentManagedAccess. If the cudaMemAttachSingle flag is specified and stream is associated
with a device that has a zero value for the device attribute cudaDevAttrConcurrentManagedAccess, the
program makes a guarantee that it will only access the memory on the device from stream. It is illegal to
attach singly to the NULL stream, because the NULL stream is a virtual global stream and not a specific
stream. An error will be returned in this case.
When memory is associated with a single stream, the Unified Memory system will allow CPU access to this
memory region so long as all operations in stream have completed, regardless of whether other streams are
active. In effect, this constrains exclusive ownership of the managed memory region by an active GPU to
per-stream activity instead of whole-GPU activity.
Accessing memory on the device from streams that are not associated with it will produce undefined
results. No error checking is performed by the Unified Memory system to ensure that kernels launched into
other streams do not access this region.
It is a program's responsibility to order calls to cudaStreamAttachMemAsync via events, synchronization
or other means to ensure legal access to memory at all times. Data visibility and coherency will be
changed appropriately for all kernels which follow a stream-association change.
If stream is destroyed while data is associated with it, the association is removed and the association
reverts to the default visibility of the allocation as specified at cudaMallocManaged. For __managed__
variables, the default association is always cudaMemAttachGlobal. Note that destroying a stream is an
asynchronous operation, and as a result, the change to default association won't happen until all work in
the stream has completed.
Parameters:
stream - Stream in which to enqueue the attach operation
devPtr - Pointer to memory (must be a pointer to managed memory or to a valid host-accessible region
of system-allocated memory)
length - Length of memory (defaults to zero)
flags - Must be one of cudaMemAttachGlobal, cudaMemAttachHost or cudaMemAttachSingle (defaults to
cudaMemAttachSingle)
Returns:
cudaSuccess, cudaErrorNotReady, cudaErrorInvalidValue, cudaErrorInvalidResourceHandle
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaStreamCreate, cudaStreamCreateWithFlags, cudaStreamWaitEvent, cudaStreamSynchronize,
cudaStreamAddCallback, cudaStreamDestroy, cudaMallocManaged
template<class T , int dim, enum cudaTextureReadMode readMode> cudaError_t cudaUnbindTexture (const struct
texture< T, dim, readMode > & tex)
Unbinds the texture bound to tex. If texref is not currently bound, no operation is performed.
Parameters:
tex - Texture to unbind
Returns:
cudaSuccess, cudaErrorInvalidTexture
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaCreateChannelDesc (C++ API), cudaGetChannelDesc, cudaGetTextureReference, cudaBindTexture (C++
API), cudaBindTexture (C++ API, inherited channel descriptor), cudaBindTexture2D (C++ API),
cudaBindTexture2D (C++ API, inherited channel descriptor), cudaBindTextureToArray (C++ API),
cudaBindTextureToArray (C++ API, inherited channel descriptor), cudaUnbindTexture (C API),
cudaGetTextureAlignmentOffset (C++ API)
Author
Generated automatically by Doxygen from the source code.
Version 6.0 28 Jul 2019 C++ API Routines(3)