Note that some function attributes such as maxThreadsPerBlock may vary based on the device For templated functions, pass the function If the specified function does not exist, thenĬudaErrorInvalidDeviceFunction is returned. func is a deviceįunction symbol and must be declared as a _global_ function. This function obtains the attributes of a function specified via func.
Some functions have overloaded C++ API template versions documented separately in the C++ API Routines module.įunction Documentation _cudart_builtin_ cudaError_t cudaFuncGetAttributes (struct cudaFuncAttributes * attr, const void * func) This section describes the execution control functions of the CUDA runtime application \brief execution control functions of the CUDA runtime API (cuda_runtime_api.h) cudaError_t cudaSetDoubleForHost (double *d)Ĭonverts a double argument after execution on a device.
cudaError_t cudaSetDoubleForDevice (double *d)Ĭonverts a double argument to be executed on a device. cudaError_t cudaLaunchKernel (const void *func, dim3 gridDim, dim3 blockDim, void **args, Launches device functions on multiple devices where thread blocks can cooperate and synchronize as they execute. *launchParamsList, unsigned int numDevices, unsigned int flags=0) cudaError_t cudaLaunchCooperativeKernelMultiDevice (struct cudaLaunchParams Launches a device function where thread blocks can cooperate and synchronize as they execute. Void **args, size_t sharedMem, cudaStream_t stream) cudaError_t cudaLaunchCooperativeKernel (const void *func, dim3 gridDim, dim3 blockDim, GridDimension, dim3 blockDimension, unsigned int sharedMemSize) _device_ _cudart_builtin_ void * cudaGetParameterBufferV2 (void *func, dim3 _device_ _cudart_builtin_ void * cudaGetParameterBuffer (size_t alignment, size_t Sets the shared memory configuration for a device function. cudaError_t cudaFuncSetSharedMemConfig (const void *func, enum cudaSharedMemConfig config) Sets the preferred cache configuration for a device function. cudaError_t cudaFuncSetCacheConfig (const void *func, enum cudaFuncCache cacheConfig)
_cudart_builtin_ cudaError_t cudaFuncSetAttribute (const void *func, enum _cudart_builtin_ cudaError_t cudaFuncGetAttributes (struct cudaFuncAttributes *attr,įind out attributes for a given function. Provided by: nvidia-cuda-dev_9.1.85-3ubuntu1_amd64
0 kommentar(er)
