If the specified function does not exist, then cudaErrorInvalidDeviceFunction is returned.
The runtime will use the requested configuration if possible, but it is free to choose a differentĬonfiguration if required to execute func.įunc is a device function symbol and must be declared as a _global_ function. 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. cudaError_t cudaSetupArgument ( const void* arg, size_t size, size_t offset ) Configure a device launch. cudaError_t cudaSetDoubleForHost ( double* d ) Converts a double argument after execution on a device. cudaError_t cudaSetDoubleForDevice ( double* d ) Converts a double argument to be executed on a device. cudaError_t cudaLaunch ( const void* func ) Launches a device function. cudaError_t cudaFuncSetSharedMemConfig ( const void* func, cudaSharedMemConfig config ) Sets the shared memory configuration for a device function. cudaError_t cudaFuncSetCacheConfig ( const void* func, cudaFuncCache cacheConfig ) Sets the preferred cache configuration for a device function. cudaError_t cudaFuncGetAttributes ( cudaFuncAttributes* attr, const void* func ) Find out attributes for a given function. Some functions have overloaded C++ API template versions documented separately in the C++ API Routines module.įunctions cudaError_t cudaConfigureCall ( dim3 gridDim, dim3 blockDim, size_t sharedMem = 0, cudaStream_t stream = 0 ) Configure a device-launch. This section describes the execution control functions of the CUDA runtime application programming interface.