Single Task (cudaFlow)
cudaFlow provides a template function that constructs a task to run the given callable using a single kernel thread.
Run a Task with a Single Thread
You can create a task to run a kernel function just once, i.e., using one GPU thread. This is handy when you want to set up a single or a few global parameters that do not need multiple threads and will be used by multiple kernels afterwards. The following example creates a single-task kernel that sets gpu_parameter
to 1.
int* gpu_parameter; cudaMalloc(&gpu_parameter, sizeof(int)); tf::Task = taskflow.emplace([&] (tf::cudaFlow& cf) { // create a single task to set the gpu_parameter to 1 tf::cudaTask set_par = cf.single_task([gpu_parameter] __device__ () { *gpu_parameter = 1; }) // create two kernel tasks that need access to gpu_parameter tf::cudaTask kernel1 = cf.kernel(grid1, block1, shm1, my_kernel_1, ...); tf::cudaTask kernel2 = cf.kernel(grid2, block2, shm2, my_kernel_2, ...); set_par.precede(kernel1, kernel2); });
Since the callable runs on GPU, it must be declared with a __device__
specifier.
Miscellaneous Items
The single-task algorithm is also available in tf::cudaFlowCapturerBase::single_task.