cuLaunchKernel Function

public function cuLaunchKernel(func, in, out, blocks, threads, stream, args) result(cuResult)

Launches a CUDA function CUfunction or a CUDA kernel CUkernel.

Arguments

Type IntentOptional Attributes Name
type(CUfunction) :: func

Function CUfunction or Kernel CUkernel to launch
type(c_ptr) :: in

Input pointer
type(c_ptr) :: out

Output pointer
type(dim3) :: blocks

Grid in blocks
type(dim3) :: threads

Thread block
type(dtfft_stream_t) :: stream

Stream identifier
type(kernelArgs) :: args

Kernel parameters

Return Value integer(kind=c_int)

Driver result code


Calls

proc~~culaunchkernel~~CallsGraph proc~culaunchkernel cuLaunchKernel interface~run_cuda_kernel run_cuda_kernel proc~culaunchkernel->interface~run_cuda_kernel

Called by

proc~~culaunchkernel~~CalledByGraph proc~culaunchkernel cuLaunchKernel proc~execute~3 nvrtc_kernel%execute proc~execute~3->proc~culaunchkernel proc~execute_mpi backend_mpi%execute_mpi proc~execute_mpi->proc~execute~3 proc~execute_nccl backend_nccl%execute_nccl proc~execute_nccl->proc~execute~3 proc~execute~7 abstract_backend%execute proc~execute~7->proc~execute~3 proc~execute~8 transpose_handle_cuda%execute proc~execute~8->proc~execute~3 proc~execute_cuda transpose_plan_cuda%execute_cuda proc~execute_cuda->proc~execute~8 proc~run_autotune_backend run_autotune_backend proc~run_autotune_backend->proc~execute~8 proc~autotune_grid autotune_grid proc~autotune_grid->proc~run_autotune_backend proc~create_cuda transpose_plan_cuda%create_cuda proc~create_cuda->proc~run_autotune_backend proc~autotune_grid_decomposition autotune_grid_decomposition proc~create_cuda->proc~autotune_grid_decomposition proc~autotune_grid_decomposition->proc~autotune_grid