execute Subroutine

private subroutine execute(self, in, out, stream, aux)

Uses

  • proc~~execute~7~~UsesGraph proc~execute~7 abstract_backend%execute iso_c_binding iso_c_binding proc~execute~7->iso_c_binding iso_fortran_env iso_fortran_env proc~execute~7->iso_fortran_env

Executes GPU Backend

Type Bound

abstract_backend

Arguments

Type IntentOptional Attributes Name
class(abstract_backend), intent(inout) :: self

Self-copying backend
real(kind=real32), intent(inout) :: in(:)

Send pointer
real(kind=real32), intent(inout) :: out(:)

Recv pointer
type(dtfft_stream_t), intent(in) :: stream

CUDA stream
real(kind=real32), intent(inout) :: aux(:)

Aux pointer

Calls

proc~~execute~7~~CallsGraph proc~execute~7 abstract_backend%execute execute_private execute_private proc~execute~7->execute_private interface~cudaeventrecord cudaEventRecord proc~execute~7->interface~cudaeventrecord interface~cudamemcpyasync cudaMemcpyAsync proc~execute~7->interface~cudamemcpyasync interface~cudastreamwaitevent cudaStreamWaitEvent proc~execute~7->interface~cudastreamwaitevent interface~int_to_str int_to_str proc~execute~7->interface~int_to_str mpi_abort mpi_abort proc~execute~7->mpi_abort proc~cudageterrorstring cudaGetErrorString proc~execute~7->proc~cudageterrorstring proc~execute~3 nvrtc_kernel%execute proc~execute~7->proc~execute~3 proc~int_to_str_int32 int_to_str_int32 interface~int_to_str->proc~int_to_str_int32 proc~int_to_str_int64 int_to_str_int64 interface~int_to_str->proc~int_to_str_int64 proc~int_to_str_int8 int_to_str_int8 interface~int_to_str->proc~int_to_str_int8 interface~cudageterrorstring_c cudaGetErrorString_c proc~cudageterrorstring->interface~cudageterrorstring_c proc~string_c2f string_c2f proc~cudageterrorstring->proc~string_c2f proc~execute~3->interface~cudamemcpyasync proc~execute~3->interface~int_to_str proc~execute~3->mpi_abort proc~execute~3->proc~cudageterrorstring mpi_comm_rank mpi_comm_rank proc~execute~3->mpi_comm_rank proc~culaunchkernel cuLaunchKernel proc~execute~3->proc~culaunchkernel proc~get_contiguous_execution_blocks get_contiguous_execution_blocks proc~execute~3->proc~get_contiguous_execution_blocks interface~run_cuda_kernel run_cuda_kernel proc~culaunchkernel->interface~run_cuda_kernel