Automatic Differentiation
 
Loading...
Searching...
No Matches

◆ mpi_parallel_call() [1/2]

template<int call_id, typename ReduceF , typename CombineF >
template<typename T_shared_param , typename T_job_param >
stan::math::mpi_parallel_call< call_id, ReduceF, CombineF >::mpi_parallel_call ( const T_shared_param &  shared_params,
const std::vector< Eigen::Matrix< T_job_param, Eigen::Dynamic, 1 > > &  job_params,
const std::vector< std::vector< double > > &  x_r,
const std::vector< std::vector< int > > &  x_i 
)
inline

Initiates a parallel MPI call on the root.

The constructor allocates the MPI resource and initiates on all workers the MPI parallel call which mirror the communication and execute a chunk of the overall work.

Template Parameters
T_shared_paramtype of shared parameters
T_job_paramtype of job-specific parameters
Parameters
shared_paramsshared parameter vector
job_paramsarray of job-specific parameter vectors
x_rarray of job-specific real arrays (data only argument)
x_iarray of job-specific int arrays (data only argument)

Definition at line 204 of file mpi_parallel_call.hpp.