VecGetArrayReadAndMemTypeAsync#
Returns a read-only pointer to this MPI process’s portion of the vector data.
Synopsis#
#include "petscvec.h"
PetscErrorCode VecGetArrayReadAndMemTypeAsync(Vec x, const PetscScalar *a[], PetscMemType *mtype)
Not Collective; No Fortran Support
Input Parameter#
x - the vector
Output Parameters#
a - pointer to this MPI process’s portion of the vector data, borrowed from the vector
mtype - memory type of the array, or
NULLif not needed
Notes#
For CUDA and HIP vectors that are not bound to the CPU, this routine always returns a device
pointer, even when the latest values are on the host. It queues any required host-to-device
copy on the current PetscDeviceContext without waiting for it. The caller must order
subsequent accesses after that context’s work, for example with
PetscDeviceContextSynchronize(). Do not modify host storage while its copy is pending.
Device allocation and runtime staging of pageable host memory may still block.
Other vector types, including vectors bound to the CPU, use VecGetArrayReadAndMemType()
and retain its synchronization behavior.
The array must not be modified.
The pointer is borrowed until VecRestoreArrayReadAndMemType() is called. Complete external
asynchronous work before restoring the array. Do not replace the vector’s storage or
change its type or CPU binding while the array is acquired.
See Also#
Vectors and Parallel Data, Vec, VecGetArrayReadAndMemType(), VecRestoreArrayReadAndMemType(),
VecGetArrayAndMemTypeAsync(), VecGetArrayWriteAndMemTypeAsync(),
PetscDeviceContextGetCurrentContext(), PetscDeviceContextSynchronize()
Level#
advanced
Location#
Examples#
Index of all Vec routines
Table of Contents for all manual pages
Index of all manual pages