In C, subroutines which modify variables that are not in the argument list will not cause register optimization problems. This is because taking pointers to storage objects by using the & operator and later referencing the objects by indirection on the pointer is an integral part of the language. A C compiler understands the implications, so that the problem should not occur, in general. However, some compilers do offer optional aggressive optimization levels which may not be safe. Problems due to temporary memory modifications can also occur in C. As above, the best advice is to avoid the problem: use different variables for buffers in nonblocking MPI operations and computation that is executed while a nonblocking operation is pending.
Example
Protecting GPU optimizations with the ASYNCHRONOUS attribute.
USE mpi_f08
REAL :: buf(100,100)
CALL separated_sections(buf(1:1,1:100), buf(2:100,1:100))
END
SUBROUTINE separated_sections(buf_halo, buf_inner)
REAL, ASYNCHRONOUS :: buf_halo(1:1,1:100)
REAL :: buf_inner(2:100,1:100)
REAL :: local_buf(2:100,100)
CALL MPI_Irecv(buf_halo(1,1:100),...req,...)
local_buf = buf_inner
DO j=1,100
DO i=2,100
local_buf(i,j)=....
END DO
END DO
buf_inner = local_buf ! buf_halo is not touched!!!
CALL MPI_Wait(req,...)