<div class="gmail_quote">On Mon, Jul 16, 2012 at 10:44 PM, Barry Smith <span dir="ltr"><<a href="mailto:bsmith@mcs.anl.gov" target="_blank">bsmith@mcs.anl.gov</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div id=":43g"> /* PETSC_COMM_SELF = PETSC_COMM_WORLD for MPIUNI */<br>
#if !defined(PETSC_HAVE_MPIUNI)<br>
ierr = PetscCommDuplicate(PETSC_COMM_WORLD,&icomm,PETSC_NULL);CHKERRQ(ierr);<br>
ierr = MPI_Attr_put(icomm,Petsc_ThreadComm_keyval,(void*)tcomm);CHKERRQ(ierr);<br>
tcomm->refct++; /* Share the threadcomm with PETSC_COMM_SELF */<br>
#endif<br>
<br>
ierr = PetscCommDuplicate(PETSC_COMM_SELF,&icomm,PETSC_NULL);CHKERRQ(ierr);<br>
ierr = MPI_Attr_put(icomm,Petsc_ThreadComm_keyval,(void*)tcomm);CHKERRQ(ierr);<br>
<br>
<br>
I would not do it this way. Instead I would write a general routine that attached a threadcomm to a MPI_Comm; this routine would get the threadcomm_keyval and if it did NOT find it then would be put the attribute, otherwise it would know one was already there. Say it is called PetscThreadCommAttach(MPI_Comm, threadcomm); then in this routine you would just write<br>
<br>
PetscThreadCommAttach(PETSC_COMM_WORLD, tcomm);<br>
PetscThreadCommAttach(PETSC_COMM_SELF,tcomm); /* won't attr it again for MPIUni because it is already there */</div></blockquote></div><br><div>This looks good, but there is also a ref-counting check needed in PetscThreadCommDetach/Destroy because the thread pool (presumably) needs to be closed before PetscFinalize returns.</div>