Skip to content

coll/HAN: Don't DQ HAN dynamic @ intra-node subcomm + typo fixes #10458

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 29, 2022
Merged

coll/HAN: Don't DQ HAN dynamic @ intra-node subcomm + typo fixes #10458

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions ompi/mca/coll/han/coll_han_allreduce.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,7 @@ mca_coll_han_allreduce_intra(const void *sbuf,
/* HAN cannot work with this communicator so fallback on all collectives */
HAN_LOAD_FALLBACK_COLLECTIVES(han_module, comm);
return comm->c_coll->coll_allreduce(sbuf, rbuf, count, dtype, op,
comm, comm->c_coll->coll_reduce_module);
comm, comm->c_coll->coll_allreduce_module);
}

ptrdiff_t extent, lb;
Expand Down Expand Up @@ -444,7 +444,7 @@ mca_coll_han_allreduce_intra_simple(const void *sbuf,
/* HAN cannot work with this communicator so fallback on all collectives */
HAN_LOAD_FALLBACK_COLLECTIVES(han_module, comm);
return comm->c_coll->coll_allreduce(sbuf, rbuf, count, dtype, op,
comm, comm->c_coll->coll_reduce_module);
comm, comm->c_coll->coll_allreduce_module);
}

low_comm = han_module->sub_comm[INTRA_NODE];
Expand Down
18 changes: 11 additions & 7 deletions ompi/mca/coll/han/coll_han_module.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,13 +199,6 @@ mca_coll_han_comm_query(struct ompi_communicator_t * comm, int *priority)
ompi_comm_print_cid(comm), comm->c_name);
return NULL;
}
if( !ompi_group_have_remote_peers(comm->c_local_group) ) {
/* The group only contains local processes. Disable HAN for now */
opal_output_verbose(10, ompi_coll_base_framework.framework_output,
"coll:han:comm_query (%s/%s): comm has only local processes; disqualifying myself",
ompi_comm_print_cid(comm), comm->c_name);
return NULL;
}
/* Get the priority level attached to this module. If priority is less
* than or equal to 0, then the module is unavailable. */
*priority = mca_coll_han_component.han_priority;
Expand Down Expand Up @@ -240,6 +233,17 @@ mca_coll_han_comm_query(struct ompi_communicator_t * comm, int *priority)
}
}

if( !ompi_group_have_remote_peers(comm->c_local_group)
&& INTRA_NODE != han_module->topologic_level ) {
/* The group only contains local processes, and this is not a
* intra-node subcomm we created. Disable HAN for now */
opal_output_verbose(10, ompi_coll_base_framework.framework_output,
"coll:han:comm_query (%s/%s): comm has only local processes; disqualifying myself",
ompi_comm_print_cid(comm), comm->c_name);
OBJ_RELEASE(han_module);
return NULL;
}

han_module->super.coll_module_enable = han_module_enable;
han_module->super.coll_alltoall = NULL;
han_module->super.coll_alltoallv = NULL;
Expand Down