d42e0968b1
This commit rewrites parts of libnbc to fix issues identified by coverity and myself. The changes are as follows: - libnbc function would return invalid error codes (internal to libnbc) to the mpi layer. These codes names are of the form NBC_. They do not match up with the error codes expected by the mpi layer. I purged the use of all these error codes with the exception of NBC_OK and NBC_CONTINUE in progress. These codes are used to identify when a request handle is complete. - Handles and schedules were leaked by all collective routines on error. A new routine was added to return a collective handle (NBC_Return_handle). - Temporary buffers containting in/out neighbors for neighborhood collectives were always leaked. - Neigborhood collectives contained code to handle MPI_IN_PLACE which is never a valid input for the send or receive buffer. Stipped this code out. - Files were inconsistently named. Most are nbc_isomething.c but one was named coll_libnbc_ireduce_scatter_block.c. - Made the NBC_Schedule "structure" and object so it can be retained/released. This may enable the use of schedule caching at a later time. More testing will be needed to ensure the caching code works. If it doesn't the code should be stripped out completely. - Added code to simply common case of scheduling send/recv + barrier. - Code cleanup for readability. The code now passes the clang static analyzer. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
84 строки
2.5 KiB
C
84 строки
2.5 KiB
C
/* -*- Mode: C; c-basic-offset:2 ; indent-tabs-mode:nil -*- */
|
|
/*
|
|
* Copyright (c) 2006 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2006 The Technical University of Chemnitz. All
|
|
* rights reserved.
|
|
* Copyright (c) 2014 Research Organization for Information Science
|
|
* and Technology (RIST). All rights reserved.
|
|
* Copyright (c) 2015 Los Alamos National Security, LLC. All rights
|
|
* reserved.
|
|
*
|
|
* Author(s): Torsten Hoefler <htor@cs.indiana.edu>
|
|
*
|
|
*/
|
|
#include "nbc_internal.h"
|
|
|
|
int ompi_coll_libnbc_ibcast_inter(void *buffer, int count, MPI_Datatype datatype, int root,
|
|
struct ompi_communicator_t *comm, ompi_request_t ** request,
|
|
struct mca_coll_base_module_2_1_0_t *module) {
|
|
int res, size;
|
|
NBC_Schedule *schedule;
|
|
NBC_Handle *handle;
|
|
ompi_coll_libnbc_module_t *libnbc_module = (ompi_coll_libnbc_module_t*) module;
|
|
|
|
res = MPI_Type_size(datatype, &size);
|
|
if (MPI_SUCCESS != res) {
|
|
NBC_Error("MPI Error in MPI_Type_size() (%i)", res);
|
|
return res;
|
|
}
|
|
|
|
schedule = OBJ_NEW(NBC_Schedule);
|
|
if (OPAL_UNLIKELY(NULL == schedule)) {
|
|
return OMPI_ERR_OUT_OF_RESOURCE;
|
|
}
|
|
|
|
if (root != MPI_PROC_NULL) {
|
|
/* send to all others */
|
|
if (root == MPI_ROOT) {
|
|
int remsize;
|
|
|
|
remsize = ompi_comm_remote_size (comm);
|
|
|
|
for (int peer = 0 ; peer < remsize ; ++peer) {
|
|
/* send msg to peer */
|
|
res = NBC_Sched_send (buffer, false, count, datatype, peer, schedule, false);
|
|
if (OPAL_UNLIKELY(OMPI_SUCCESS != res)) {
|
|
OBJ_RELEASE(schedule);
|
|
return res;
|
|
}
|
|
}
|
|
} else {
|
|
/* recv msg from root */
|
|
res = NBC_Sched_recv (buffer, false, count, datatype, root, schedule, false);
|
|
if (OPAL_UNLIKELY(OMPI_SUCCESS != res)) {
|
|
OBJ_RELEASE(schedule);
|
|
return res;
|
|
}
|
|
}
|
|
}
|
|
|
|
res = NBC_Sched_commit (schedule);
|
|
if (OPAL_UNLIKELY(OMPI_SUCCESS != res)) {
|
|
OBJ_RELEASE(schedule);
|
|
return res;
|
|
}
|
|
|
|
res = NBC_Init_handle (comm, &handle, libnbc_module);
|
|
if (OPAL_UNLIKELY(OMPI_SUCCESS != res)) {
|
|
OBJ_RELEASE(schedule);
|
|
return res;
|
|
}
|
|
|
|
res = NBC_Start(handle, schedule);
|
|
if (OPAL_UNLIKELY(OMPI_SUCCESS != res)) {
|
|
NBC_Return_handle (handle);
|
|
return res;
|
|
}
|
|
|
|
*request = (ompi_request_t *) handle;
|
|
|
|
return OMPI_SUCCESS;
|
|
}
|