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>
194 строки
5.7 KiB
C
194 строки
5.7 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"
|
|
|
|
/* an alltoallv schedule can not be cached easily because the contents
|
|
* ot the recvcounts array may change, so a comparison of the address
|
|
* would not be sufficient ... we simply do not cache it */
|
|
|
|
/* simple linear Alltoallv */
|
|
int ompi_coll_libnbc_ialltoallv(void* sendbuf, int *sendcounts, int *sdispls,
|
|
MPI_Datatype sendtype, void* recvbuf, int *recvcounts, int *rdispls,
|
|
MPI_Datatype recvtype, struct ompi_communicator_t *comm, ompi_request_t ** request,
|
|
struct mca_coll_base_module_2_1_0_t *module)
|
|
{
|
|
int rank, p, res;
|
|
MPI_Aint sndext, rcvext;
|
|
NBC_Schedule *schedule;
|
|
char *rbuf, *sbuf, inplace;
|
|
NBC_Handle *handle;
|
|
ompi_coll_libnbc_module_t *libnbc_module = (ompi_coll_libnbc_module_t*) module;
|
|
|
|
NBC_IN_PLACE(sendbuf, recvbuf, inplace);
|
|
|
|
rank = ompi_comm_rank (comm);
|
|
p = ompi_comm_size (comm);
|
|
|
|
res = MPI_Type_extent (sendtype, &sndext);
|
|
if (MPI_SUCCESS != res) {
|
|
NBC_Error("MPI Error in MPI_Type_extent() (%i)", res);
|
|
return res;
|
|
}
|
|
|
|
res = MPI_Type_extent (recvtype, &rcvext);
|
|
if (MPI_SUCCESS != res) {
|
|
NBC_Error("MPI Error in MPI_Type_extent() (%i)", res);
|
|
return res;
|
|
}
|
|
|
|
/* copy data to receivbuffer */
|
|
if ((sendcounts[rank] != 0) && !inplace) {
|
|
rbuf = (char *) recvbuf + rdispls[rank] * rcvext;
|
|
sbuf = (char *) sendbuf + sdispls[rank] * sndext;
|
|
res = NBC_Copy (sbuf, sendcounts[rank], sendtype, rbuf, recvcounts[rank], recvtype, comm);
|
|
if (OPAL_UNLIKELY(OMPI_SUCCESS != res)) {
|
|
return res;
|
|
}
|
|
}
|
|
|
|
schedule = OBJ_NEW(NBC_Schedule);
|
|
if (OPAL_UNLIKELY(NULL == schedule)) {
|
|
return OMPI_ERR_OUT_OF_RESOURCE;
|
|
}
|
|
|
|
for (int i = 0 ; i < p ; ++i) {
|
|
if (i == rank) {
|
|
continue;
|
|
}
|
|
|
|
/* post all sends */
|
|
if (sendcounts[i] != 0) {
|
|
sbuf = ((char *) sendbuf) + (sdispls[i] * sndext);
|
|
res = NBC_Sched_send(sbuf, false, sendcounts[i], sendtype, i, schedule, false);
|
|
if (OPAL_UNLIKELY(OMPI_SUCCESS != res)) {
|
|
OBJ_RELEASE(schedule);
|
|
return res;
|
|
}
|
|
}
|
|
|
|
/* post all receives */
|
|
if (recvcounts[i] != 0) {
|
|
rbuf = ((char *) recvbuf) + (rdispls[i] * rcvext);
|
|
res = NBC_Sched_recv(rbuf, false, recvcounts[i], recvtype, i, 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);
|
|
OBJ_RELEASE(schedule);
|
|
return res;
|
|
}
|
|
|
|
*request = (ompi_request_t *) handle;
|
|
|
|
return OMPI_SUCCESS;
|
|
}
|
|
|
|
/* simple linear Alltoallv */
|
|
int ompi_coll_libnbc_ialltoallv_inter (void* sendbuf, int *sendcounts, int *sdispls,
|
|
MPI_Datatype sendtype, void* recvbuf, int *recvcounts, int *rdispls,
|
|
MPI_Datatype recvtype, struct ompi_communicator_t *comm, ompi_request_t ** request,
|
|
struct mca_coll_base_module_2_1_0_t *module)
|
|
{
|
|
int res, rsize;
|
|
MPI_Aint sndext, rcvext;
|
|
NBC_Schedule *schedule;
|
|
char *rbuf, *sbuf;
|
|
NBC_Handle *handle;
|
|
ompi_coll_libnbc_module_t *libnbc_module = (ompi_coll_libnbc_module_t*) module;
|
|
|
|
|
|
res = MPI_Type_extent(sendtype, &sndext);
|
|
if (MPI_SUCCESS != res) {
|
|
NBC_Error("MPI Error in MPI_Type_extent() (%i)", res);
|
|
return res;
|
|
}
|
|
|
|
res = MPI_Type_extent(recvtype, &rcvext);
|
|
if (MPI_SUCCESS != res) {
|
|
NBC_Error("MPI Error in MPI_Type_extent() (%i)", res);
|
|
return res;
|
|
}
|
|
|
|
rsize = ompi_comm_remote_size (comm);
|
|
|
|
schedule = OBJ_NEW(NBC_Schedule);
|
|
if (OPAL_UNLIKELY(NULL == schedule)) {
|
|
return OMPI_ERR_OUT_OF_RESOURCE;
|
|
}
|
|
|
|
for (int i = 0; i < rsize; i++) {
|
|
/* post all sends */
|
|
if (sendcounts[i] != 0) {
|
|
sbuf = (char *) sendbuf + sdispls[i] * sndext;
|
|
res = NBC_Sched_send (sbuf, false, sendcounts[i], sendtype, i, schedule, false);
|
|
if (OPAL_UNLIKELY(OMPI_SUCCESS != res)) {
|
|
OBJ_RELEASE(schedule);
|
|
return res;
|
|
}
|
|
}
|
|
/* post all receives */
|
|
if (recvcounts[i] != 0) {
|
|
rbuf = (char *) recvbuf + rdispls[i] * rcvext;
|
|
res = NBC_Sched_recv (rbuf, false, recvcounts[i], recvtype, i, 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);
|
|
OBJ_RELEASE(schedule);
|
|
return res;
|
|
}
|
|
|
|
*request = (ompi_request_t *) handle;
|
|
|
|
return OMPI_SUCCESS;
|
|
}
|