1
1
openmpi/ompi/mca/coll/hierarch/coll_hierarch_allreduce.c
Rainer Keller 6c5532072a - Split the datatype engine into two parts: an MPI specific part in
OMPI
   and a language agnostic part in OPAL. The convertor is completely
   moved into OPAL.  This offers several benefits as described in RFC
   http://www.open-mpi.org/community/lists/devel/2009/07/6387.php
   namely:
    - Fewer basic types (int* and float* types, boolean and wchar
    - Fixing naming scheme to ompi-nomenclature.
    - Usability outside of the ompi-layer.
 - Due to the fixed nature of simple opal types, their information is
   completely
   known at compile time and therefore constified
 - With fewer datatypes (22), the actual sizes of bit-field types may be
   reduced
   from 64 to 32 bits, allowing reorganizing the opal_datatype
   structure, eliminating holes and keeping data required in convertor
   (upon send/recv) in one cacheline...
   This has implications to the convertor-datastructure and other parts
   of the code.
 - Several performance tests have been run, the netpipe latency does not
   change with
   this patch on Linux/x86-64 on the smoky cluster.
 - Extensive tests have been done to verify correctness (no new
   regressions) using:
   1. mpi_test_suite on linux/x86-64 using clean ompi-trunk and
    ompi-ddt:
    a. running both trunk and ompi-ddt resulted in no differences
       (except for MPI_SHORT_INT and MPI_TYPE_MIX_LB_UB do now run
       correctly).
    b. with --enable-memchecker and running under valgrind (one buglet
       when run with static found in test-suite, commited)
   2. ibm testsuite on linux/x86-64 using clean ompi-trunk and ompi-ddt:
      all passed (except for the dynamic/ tests failed!! as trunk/MTT)
   3. compilation and usage of HDF5 tests on Jaguar using PGI and
      PathScale compilers.
   4. compilation and usage on Scicortex.
 - Please note, that for the heterogeneous case, (-m32 compiled
   binaries/ompi), neither
   ompi-trunk, nor ompi-ddt branch would successfully launch.

This commit was SVN r21641.
2009-07-13 04:56:31 +00:00

116 строки
3.4 KiB
C

/*
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2006 The University of Tennessee and The University
* of Tennessee Research Foundation. All rights
* reserved.
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
* University of Stuttgart. All rights reserved.
* Copyright (c) 2004-2005 The Regents of the University of California.
* All rights reserved.
* Copyright (c) 2007 University of Houston. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#include "ompi_config.h"
#include "coll_hierarch.h"
#include <stdio.h>
#include "mpi.h"
#include "ompi/constants.h"
#include "ompi/communicator/communicator.h"
#include "ompi/datatype/ompi_datatype.h"
#include "ompi/mca/coll/coll.h"
/*
* reduce_intra
*
* Function: - reduction using two level hierarchy algorithm
* Accepts: - same as MPI_Reduce()
* Returns: - MPI_SUCCESS or error code
*/
int mca_coll_hierarch_allreduce_intra(void *sbuf, void *rbuf, int count,
struct ompi_datatype_t *dtype,
struct ompi_op_t *op,
struct ompi_communicator_t *comm,
mca_coll_base_module_t *module)
{
struct ompi_communicator_t *llcomm=NULL;
struct ompi_communicator_t *lcomm=NULL;
mca_coll_hierarch_module_t *hierarch_module = (mca_coll_hierarch_module_t *) module;
int rank;
int lroot, llroot;
ptrdiff_t extent, true_extent, lb, true_lb;
char *tmpbuf=NULL, *tbuf=NULL;
int ret=OMPI_SUCCESS;
int root=0;
rank = ompi_comm_rank ( comm );
lcomm = hierarch_module->hier_lcomm;
if ( mca_coll_hierarch_verbose_param ) {
printf("%s:%d: executing hierarchical allreduce with cnt=%d \n",
comm->c_name, rank, count );
}
llcomm = mca_coll_hierarch_get_llcomm ( root, hierarch_module, &llroot, &lroot);
if ( MPI_COMM_NULL != lcomm ) {
ompi_datatype_get_extent(dtype, &lb, &extent);
ompi_datatype_get_true_extent(dtype, &true_lb, &true_extent);
tbuf = (char*)malloc(true_extent + (count - 1) * extent);
if (NULL == tbuf) {
return OMPI_ERR_OUT_OF_RESOURCE;
}
tmpbuf = tbuf - lb;
if ( MPI_IN_PLACE != sbuf ) {
ret = lcomm->c_coll.coll_reduce (sbuf, tmpbuf, count, dtype,
op, lroot, lcomm,
lcomm->c_coll.coll_reduce_module);
}
else {
ret = lcomm->c_coll.coll_reduce (rbuf, tmpbuf, count, dtype,
op, lroot, lcomm,
lcomm->c_coll.coll_reduce_module);
}
if ( OMPI_SUCCESS != ret ) {
goto exit;
}
}
if ( MPI_UNDEFINED != llroot ) {
if ( MPI_COMM_NULL != lcomm ) {
ret = llcomm->c_coll.coll_allreduce (tmpbuf, rbuf, count, dtype,
op, llcomm,
llcomm->c_coll.coll_allreduce_module);
}
else {
ret = llcomm->c_coll.coll_allreduce (sbuf, rbuf, count, dtype,
op, llcomm,
llcomm->c_coll.coll_allreduce_module);
}
}
if ( MPI_COMM_NULL != lcomm ) {
ret = lcomm->c_coll.coll_bcast(rbuf, count, dtype, lroot, lcomm,
lcomm->c_coll.coll_bcast_module );
}
exit:
if ( NULL != tmpbuf ) {
free ( tmpbuf );
}
return ret;
}