2004-01-25 04:51:49 +03:00
|
|
|
/*
|
2007-03-17 02:11:45 +03:00
|
|
|
* Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
|
2005-11-05 22:57:48 +03:00
|
|
|
* University Research and Technology
|
|
|
|
* Corporation. All rights reserved.
|
|
|
|
* Copyright (c) 2004-2005 The University of Tennessee and The University
|
|
|
|
* of Tennessee Research Foundation. All rights
|
|
|
|
* reserved.
|
2008-02-12 11:46:27 +03:00
|
|
|
* Copyright (c) 2004-2008 High Performance Computing Center Stuttgart,
|
2004-11-28 23:09:25 +03:00
|
|
|
* University of Stuttgart. All rights reserved.
|
2005-03-24 15:43:37 +03:00
|
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
|
|
* All rights reserved.
|
2004-11-22 04:38:40 +03:00
|
|
|
* $COPYRIGHT$
|
|
|
|
*
|
|
|
|
* Additional copyrights may follow
|
|
|
|
*
|
2004-10-15 23:31:47 +04:00
|
|
|
* $HEADER$
|
2004-01-25 04:51:49 +03:00
|
|
|
*/
|
2004-06-07 19:33:53 +04:00
|
|
|
#include "ompi_config.h"
|
2004-01-25 04:51:49 +03:00
|
|
|
#include <stdio.h>
|
|
|
|
|
2006-02-12 04:33:29 +03:00
|
|
|
#include "ompi/mpi/c/bindings.h"
|
2009-04-29 05:32:14 +04:00
|
|
|
#include "ompi/runtime/params.h"
|
|
|
|
#include "ompi/communicator/communicator.h"
|
|
|
|
#include "ompi/errhandler/errhandler.h"
|
- 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 08:56:31 +04:00
|
|
|
#include "ompi/datatype/ompi_datatype.h"
|
2008-02-12 21:01:17 +03:00
|
|
|
#include "ompi/memchecker.h"
|
2004-01-25 04:51:49 +03:00
|
|
|
|
2009-05-07 00:11:28 +04:00
|
|
|
#if OPAL_HAVE_WEAK_SYMBOLS && OMPI_PROFILING_DEFINES
|
2004-01-25 04:51:49 +03:00
|
|
|
#pragma weak MPI_Get_elements = PMPI_Get_elements
|
|
|
|
#endif
|
|
|
|
|
2004-06-07 19:33:53 +04:00
|
|
|
#if OMPI_PROFILING_DEFINES
|
2006-02-12 04:33:29 +03:00
|
|
|
#include "ompi/mpi/c/profile/defines.h"
|
2004-04-20 22:50:43 +04:00
|
|
|
#endif
|
|
|
|
|
2004-07-30 06:58:53 +04:00
|
|
|
static const char FUNC_NAME[] = "MPI_Get_elements";
|
|
|
|
|
|
|
|
|
|
|
|
int MPI_Get_elements(MPI_Status *status, MPI_Datatype datatype, int *count)
|
|
|
|
{
|
2006-10-18 00:20:58 +04:00
|
|
|
int i;
|
|
|
|
size_t size;
|
2008-02-20 01:15:52 +03:00
|
|
|
|
|
|
|
OPAL_CR_NOOP_PROGRESS();
|
|
|
|
|
2008-02-12 11:46:27 +03:00
|
|
|
MEMCHECKER(
|
|
|
|
if (status != MPI_STATUSES_IGNORE) {
|
|
|
|
/*
|
|
|
|
* Before checking the complete status, we need to reset the definedness
|
|
|
|
* of the MPI_ERROR-field (single-completion calls wait/test).
|
|
|
|
*/
|
|
|
|
opal_memchecker_base_mem_defined(&status->MPI_ERROR, sizeof(int));
|
|
|
|
memchecker_status(status);
|
|
|
|
memchecker_datatype(datatype);
|
|
|
|
}
|
|
|
|
);
|
2004-09-19 17:56:39 +04:00
|
|
|
|
|
|
|
if (MPI_PARAM_CHECK) {
|
2006-11-07 05:47:35 +03:00
|
|
|
int err = MPI_SUCCESS;
|
2004-09-19 17:56:39 +04:00
|
|
|
OMPI_ERR_INIT_FINALIZE(FUNC_NAME);
|
2006-11-07 05:47:35 +03:00
|
|
|
if (NULL == status || MPI_STATUSES_IGNORE == status ||
|
|
|
|
MPI_STATUS_IGNORE == status || NULL == count) {
|
|
|
|
err = MPI_ERR_ARG;
|
|
|
|
} else if (NULL == datatype || MPI_DATATYPE_NULL == datatype) {
|
|
|
|
err = MPI_ERR_TYPE;
|
|
|
|
} else {
|
|
|
|
OMPI_CHECK_DATATYPE_FOR_RECV(err, datatype, 1);
|
|
|
|
}
|
|
|
|
OMPI_ERRHANDLER_CHECK(err, MPI_COMM_WORLD, err, FUNC_NAME);
|
2004-09-19 17:56:39 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
*count = 0;
|
- 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 08:56:31 +04:00
|
|
|
if( ompi_datatype_type_size( datatype, &size ) == MPI_SUCCESS ) {
|
2004-09-19 17:56:39 +04:00
|
|
|
if( size == 0 ) {
|
2006-06-06 23:51:42 +04:00
|
|
|
/* If the size of the datatype is zero let's return a count of zero */
|
2004-09-19 17:56:39 +04:00
|
|
|
return MPI_SUCCESS;
|
|
|
|
}
|
2006-10-20 07:57:44 +04:00
|
|
|
*count = (int)(status->_count / size);
|
2004-09-19 17:56:39 +04:00
|
|
|
size = status->_count - (*count) * size;
|
|
|
|
/* if basic type we should return the same result as MPI_Get_count */
|
- 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 08:56:31 +04:00
|
|
|
if( ompi_datatype_is_predefined(datatype) ) {
|
2004-09-19 17:56:39 +04:00
|
|
|
if( size != 0 ) {
|
|
|
|
*count = MPI_UNDEFINED;
|
|
|
|
}
|
|
|
|
return MPI_SUCCESS;
|
|
|
|
}
|
|
|
|
if( (*count) != 0 ) {
|
|
|
|
int total; /* count the basic elements in the datatype */
|
- 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 08:56:31 +04:00
|
|
|
for( i = 4, total = 0; i < OMPI_DATATYPE_MAX_PREDEFINED; i++ )
|
|
|
|
total += datatype->super.btypes[i];
|
2004-09-19 17:56:39 +04:00
|
|
|
*count = total * (*count);
|
|
|
|
}
|
|
|
|
if( size > 0 ) {
|
- 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 08:56:31 +04:00
|
|
|
if( (i = ompi_datatype_get_element_count( datatype, size )) != -1 )
|
2005-04-15 20:00:35 +04:00
|
|
|
*count += i;
|
|
|
|
else
|
|
|
|
*count = MPI_UNDEFINED;
|
2004-09-19 17:56:39 +04:00
|
|
|
}
|
|
|
|
return MPI_SUCCESS;
|
|
|
|
}
|
|
|
|
return OMPI_ERRHANDLER_INVOKE(MPI_COMM_WORLD, MPI_ERR_ARG, FUNC_NAME);
|
2004-01-25 04:51:49 +03:00
|
|
|
}
|