1
1
openmpi/ompi/mca/coll/tuned/coll_tuned_util.h

126 строки
5.3 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2012 The University of Tennessee and The University
* of Tennessee Research Foundation. All rights
* reserved.
* Copyright (c) 2004-2007 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.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#ifndef MCA_COLL_TUNED_UTIL_EXPORT_H
#define MCA_COLL_TUNED_UTIL_EXPORT_H
#include "ompi_config.h"
#include "mpi.h"
#include "opal/mca/mca.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"
#include "ompi/request/request.h"
#include "ompi/mca/pml/pml.h"
- Replace combinations of #if defined (c_plusplus) defined (__cplusplus) followed by extern "C" { and the closing counterpart by BEGIN_C_DECLS and END_C_DECLS. Notable exceptions are: - opal/include/opal_config_bottom.h: This is our generated code, that itself defines BEGIN_C_DECL and END_C_DECL - ompi/mpi/cxx/mpicxx.h: Here we do not include opal_config_bottom.h: - Belongs to external code: opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.c opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.h - opal/include/opal/prefetch.h: Has C++ specific macros that are protected: - Had #if ... } #endif _and_ END_C_DECLS (aka end up with 2x END_C_DECLS) ompi/mca/btl/openib/btl_openib.h - opal/event/event.h has #ifdef __cplusplus as BEGIN_C_DECLS... - opal/win32/ompi_process.h: had extern "C"\n {... opal/win32/ompi_process.h: dito - ompi/mca/btl/pcie/btl_pcie_lex.l: needed to add *_C_DECLS ompi/mpi/f90/test/align_c.c: dito - ompi/debuggers/msgq_interface.h: used #ifdef __cplusplus - ompi/mpi/f90/xml/common-C.xsl: Amend Tested on linux using --with-openib and --with-mx The following do not contain either opal_config.h, orte_config.h or ompi_config.h (but possibly other header files, that include one of the above): ompi/mca/bml/r2/bml_r2_ft.h ompi/mca/btl/gm/btl_gm_endpoint.h ompi/mca/btl/gm/btl_gm_proc.h ompi/mca/btl/mx/btl_mx_endpoint.h ompi/mca/btl/ofud/btl_ofud_endpoint.h ompi/mca/btl/ofud/btl_ofud_frag.h ompi/mca/btl/ofud/btl_ofud_proc.h ompi/mca/btl/openib/btl_openib_mca.h ompi/mca/btl/portals/btl_portals_endpoint.h ompi/mca/btl/portals/btl_portals_frag.h ompi/mca/btl/sctp/btl_sctp_endpoint.h ompi/mca/btl/sctp/btl_sctp_proc.h ompi/mca/btl/tcp/btl_tcp_endpoint.h ompi/mca/btl/tcp/btl_tcp_ft.h ompi/mca/btl/tcp/btl_tcp_proc.h ompi/mca/btl/template/btl_template_endpoint.h ompi/mca/btl/template/btl_template_proc.h ompi/mca/btl/udapl/btl_udapl_eager_rdma.h ompi/mca/btl/udapl/btl_udapl_endpoint.h ompi/mca/btl/udapl/btl_udapl_mca.h ompi/mca/btl/udapl/btl_udapl_proc.h ompi/mca/mtl/mx/mtl_mx_endpoint.h ompi/mca/mtl/mx/mtl_mx.h ompi/mca/mtl/psm/mtl_psm_endpoint.h ompi/mca/mtl/psm/mtl_psm.h ompi/mca/pml/cm/pml_cm_component.h ompi/mca/pml/csum/pml_csum_comm.h ompi/mca/pml/dr/pml_dr_comm.h ompi/mca/pml/dr/pml_dr_component.h ompi/mca/pml/dr/pml_dr_endpoint.h ompi/mca/pml/dr/pml_dr_recvfrag.h ompi/mca/pml/example/pml_example.h ompi/mca/pml/ob1/pml_ob1_comm.h ompi/mca/pml/ob1/pml_ob1_component.h ompi/mca/pml/ob1/pml_ob1_endpoint.h ompi/mca/pml/ob1/pml_ob1_rdmafrag.h ompi/mca/pml/ob1/pml_ob1_recvfrag.h ompi/mca/pml/v/pml_v_output.h opal/include/opal/prefetch.h opal/mca/timer/aix/timer_aix.h opal/util/qsort.h test/support/components.h This commit was SVN r21855. The following SVN revision numbers were found above: r2 --> open-mpi/ompi@58fdc188553052bc2e893ba28fb28fddbe78435a
2009-08-20 15:42:18 +04:00
BEGIN_C_DECLS
/* prototypes */
int ompi_coll_tuned_sendrecv_actual( void* sendbuf, size_t scount,
ompi_datatype_t* sdatatype,
int dest, int stag,
void* recvbuf, size_t rcount,
ompi_datatype_t* rdatatype,
int source, int rtag,
struct ompi_communicator_t* comm,
ompi_status_public_t* status );
/* inline functions */
static inline int
ompi_coll_tuned_sendrecv( void* sendbuf, size_t scount, ompi_datatype_t* sdatatype,
int dest, int stag,
void* recvbuf, size_t rcount, ompi_datatype_t* rdatatype,
int source, int rtag,
struct ompi_communicator_t* comm,
ompi_status_public_t* status, int myid )
{
if ((dest == myid) && (source == myid)) {
- 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
return (int) ompi_datatype_sndrcv(sendbuf, (int32_t) scount, sdatatype,
recvbuf, (int32_t) rcount, rdatatype);
}
return ompi_coll_tuned_sendrecv_actual (sendbuf, scount, sdatatype,
dest, stag,
recvbuf, rcount, rdatatype,
source, rtag, comm, status);
}
int
ompi_coll_tuned_sendrecv_actual_localcompleted( void* sendbuf, size_t scount,
ompi_datatype_t* sdatatype,
int dest, int stag,
void* recvbuf, size_t rcount,
ompi_datatype_t* rdatatype,
int source, int rtag,
struct ompi_communicator_t* comm,
ompi_status_public_t* status );
/* inline functions */
static inline int
ompi_coll_tuned_sendrecv_localcompleted( void* sendbuf, size_t scount,
ompi_datatype_t* sdatatype,
int dest, int stag,
void* recvbuf, size_t rcount,
ompi_datatype_t* rdatatype,
int source, int rtag,
struct ompi_communicator_t* comm,
ompi_status_public_t* status, int myid )
{
if ((dest == myid) && (source == myid)) {
- 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
return (int) ompi_datatype_sndrcv(sendbuf, (int32_t) scount, sdatatype,
recvbuf, (int32_t) rcount, rdatatype);
}
return ompi_coll_tuned_sendrecv_actual_localcompleted (sendbuf, scount,
sdatatype, dest,
stag,
recvbuf, rcount,
rdatatype,
source, rtag, comm,
status);
}
/* inline functions */
static inline int
ompi_coll_tuned_isendrecv( void* sendbuf, size_t scount, ompi_datatype_t* sdtype,
int dest, int stag, ompi_request_t** sreq,
void* recvbuf, size_t rcount, ompi_datatype_t* rdtype,
int source, int rtag, ompi_request_t** rreq,
struct ompi_communicator_t* comm ) {
int ret, line;
ret = MCA_PML_CALL(irecv(recvbuf, rcount, rdtype, source, rtag, comm, rreq));
if (MPI_SUCCESS != ret) { line = __LINE__; goto error_handler; }
ret = MCA_PML_CALL(isend(sendbuf, scount, sdtype, dest, stag,
MCA_PML_BASE_SEND_STANDARD, comm, sreq));
if (MPI_SUCCESS != ret) { line = __LINE__; goto error_handler; }
return MPI_SUCCESS;
error_handler:
OPAL_OUTPUT((ompi_coll_tuned_stream, "%s:%d\tError occurred %d\n",
__FILE__, line, ret));
return ret;
}
- Replace combinations of #if defined (c_plusplus) defined (__cplusplus) followed by extern "C" { and the closing counterpart by BEGIN_C_DECLS and END_C_DECLS. Notable exceptions are: - opal/include/opal_config_bottom.h: This is our generated code, that itself defines BEGIN_C_DECL and END_C_DECL - ompi/mpi/cxx/mpicxx.h: Here we do not include opal_config_bottom.h: - Belongs to external code: opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.c opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.h - opal/include/opal/prefetch.h: Has C++ specific macros that are protected: - Had #if ... } #endif _and_ END_C_DECLS (aka end up with 2x END_C_DECLS) ompi/mca/btl/openib/btl_openib.h - opal/event/event.h has #ifdef __cplusplus as BEGIN_C_DECLS... - opal/win32/ompi_process.h: had extern "C"\n {... opal/win32/ompi_process.h: dito - ompi/mca/btl/pcie/btl_pcie_lex.l: needed to add *_C_DECLS ompi/mpi/f90/test/align_c.c: dito - ompi/debuggers/msgq_interface.h: used #ifdef __cplusplus - ompi/mpi/f90/xml/common-C.xsl: Amend Tested on linux using --with-openib and --with-mx The following do not contain either opal_config.h, orte_config.h or ompi_config.h (but possibly other header files, that include one of the above): ompi/mca/bml/r2/bml_r2_ft.h ompi/mca/btl/gm/btl_gm_endpoint.h ompi/mca/btl/gm/btl_gm_proc.h ompi/mca/btl/mx/btl_mx_endpoint.h ompi/mca/btl/ofud/btl_ofud_endpoint.h ompi/mca/btl/ofud/btl_ofud_frag.h ompi/mca/btl/ofud/btl_ofud_proc.h ompi/mca/btl/openib/btl_openib_mca.h ompi/mca/btl/portals/btl_portals_endpoint.h ompi/mca/btl/portals/btl_portals_frag.h ompi/mca/btl/sctp/btl_sctp_endpoint.h ompi/mca/btl/sctp/btl_sctp_proc.h ompi/mca/btl/tcp/btl_tcp_endpoint.h ompi/mca/btl/tcp/btl_tcp_ft.h ompi/mca/btl/tcp/btl_tcp_proc.h ompi/mca/btl/template/btl_template_endpoint.h ompi/mca/btl/template/btl_template_proc.h ompi/mca/btl/udapl/btl_udapl_eager_rdma.h ompi/mca/btl/udapl/btl_udapl_endpoint.h ompi/mca/btl/udapl/btl_udapl_mca.h ompi/mca/btl/udapl/btl_udapl_proc.h ompi/mca/mtl/mx/mtl_mx_endpoint.h ompi/mca/mtl/mx/mtl_mx.h ompi/mca/mtl/psm/mtl_psm_endpoint.h ompi/mca/mtl/psm/mtl_psm.h ompi/mca/pml/cm/pml_cm_component.h ompi/mca/pml/csum/pml_csum_comm.h ompi/mca/pml/dr/pml_dr_comm.h ompi/mca/pml/dr/pml_dr_component.h ompi/mca/pml/dr/pml_dr_endpoint.h ompi/mca/pml/dr/pml_dr_recvfrag.h ompi/mca/pml/example/pml_example.h ompi/mca/pml/ob1/pml_ob1_comm.h ompi/mca/pml/ob1/pml_ob1_component.h ompi/mca/pml/ob1/pml_ob1_endpoint.h ompi/mca/pml/ob1/pml_ob1_rdmafrag.h ompi/mca/pml/ob1/pml_ob1_recvfrag.h ompi/mca/pml/v/pml_v_output.h opal/include/opal/prefetch.h opal/mca/timer/aix/timer_aix.h opal/util/qsort.h test/support/components.h This commit was SVN r21855. The following SVN revision numbers were found above: r2 --> open-mpi/ompi@58fdc188553052bc2e893ba28fb28fddbe78435a
2009-08-20 15:42:18 +04:00
END_C_DECLS
#endif /* MCA_COLL_TUNED_UTIL_EXPORT_H */