1
1
openmpi/ompi/mca/osc/pt2pt/osc_pt2pt_replyreq.h

144 строки
4.8 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004-2005 The Trustees of Indiana University.
* All rights reserved.
* Copyright (c) 2004-2005 The Trustees of the University of Tennessee.
* 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) 2010 Cisco Systems, Inc. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#ifndef OMPI_OSC_PT2PT_REPLYREQ_H
#define OMPI_OSC_PT2PT_REPLYREQ_H
#include "osc_pt2pt.h"
#include "osc_pt2pt_longreq.h"
Preparation work for another commit (after RFC): - This patch solely _adds_ required headers and is rather localized The next patch (after RFC) heavily removes headers (based on script) - ompi/communicator/communicator.h: For sources that use ompi_mpi_comm_world, don't require them to include "mpi.h" - ompi/debuggers/ompi_common_dll.c: mca_topo_base_comm_1_0_0_t needs #include "ompi/mca/topo/topo.h" - ompi/errhandler/errhandler_predefined.h: ompi/communicator/communicator.h depends on this header file! To prevent recursion just have fwd declarations. #include "ompi/types.h" for fwd declarations of the main structs. - ompi/mca/btl/btl.h: #include "opal/types.h" for ompi_ptr_t - ompi/mca/mpool/base/mpool_base_tree.c: We use ompi_free_list_t and ompi_rb_tree_t, so have the proper classes - ompi/mca/op/op.h: Op is pretty self-contained: Nobody up to now has done #include "opal/class/opal_object.h" - ompi/mca/osc/pt2pt/osc_pt2pt_replyreq.h: #include "opal/types.h" for ompi_ptr_t - ompi/mca/pml/base/base.h: We use opal_lists - ompi/mca/pml/dr/pml_dr_vfrag.h: #include "opal/types.h" for ompi_ptr_t - ompi/mca/pml/ob1/pml_ob1_hdr.h: #include "ompi/mca/btl/btl.h" for mca_btl_base_segment_t - opal/dss/dss_unpack.c: #include "opal/types.h" - opal/mca/base/base.h: #include "opal/util/cmd_line.h" for opal_cmd_line_t - orte/mca/oob/tcp/oob_tcp.c: #include "opal/types.h" for opal_socklen_t - orte/mca/oob/tcp/oob_tcp.h: #include "opal/threads/threads.h" for opal_thread_t - orte/mca/oob/tcp/oob_tcp_msg.c: #include "opal/types.h" - orte/mca/oob/tcp/oob_tcp_peer.c: #include "opal/types.h" for opal_socklen_t - orte/mca/oob/tcp/oob_tcp_send.c: #include "opal/types.h" - orte/mca/plm/base/plm_base_proxy.c: #include "orte/util/name_fns.h" for ORTE_NAME_PRINT - orte/mca/rml/base/rml_base_receive.c: #include "opal/util/output.h" for OPAL_OUTPUT_VERBOSE - orte/mca/rml/oob/rml_oob_recv.c: #include "opal/types.h" for ompi_iov_base_ptr_t - orte/mca/rml/oob/rml_oob_send.c: #include "opal/types.h" for ompi_iov_base_ptr_t - orte/runtime/orte_data_server.c #include "opal/util/output.h" for OPAL_OUTPUT_VERBOSE - orte/runtime/orte_globals.h: #include "orte/util/name_fns.h" for ORTE_NAME_PRINT Tested on Linux/x86-64 This commit was SVN r20817.
2009-03-17 21:34:30 +00:00
#include "opal/types.h"
#include "opal/class/opal_list.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 04:56:31 +00:00
#include "ompi/datatype/ompi_datatype.h"
#include "opal/datatype/opal_convertor.h"
#include "ompi/communicator/communicator.h"
#include "ompi/proc/proc.h"
#include "ompi/memchecker.h"
struct ompi_osc_pt2pt_replyreq_t {
opal_list_item_t super;
/** pointer to the module that created the replyreq */
ompi_osc_pt2pt_module_t *rep_module;
/** Datatype for the target side of the operation */
struct ompi_datatype_t *rep_target_datatype;
/** Convertor for the target. Always setup for send. */
- 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
opal_convertor_t rep_target_convertor;
/** packed size of message on the target side */
size_t rep_target_bytes_packed;
/** rank in module's communicator for origin of operation */
int rep_origin_rank;
/** pointer to the proc structure for the origin of the operation */
ompi_proc_t *rep_origin_proc;
ompi_ptr_t rep_origin_sendreq;
};
typedef struct ompi_osc_pt2pt_replyreq_t ompi_osc_pt2pt_replyreq_t;
OBJ_CLASS_DECLARATION(ompi_osc_pt2pt_replyreq_t);
/** allocate and populate a replyreq structure. datatype is
RETAINed for the life of the replyreq */
int
ompi_osc_pt2pt_replyreq_alloc_init(ompi_osc_pt2pt_module_t *module,
int origin,
ompi_ptr_t origin_request,
OPAL_PTRDIFF_TYPE target_displacement,
int target_count,
struct ompi_datatype_t *datatype,
ompi_osc_pt2pt_replyreq_t **replyreq);
static inline int
ompi_osc_pt2pt_replyreq_alloc(ompi_osc_pt2pt_module_t *module,
int origin_rank,
ompi_osc_pt2pt_replyreq_t **replyreq)
{
int ret;
opal_free_list_item_t *item;
ompi_proc_t *proc = ompi_comm_peer_lookup( module->p2p_comm, origin_rank );
/* BWB - FIX ME - is this really the right return code? */
if (NULL == proc) return OMPI_ERR_OUT_OF_RESOURCE;
OPAL_FREE_LIST_GET(&mca_osc_pt2pt_component.p2p_c_replyreqs,
item, ret);
if (OMPI_SUCCESS != ret) return ret;
*replyreq = (ompi_osc_pt2pt_replyreq_t*) item;
(*replyreq)->rep_module = module;
(*replyreq)->rep_origin_rank = origin_rank;
(*replyreq)->rep_origin_proc = proc;
return OMPI_SUCCESS;
}
static inline int
ompi_osc_pt2pt_replyreq_init_target(ompi_osc_pt2pt_replyreq_t *replyreq,
void *target_addr,
int target_count,
struct ompi_datatype_t *target_dt)
{
OBJ_RETAIN(target_dt);
replyreq->rep_target_datatype = target_dt;
- 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
opal_convertor_copy_and_prepare_for_send(replyreq->rep_origin_proc->proc_convertor,
&(target_dt->super),
target_count,
target_addr,
0,
&(replyreq->rep_target_convertor));
- 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
opal_convertor_get_packed_size(&replyreq->rep_target_convertor,
&replyreq->rep_target_bytes_packed);
return OMPI_SUCCESS;
}
static inline int
ompi_osc_pt2pt_replyreq_init_origin(ompi_osc_pt2pt_replyreq_t *replyreq,
ompi_ptr_t origin_request)
{
replyreq->rep_origin_sendreq = origin_request;
return OMPI_SUCCESS;
}
static inline int
ompi_osc_pt2pt_replyreq_free(ompi_osc_pt2pt_replyreq_t *replyreq)
{
MEMCHECKER(
memchecker_convertor_call(&opal_memchecker_base_mem_defined,
&replyreq->rep_target_convertor);
);
- 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
opal_convertor_cleanup(&replyreq->rep_target_convertor);
OBJ_RELEASE(replyreq->rep_target_datatype);
OPAL_FREE_LIST_RETURN(&mca_osc_pt2pt_component.p2p_c_replyreqs,
(opal_list_item_t*) replyreq);
return OMPI_SUCCESS;
}
#endif /* OMPI_OSC_PT2PT_REPLYREQ_H */