ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
a7c79558ad
openmpi/ompi/mca/coll/base/coll_base_find_available.c

211 строки
7.0 KiB
C
Исходник Обычный вид История

Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
/*
Update the copyright notices for IU and UTK. This commit was SVN r7999.
2005-11-05 22:57:48 +03:00
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
* 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.
Add HLRS copyright This commit was SVN r3665.
2004-11-28 23:09:25 +03:00
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
* University of Stuttgart. All rights reserved.
Add UC copyright This commit was SVN r5009.
2005-03-24 15:43:37 +03:00
* Copyright (c) 2004-2005 The Regents of the University of California.
* All rights reserved.
First cut at copyrights: IU, UTK, and some OSU. LANL and HLRS still pending. This commit was SVN r3655.
2004-11-22 04:38:40 +03:00
* $COPYRIGHT$
*
* Additional copyrights may follow
*
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
* $HEADER$
*/
#include "ompi_config.h"
#include <stdio.h>
#include <stdlib.h>
I hate waiting on the airports. SO I start doing something usefull ... I remove a lot of inter-dependence, I use the struct_t type. BEWARE not all the function are ready. This commit was SVN r3524.
2004-11-05 10:52:30 +03:00
#include <string.h>
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
#include "mpi.h"
Next step in the project split, mainly source code re-arranging - move files out of toplevel include/ and etc/, moving it into the sub-projects - rather than including config headers with <project>/include, have them as <project> - require all headers to be included with a project prefix, with the exception of the config headers ({opal,orte,ompi}_config.h mpi.h, and mpif.h) This commit was SVN r8985.
2006-02-12 04:33:29 +03:00
#include "ompi/constants.h"
* rename ompi_list to opal_list This commit was SVN r6322.
2005-07-03 20:22:16 +04:00
#include "opal/class/opal_list.h"
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 18:53:58 +04:00
#include "orte/util/show_help.h"
- Add to AM_CPPFLAGS $(OPAL_LTDL_CPPFLAGS) where necessary in order to add a -I to find the included ltdl.h (vs. a system-installed ltdl.h) - Clean up kruft in a bunch of Makefile.am's to remove now-unnecessary AM_CPPFLAGS settings to get static-components.h for each framework - Move the component_repository API functions out of opal/mca/base/base.h and into opal/mca/base/mca_base_component_repository.h in order to decrease unnecessary dependencies (e.g., before this, almost everything in the tree depended on ltdl.h, which is unnecessary -- only a small number of files really need ltdl.h) This commit was SVN r7127.
2005-09-01 16:16:36 +04:00
#include "opal/mca/mca.h"
#include "opal/mca/base/base.h"
#include "opal/mca/base/mca_base_component_repository.h"
#include "ompi/mca/coll/coll.h"
#include "ompi/mca/coll/base/base.h"
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
/*
* Global variables
*/
bool mca_coll_base_components_available_valid = false;
* rename ompi_list to opal_list This commit was SVN r6322.
2005-07-03 20:22:16 +04:00
opal_list_t mca_coll_base_components_available;
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
/*
* Private functions
*/
- massive change for module<-->component name fixes throughout the code base. - many (most) mca type names have "component" or "module" in them, as relevant, just to further distinguish the difference between component data/actions and module data/actions. All developers are encouraged to perpetuate this convention when you create types that are specific to a framework, component, or module - did very little to entire framework (just the basics to make it compile) because it's just about to be almost entirely replaced - ditto for io / romio - did not work on elan or ib components; have to commit and then convert those on a different machine with the right libraries and headers - renamed a bunch of *_module.c files to *_component.c and *module*c to *component*c (a few still remain, e.g., ptl/ib, ptl/elan, etc.) - modified autogen/configure/build process to match new filenames (e.g., output static-components.h instead of static-modules.h) - removed DOS-style cr/lf stuff in ns/ns.h - added newline to end of file src/util/numtostr.h - removed some redundant error checking in the top-level topo functions - added a few {} here and there where people "forgot" to put them in for 1 line blocks ;-) - removed a bunch of MPI_* types from mca header files (replaced with corresponding ompi_* types) - all the ptl components had version numbers in their structs; removed - converted a few more elements in the MCA base to use the OBJ interface -- removed some old manual reference counting kruft This commit was SVN r1830.
2004-08-02 04:24:22 +04:00
static int init_query(const mca_base_component_t *ls,
Change the orientation of the thread level determination in ompi_mpi_init(): we no longer *query* the components to see what they can support -- instead, we *tell* the components what they need to support (if they can't support it, they should disqualify themselves from selection). This involved a bunch of things: - pass the configure-time-decided OMPI_ENABLE_PROGRESS_THREADS and OMPI_ENABLE_MPI_THREADS constants to each framework selection function - eliminate mca_base_init_select_components() - eliminate all "allow_multi_user_threads" and "have_hidden_threads" kinds of arguments and aggregation from various framework selection and component/module functions - correctly determine the max MPI thread level that we can support and limit the final MPI thread level as appropriate during ompi_mpi_init() As a side effect, while editing nearly every MPI component I also did the following: - found 2 places (gm and ib ptls) where ompi_set_using_threads() was erroneously being called (I think this is left over kruft from misunderstandings by the original authors). I removed these. This commit was SVN r5055.
2005-03-27 17:05:23 +04:00
mca_base_component_priority_list_item_t *entry,
bool enable_progress_threads,
bool enable_mpi_threads);
Update collectives selection logic to allow for multiple components to be used at nce (up to one unique collective module per collective function). Matches r15795:15921 of the tmp/bwb-coll-select branch This commit was SVN r15924. The following SVN revisions from the original message are invalid or inconsistent and therefore were not cross-referenced: r15795 r15921
2007-08-19 07:37:49 +04:00
static int init_query_1_1_0(const mca_base_component_t *ls,
Change the orientation of the thread level determination in ompi_mpi_init(): we no longer *query* the components to see what they can support -- instead, we *tell* the components what they need to support (if they can't support it, they should disqualify themselves from selection). This involved a bunch of things: - pass the configure-time-decided OMPI_ENABLE_PROGRESS_THREADS and OMPI_ENABLE_MPI_THREADS constants to each framework selection function - eliminate mca_base_init_select_components() - eliminate all "allow_multi_user_threads" and "have_hidden_threads" kinds of arguments and aggregation from various framework selection and component/module functions - correctly determine the max MPI thread level that we can support and limit the final MPI thread level as appropriate during ompi_mpi_init() As a side effect, while editing nearly every MPI component I also did the following: - found 2 places (gm and ib ptls) where ompi_set_using_threads() was erroneously being called (I think this is left over kruft from misunderstandings by the original authors). I removed these. This commit was SVN r5055.
2005-03-27 17:05:23 +04:00
mca_base_component_priority_list_item_t *entry,
bool enable_progress_threads,
bool enable_mpi_threads);
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
/*
* Scan down the list of successfully opened components and query each of
* them (the opened list will be one or more components. If the user
* requested a specific component, it will be the only component in the
* opened list). Create and populate the available list of all
* components who indicate that they want to be considered for selection.
* Close all components who do not want to be considered for selection,
* and destroy the opened list.
*
* Also find the basic component while we're doing all of this, and save
* it in a global variable so that we can find it easily later (e.g.,
* during scope selection).
*/
Change the orientation of the thread level determination in ompi_mpi_init(): we no longer *query* the components to see what they can support -- instead, we *tell* the components what they need to support (if they can't support it, they should disqualify themselves from selection). This involved a bunch of things: - pass the configure-time-decided OMPI_ENABLE_PROGRESS_THREADS and OMPI_ENABLE_MPI_THREADS constants to each framework selection function - eliminate mca_base_init_select_components() - eliminate all "allow_multi_user_threads" and "have_hidden_threads" kinds of arguments and aggregation from various framework selection and component/module functions - correctly determine the max MPI thread level that we can support and limit the final MPI thread level as appropriate during ompi_mpi_init() As a side effect, while editing nearly every MPI component I also did the following: - found 2 places (gm and ib ptls) where ompi_set_using_threads() was erroneously being called (I think this is left over kruft from misunderstandings by the original authors). I removed these. This commit was SVN r5055.
2005-03-27 17:05:23 +04:00
int mca_coll_base_find_available(bool enable_progress_threads,
bool enable_mpi_threads)
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
{
bool found = false;
mca_base_component_priority_list_item_t *entry;
* rename ompi_list to opal_list This commit was SVN r6322.
2005-07-03 20:22:16 +04:00
opal_list_item_t *p;
- massive change for module<-->component name fixes throughout the code base. - many (most) mca type names have "component" or "module" in them, as relevant, just to further distinguish the difference between component data/actions and module data/actions. All developers are encouraged to perpetuate this convention when you create types that are specific to a framework, component, or module - did very little to entire framework (just the basics to make it compile) because it's just about to be almost entirely replaced - ditto for io / romio - did not work on elan or ib components; have to commit and then convert those on a different machine with the right libraries and headers - renamed a bunch of *_module.c files to *_component.c and *module*c to *component*c (a few still remain, e.g., ptl/ib, ptl/elan, etc.) - modified autogen/configure/build process to match new filenames (e.g., output static-components.h instead of static-modules.h) - removed DOS-style cr/lf stuff in ns/ns.h - added newline to end of file src/util/numtostr.h - removed some redundant error checking in the top-level topo functions - added a few {} here and there where people "forgot" to put them in for 1 line blocks ;-) - removed a bunch of MPI_* types from mca header files (replaced with corresponding ompi_* types) - all the ptl components had version numbers in their structs; removed - converted a few more elements in the MCA base to use the OBJ interface -- removed some old manual reference counting kruft This commit was SVN r1830.
2004-08-02 04:24:22 +04:00
const mca_base_component_t *component;
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
/* Initialize the list */
* rename ompi_list to opal_list This commit was SVN r6322.
2005-07-03 20:22:16 +04:00
OBJ_CONSTRUCT(&mca_coll_base_components_available, opal_list_t);
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
mca_coll_base_components_available_valid = true;
/* The list of components that we should check has already been
established in mca_coll_base_open. */
for (found = false,
* rename ompi_list to opal_list This commit was SVN r6322.
2005-07-03 20:22:16 +04:00
p = opal_list_remove_first(&mca_coll_base_components_opened);
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
p != NULL;
* rename ompi_list to opal_list This commit was SVN r6322.
2005-07-03 20:22:16 +04:00
p = opal_list_remove_first(&mca_coll_base_components_opened)) {
- massive change for module<-->component name fixes throughout the code base. - many (most) mca type names have "component" or "module" in them, as relevant, just to further distinguish the difference between component data/actions and module data/actions. All developers are encouraged to perpetuate this convention when you create types that are specific to a framework, component, or module - did very little to entire framework (just the basics to make it compile) because it's just about to be almost entirely replaced - ditto for io / romio - did not work on elan or ib components; have to commit and then convert those on a different machine with the right libraries and headers - renamed a bunch of *_module.c files to *_component.c and *module*c to *component*c (a few still remain, e.g., ptl/ib, ptl/elan, etc.) - modified autogen/configure/build process to match new filenames (e.g., output static-components.h instead of static-modules.h) - removed DOS-style cr/lf stuff in ns/ns.h - added newline to end of file src/util/numtostr.h - removed some redundant error checking in the top-level topo functions - added a few {} here and there where people "forgot" to put them in for 1 line blocks ;-) - removed a bunch of MPI_* types from mca header files (replaced with corresponding ompi_* types) - all the ptl components had version numbers in their structs; removed - converted a few more elements in the MCA base to use the OBJ interface -- removed some old manual reference counting kruft This commit was SVN r1830.
2004-08-02 04:24:22 +04:00
component = ((mca_base_component_list_item_t *) p)->cli_component;
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
/* Call a subroutine to do the work, because the component may
represent different versions of the coll MCA. */
Oops -- need to initialized "entry" before we used it. Duh. :-( This commit was SVN r1695.
2004-07-14 00:41:46 +04:00
entry = OBJ_NEW(mca_base_component_priority_list_item_t);
Fix component close issue with topo, coll, and io. This commit was SVN r3556.
2004-11-12 19:55:41 +03:00
entry->super.cli_component = component;
Oops -- need to initialized "entry" before we used it. Duh. :-( This commit was SVN r1695.
2004-07-14 00:41:46 +04:00
entry->cpli_priority = 0;
Change the orientation of the thread level determination in ompi_mpi_init(): we no longer *query* the components to see what they can support -- instead, we *tell* the components what they need to support (if they can't support it, they should disqualify themselves from selection). This involved a bunch of things: - pass the configure-time-decided OMPI_ENABLE_PROGRESS_THREADS and OMPI_ENABLE_MPI_THREADS constants to each framework selection function - eliminate mca_base_init_select_components() - eliminate all "allow_multi_user_threads" and "have_hidden_threads" kinds of arguments and aggregation from various framework selection and component/module functions - correctly determine the max MPI thread level that we can support and limit the final MPI thread level as appropriate during ompi_mpi_init() As a side effect, while editing nearly every MPI component I also did the following: - found 2 places (gm and ib ptls) where ompi_set_using_threads() was erroneously being called (I think this is left over kruft from misunderstandings by the original authors). I removed these. This commit was SVN r5055.
2005-03-27 17:05:23 +04:00
if (OMPI_SUCCESS == init_query(component, entry,
enable_progress_threads,
enable_mpi_threads)) {
* rename ompi_list to opal_list This commit was SVN r6322.
2005-07-03 20:22:16 +04:00
opal_list_append(&mca_coll_base_components_available,
(opal_list_item_t *) entry);
Update collectives selection logic to allow for multiple components to be used at nce (up to one unique collective module per collective function). Matches r15795:15921 of the tmp/bwb-coll-select branch This commit was SVN r15924. The following SVN revisions from the original message are invalid or inconsistent and therefore were not cross-referenced: r15795 r15921
2007-08-19 07:37:49 +04:00
found = true;
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
} else {
/* If the component doesn't want to run, then close it. It's
already had its close() method invoked; now close it out of
the DSO repository (if it's there). */
- massive change for module<-->component name fixes throughout the code base. - many (most) mca type names have "component" or "module" in them, as relevant, just to further distinguish the difference between component data/actions and module data/actions. All developers are encouraged to perpetuate this convention when you create types that are specific to a framework, component, or module - did very little to entire framework (just the basics to make it compile) because it's just about to be almost entirely replaced - ditto for io / romio - did not work on elan or ib components; have to commit and then convert those on a different machine with the right libraries and headers - renamed a bunch of *_module.c files to *_component.c and *module*c to *component*c (a few still remain, e.g., ptl/ib, ptl/elan, etc.) - modified autogen/configure/build process to match new filenames (e.g., output static-components.h instead of static-modules.h) - removed DOS-style cr/lf stuff in ns/ns.h - added newline to end of file src/util/numtostr.h - removed some redundant error checking in the top-level topo functions - added a few {} here and there where people "forgot" to put them in for 1 line blocks ;-) - removed a bunch of MPI_* types from mca header files (replaced with corresponding ompi_* types) - all the ptl components had version numbers in their structs; removed - converted a few more elements in the MCA base to use the OBJ interface -- removed some old manual reference counting kruft This commit was SVN r1830.
2004-08-02 04:24:22 +04:00
mca_base_component_repository_release(component);
Oops -- need to initialized "entry" before we used it. Duh. :-( This commit was SVN r1695.
2004-07-14 00:41:46 +04:00
OBJ_RELEASE(entry);
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
}
/* Free the entry from the "opened" list */
Fix some stylistic problems and code errors, found during code review with Anju This commit was SVN r1656.
2004-07-13 08:43:16 +04:00
OBJ_RELEASE(p);
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
}
/* The opened list is now no longer useful and we can free it */
OBJ_DESTRUCT(&mca_coll_base_components_opened);
mca_coll_base_components_opened_valid = false;
/* If we have no collective components available, it's an error.
Thanks for playing! */
if (!found) {
/* Need to free all items in the list */
OBJ_DESTRUCT(&mca_coll_base_components_available);
mca_coll_base_components_available_valid = false;
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 18:53:58 +04:00
opal_output_verbose(10, mca_coll_base_output,
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
"coll:find_available: no coll components available!");
This commit represents a bunch of work on a Mercurial side branch. As such, the commit message back to the master SVN repository is fairly long. = ORTE Job-Level Output Messages = Add two new interfaces that should be used for all new code throughout the ORTE and OMPI layers (we already make the search-and-replace on the existing ORTE / OMPI layers): * orte_output(): (and corresponding friends ORTE_OUTPUT, orte_output_verbose, etc.) This function sends the output directly to the HNP for processing as part of a job-specific output channel. It supports all the same outputs as opal_output() (syslog, file, stdout, stderr), but for stdout/stderr, the output is sent to the HNP for processing and output. More on this below. * orte_show_help(): This function is a drop-in-replacement for opal_show_help(), with two differences in functionality: 1. the rendered text help message output is sent to the HNP for display (rather than outputting directly into the process' stderr stream) 1. the HNP detects duplicate help messages and does not display them (so that you don't see the same error message N times, once from each of your N MPI processes); instead, it counts "new" instances of the help message and displays a message every ~5 seconds when there are new ones ("I got X new copies of the help message...") opal_show_help and opal_output still exist, but they only output in the current process. The intent for the new orte_* functions is that they can apply job-level intelligence to the output. As such, we recommend that all new ORTE and OMPI code use the new orte_* functions, not thei opal_* functions. === New code === For ORTE and OMPI programmers, here's what you need to do differently in new code: * Do not include opal/util/show_help.h or opal/util/output.h. Instead, include orte/util/output.h (this one header file has declarations for both the orte_output() series of functions and orte_show_help()). * Effectively s/opal_output/orte_output/gi throughout your code. Note that orte_output_open() takes a slightly different argument list (as a way to pass data to the filtering stream -- see below), so you if explicitly call opal_output_open(), you'll need to slightly adapt to the new signature of orte_output_open(). * Literally s/opal_show_help/orte_show_help/. The function signature is identical. === Notes === * orte_output'ing to stream 0 will do similar to what opal_output'ing did, so leaving a hard-coded "0" as the first argument is safe. * For systems that do not use ORTE's RML or the HNP, the effect of orte_output_* and orte_show_help will be identical to their opal counterparts (the additional information passed to orte_output_open() will be lost!). Indeed, the orte_* functions simply become trivial wrappers to their opal_* counterparts. Note that we have not tested this; the code is simple but it is quite possible that we mucked something up. = Filter Framework = Messages sent view the new orte_* functions described above and messages output via the IOF on the HNP will now optionally be passed through a new "filter" framework before being output to stdout/stderr. The "filter" OPAL MCA framework is intended to allow preprocessing to messages before they are sent to their final destinations. The first component that was written in the filter framework was to create an XML stream, segregating all the messages into different XML tags, etc. This will allow 3rd party tools to read the stdout/stderr from the HNP and be able to know exactly what each text message is (e.g., a help message, another OMPI infrastructure message, stdout from the user process, stderr from the user process, etc.). Filtering is not active by default. Filter components must be specifically requested, such as: {{{ $ mpirun --mca filter xml ... }}} There can only be one filter component active. = New MCA Parameters = The new functionality described above introduces two new MCA parameters: * '''orte_base_help_aggregate''': Defaults to 1 (true), meaning that help messages will be aggregated, as described above. If set to 0, all help messages will be displayed, even if they are duplicates (i.e., the original behavior). * '''orte_base_show_output_recursions''': An MCA parameter to help debug one of the known issues, described below. It is likely that this MCA parameter will disappear before v1.3 final. = Known Issues = * The XML filter component is not complete. The current output from this component is preliminary and not real XML. A bit more work needs to be done to configure.m4 search for an appropriate XML library/link it in/use it at run time. * There are possible recursion loops in the orte_output() and orte_show_help() functions -- e.g., if RML send calls orte_output() or orte_show_help(). We have some ideas how to fix these, but figured that it was ok to commit before feature freeze with known issues. The code currently contains sub-optimal workarounds so that this will not be a problem, but it would be good to actually solve the problem rather than have hackish workarounds before v1.3 final. This commit was SVN r18434.
2008-05-14 00:00:55 +04:00
orte_show_help("help-mca-base", "find-available:none-found", true,
First cut of the Show Help Subsystem (SHS) - see src/util/show_help.h for details (doxygen); main function call is ompi_show_help() - text message files are expected to be located in $pkgdatadir (usually $prefix/share/openmpi). Anyone can install a text file in $pkgdatadir with their message(s) in it and then have them displayed via ompi_show_help(). "pkgdata_DATA" is the keyword to use in Makefile.am's, for example (from src/mca/base/Makefile.am): pkgdata_DATA = help-mca-base.txt - added a few examples in the code base using ompi_show_help(), but not too many -- can convert more "show_help" comments in the code over time; no huge rush. :-) - no i18n-like support yet; waiting for advice and consensus from other developers This commit was SVN r2519.
2004-09-05 20:05:37 +04:00
"coll");
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
return OMPI_ERROR;
}
/* All done */
return OMPI_SUCCESS;
}
/*
* Query a component, see if it wants to run at all. If it does, save
* some information. If it doesn't, close it.
*/
- massive change for module<-->component name fixes throughout the code base. - many (most) mca type names have "component" or "module" in them, as relevant, just to further distinguish the difference between component data/actions and module data/actions. All developers are encouraged to perpetuate this convention when you create types that are specific to a framework, component, or module - did very little to entire framework (just the basics to make it compile) because it's just about to be almost entirely replaced - ditto for io / romio - did not work on elan or ib components; have to commit and then convert those on a different machine with the right libraries and headers - renamed a bunch of *_module.c files to *_component.c and *module*c to *component*c (a few still remain, e.g., ptl/ib, ptl/elan, etc.) - modified autogen/configure/build process to match new filenames (e.g., output static-components.h instead of static-modules.h) - removed DOS-style cr/lf stuff in ns/ns.h - added newline to end of file src/util/numtostr.h - removed some redundant error checking in the top-level topo functions - added a few {} here and there where people "forgot" to put them in for 1 line blocks ;-) - removed a bunch of MPI_* types from mca header files (replaced with corresponding ompi_* types) - all the ptl components had version numbers in their structs; removed - converted a few more elements in the MCA base to use the OBJ interface -- removed some old manual reference counting kruft This commit was SVN r1830.
2004-08-02 04:24:22 +04:00
static int init_query(const mca_base_component_t *m,
Change the orientation of the thread level determination in ompi_mpi_init(): we no longer *query* the components to see what they can support -- instead, we *tell* the components what they need to support (if they can't support it, they should disqualify themselves from selection). This involved a bunch of things: - pass the configure-time-decided OMPI_ENABLE_PROGRESS_THREADS and OMPI_ENABLE_MPI_THREADS constants to each framework selection function - eliminate mca_base_init_select_components() - eliminate all "allow_multi_user_threads" and "have_hidden_threads" kinds of arguments and aggregation from various framework selection and component/module functions - correctly determine the max MPI thread level that we can support and limit the final MPI thread level as appropriate during ompi_mpi_init() As a side effect, while editing nearly every MPI component I also did the following: - found 2 places (gm and ib ptls) where ompi_set_using_threads() was erroneously being called (I think this is left over kruft from misunderstandings by the original authors). I removed these. This commit was SVN r5055.
2005-03-27 17:05:23 +04:00
mca_base_component_priority_list_item_t *entry,
bool enable_progress_threads,
bool enable_mpi_threads)
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
{
int ret;
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 18:53:58 +04:00
opal_output_verbose(10, mca_coll_base_output,
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
"coll:find_available: querying coll component %s",
- massive change for module<-->component name fixes throughout the code base. - many (most) mca type names have "component" or "module" in them, as relevant, just to further distinguish the difference between component data/actions and module data/actions. All developers are encouraged to perpetuate this convention when you create types that are specific to a framework, component, or module - did very little to entire framework (just the basics to make it compile) because it's just about to be almost entirely replaced - ditto for io / romio - did not work on elan or ib components; have to commit and then convert those on a different machine with the right libraries and headers - renamed a bunch of *_module.c files to *_component.c and *module*c to *component*c (a few still remain, e.g., ptl/ib, ptl/elan, etc.) - modified autogen/configure/build process to match new filenames (e.g., output static-components.h instead of static-modules.h) - removed DOS-style cr/lf stuff in ns/ns.h - added newline to end of file src/util/numtostr.h - removed some redundant error checking in the top-level topo functions - added a few {} here and there where people "forgot" to put them in for 1 line blocks ;-) - removed a bunch of MPI_* types from mca header files (replaced with corresponding ompi_* types) - all the ptl components had version numbers in their structs; removed - converted a few more elements in the MCA base to use the OBJ interface -- removed some old manual reference counting kruft This commit was SVN r1830.
2004-08-02 04:24:22 +04:00
m->mca_component_name);
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
/* This component has already been successfully opened. So now query
it. */
Fix some stylistic problems and code errors, found during code review with Anju This commit was SVN r1656.
2004-07-13 08:43:16 +04:00
if (1 == m->mca_type_major_version &&
Some more changes to update to coll v1.1.0 that were missed yesterday. This actually exposed a very, very long-standing bug where part of the coll base was incorrectly checking the coll API version against the MCA API version. When coll went to v1.1 (yesterday) and was no longer the same as the MCA v1.0, the test started failing. This commit fixes to check for v1.1 everywhere in the coll base, and to ensure to check coll framework/API version numbers against coll framework/API version numbers (vs. against the MCA API version number). This commit was SVN r16373.
2007-10-07 16:20:22 +04:00
1 == m->mca_type_minor_version &&
Fix some stylistic problems and code errors, found during code review with Anju This commit was SVN r1656.
2004-07-13 08:43:16 +04:00
0 == m->mca_type_release_version) {
Update collectives selection logic to allow for multiple components to be used at nce (up to one unique collective module per collective function). Matches r15795:15921 of the tmp/bwb-coll-select branch This commit was SVN r15924. The following SVN revisions from the original message are invalid or inconsistent and therefore were not cross-referenced: r15795 r15921
2007-08-19 07:37:49 +04:00
ret = init_query_1_1_0(m, entry, enable_progress_threads,
Change the orientation of the thread level determination in ompi_mpi_init(): we no longer *query* the components to see what they can support -- instead, we *tell* the components what they need to support (if they can't support it, they should disqualify themselves from selection). This involved a bunch of things: - pass the configure-time-decided OMPI_ENABLE_PROGRESS_THREADS and OMPI_ENABLE_MPI_THREADS constants to each framework selection function - eliminate mca_base_init_select_components() - eliminate all "allow_multi_user_threads" and "have_hidden_threads" kinds of arguments and aggregation from various framework selection and component/module functions - correctly determine the max MPI thread level that we can support and limit the final MPI thread level as appropriate during ompi_mpi_init() As a side effect, while editing nearly every MPI component I also did the following: - found 2 places (gm and ib ptls) where ompi_set_using_threads() was erroneously being called (I think this is left over kruft from misunderstandings by the original authors). I removed these. This commit was SVN r5055.
2005-03-27 17:05:23 +04:00
enable_mpi_threads);
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
} else {
/* Unrecognized coll API version */
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 18:53:58 +04:00
opal_output_verbose(10, mca_coll_base_output,
First cut of the Show Help Subsystem (SHS) - see src/util/show_help.h for details (doxygen); main function call is ompi_show_help() - text message files are expected to be located in $pkgdatadir (usually $prefix/share/openmpi). Anyone can install a text file in $pkgdatadir with their message(s) in it and then have them displayed via ompi_show_help(). "pkgdata_DATA" is the keyword to use in Makefile.am's, for example (from src/mca/base/Makefile.am): pkgdata_DATA = help-mca-base.txt - added a few examples in the code base using ompi_show_help(), but not too many -- can convert more "show_help" comments in the code over time; no huge rush. :-) - no i18n-like support yet; waiting for advice and consensus from other developers This commit was SVN r2519.
2004-09-05 20:05:37 +04:00
"coll:find_available: unrecognized coll API version (%d.%d.%d, ignored)",
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
m->mca_type_major_version,
m->mca_type_minor_version,
m->mca_type_release_version);
return OMPI_ERROR;
}
/* Query done -- look at the return value to see what happened */
Fix some stylistic problems and code errors, found during code review with Anju This commit was SVN r1656.
2004-07-13 08:43:16 +04:00
if (OMPI_SUCCESS != ret) {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 18:53:58 +04:00
opal_output_verbose(10, mca_coll_base_output,
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
"coll:find_available: coll component %s is not available",
- massive change for module<-->component name fixes throughout the code base. - many (most) mca type names have "component" or "module" in them, as relevant, just to further distinguish the difference between component data/actions and module data/actions. All developers are encouraged to perpetuate this convention when you create types that are specific to a framework, component, or module - did very little to entire framework (just the basics to make it compile) because it's just about to be almost entirely replaced - ditto for io / romio - did not work on elan or ib components; have to commit and then convert those on a different machine with the right libraries and headers - renamed a bunch of *_module.c files to *_component.c and *module*c to *component*c (a few still remain, e.g., ptl/ib, ptl/elan, etc.) - modified autogen/configure/build process to match new filenames (e.g., output static-components.h instead of static-modules.h) - removed DOS-style cr/lf stuff in ns/ns.h - added newline to end of file src/util/numtostr.h - removed some redundant error checking in the top-level topo functions - added a few {} here and there where people "forgot" to put them in for 1 line blocks ;-) - removed a bunch of MPI_* types from mca header files (replaced with corresponding ompi_* types) - all the ptl components had version numbers in their structs; removed - converted a few more elements in the MCA base to use the OBJ interface -- removed some old manual reference counting kruft This commit was SVN r1830.
2004-08-02 04:24:22 +04:00
m->mca_component_name);
if (NULL != m->mca_close_component) {
m->mca_close_component();
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
}
} else {
Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. After much work by Jeff and myself, and quite a lot of discussion, it has become clear that we simply cannot resolve the infinite loops caused by RML-involved subsystems calling orte_output. The original rationale for the change to orte_output has also been reduced by shifting the output of XML-formatted vs human readable messages to an alternative approach. I have globally replaced the orte_output/ORTE_OUTPUT calls in the code base, as well as the corresponding .h file name. I have test compiled and run this on the various environments within my reach, so hopefully this will prove minimally disruptive. This commit was SVN r18619.
2008-06-09 18:53:58 +04:00
opal_output_verbose(10, mca_coll_base_output,
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
"coll:find_available: coll component %s is available",
- massive change for module<-->component name fixes throughout the code base. - many (most) mca type names have "component" or "module" in them, as relevant, just to further distinguish the difference between component data/actions and module data/actions. All developers are encouraged to perpetuate this convention when you create types that are specific to a framework, component, or module - did very little to entire framework (just the basics to make it compile) because it's just about to be almost entirely replaced - ditto for io / romio - did not work on elan or ib components; have to commit and then convert those on a different machine with the right libraries and headers - renamed a bunch of *_module.c files to *_component.c and *module*c to *component*c (a few still remain, e.g., ptl/ib, ptl/elan, etc.) - modified autogen/configure/build process to match new filenames (e.g., output static-components.h instead of static-modules.h) - removed DOS-style cr/lf stuff in ns/ns.h - added newline to end of file src/util/numtostr.h - removed some redundant error checking in the top-level topo functions - added a few {} here and there where people "forgot" to put them in for 1 line blocks ;-) - removed a bunch of MPI_* types from mca header files (replaced with corresponding ompi_* types) - all the ptl components had version numbers in their structs; removed - converted a few more elements in the MCA base to use the OBJ interface -- removed some old manual reference counting kruft This commit was SVN r1830.
2004-08-02 04:24:22 +04:00
m->mca_component_name);
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
}
/* All done */
return ret;
}
/*
* Query a specific component, coll v1.0.0
*/
Update collectives selection logic to allow for multiple components to be used at nce (up to one unique collective module per collective function). Matches r15795:15921 of the tmp/bwb-coll-select branch This commit was SVN r15924. The following SVN revisions from the original message are invalid or inconsistent and therefore were not cross-referenced: r15795 r15921
2007-08-19 07:37:49 +04:00
static int init_query_1_1_0(const mca_base_component_t *component,
Change the orientation of the thread level determination in ompi_mpi_init(): we no longer *query* the components to see what they can support -- instead, we *tell* the components what they need to support (if they can't support it, they should disqualify themselves from selection). This involved a bunch of things: - pass the configure-time-decided OMPI_ENABLE_PROGRESS_THREADS and OMPI_ENABLE_MPI_THREADS constants to each framework selection function - eliminate mca_base_init_select_components() - eliminate all "allow_multi_user_threads" and "have_hidden_threads" kinds of arguments and aggregation from various framework selection and component/module functions - correctly determine the max MPI thread level that we can support and limit the final MPI thread level as appropriate during ompi_mpi_init() As a side effect, while editing nearly every MPI component I also did the following: - found 2 places (gm and ib ptls) where ompi_set_using_threads() was erroneously being called (I think this is left over kruft from misunderstandings by the original authors). I removed these. This commit was SVN r5055.
2005-03-27 17:05:23 +04:00
mca_base_component_priority_list_item_t *entry,
bool enable_progress_threads,
bool enable_mpi_threads)
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
{
Update collectives selection logic to allow for multiple components to be used at nce (up to one unique collective module per collective function). Matches r15795:15921 of the tmp/bwb-coll-select branch This commit was SVN r15924. The following SVN revisions from the original message are invalid or inconsistent and therefore were not cross-referenced: r15795 r15921
2007-08-19 07:37:49 +04:00
mca_coll_base_component_1_1_0_t *coll =
(mca_coll_base_component_1_1_0_t *) component;
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
Change the orientation of the thread level determination in ompi_mpi_init(): we no longer *query* the components to see what they can support -- instead, we *tell* the components what they need to support (if they can't support it, they should disqualify themselves from selection). This involved a bunch of things: - pass the configure-time-decided OMPI_ENABLE_PROGRESS_THREADS and OMPI_ENABLE_MPI_THREADS constants to each framework selection function - eliminate mca_base_init_select_components() - eliminate all "allow_multi_user_threads" and "have_hidden_threads" kinds of arguments and aggregation from various framework selection and component/module functions - correctly determine the max MPI thread level that we can support and limit the final MPI thread level as appropriate during ompi_mpi_init() As a side effect, while editing nearly every MPI component I also did the following: - found 2 places (gm and ib ptls) where ompi_set_using_threads() was erroneously being called (I think this is left over kruft from misunderstandings by the original authors). I removed these. This commit was SVN r5055.
2005-03-27 17:05:23 +04:00
return coll->collm_init_query(enable_progress_threads,
enable_mpi_threads);
Lots of changes in this commit, mostly having to do with the first real commit of the collectives. MPI_SCAN and MPI_EXSCAN are still not implemented, but lots of other things are in the critical path and holding up other people, so it's ok to commit without them: - better checks for sizes in configure, and add defaults for fortran sizes if we don't have a fortran compiler - fix some logic that was accidentally broken for size checks for the file type offset_t - add some C equivalent types for fortran's complex and double complex (for use in internal reduction/op functions) - additionals and slight reorganization of ompi_mpi_init() ompi_mpi_finalize() - fully implement all top-level MPI collective calls, including all param checking for both intra- and inter-communicators (woof) - change the communicator_t type for stuff that we need in coll, and update all references throughout the code base to match - all kinds of updates to the coll framework base - next cut of the basic coll module -- has all intracommunicator collectives implemented except scan and exscan (see note above). All intercommunicator functions return ERR_NOT_IMPLEMENTED. - MPI_Op is a fixed implementation -- not component-ized yet. So there are generic C loops for all implementations. This commit was SVN r1491.
2004-06-29 04:02:25 +04:00
}
Копировать постоянную ссылку