ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
5c7059c955
openmpi/ompi/mca/topo/base/base.h

141 строка
5.4 KiB
C
Исходник Обычный вид История

The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
/*
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
*
The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
* $HEADER$
*/
#ifndef MCA_TOPO_BASE_H
#define MCA_TOPO_BASE_H
First pass of lam -> ompi conversion This commit was SVN r1191.
2004-06-07 19:33:53 +04:00
#include "ompi_config.h"
The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
Changing some stuff in topo module ... This commit was SVN r1043.
2004-04-17 00:54:48 +04:00
#include "mpi.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"
Updating header file names after the great directory reorganization. This commit was SVN r877.
2004-03-17 21:45:16 +03:00
#include "mca/topo/topo.h"
Oops, this commit went to the wrong branch ... This commit was SVN r1788.
2004-07-21 02:32:45 +04:00
#include "proc/proc.h"
these are the topo/base functions which are always present. topo module authors need not implement these functions at all if they so choose. this is teh first version. i require that lam_comm_ functions be implemented so that i can test some of them out. obviously, not all of them depend on lam_comm or lam_group functions This commit was SVN r839.
2004-03-08 09:48:24 +03:00
The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
/*
* All stuff goes in here
*/
#if defined(c_plusplus) || defined(__cplusplus)
extern "C" {
#endif
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_open(void);
Oops, this commit went to the wrong branch ... This commit was SVN r1788.
2004-07-21 02:32:45 +04:00
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_close(void);
Oops, this commit went to the wrong branch ... This commit was SVN r1788.
2004-07-21 02:32:45 +04:00
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_comm_select(struct ompi_communicator_t *comm,
- 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
struct mca_base_component_t *preferred);
Oops, this commit went to the wrong branch ... This commit was SVN r1788.
2004-07-21 02:32:45 +04:00
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_comm_unselect(struct ompi_communicator_t *comm);
Oops, this commit went to the wrong branch ... This commit was SVN r1788.
2004-07-21 02:32:45 +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
OMPI_DECLSPEC int mca_topo_base_find_available (bool enable_progress_threads,
bool enable_mpi_threads);
The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_init_comm (struct ompi_communicator_t *comm);
Oops, this commit went to the wrong branch ... This commit was SVN r1788.
2004-07-21 02:32:45 +04:00
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_get_param (struct ompi_communicator_t *comm, int keyval);
The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
/*
- 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
* All the glue functions which we will provide to the users by
* default. The component authors need to only write back-end
* functions for graph_map() and cart_map() for their topology
* components. But they can implement these glue functions if
* they want.
The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
*/
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_cart_coords (struct ompi_communicator_t *comm,
- 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
int rank,
int maxdims,
int *coords);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_cart_create (mca_topo_base_comm_t *topo_data,
- 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
int *proc_count,
ompi_proc_t **proc_pointers,
int *new_rank,
int ndims,
int *dims,
int *periods,
bool reorder);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_cartdim_get (struct ompi_communicator_t *comm,
- 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
int *ndims);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_cart_get (struct ompi_communicator_t *comm,
- 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
int maxdims,
int *dims,
int *periods,
int *coords);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_cart_rank (struct ompi_communicator_t *comm,
- 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
int *coords,
int *rank);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_cart_shift (struct ompi_communicator_t *comm,
- 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
int direction,
int disp,
int *rank_source,
int *rank_dest);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_cart_sub (struct ompi_communicator_t *comm,
- 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
int *remain_dims,
struct ompi_communicator_t **new_comm);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_graph_create (mca_topo_base_comm_t *topo_data,
- 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
int *proc_count,
ompi_proc_t **proc_pointers,
int *new_rank,
int nnodes,
int *index,
int *edges,
bool reorder);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_graphdims_get (struct ompi_communicator_t *comm,
- 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
int *nodes,
int *nedges);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_graph_get (struct ompi_communicator_t *comm,
- 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
int maxindex,
int maxedges,
int *index,
int *edges);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_graph_neighbors (struct ompi_communicator_t *comm,
- 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
int rank,
int maxneighbors,
int *neighbors);
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC int mca_topo_base_graph_neighbors_count (struct ompi_communicator_t *comm,
- 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
int rank,
int *nneighbors);
The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
/*
* Globals
*/
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC extern int mca_topo_base_output;
OMPI_DECLSPEC extern int mca_topo_base_param;
Oops, this commit went to the wrong branch ... This commit was SVN r1788.
2004-07-21 02:32:45 +04:00
* rename ompi_list to opal_list This commit was SVN r6322.
2005-07-03 20:22:16 +04:00
OMPI_DECLSPEC extern opal_list_t mca_topo_base_components_available;
OMPI_DECLSPEC extern opal_list_t mca_topo_base_components_opened;
Oops, this commit went to the wrong branch ... This commit was SVN r1788.
2004-07-21 02:32:45 +04:00
this is the big windows commit. there are more things which have gone into this than i can remember. but basically, we are looking for 1. header file and source file protections using #ifdef WIN32 2. new files and directories to support windows functionality 3. appropritate linkage symbols added (OMPI_DECLSPEC) for windows 4. some functions are unimplemented on the windows side. this is mostly because there might not be need to implement it in windows land. eg., forking a daemon off 5. Introduced locking mechanisms for windows This commit was SVN r3286.
2004-10-22 20:06:05 +04:00
OMPI_DECLSPEC extern bool mca_topo_base_components_opened_valid;
OMPI_DECLSPEC extern bool mca_topo_base_components_available_valid;
The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
committing the header file fixes for protection against C++ name mangling. This is a hge commit. Please make sure that your files are protected right. There is some redundan protection in that the protection has been added right at teh beginning and at teh end ion some cases even thught typedefs are not requred to be protected. But this was done in order to have teh minimal change to the code base This commit was SVN r3246.
2004-10-21 02:31:03 +04:00
#if defined(c_plusplus) || defined(__cplusplus)
}
#endif
The 'base' functions for topology. Topology module authors need not bother to write these fucntions in their modules. They can leave the function pointers as NULL. This commit was SVN r823.
2004-03-07 01:40:26 +03:00
#endif /* MCA_BASE_TOPO_H */
Копировать постоянную ссылку