2005-06-28 01:21:15 +04:00
|
|
|
/*
|
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.
|
2011-02-25 03:36:08 +03:00
|
|
|
* Copyright (c) 2004-2011 The University of Tennessee and The University
|
2005-11-05 22:57:48 +03:00
|
|
|
* of Tennessee Research Foundation. All rights
|
|
|
|
* reserved.
|
2015-06-24 06:59:57 +03:00
|
|
|
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
2005-06-28 01:21:15 +04:00
|
|
|
* University of Stuttgart. All rights reserved.
|
|
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
|
|
* All rights reserved.
|
|
|
|
* $COPYRIGHT$
|
2015-06-24 06:59:57 +03:00
|
|
|
*
|
2005-06-28 01:21:15 +04:00
|
|
|
* Additional copyrights may follow
|
2015-06-24 06:59:57 +03:00
|
|
|
*
|
2005-06-28 01:21:15 +04:00
|
|
|
* $HEADER$
|
|
|
|
*/
|
|
|
|
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
#include "opal_config.h"
|
2005-06-28 01:21:15 +04:00
|
|
|
|
|
|
|
|
2005-06-30 09:50:55 +04:00
|
|
|
#include "btl_template.h"
|
|
|
|
#include "btl_template_proc.h"
|
2005-06-28 01:21:15 +04:00
|
|
|
|
2005-06-30 09:50:55 +04:00
|
|
|
static void mca_btl_template_proc_construct(mca_btl_template_proc_t* proc);
|
|
|
|
static void mca_btl_template_proc_destruct(mca_btl_template_proc_t* proc);
|
2005-06-28 01:21:15 +04:00
|
|
|
|
2015-06-24 06:59:57 +03:00
|
|
|
OBJ_CLASS_INSTANCE(mca_btl_template_proc_t,
|
|
|
|
opal_list_item_t, mca_btl_template_proc_construct,
|
2005-06-30 09:50:55 +04:00
|
|
|
mca_btl_template_proc_destruct);
|
2005-06-28 01:21:15 +04:00
|
|
|
|
2009-01-05 17:14:38 +03:00
|
|
|
void mca_btl_template_proc_construct(mca_btl_template_proc_t* template_proc)
|
2005-06-28 01:21:15 +04:00
|
|
|
{
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
template_proc->proc_opal = 0;
|
2009-01-05 17:14:38 +03:00
|
|
|
template_proc->proc_addr_count = 0;
|
|
|
|
template_proc->proc_endpoints = 0;
|
|
|
|
template_proc->proc_endpoint_count = 0;
|
|
|
|
OBJ_CONSTRUCT(&template_proc->proc_lock, opal_mutex_t);
|
2005-06-28 01:21:15 +04:00
|
|
|
/* add to list of all proc instance */
|
2005-07-04 02:45:48 +04:00
|
|
|
OPAL_THREAD_LOCK(&mca_btl_template_component.template_lock);
|
2009-01-05 17:14:38 +03:00
|
|
|
opal_list_append(&mca_btl_template_component.template_procs, &template_proc->super);
|
2005-07-04 02:45:48 +04:00
|
|
|
OPAL_THREAD_UNLOCK(&mca_btl_template_component.template_lock);
|
2005-06-28 01:21:15 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Cleanup ib proc instance
|
|
|
|
*/
|
|
|
|
|
2009-01-05 17:14:38 +03:00
|
|
|
void mca_btl_template_proc_destruct(mca_btl_template_proc_t* template_proc)
|
2005-06-28 01:21:15 +04:00
|
|
|
{
|
|
|
|
/* remove from list of all proc instances */
|
2005-07-04 02:45:48 +04:00
|
|
|
OPAL_THREAD_LOCK(&mca_btl_template_component.template_lock);
|
2009-01-05 17:14:38 +03:00
|
|
|
opal_list_remove_item(&mca_btl_template_component.template_procs,
|
|
|
|
&template_proc->super);
|
2005-07-04 02:45:48 +04:00
|
|
|
OPAL_THREAD_UNLOCK(&mca_btl_template_component.template_lock);
|
2005-06-28 01:21:15 +04:00
|
|
|
|
|
|
|
/* release resources */
|
2009-01-05 17:14:38 +03:00
|
|
|
if(NULL != template_proc->proc_endpoints) {
|
|
|
|
free(template_proc->proc_endpoints);
|
2005-06-28 01:21:15 +04:00
|
|
|
}
|
2009-01-05 17:14:38 +03:00
|
|
|
OBJ_DESTRUCT(&template_proc->proc_lock);
|
2005-06-28 01:21:15 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Look for an existing TEMPLATE process instances based on the associated
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
* opal_proc_t instance.
|
2005-06-28 01:21:15 +04:00
|
|
|
*/
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
static mca_btl_template_proc_t* mca_btl_template_proc_lookup_opal(opal_proc_t* opal_proc)
|
2005-06-28 01:21:15 +04:00
|
|
|
{
|
2005-06-30 09:50:55 +04:00
|
|
|
mca_btl_template_proc_t* template_proc;
|
2005-06-28 01:21:15 +04:00
|
|
|
|
2005-07-04 02:45:48 +04:00
|
|
|
OPAL_THREAD_LOCK(&mca_btl_template_component.template_lock);
|
2005-06-28 01:21:15 +04:00
|
|
|
|
2005-06-30 09:50:55 +04:00
|
|
|
for(template_proc = (mca_btl_template_proc_t*)
|
2005-07-03 20:22:16 +04:00
|
|
|
opal_list_get_first(&mca_btl_template_component.template_procs);
|
2005-06-30 09:50:55 +04:00
|
|
|
template_proc != (mca_btl_template_proc_t*)
|
2005-07-03 20:22:16 +04:00
|
|
|
opal_list_get_end(&mca_btl_template_component.template_procs);
|
|
|
|
template_proc = (mca_btl_template_proc_t*)opal_list_get_next(template_proc)) {
|
2005-06-28 01:21:15 +04:00
|
|
|
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
if(template_proc->proc_opal == opal_proc) {
|
2005-07-04 02:45:48 +04:00
|
|
|
OPAL_THREAD_UNLOCK(&mca_btl_template_component.template_lock);
|
2005-06-28 01:21:15 +04:00
|
|
|
return template_proc;
|
|
|
|
}
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2005-07-04 02:45:48 +04:00
|
|
|
OPAL_THREAD_UNLOCK(&mca_btl_template_component.template_lock);
|
2005-06-28 01:21:15 +04:00
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Create a TEMPLATE process structure. There is a one-to-one correspondence
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
* between a opal_proc_t and a mca_btl_template_proc_t instance. We cache
|
2015-06-24 06:59:57 +03:00
|
|
|
* additional data (specifically the list of mca_btl_template_endpoint_t instances,
|
2005-06-28 01:21:15 +04:00
|
|
|
* and published addresses) associated w/ a given destination on this
|
|
|
|
* datastructure.
|
|
|
|
*/
|
|
|
|
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
mca_btl_template_proc_t* mca_btl_template_proc_create(opal_proc_t* opal_proc)
|
2005-06-28 01:21:15 +04:00
|
|
|
{
|
2005-06-30 09:50:55 +04:00
|
|
|
mca_btl_template_proc_t* module_proc = NULL;
|
2005-06-28 01:21:15 +04:00
|
|
|
|
|
|
|
/* Check if we have already created a TEMPLATE proc
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
* structure for this process */
|
|
|
|
module_proc = mca_btl_template_proc_lookup_opal(opal_proc);
|
2005-06-28 01:21:15 +04:00
|
|
|
|
|
|
|
if(module_proc != NULL) {
|
|
|
|
|
|
|
|
/* Gotcha! */
|
|
|
|
return module_proc;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Oops! First time, gotta create a new TEMPLATE proc
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
* out of the opal_proc ... */
|
2005-06-28 01:21:15 +04:00
|
|
|
|
2005-06-30 09:50:55 +04:00
|
|
|
module_proc = OBJ_NEW(mca_btl_template_proc_t);
|
2005-06-28 01:21:15 +04:00
|
|
|
|
|
|
|
/* Initialize number of peer */
|
|
|
|
module_proc->proc_endpoint_count = 0;
|
|
|
|
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
module_proc->proc_opal = opal_proc;
|
2005-06-28 01:21:15 +04:00
|
|
|
|
|
|
|
/* TEMPLATE module doesn't have addresses exported at
|
|
|
|
* initialization, so the addr_count is set to one. */
|
|
|
|
module_proc->proc_addr_count = 1;
|
|
|
|
|
|
|
|
/* XXX: Right now, there can be only 1 peer associated
|
2015-06-24 06:59:57 +03:00
|
|
|
* with a proc. Needs a little bit change in
|
2005-06-30 09:50:55 +04:00
|
|
|
* mca_btl_template_proc_t to allow on demand increasing of
|
2005-06-28 01:21:15 +04:00
|
|
|
* number of endpoints for this proc */
|
|
|
|
|
2005-06-30 09:50:55 +04:00
|
|
|
module_proc->proc_endpoints = (mca_btl_base_endpoint_t**)
|
|
|
|
malloc(module_proc->proc_addr_count * sizeof(mca_btl_base_endpoint_t*));
|
2005-06-28 01:21:15 +04:00
|
|
|
|
|
|
|
if(NULL == module_proc->proc_endpoints) {
|
|
|
|
OBJ_RELEASE(module_proc);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
return module_proc;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Note that this routine must be called with the lock on the process
|
2015-06-24 06:59:57 +03:00
|
|
|
* already held. Insert a btl instance into the proc array and assign
|
2005-06-28 01:21:15 +04:00
|
|
|
* it an address.
|
|
|
|
*/
|
2015-06-24 06:59:57 +03:00
|
|
|
int mca_btl_template_proc_insert(mca_btl_template_proc_t* module_proc,
|
2005-06-30 09:50:55 +04:00
|
|
|
mca_btl_base_endpoint_t* module_endpoint)
|
2005-06-28 01:21:15 +04:00
|
|
|
{
|
|
|
|
/* insert into endpoint array */
|
|
|
|
module_endpoint->endpoint_proc = module_proc;
|
|
|
|
module_proc->proc_endpoints[module_proc->proc_endpoint_count++] = module_endpoint;
|
|
|
|
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 04:47:28 +04:00
|
|
|
return OPAL_SUCCESS;
|
2005-06-28 01:21:15 +04:00
|
|
|
}
|