1
1
openmpi/opal/mca/btl/sm/btl_sm_frag.h

116 строки
4.0 KiB
C
Исходник Обычный вид История

/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
/*
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2013 The University of Tennessee and The University
* of Tennessee Research Foundation. All rights
* reserved.
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
* University of Stuttgart. All rights reserved.
* Copyright (c) 2004-2005 The Regents of the University of California.
* All rights reserved.
* Copyright (c) 2008 Sun Microsystems, Inc. All rights reserved.
* Copyright (c) 2009 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2014-2015 Los Alamos National Security, LLC. All rights
* reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
/**
* @file
*/
#ifndef MCA_BTL_SM_SEND_FRAG_H
#define MCA_BTL_SM_SEND_FRAG_H
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"
#include "btl_sm.h"
#define MCA_BTL_SM_FRAG_TYPE_MASK ((uintptr_t)0x3)
#define MCA_BTL_SM_FRAG_SEND ((uintptr_t)0x0)
#define MCA_BTL_SM_FRAG_ACK ((uintptr_t)0x1)
#define MCA_BTL_SM_FRAG_PUT ((uintptr_t)0x2)
#define MCA_BTL_SM_FRAG_GET ((uintptr_t)0x3)
#define MCA_BTL_SM_FRAG_STATUS_MASK ((uintptr_t)0x4)
struct mca_btl_sm_frag_t;
struct mca_btl_sm_hdr_t {
struct mca_btl_sm_frag_t *frag;
size_t len;
int my_smp_rank;
mca_btl_base_tag_t tag;
};
typedef struct mca_btl_sm_hdr_t mca_btl_sm_hdr_t;
struct mca_btl_sm_segment_t {
mca_btl_base_segment_t base;
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 OPAL_BTL_SM_HAVE_KNEM || OPAL_BTL_SM_HAVE_CMA
uint64_t key;
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
#endif /* OPAL_BTL_SM_HAVE_KNEM || OPAL_BTL_SM_HAVE_CMA */
};
typedef struct mca_btl_sm_segment_t mca_btl_sm_segment_t;
/**
* shared memory send fragment derived type.
*/
struct mca_btl_sm_frag_t {
mca_btl_base_descriptor_t base;
mca_btl_sm_segment_t segment;
struct mca_btl_base_endpoint_t *endpoint;
size_t size;
/* pointer written to the FIFO, this is the base of the shared memory region */
mca_btl_sm_hdr_t *hdr;
opal_free_list_t* my_list;
#if OPAL_BTL_SM_HAVE_KNEM
/* rdma callback data. required for async get */
struct {
mca_btl_base_rdma_completion_fn_t func;
void *local_address;
struct mca_btl_base_registration_handle_t *local_handle;
void *context;
void *data;
} cb;
#endif
};
typedef struct mca_btl_sm_frag_t mca_btl_sm_frag_t;
typedef struct mca_btl_sm_frag_t mca_btl_sm_frag1_t;
typedef struct mca_btl_sm_frag_t mca_btl_sm_frag2_t;
typedef struct mca_btl_sm_frag_t mca_btl_sm_user_t;
OBJ_CLASS_DECLARATION(mca_btl_sm_frag_t);
OBJ_CLASS_DECLARATION(mca_btl_sm_frag1_t);
OBJ_CLASS_DECLARATION(mca_btl_sm_frag2_t);
OBJ_CLASS_DECLARATION(mca_btl_sm_user_t);
#define MCA_BTL_SM_FRAG_ALLOC_EAGER(frag) \
{ \
frag = (mca_btl_sm_frag_t*) \
opal_free_list_get (&mca_btl_sm_component.sm_frags_eager); \
}
#define MCA_BTL_SM_FRAG_ALLOC_MAX(frag) \
{ \
frag = (mca_btl_sm_frag_t*) \
opal_free_list_get (&mca_btl_sm_component.sm_frags_max); \
}
#define MCA_BTL_SM_FRAG_ALLOC_USER(frag) \
{ \
frag = (mca_btl_sm_frag_t*) \
opal_free_list_get (&mca_btl_sm_component.sm_frags_user); \
}
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
#define MCA_BTL_SM_FRAG_RETURN(frag) \
{ \
opal_free_list_return (frag->my_list, (opal_free_list_item_t*)(frag)); \
}
#endif