552c9ca5a0
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.
104 строки
3.1 KiB
C
104 строки
3.1 KiB
C
/*
|
|
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2006 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) 2006 Voltaire. All rights reserved.
|
|
* Copyright (c) 2012 NVIDIA Corporation. All rights reserved.
|
|
*
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/**
|
|
* @file
|
|
*/
|
|
#ifndef MCA_MPOOL_GPUSM_H
|
|
#define MCA_MPOOL_GPUSM_H
|
|
|
|
#include "opal_config.h"
|
|
#include "opal/class/opal_list.h"
|
|
#include "opal/class/ompi_free_list.h"
|
|
#include "opal/mca/mpool/mpool.h"
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
#define MEMHANDLE_SIZE 8
|
|
#define EVTHANDLE_SIZE 8
|
|
struct mca_mpool_gpusm_registration_t {
|
|
mca_mpool_base_registration_t base;
|
|
uint64_t memHandle[MEMHANDLE_SIZE];
|
|
uint64_t evtHandle[EVTHANDLE_SIZE];
|
|
uint64_t event;
|
|
};
|
|
typedef struct mca_mpool_gpusm_registration_t mca_mpool_gpusm_registration_t;
|
|
OPAL_DECLSPEC OBJ_CLASS_DECLARATION(mca_mpool_gpusm_registration_t);
|
|
|
|
struct mca_mpool_gpusm_component_t {
|
|
mca_mpool_base_component_t super;
|
|
};
|
|
typedef struct mca_mpool_gpusm_component_t mca_mpool_gpusm_component_t;
|
|
|
|
OPAL_DECLSPEC extern mca_mpool_gpusm_component_t mca_mpool_gpusm_component;
|
|
|
|
struct mca_mpool_base_resources_t {
|
|
void *reg_data;
|
|
size_t sizeof_reg;
|
|
int (*register_mem)(void *base, size_t size, mca_mpool_base_registration_t *newreg,
|
|
mca_mpool_base_registration_t *hdrreg);
|
|
int (*deregister_mem)(void *reg_data, mca_mpool_base_registration_t *reg);
|
|
};
|
|
typedef struct mca_mpool_base_resources_t mca_mpool_base_resources_t;
|
|
|
|
struct mca_mpool_gpusm_module_t {
|
|
mca_mpool_base_module_t super;
|
|
struct mca_mpool_base_resources_t resources;
|
|
ompi_free_list_t reg_list;
|
|
}; typedef struct mca_mpool_gpusm_module_t mca_mpool_gpusm_module_t;
|
|
|
|
/*
|
|
* Initializes the mpool module.
|
|
*/
|
|
void mca_mpool_gpusm_module_init(mca_mpool_gpusm_module_t *mpool);
|
|
|
|
/**
|
|
* register block of memory
|
|
*/
|
|
int mca_mpool_gpusm_register(mca_mpool_base_module_t* mpool, void *addr,
|
|
size_t size, uint32_t flags, mca_mpool_base_registration_t **reg);
|
|
|
|
/**
|
|
* deregister memory
|
|
*/
|
|
int mca_mpool_gpusm_deregister(mca_mpool_base_module_t *mpool,
|
|
mca_mpool_base_registration_t *reg);
|
|
|
|
/**
|
|
* find registration for a given block of memory
|
|
*/
|
|
int mca_mpool_gpusm_find(struct mca_mpool_base_module_t* mpool, void* addr,
|
|
size_t size, mca_mpool_base_registration_t **reg);
|
|
|
|
/**
|
|
* finalize mpool
|
|
*/
|
|
void mca_mpool_gpusm_finalize(struct mca_mpool_base_module_t *mpool);
|
|
|
|
/**
|
|
* Fault Tolerance Event Notification Function
|
|
* @param state Checkpoint Stae
|
|
* @return OPAL_SUCCESS or failure status
|
|
*/
|
|
int mca_mpool_gpusm_ft_event(int state);
|
|
|
|
END_C_DECLS
|
|
#endif
|