1
1
openmpi/opal/mca/btl/smcuda/btl_smcuda_frag.h

123 строки
4.4 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) 2012 NVIDIA Corporation. All rights reserved.
* Copyright (c) 2015 Los Alamos National Security, LLC. All rights
* reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
/**
* @file
*/
#ifndef MCA_BTL_SMCUDA_SEND_FRAG_H
#define MCA_BTL_SMCUDA_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 00:47:28 +00:00
#include "opal_config.h"
#include "btl_smcuda.h"
#if OPAL_CUDA_SUPPORT
#include "opal/mca/common/cuda/common_cuda.h"
#endif
#define MCA_BTL_SMCUDA_FRAG_TYPE_MASK ((uintptr_t)0x3)
#define MCA_BTL_SMCUDA_FRAG_SEND ((uintptr_t)0x0)
#define MCA_BTL_SMCUDA_FRAG_ACK ((uintptr_t)0x1)
#define MCA_BTL_SMCUDA_FRAG_PUT ((uintptr_t)0x2)
#define MCA_BTL_SMCUDA_FRAG_GET ((uintptr_t)0x3)
#define MCA_BTL_SMCUDA_FRAG_STATUS_MASK ((uintptr_t)0x4)
struct mca_btl_smcuda_frag_t;
struct mca_btl_smcuda_hdr_t {
struct mca_btl_smcuda_frag_t *frag;
size_t len;
int my_smp_rank;
mca_btl_base_tag_t tag;
};
typedef struct mca_btl_smcuda_hdr_t mca_btl_smcuda_hdr_t;
#if OPAL_CUDA_SUPPORT
struct mca_btl_base_registration_handle_t {
opal: rework mpool and rcache frameworks This commit rewrites both the mpool and rcache frameworks. Summary of changes: - Before this change a significant portion of the rcache functionality lived in mpool components. This meant that it was impossible to add a new memory pool to use with rdma networks (ugni, openib, etc) without duplicating the functionality of an existing mpool component. All the registration functionality has been removed from the mpool and placed in the rcache framework. - All registration cache mpools components (udreg, grdma, gpusm, rgpusm) have been changed to rcache components. rcaches are allocated and released in the same way mpool components were. - It is now valid to pass NULL as the resources argument when creating an rcache. At this time the gpusm and rgpusm components support this. All other rcache components require non-NULL resources. - A new mpool component has been added: hugepage. This component supports huge page allocations on linux. - Memory pools are now allocated using "hints". Each mpool component is queried with the hints and returns a priority. The current hints supported are NULL (uses posix_memalign/malloc), page_size=x (huge page mpool), and mpool=x. - The sm mpool has been moved to common/sm. This reflects that the sm mpool is specialized and not meant for any general allocations. This mpool may be moved back into the mpool framework if there is any objection. - The opal_free_list_init arguments have been updated. The unused0 argument is not used to pass in the registration cache module. The mpool registration flags are now rcache registration flags. - All components have been updated to make use of the new framework interfaces. As this commit makes significant changes to both the mpool and rcache frameworks both versions have been bumped to 3.0.0. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-11-02 12:07:08 -07:00
mca_rcache_common_cuda_reg_data_t reg_data;
};
#endif
struct mca_btl_smcuda_segment_t {
mca_btl_base_segment_t base;
#if OPAL_CUDA_SUPPORT
uint8_t key[128]; /* 64 bytes for CUDA mem handle, 64 bytes for CUDA event handle */
/** Address of the entire memory handle */
2015-06-23 20:59:57 -07:00
opal_ptr_t memh_seg_addr;
/** Length in bytes of entire memory handle */
2015-06-23 20:59:57 -07:00
uint32_t memh_seg_len;
#endif /* OPAL_CUDA_SUPPORT */
};
typedef struct mca_btl_smcuda_segment_t mca_btl_smcuda_segment_t;
/**
* shared memory send fragment derived type.
*/
struct mca_btl_smcuda_frag_t {
mca_btl_base_descriptor_t base;
mca_btl_base_segment_t segment;
struct mca_btl_base_endpoint_t *endpoint;
#if OPAL_CUDA_SUPPORT
opal: rework mpool and rcache frameworks This commit rewrites both the mpool and rcache frameworks. Summary of changes: - Before this change a significant portion of the rcache functionality lived in mpool components. This meant that it was impossible to add a new memory pool to use with rdma networks (ugni, openib, etc) without duplicating the functionality of an existing mpool component. All the registration functionality has been removed from the mpool and placed in the rcache framework. - All registration cache mpools components (udreg, grdma, gpusm, rgpusm) have been changed to rcache components. rcaches are allocated and released in the same way mpool components were. - It is now valid to pass NULL as the resources argument when creating an rcache. At this time the gpusm and rgpusm components support this. All other rcache components require non-NULL resources. - A new mpool component has been added: hugepage. This component supports huge page allocations on linux. - Memory pools are now allocated using "hints". Each mpool component is queried with the hints and returns a priority. The current hints supported are NULL (uses posix_memalign/malloc), page_size=x (huge page mpool), and mpool=x. - The sm mpool has been moved to common/sm. This reflects that the sm mpool is specialized and not meant for any general allocations. This mpool may be moved back into the mpool framework if there is any objection. - The opal_free_list_init arguments have been updated. The unused0 argument is not used to pass in the registration cache module. The mpool registration flags are now rcache registration flags. - All components have been updated to make use of the new framework interfaces. As this commit makes significant changes to both the mpool and rcache frameworks both versions have been bumped to 3.0.0. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-11-02 12:07:08 -07:00
struct mca_rcache_base_registration_t *registration;
struct mca_btl_base_registration_handle_t *local_handle;
#endif /* OPAL_CUDA_SUPPORT */
size_t size;
/* pointer written to the FIFO, this is the base of the shared memory region */
mca_btl_smcuda_hdr_t *hdr;
opal_free_list_t* my_list;
};
typedef struct mca_btl_smcuda_frag_t mca_btl_smcuda_frag_t;
typedef struct mca_btl_smcuda_frag_t mca_btl_smcuda_frag1_t;
typedef struct mca_btl_smcuda_frag_t mca_btl_smcuda_frag2_t;
typedef struct mca_btl_smcuda_frag_t mca_btl_smcuda_user_t;
OBJ_CLASS_DECLARATION(mca_btl_smcuda_frag_t);
OBJ_CLASS_DECLARATION(mca_btl_smcuda_frag1_t);
OBJ_CLASS_DECLARATION(mca_btl_smcuda_frag2_t);
OBJ_CLASS_DECLARATION(mca_btl_smcuda_user_t);
#define MCA_BTL_SMCUDA_FRAG_ALLOC_EAGER(frag) \
{ \
frag = (mca_btl_smcuda_frag_t *) \
opal_free_list_get (&mca_btl_smcuda_component.sm_frags_eager); \
}
#define MCA_BTL_SMCUDA_FRAG_ALLOC_MAX(frag) \
{ \
frag = (mca_btl_smcuda_frag_t *) \
opal_free_list_get (&mca_btl_smcuda_component.sm_frags_max); \
}
#define MCA_BTL_SMCUDA_FRAG_ALLOC_USER(frag) \
{ \
frag = (mca_btl_smcuda_frag_t *) \
opal_free_list_get (&mca_btl_smcuda_component.sm_frags_user); \
}
#define MCA_BTL_SMCUDA_FRAG_RETURN(frag) \
{ \
opal_free_list_return (frag->my_list, (opal_free_list_item_t*)(frag)); \
}
#endif