1
1
openmpi/ompi/mca/btl/gm/btl_gm.h

378 строки
13 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2009 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) 2007 Cisco Systems, Inc. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
/**
* @file
*/
#ifndef MCA_BTL_GM_H
#define MCA_BTL_GM_H
#include "ompi_config.h"
#include <sys/types.h>
#include <string.h>
#include <gm.h>
/* Open MPI includes */
#include "opal/event/event.h"
#include "ompi/class/ompi_free_list.h"
#include "ompi/mca/btl/btl.h"
#include "ompi/mca/btl/base/base.h"
#include "ompi/mca/mpool/mpool.h"
#include "ompi/mca/btl/btl.h"
#include "btl_gm_endpoint.h"
- Replace combinations of #if defined (c_plusplus) defined (__cplusplus) followed by extern "C" { and the closing counterpart by BEGIN_C_DECLS and END_C_DECLS. Notable exceptions are: - opal/include/opal_config_bottom.h: This is our generated code, that itself defines BEGIN_C_DECL and END_C_DECL - ompi/mpi/cxx/mpicxx.h: Here we do not include opal_config_bottom.h: - Belongs to external code: opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.c opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.h - opal/include/opal/prefetch.h: Has C++ specific macros that are protected: - Had #if ... } #endif _and_ END_C_DECLS (aka end up with 2x END_C_DECLS) ompi/mca/btl/openib/btl_openib.h - opal/event/event.h has #ifdef __cplusplus as BEGIN_C_DECLS... - opal/win32/ompi_process.h: had extern "C"\n {... opal/win32/ompi_process.h: dito - ompi/mca/btl/pcie/btl_pcie_lex.l: needed to add *_C_DECLS ompi/mpi/f90/test/align_c.c: dito - ompi/debuggers/msgq_interface.h: used #ifdef __cplusplus - ompi/mpi/f90/xml/common-C.xsl: Amend Tested on linux using --with-openib and --with-mx The following do not contain either opal_config.h, orte_config.h or ompi_config.h (but possibly other header files, that include one of the above): ompi/mca/bml/r2/bml_r2_ft.h ompi/mca/btl/gm/btl_gm_endpoint.h ompi/mca/btl/gm/btl_gm_proc.h ompi/mca/btl/mx/btl_mx_endpoint.h ompi/mca/btl/ofud/btl_ofud_endpoint.h ompi/mca/btl/ofud/btl_ofud_frag.h ompi/mca/btl/ofud/btl_ofud_proc.h ompi/mca/btl/openib/btl_openib_mca.h ompi/mca/btl/portals/btl_portals_endpoint.h ompi/mca/btl/portals/btl_portals_frag.h ompi/mca/btl/sctp/btl_sctp_endpoint.h ompi/mca/btl/sctp/btl_sctp_proc.h ompi/mca/btl/tcp/btl_tcp_endpoint.h ompi/mca/btl/tcp/btl_tcp_ft.h ompi/mca/btl/tcp/btl_tcp_proc.h ompi/mca/btl/template/btl_template_endpoint.h ompi/mca/btl/template/btl_template_proc.h ompi/mca/btl/udapl/btl_udapl_eager_rdma.h ompi/mca/btl/udapl/btl_udapl_endpoint.h ompi/mca/btl/udapl/btl_udapl_mca.h ompi/mca/btl/udapl/btl_udapl_proc.h ompi/mca/mtl/mx/mtl_mx_endpoint.h ompi/mca/mtl/mx/mtl_mx.h ompi/mca/mtl/psm/mtl_psm_endpoint.h ompi/mca/mtl/psm/mtl_psm.h ompi/mca/pml/cm/pml_cm_component.h ompi/mca/pml/csum/pml_csum_comm.h ompi/mca/pml/dr/pml_dr_comm.h ompi/mca/pml/dr/pml_dr_component.h ompi/mca/pml/dr/pml_dr_endpoint.h ompi/mca/pml/dr/pml_dr_recvfrag.h ompi/mca/pml/example/pml_example.h ompi/mca/pml/ob1/pml_ob1_comm.h ompi/mca/pml/ob1/pml_ob1_component.h ompi/mca/pml/ob1/pml_ob1_endpoint.h ompi/mca/pml/ob1/pml_ob1_rdmafrag.h ompi/mca/pml/ob1/pml_ob1_recvfrag.h ompi/mca/pml/v/pml_v_output.h opal/include/opal/prefetch.h opal/mca/timer/aix/timer_aix.h opal/util/qsort.h test/support/components.h This commit was SVN r21855. The following SVN revision numbers were found above: r2 --> open-mpi/ompi@58fdc188553052bc2e893ba28fb28fddbe78435a
2009-08-20 11:42:18 +00:00
BEGIN_C_DECLS
2005-07-07 16:56:58 +00:00
#define GM_BUFFER_SIZE 7
#define GM_BUFFER_LENGTH gm_max_length_for_size(GM_BUFFER_SIZE)
/**
2005-07-07 16:56:58 +00:00
* Myrinet (GM) BTL component.
*/
struct mca_btl_gm_component_t {
mca_btl_base_component_2_0_0_t super; /**< base BTL component */
size_t gm_num_btls; /**< number of hcas available to the GM component */
size_t gm_max_btls; /**< maximum number of supported hcas */
struct mca_btl_gm_module_t **gm_btls; /**< array of available BTL modules */
size_t gm_max_ports; /**< maximum number of ports per board */
size_t gm_max_boards; /**< maximum number of boards */
size_t gm_eager_frag_size;
size_t gm_max_frag_size;
char* gm_port_name;
int32_t gm_num_repost;
int32_t gm_num_high_priority; /**< number of receive descriptors at high priority */
int gm_debug; /**< turn on debug output */
int gm_free_list_num; /**< initial size of free lists */
int gm_free_list_max; /**< maximum size of free lists */
int gm_free_list_inc; /**< number of elements to alloc when growing free lists */
opal_list_t gm_procs; /**< list of gm proc structures */
opal_mutex_t gm_lock; /**< lock for accessing module state */
char* gm_mpool_name; /**< name of memory pool */
};
typedef struct mca_btl_gm_component_t mca_btl_gm_component_t;
OMPI_MODULE_DECLSPEC extern mca_btl_gm_component_t mca_btl_gm_component;
/**
* BTL Module Interface
*/
struct mca_btl_gm_module_t {
mca_btl_base_module_t super; /**< base BTL interface */
/* local port handle/address */
2005-07-07 16:56:58 +00:00
struct gm_port *port;
mca_btl_gm_addr_t gm_addr;
/* free list of fragment descriptors */
ompi_free_list_t gm_frag_eager;
ompi_free_list_t gm_frag_max;
ompi_free_list_t gm_frag_user;
/* number of send/recv tokens */
int32_t gm_num_send_tokens;
int32_t gm_max_send_tokens;
int32_t gm_num_recv_tokens;
int32_t gm_max_recv_tokens;
int32_t gm_num_repost;
/* lock for accessing module state */
opal_list_t gm_pending; /**< list of pending send descriptors */
opal_list_t gm_repost; /**< list of pending fragments */
#if OPAL_ENABLE_PROGRESS_THREADS
opal_thread_t gm_thread;
bool gm_progress;
#endif
mca_btl_base_module_error_cb_fn_t error_cb;
};
typedef struct mca_btl_gm_module_t mca_btl_gm_module_t;
extern mca_btl_gm_module_t mca_btl_gm_module;
/**
* Register GM component parameters with the MCA framework
*/
extern int mca_btl_gm_component_open(void);
/**
* Any final cleanup before being unloaded.
*/
extern int mca_btl_gm_component_close(void);
/**
* GM component initialization.
*
* @param num_btl_modules (OUT) Number of BTLs returned in BTL array.
* @param allow_multi_user_threads (OUT) Flag indicating wether BTL supports user threads (TRUE)
* @param have_hidden_threads (OUT) Flag indicating wether BTL uses threads (TRUE)
*/
extern mca_btl_base_module_t** mca_btl_gm_component_init(
int *num_btl_modules,
bool allow_multi_user_threads,
bool have_hidden_threads
);
/**
* GM component progress.
*/
extern int mca_btl_gm_component_progress(void);
/**
* Cleanup any resources held by the BTL.
*
* @param btl BTL instance.
* @return OMPI_SUCCESS or error status on failure.
*/
extern int mca_btl_gm_finalize(
struct mca_btl_base_module_t* btl
);
/**
* PML->BTL notification of change in the process list.
*
* @param btl (IN)
* @param nprocs (IN) Number of processes
* @param procs (IN) Set of processes
* @param peers (OUT) Set of (optional) peer addressing info.
* @param peers (IN/OUT) Set of processes that are reachable via this BTL.
* @return OMPI_SUCCESS or error status on failure.
*
*/
extern int mca_btl_gm_add_procs(
struct mca_btl_base_module_t* btl,
size_t nprocs,
struct ompi_proc_t **procs,
struct mca_btl_base_endpoint_t** peers,
opal_bitmap_t* reachable
);
/**
* PML->BTL notification of change in the process list.
*
* @param btl (IN) BTL instance
* @param nproc (IN) Number of processes.
* @param procs (IN) Set of processes.
* @param peers (IN) Set of peer data structures.
* @return Status indicating if cleanup was successful
*
*/
extern int mca_btl_gm_del_procs(
struct mca_btl_base_module_t* btl,
size_t nprocs,
struct ompi_proc_t **procs,
struct mca_btl_base_endpoint_t** peers
);
/**
* Initiate an asynchronous send.
*
* @param btl (IN) BTL module
* @param endpoint (IN) BTL addressing information
* @param descriptor (IN) Description of the data to be transfered
* @param tag (IN) The tag value used to notify the peer.
*/
extern int mca_btl_gm_send(
struct mca_btl_base_module_t* btl,
struct mca_btl_base_endpoint_t* btl_peer,
struct mca_btl_base_descriptor_t* descriptor,
mca_btl_base_tag_t tag
);
/**
* Initiate an asynchronous put.
*
* @param btl (IN) BTL module
* @param endpoint (IN) BTL addressing information
* @param descriptor (IN) Description of the data to be transferred
*/
extern int mca_btl_gm_put(
struct mca_btl_base_module_t* btl,
struct mca_btl_base_endpoint_t* btl_peer,
struct mca_btl_base_descriptor_t* decriptor
);
/**
* Initiate an asynchronous get.
*
* @param btl (IN) BTL module
* @param endpoint (IN) BTL addressing information
* @param descriptor (IN) Description of the data to be transferred
*/
extern int mca_btl_gm_get(
struct mca_btl_base_module_t* btl,
struct mca_btl_base_endpoint_t* btl_peer,
struct mca_btl_base_descriptor_t* decriptor
);
/**
* Register a callback function that is called on error.
*
* @param btl (IN) BTL module
* @return Status indicating if registration was successful
*
*/
extern int mca_btl_gm_register_error_cb(
struct mca_btl_base_module_t* btl,
mca_btl_base_module_error_cb_fn_t cbfunc);
/**
* Allocate a descriptor with a segment of the requested size.
* Note that the BTL layer may choose to return a smaller size
* if it cannot support the request.
*
* @param btl (IN) BTL module
* @param size (IN) Request segment size.
*/
extern mca_btl_base_descriptor_t* mca_btl_gm_alloc(
struct mca_btl_base_module_t* btl,
struct mca_btl_base_endpoint_t* endpoint,
uint8_t order,
size_t size,
uint32_t flags);
/**
* Return a segment allocated by this BTL.
*
* @param btl (IN) BTL module
* @param descriptor (IN) Allocated descriptor.
*/
extern int mca_btl_gm_free(
struct mca_btl_base_module_t* btl,
mca_btl_base_descriptor_t* des);
/**
* Prepare a descriptor for send/rdma using the supplied
* convertor. If the convertor references data that is contigous,
* the descriptor may simply point to the user buffer. Otherwise,
* this routine is responsible for allocating buffer space and
* packing if required.
*
* @param btl (IN) BTL module
* @param endpoint (IN) BTL peer addressing
* @param convertor (IN) Data type convertor
* @param reserve (IN) Additional bytes requested by upper layer to precede user data
* @param size (IN/OUT) Number of bytes to prepare (IN), number of bytes actually prepared (OUT)
*/
mca_btl_base_descriptor_t* mca_btl_gm_prepare_src(
struct mca_btl_base_module_t* btl,
struct mca_btl_base_endpoint_t* peer,
struct mca_mpool_base_registration_t*,
- Split the datatype engine into two parts: an MPI specific part in OMPI and a language agnostic part in OPAL. The convertor is completely moved into OPAL. This offers several benefits as described in RFC http://www.open-mpi.org/community/lists/devel/2009/07/6387.php namely: - Fewer basic types (int* and float* types, boolean and wchar - Fixing naming scheme to ompi-nomenclature. - Usability outside of the ompi-layer. - Due to the fixed nature of simple opal types, their information is completely known at compile time and therefore constified - With fewer datatypes (22), the actual sizes of bit-field types may be reduced from 64 to 32 bits, allowing reorganizing the opal_datatype structure, eliminating holes and keeping data required in convertor (upon send/recv) in one cacheline... This has implications to the convertor-datastructure and other parts of the code. - Several performance tests have been run, the netpipe latency does not change with this patch on Linux/x86-64 on the smoky cluster. - Extensive tests have been done to verify correctness (no new regressions) using: 1. mpi_test_suite on linux/x86-64 using clean ompi-trunk and ompi-ddt: a. running both trunk and ompi-ddt resulted in no differences (except for MPI_SHORT_INT and MPI_TYPE_MIX_LB_UB do now run correctly). b. with --enable-memchecker and running under valgrind (one buglet when run with static found in test-suite, commited) 2. ibm testsuite on linux/x86-64 using clean ompi-trunk and ompi-ddt: all passed (except for the dynamic/ tests failed!! as trunk/MTT) 3. compilation and usage of HDF5 tests on Jaguar using PGI and PathScale compilers. 4. compilation and usage on Scicortex. - Please note, that for the heterogeneous case, (-m32 compiled binaries/ompi), neither ompi-trunk, nor ompi-ddt branch would successfully launch. This commit was SVN r21641.
2009-07-13 04:56:31 +00:00
struct opal_convertor_t* convertor,
uint8_t order,
size_t reserve,
size_t* size,
uint32_t flags
);
extern mca_btl_base_descriptor_t* mca_btl_gm_prepare_dst(
struct mca_btl_base_module_t* btl,
struct mca_btl_base_endpoint_t* peer,
struct mca_mpool_base_registration_t*,
- Split the datatype engine into two parts: an MPI specific part in OMPI and a language agnostic part in OPAL. The convertor is completely moved into OPAL. This offers several benefits as described in RFC http://www.open-mpi.org/community/lists/devel/2009/07/6387.php namely: - Fewer basic types (int* and float* types, boolean and wchar - Fixing naming scheme to ompi-nomenclature. - Usability outside of the ompi-layer. - Due to the fixed nature of simple opal types, their information is completely known at compile time and therefore constified - With fewer datatypes (22), the actual sizes of bit-field types may be reduced from 64 to 32 bits, allowing reorganizing the opal_datatype structure, eliminating holes and keeping data required in convertor (upon send/recv) in one cacheline... This has implications to the convertor-datastructure and other parts of the code. - Several performance tests have been run, the netpipe latency does not change with this patch on Linux/x86-64 on the smoky cluster. - Extensive tests have been done to verify correctness (no new regressions) using: 1. mpi_test_suite on linux/x86-64 using clean ompi-trunk and ompi-ddt: a. running both trunk and ompi-ddt resulted in no differences (except for MPI_SHORT_INT and MPI_TYPE_MIX_LB_UB do now run correctly). b. with --enable-memchecker and running under valgrind (one buglet when run with static found in test-suite, commited) 2. ibm testsuite on linux/x86-64 using clean ompi-trunk and ompi-ddt: all passed (except for the dynamic/ tests failed!! as trunk/MTT) 3. compilation and usage of HDF5 tests on Jaguar using PGI and PathScale compilers. 4. compilation and usage on Scicortex. - Please note, that for the heterogeneous case, (-m32 compiled binaries/ompi), neither ompi-trunk, nor ompi-ddt branch would successfully launch. This commit was SVN r21641.
2009-07-13 04:56:31 +00:00
struct opal_convertor_t* convertor,
uint8_t order,
size_t reserve,
size_t* size,
uint32_t flags);
/**
* Fault Tolerance Event Notification Function
* @param state Checkpoint Stae
* @return OMPI_SUCCESS or failure status
*/
int mca_btl_gm_ft_event(int state);
/**
* Acquire a send token - queue the fragment if none available
*/
#define MCA_BTL_GM_ACQUIRE_TOKEN_NL(btl, frag) \
do { \
/* queue the descriptor if there are no send tokens */ \
if(OPAL_THREAD_ADD32(&gm_btl->gm_num_send_tokens, -1) < 0) { \
opal_list_append(&gm_btl->gm_pending, (opal_list_item_t*)frag); \
OPAL_THREAD_ADD32(&gm_btl->gm_num_send_tokens, 1); \
return OMPI_SUCCESS; \
} \
} while (0) \
#define MCA_BTL_GM_ACQUIRE_TOKEN(btl, frag) \
do { \
/* queue the descriptor if there are no send tokens */ \
if(OPAL_THREAD_ADD32(&gm_btl->gm_num_send_tokens, -1) < 0) { \
opal_list_append(&gm_btl->gm_pending, (opal_list_item_t*)frag); \
OPAL_THREAD_ADD32(&gm_btl->gm_num_send_tokens, 1); \
OPAL_THREAD_UNLOCK(&mca_btl_gm_component.gm_lock); \
return OMPI_SUCCESS; \
} \
} while (0) \
/**
* Return send token and dequeue and pending fragments
* mca_btl_gm_component.gm_lock is already held.
*/
#define MCA_BTL_GM_RETURN_TOKEN(btl) \
do { \
OPAL_THREAD_ADD32( &btl->gm_num_send_tokens, 1 ); \
if(opal_list_get_size(&btl->gm_pending)) { \
mca_btl_gm_frag_t* frag; \
frag = (mca_btl_gm_frag_t*)opal_list_remove_first(&btl->gm_pending); \
if(NULL != frag) { \
switch(frag->type) { \
case MCA_BTL_GM_SEND: \
case MCA_BTL_GM_EAGER: \
mca_btl_gm_send_nl(&btl->super, frag->endpoint, &frag->base, frag->hdr->tag); \
break; \
case MCA_BTL_GM_PUT: \
mca_btl_gm_put_nl(&btl->super, frag->endpoint, &frag->base); \
break; \
case MCA_BTL_GM_GET: \
mca_btl_gm_get_nl(&btl->super, frag->endpoint, &frag->base); \
break; \
} \
} \
} \
} while (0)
- Replace combinations of #if defined (c_plusplus) defined (__cplusplus) followed by extern "C" { and the closing counterpart by BEGIN_C_DECLS and END_C_DECLS. Notable exceptions are: - opal/include/opal_config_bottom.h: This is our generated code, that itself defines BEGIN_C_DECL and END_C_DECL - ompi/mpi/cxx/mpicxx.h: Here we do not include opal_config_bottom.h: - Belongs to external code: opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.c opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.h - opal/include/opal/prefetch.h: Has C++ specific macros that are protected: - Had #if ... } #endif _and_ END_C_DECLS (aka end up with 2x END_C_DECLS) ompi/mca/btl/openib/btl_openib.h - opal/event/event.h has #ifdef __cplusplus as BEGIN_C_DECLS... - opal/win32/ompi_process.h: had extern "C"\n {... opal/win32/ompi_process.h: dito - ompi/mca/btl/pcie/btl_pcie_lex.l: needed to add *_C_DECLS ompi/mpi/f90/test/align_c.c: dito - ompi/debuggers/msgq_interface.h: used #ifdef __cplusplus - ompi/mpi/f90/xml/common-C.xsl: Amend Tested on linux using --with-openib and --with-mx The following do not contain either opal_config.h, orte_config.h or ompi_config.h (but possibly other header files, that include one of the above): ompi/mca/bml/r2/bml_r2_ft.h ompi/mca/btl/gm/btl_gm_endpoint.h ompi/mca/btl/gm/btl_gm_proc.h ompi/mca/btl/mx/btl_mx_endpoint.h ompi/mca/btl/ofud/btl_ofud_endpoint.h ompi/mca/btl/ofud/btl_ofud_frag.h ompi/mca/btl/ofud/btl_ofud_proc.h ompi/mca/btl/openib/btl_openib_mca.h ompi/mca/btl/portals/btl_portals_endpoint.h ompi/mca/btl/portals/btl_portals_frag.h ompi/mca/btl/sctp/btl_sctp_endpoint.h ompi/mca/btl/sctp/btl_sctp_proc.h ompi/mca/btl/tcp/btl_tcp_endpoint.h ompi/mca/btl/tcp/btl_tcp_ft.h ompi/mca/btl/tcp/btl_tcp_proc.h ompi/mca/btl/template/btl_template_endpoint.h ompi/mca/btl/template/btl_template_proc.h ompi/mca/btl/udapl/btl_udapl_eager_rdma.h ompi/mca/btl/udapl/btl_udapl_endpoint.h ompi/mca/btl/udapl/btl_udapl_mca.h ompi/mca/btl/udapl/btl_udapl_proc.h ompi/mca/mtl/mx/mtl_mx_endpoint.h ompi/mca/mtl/mx/mtl_mx.h ompi/mca/mtl/psm/mtl_psm_endpoint.h ompi/mca/mtl/psm/mtl_psm.h ompi/mca/pml/cm/pml_cm_component.h ompi/mca/pml/csum/pml_csum_comm.h ompi/mca/pml/dr/pml_dr_comm.h ompi/mca/pml/dr/pml_dr_component.h ompi/mca/pml/dr/pml_dr_endpoint.h ompi/mca/pml/dr/pml_dr_recvfrag.h ompi/mca/pml/example/pml_example.h ompi/mca/pml/ob1/pml_ob1_comm.h ompi/mca/pml/ob1/pml_ob1_component.h ompi/mca/pml/ob1/pml_ob1_endpoint.h ompi/mca/pml/ob1/pml_ob1_rdmafrag.h ompi/mca/pml/ob1/pml_ob1_recvfrag.h ompi/mca/pml/v/pml_v_output.h opal/include/opal/prefetch.h opal/mca/timer/aix/timer_aix.h opal/util/qsort.h test/support/components.h This commit was SVN r21855. The following SVN revision numbers were found above: r2 --> open-mpi/ompi@58fdc188553052bc2e893ba28fb28fddbe78435a
2009-08-20 11:42:18 +00:00
END_C_DECLS
#endif