23e8ce91ba
now are able to use the dynamic rules. Moreover, these rules are loaded only once, and stored at the component level. All communicators are able to use these rules (not only MPI_COMM_WORLD as until now). A lot of minor corrections, memory management issues and reduction in the amount of memory used by the tuned collectives. This commit was SVN r21825.
280 строки
12 KiB
C
280 строки
12 KiB
C
/*
|
|
* 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) 2008 Sun Microsystems, Inc. All rights reserved.
|
|
* Copyright (c) 2008 Cisco Systems, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*
|
|
* These symbols are in a file by themselves to provide nice linker
|
|
* semantics. Since linkers generally pull in symbols by object
|
|
* files, keeping these symbols as the only symbols in this file
|
|
* prevents utility programs such as "ompi_info" from having to import
|
|
* entire components just to query their version and parameters.
|
|
*/
|
|
|
|
#include "ompi_config.h"
|
|
#include "opal/util/output.h"
|
|
#include "coll_tuned.h"
|
|
|
|
#include "mpi.h"
|
|
#include "ompi/mca/coll/coll.h"
|
|
#include "coll_tuned.h"
|
|
#include "coll_tuned_dynamic_file.h"
|
|
|
|
/*
|
|
* Public string showing the coll ompi_tuned component version number
|
|
*/
|
|
const char *ompi_coll_tuned_component_version_string =
|
|
"Open MPI tuned collective MCA component version " OMPI_VERSION;
|
|
|
|
/*
|
|
* Global variable
|
|
*/
|
|
int ompi_coll_tuned_stream = -1;
|
|
int ompi_coll_tuned_priority = 30;
|
|
int ompi_coll_tuned_preallocate_memory_comm_size_limit = (32 * 1024);
|
|
int ompi_coll_tuned_use_dynamic_rules = 0;
|
|
char* ompi_coll_tuned_dynamic_rules_filename = (char*) NULL;
|
|
int ompi_coll_tuned_init_tree_fanout = 4;
|
|
int ompi_coll_tuned_init_chain_fanout = 4;
|
|
int ompi_coll_tuned_init_max_requests = 128;
|
|
|
|
/* forced alogrithm variables */
|
|
/* indices for the MCA parameters */
|
|
coll_tuned_force_algorithm_mca_param_indices_t ompi_coll_tuned_forced_params[COLLCOUNT];
|
|
/* max algorithm values */
|
|
int ompi_coll_tuned_forced_max_algorithms[COLLCOUNT];
|
|
|
|
/*
|
|
* Local function
|
|
*/
|
|
static int tuned_open(void);
|
|
static int tuned_close(void);
|
|
|
|
/*
|
|
* Instantiate the public struct with all of our public information
|
|
* and pointers to our public functions in it
|
|
*/
|
|
|
|
mca_coll_tuned_component_t mca_coll_tuned_component = {
|
|
/* First, fill in the super */
|
|
{
|
|
/* First, the mca_component_t struct containing meta information
|
|
about the component itself */
|
|
{
|
|
MCA_COLL_BASE_VERSION_2_0_0,
|
|
|
|
/* Component name and version */
|
|
"tuned",
|
|
OMPI_MAJOR_VERSION,
|
|
OMPI_MINOR_VERSION,
|
|
OMPI_RELEASE_VERSION,
|
|
|
|
/* Component open and close functions */
|
|
tuned_open,
|
|
tuned_close
|
|
},
|
|
{
|
|
/* The component is checkpoint ready */
|
|
MCA_BASE_METADATA_PARAM_CHECKPOINT
|
|
},
|
|
|
|
/* Initialization / querying functions */
|
|
|
|
ompi_coll_tuned_init_query,
|
|
ompi_coll_tuned_comm_query,
|
|
},
|
|
|
|
/* priority of the module */
|
|
0,
|
|
|
|
/* Tuned component specific information */
|
|
NULL /* ompi_coll_alg_rule_t ptr */
|
|
};
|
|
|
|
|
|
static int tuned_open(void)
|
|
{
|
|
int rc;
|
|
|
|
#if OPAL_ENABLE_DEBUG
|
|
{
|
|
int param;
|
|
|
|
param = mca_base_param_find("coll", NULL, "base_verbose");
|
|
if (param >= 0) {
|
|
int verbose;
|
|
mca_base_param_lookup_int(param, &verbose);
|
|
if (verbose > 0) {
|
|
ompi_coll_tuned_stream = opal_output_open(NULL);
|
|
}
|
|
}
|
|
}
|
|
#endif /* OPAL_ENABLE_DEBUG */
|
|
|
|
/* Use a low priority, but allow other components to be lower */
|
|
mca_base_param_reg_int(&mca_coll_tuned_component.super.collm_version,
|
|
"priority",
|
|
"Priority of the tuned coll component",
|
|
false, false, ompi_coll_tuned_priority,
|
|
&ompi_coll_tuned_priority);
|
|
|
|
/* parameter for pre-allocated memory requests etc */
|
|
mca_base_param_reg_int(&mca_coll_tuned_component.super.collm_version,
|
|
"pre_allocate_memory_comm_size_limit",
|
|
"Size of communicator were we stop pre-allocating memory for the fixed internal buffer used for message requests etc that is hung off the communicator data segment. I.e. if you have a 100'000 nodes you might not want to pre-allocate 200'000 request handle slots per communicator instance!",
|
|
false, false, ompi_coll_tuned_preallocate_memory_comm_size_limit,
|
|
&ompi_coll_tuned_preallocate_memory_comm_size_limit);
|
|
|
|
/* some initial guesses at topology parameters */
|
|
mca_base_param_reg_int(&mca_coll_tuned_component.super.collm_version,
|
|
"init_tree_fanout",
|
|
"Inital fanout used in the tree topologies for each communicator. This is only an initial guess, if a tuned collective needs a different fanout for an operation, it build it dynamically. This parameter is only for the first guess and might save a little time",
|
|
false, false, ompi_coll_tuned_init_tree_fanout,
|
|
&ompi_coll_tuned_init_tree_fanout);
|
|
|
|
mca_base_param_reg_int(&mca_coll_tuned_component.super.collm_version,
|
|
"init_chain_fanout",
|
|
"Inital fanout used in the chain (fanout followed by pipeline) topologies for each communicator. This is only an initial guess, if a tuned collective needs a different fanout for an operation, it build it dynamically. This parameter is only for the first guess and might save a little time",
|
|
false, false, ompi_coll_tuned_init_chain_fanout,
|
|
&ompi_coll_tuned_init_chain_fanout);
|
|
|
|
/* now check that the user hasn't overrode any of the decision functions if dynamic rules are enabled */
|
|
/* the user can redo this before every comm dup/create if they like */
|
|
/* this is useful for benchmarking and user knows best tuning */
|
|
/* as this is the component we only lookup the indicies of the mca params */
|
|
/* the actual values are looked up during comm create via module init */
|
|
|
|
/* intra functions first */
|
|
/* if dynamic rules allowed then look up dynamic rules config filename, else we leave it an empty filename (NULL) */
|
|
/* by default DISABLE dynamic rules and instead use fixed [if based] rules */
|
|
mca_base_param_reg_int(&mca_coll_tuned_component.super.collm_version,
|
|
"use_dynamic_rules",
|
|
"Switch used to decide if we use static (compiled/if statements) or dynamic (built at runtime) decision function rules",
|
|
false, false, ompi_coll_tuned_use_dynamic_rules,
|
|
&ompi_coll_tuned_use_dynamic_rules);
|
|
|
|
if (ompi_coll_tuned_use_dynamic_rules) {
|
|
mca_base_param_reg_string(&mca_coll_tuned_component.super.collm_version,
|
|
"dynamic_rules_filename",
|
|
"Filename of configuration file that contains the dynamic (@runtime) decision function rules",
|
|
false, false, ompi_coll_tuned_dynamic_rules_filename,
|
|
&ompi_coll_tuned_dynamic_rules_filename);
|
|
if( ompi_coll_tuned_dynamic_rules_filename ) {
|
|
OPAL_OUTPUT((ompi_coll_tuned_stream,"coll:tuned:component_open Reading collective rules file [%s]",
|
|
ompi_coll_tuned_dynamic_rules_filename));
|
|
rc = ompi_coll_tuned_read_rules_config_file( ompi_coll_tuned_dynamic_rules_filename,
|
|
&(mca_coll_tuned_component.all_base_rules), COLLCOUNT);
|
|
if( rc >= 0 ) {
|
|
OPAL_OUTPUT((ompi_coll_tuned_stream,"coll:tuned:module_open Read %d valid rules\n", rc));
|
|
} else {
|
|
OPAL_OUTPUT((ompi_coll_tuned_stream,"coll:tuned:module_open Reading collective rules file failed\n"));
|
|
mca_coll_tuned_component.all_base_rules = NULL;
|
|
}
|
|
}
|
|
ompi_coll_tuned_allreduce_intra_check_forced_init(&ompi_coll_tuned_forced_params[ALLREDUCE]);
|
|
ompi_coll_tuned_alltoall_intra_check_forced_init(&ompi_coll_tuned_forced_params[ALLTOALL]);
|
|
ompi_coll_tuned_allgather_intra_check_forced_init(&ompi_coll_tuned_forced_params[ALLGATHER]);
|
|
ompi_coll_tuned_allgatherv_intra_check_forced_init(&ompi_coll_tuned_forced_params[ALLGATHERV]);
|
|
ompi_coll_tuned_alltoallv_intra_check_forced_init(&ompi_coll_tuned_forced_params[ALLTOALLV]);
|
|
ompi_coll_tuned_barrier_intra_check_forced_init(&ompi_coll_tuned_forced_params[BARRIER]);
|
|
ompi_coll_tuned_bcast_intra_check_forced_init(&ompi_coll_tuned_forced_params[BCAST]);
|
|
ompi_coll_tuned_reduce_intra_check_forced_init(&ompi_coll_tuned_forced_params[REDUCE]);
|
|
ompi_coll_tuned_reduce_scatter_intra_check_forced_init(&ompi_coll_tuned_forced_params[REDUCESCATTER]);
|
|
ompi_coll_tuned_gather_intra_check_forced_init(&ompi_coll_tuned_forced_params[GATHER]);
|
|
ompi_coll_tuned_scatter_intra_check_forced_init(&ompi_coll_tuned_forced_params[SCATTER]);
|
|
}
|
|
|
|
OPAL_OUTPUT((ompi_coll_tuned_stream, "coll:tuned:component_open: done!"));
|
|
|
|
return OMPI_SUCCESS;
|
|
}
|
|
|
|
/* here we should clean up state stored on the component */
|
|
/* i.e. alg table and dynamic changable rules if allocated etc */
|
|
static int tuned_close(void)
|
|
{
|
|
OPAL_OUTPUT((ompi_coll_tuned_stream, "coll:tuned:component_close: called"));
|
|
|
|
/* dealloc alg table if allocated */
|
|
/* dealloc dynamic changable rules if allocated */
|
|
|
|
OPAL_OUTPUT((ompi_coll_tuned_stream, "coll:tuned:component_close: done!"));
|
|
|
|
if( NULL != mca_coll_tuned_component.all_base_rules ) {
|
|
ompi_coll_tuned_free_all_rules(mca_coll_tuned_component.all_base_rules, COLLCOUNT);
|
|
mca_coll_tuned_component.all_base_rules = NULL;
|
|
}
|
|
|
|
return OMPI_SUCCESS;
|
|
}
|
|
|
|
static void
|
|
mca_coll_tuned_module_construct(mca_coll_tuned_module_t *module)
|
|
{
|
|
module->tuned_data = NULL;
|
|
}
|
|
|
|
|
|
static void
|
|
mca_coll_tuned_module_destruct(mca_coll_tuned_module_t *module)
|
|
{
|
|
mca_coll_tuned_comm_t *data;
|
|
|
|
/* Free the space in the data mpool and the data hanging off the
|
|
communicator */
|
|
|
|
data = module->tuned_data;
|
|
if (NULL != data) {
|
|
#if OPAL_ENABLE_DEBUG
|
|
/* Reset the reqs to NULL/0 -- they'll be freed as part of freeing
|
|
the generel c_coll_selected_data */
|
|
data->mcct_reqs = NULL;
|
|
data->mcct_num_reqs = 0;
|
|
#endif
|
|
|
|
/* free any cached information that has been allocated */
|
|
if (data->cached_ntree) { /* destroy general tree if defined */
|
|
ompi_coll_tuned_topo_destroy_tree (&data->cached_ntree);
|
|
}
|
|
if (data->cached_bintree) { /* destroy bintree if defined */
|
|
ompi_coll_tuned_topo_destroy_tree (&data->cached_bintree);
|
|
}
|
|
if (data->cached_bmtree) { /* destroy bmtree if defined */
|
|
ompi_coll_tuned_topo_destroy_tree (&data->cached_bmtree);
|
|
}
|
|
if (data->cached_in_order_bmtree) { /* destroy bmtree if defined */
|
|
ompi_coll_tuned_topo_destroy_tree (&data->cached_in_order_bmtree);
|
|
}
|
|
if (data->cached_chain) { /* destroy general chain if defined */
|
|
ompi_coll_tuned_topo_destroy_tree (&data->cached_chain);
|
|
}
|
|
if (data->cached_pipeline) { /* destroy pipeline if defined */
|
|
ompi_coll_tuned_topo_destroy_tree (&data->cached_pipeline);
|
|
}
|
|
if (data->cached_in_order_bintree) { /* destroy in order bintree if defined */
|
|
ompi_coll_tuned_topo_destroy_tree (&data->cached_in_order_bintree);
|
|
}
|
|
|
|
free(data);
|
|
}
|
|
}
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(mca_coll_tuned_module_t,
|
|
mca_coll_base_module_t,
|
|
mca_coll_tuned_module_construct,
|
|
mca_coll_tuned_module_destruct);
|