6d173af329
some relevant updates/new functionality in the opal/mca/hwloc and
orte/mca/rmaps bases. This work was mainly developed by Mellanox,
with a bunch of advice from Ralph Castain, and some minor advice from
Brice Goglin and Jeff Squyres.
Even though this is mainly Mellanox's work, Jeff is committing only
for logistical reasons (he holds the hg+svn combo tree, and can
therefore commit it directly back to SVN).
-----
Implemented distance-based mapping algorithm as a new "mindist"
component in the rmaps framework. It allows mapping processes by NUMA
due to PCI locality information as reported by the BIOS - from the
closest to device to furthest.
To use this algorithm, specify:
{{{mpirun --map-by dist:<device_name>}}}
where <device_name> can be mlx5_0, ib0, etc.
There are two modes provided:
1. bynode: load-balancing across nodes
1. byslot: go through slots sequentially (i.e., the first nodes are
more loaded)
These options are regulated by the optional ''span'' modifier; the
command line parameter looks like:
{{{mpirun --map-by dist:<device_name>,span}}}
So, for example, if there are 2 nodes, each with 8 cores, and we'd
like to run 10 processes, the mindist algorithm will place 8 processes
to the first node and 2 to the second by default. But if you want to
place 5 processes to each node, you can add a span modifier in your
command line to do that.
If there are two NUMA nodes on the node, each with 4 cores, and we run
6 processes, the mindist algorithm will try to find the NUMA closest
to the specified device, and if successful, it will place 4 processes
on that NUMA but leaving the remaining two to the next NUMA node.
You can also specify the number of cpus per MPI process. This option
is handled so that we map as many processes to the closest NUMA as we
can (number of available processors at the NUMA divided by number of
cpus per rank) and then go on with the next closest NUMA.
The default binding option for this mapping is bind-to-numa. It works
if you don't specify any binding policy. But if you specified binding
level that was "lower" than NUMA (i.e hwthread, core, socket) it would
bind to whatever level you specify.
This commit was SVN r28552.
215 строки
6.3 KiB
C
215 строки
6.3 KiB
C
/*
|
|
* Copyright (c) 2011-2012 Cisco Systems, Inc. All rights reserved.
|
|
*
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*/
|
|
|
|
#ifndef OPAL_MCA_HWLOC_H
|
|
#define OPAL_MCA_HWLOC_H
|
|
|
|
#include "opal_config.h"
|
|
|
|
#ifdef HAVE_SYS_TYPES_H
|
|
#include <sys/types.h>
|
|
#endif
|
|
#ifdef HAVE_SYS_TIME_H
|
|
#include <sys/time.h>
|
|
#endif
|
|
#ifdef HAVE_STDINT_H
|
|
#include <stdint.h>
|
|
#endif
|
|
#ifdef HAVE_STDARG_H
|
|
#include <stdarg.h>
|
|
#endif
|
|
|
|
#include "opal/class/opal_list.h"
|
|
#include "opal/class/opal_value_array.h"
|
|
|
|
#include "opal/mca/mca.h"
|
|
#include "opal/mca/base/base.h"
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
#ifdef WIN32
|
|
#define WIN32_LEAN_AND_MEAN
|
|
#include <windows.h>
|
|
#undef WIN32_LEAN_AND_MEAN
|
|
typedef unsigned char u_char;
|
|
typedef unsigned short u_short;
|
|
#endif
|
|
|
|
/**
|
|
* Structure for hwloc components.
|
|
*/
|
|
struct opal_hwloc_base_component_2_0_0_t {
|
|
/** MCA base component */
|
|
mca_base_component_t base_version;
|
|
/** MCA base data */
|
|
mca_base_component_data_t base_data;
|
|
};
|
|
|
|
/**
|
|
* Convenience typedef
|
|
*/
|
|
typedef struct opal_hwloc_base_component_2_0_0_t opal_hwloc_base_component_2_0_0_t;
|
|
typedef struct opal_hwloc_base_component_2_0_0_t opal_hwloc_component_t;
|
|
|
|
/**
|
|
* Macro for use in components that are of type hwloc
|
|
*/
|
|
#define OPAL_HWLOC_BASE_VERSION_2_0_0 \
|
|
MCA_BASE_VERSION_2_0_0, \
|
|
"hwloc", 2, 0, 0
|
|
|
|
|
|
/* ******************************************************************** */
|
|
/* Although we cannot bind if --without-hwloc is set,
|
|
* we do still need to know some basic locality data
|
|
* like on_node and not_on_node. So ensure that we
|
|
* always have access to that much info by including
|
|
* the definitions here, outside the if-have-hwloc test
|
|
*/
|
|
typedef uint16_t opal_hwloc_locality_t;
|
|
#define OPAL_HWLOC_LOCALITY_T OPAL_UINT16
|
|
|
|
/** Process locality definitions */
|
|
enum {
|
|
OPAL_PROC_LOCALITY_UNKNOWN = 0x0000,
|
|
OPAL_PROC_NON_LOCAL = 0x8000,
|
|
OPAL_PROC_ON_CLUSTER = 0x0400,
|
|
OPAL_PROC_ON_CU = 0x0200,
|
|
OPAL_PROC_ON_NODE = 0x0100,
|
|
OPAL_PROC_ON_BOARD = 0x0080,
|
|
OPAL_PROC_ON_NUMA = 0x0040,
|
|
OPAL_PROC_ON_SOCKET = 0x0020,
|
|
OPAL_PROC_ON_L3CACHE = 0x0010,
|
|
OPAL_PROC_ON_L2CACHE = 0x0008,
|
|
OPAL_PROC_ON_L1CACHE = 0x0004,
|
|
OPAL_PROC_ON_CORE = 0x0002,
|
|
OPAL_PROC_ON_HWTHREAD = 0x0001,
|
|
OPAL_PROC_ALL_LOCAL = 0x0fff
|
|
};
|
|
|
|
/** Process locality macros */
|
|
#define OPAL_PROC_ON_LOCAL_HWTHREAD(n) ((n) & OPAL_PROC_ON_HWTHREAD)
|
|
#define OPAL_PROC_ON_LOCAL_CORE(n) ((n) & OPAL_PROC_ON_CORE)
|
|
#define OPAL_PROC_ON_LOCAL_L1CACHE(n) ((n) & OPAL_PROC_ON_L1CACHE)
|
|
#define OPAL_PROC_ON_LOCAL_L2CACHE(n) ((n) & OPAL_PROC_ON_L2CACHE)
|
|
#define OPAL_PROC_ON_LOCAL_L3CACHE(n) ((n) & OPAL_PROC_ON_L3CACHE)
|
|
#define OPAL_PROC_ON_LOCAL_SOCKET(n) ((n) & OPAL_PROC_ON_SOCKET)
|
|
#define OPAL_PROC_ON_LOCAL_NUMA(n) ((n) & OPAL_PROC_ON_NUMA)
|
|
#define OPAL_PROC_ON_LOCAL_BOARD(n) ((n) & OPAL_PROC_ON_BOARD)
|
|
#define OPAL_PROC_ON_LOCAL_NODE(n) ((n) & OPAL_PROC_ON_NODE)
|
|
#define OPAL_PROC_ON_LOCAL_CU(n) ((n) & OPAL_PROC_ON_CU)
|
|
#define OPAL_PROC_ON_LOCAL_CLUSTER(n) ((n) & OPAL_PROC_ON_CLUSTER)
|
|
|
|
/* ******************************************************************** */
|
|
|
|
/**
|
|
* Struct used to describe a section of memory (starting address
|
|
* and length). This is really the same thing as an iovec, but
|
|
* we include a separate type for it for at least 2 reasons:
|
|
*
|
|
* 1. Some OS's iovec definitions are exceedingly lame (e.g.,
|
|
* Solaris 9 has the length argument as an int, instead of a
|
|
* size_t).
|
|
*
|
|
* 2. We reserve the right to expand/change this struct in the
|
|
* future.
|
|
*/
|
|
typedef struct {
|
|
/** Starting address of segment */
|
|
void *mbs_start_addr;
|
|
/** Length of segment */
|
|
size_t mbs_len;
|
|
} opal_hwloc_base_memory_segment_t;
|
|
|
|
/* include implementation to call */
|
|
#if OPAL_HAVE_HWLOC
|
|
#include MCA_hwloc_IMPLEMENTATION_HEADER
|
|
|
|
/* define type of processor info requested */
|
|
typedef uint8_t opal_hwloc_resource_type_t;
|
|
#define OPAL_HWLOC_PHYSICAL 1
|
|
#define OPAL_HWLOC_LOGICAL 2
|
|
#define OPAL_HWLOC_AVAILABLE 3
|
|
|
|
/* structs for storing info on objects */
|
|
typedef struct {
|
|
opal_object_t super;
|
|
hwloc_cpuset_t available;
|
|
unsigned int npus;
|
|
unsigned int idx;
|
|
unsigned int num_bound;
|
|
} opal_hwloc_obj_data_t;
|
|
OBJ_CLASS_DECLARATION(opal_hwloc_obj_data_t);
|
|
|
|
typedef struct {
|
|
opal_list_item_t super;
|
|
hwloc_obj_type_t type;
|
|
unsigned cache_level;
|
|
unsigned int num_objs;
|
|
opal_hwloc_resource_type_t rtype;
|
|
opal_list_t sorted_by_dist_list;
|
|
} opal_hwloc_summary_t;
|
|
OBJ_CLASS_DECLARATION(opal_hwloc_summary_t);
|
|
|
|
typedef struct {
|
|
opal_object_t super;
|
|
hwloc_cpuset_t available;
|
|
opal_list_t summaries;
|
|
|
|
/** \brief Additional space for custom data */
|
|
void *userdata;
|
|
} opal_hwloc_topo_data_t;
|
|
OPAL_DECLSPEC OBJ_CLASS_DECLARATION(opal_hwloc_topo_data_t);
|
|
|
|
/* define binding policies */
|
|
typedef uint16_t opal_binding_policy_t;
|
|
#define OPAL_BINDING_POLICY OPAL_UINT16
|
|
|
|
/* binding directives */
|
|
#define OPAL_BIND_IF_SUPPORTED 0x1000
|
|
#define OPAL_BIND_ALLOW_OVERLOAD 0x2000
|
|
#define OPAL_BIND_GIVEN 0x4000
|
|
/* binding policies */
|
|
#define OPAL_BIND_TO_NONE 1
|
|
#define OPAL_BIND_TO_BOARD 2
|
|
#define OPAL_BIND_TO_NUMA 3
|
|
#define OPAL_BIND_TO_SOCKET 4
|
|
#define OPAL_BIND_TO_L3CACHE 5
|
|
#define OPAL_BIND_TO_L2CACHE 6
|
|
#define OPAL_BIND_TO_L1CACHE 7
|
|
#define OPAL_BIND_TO_CORE 8
|
|
#define OPAL_BIND_TO_HWTHREAD 9
|
|
#define OPAL_BIND_TO_CPUSET 10
|
|
#define OPAL_GET_BINDING_POLICY(pol) \
|
|
((pol) & 0x0fff)
|
|
#define OPAL_SET_BINDING_POLICY(target, pol) \
|
|
(target) = (pol) | (((target) & 0xf000) | OPAL_BIND_GIVEN)
|
|
/* check if policy is set */
|
|
#define OPAL_BINDING_POLICY_IS_SET(pol) \
|
|
((pol) & 0x4000)
|
|
/* macro to detect if binding was qualified */
|
|
#define OPAL_BINDING_REQUIRED(n) \
|
|
(!(OPAL_BIND_IF_SUPPORTED & (n)))
|
|
/* macro to detect if binding is forced */
|
|
#define OPAL_BIND_OVERLOAD_ALLOWED(n) \
|
|
(OPAL_BIND_ALLOW_OVERLOAD & (n))
|
|
|
|
/* some global values */
|
|
OPAL_DECLSPEC extern hwloc_topology_t opal_hwloc_topology;
|
|
OPAL_DECLSPEC extern opal_binding_policy_t opal_hwloc_binding_policy;
|
|
OPAL_DECLSPEC extern hwloc_cpuset_t opal_hwloc_my_cpuset;
|
|
OPAL_DECLSPEC extern bool opal_hwloc_report_bindings;
|
|
OPAL_DECLSPEC extern hwloc_obj_type_t opal_hwloc_levels[];
|
|
OPAL_DECLSPEC extern bool opal_hwloc_use_hwthreads_as_cpus;
|
|
|
|
#endif
|
|
|
|
END_C_DECLS
|
|
|
|
#endif /* OPAL_HWLOC_H_ */
|