1
1
openmpi/opal/mca/hwloc/hwloc.h
Ralph Castain 24c811805f ****************************************************************
This change contains a non-mandatory modification
       of the MPI-RTE interface. Anyone wishing to support
       coprocessors such as the Xeon Phi may wish to add
       the required definition and underlying support
****************************************************************

Add locality support for coprocessors such as the Intel Xeon Phi.

Detecting that we are on a coprocessor inside of a host node isn't straightforward. There are no good "hooks" provided for programmatically detecting that "we are on a coprocessor running its own OS", and the ORTE daemon just thinks it is on another node. However, in order to properly use the Phi's public interface for MPI transport, it is necessary that the daemon detect that it is colocated with procs on the host.

So we have to split the locality to separately record "on the same host" vs "on the same board". We already have the board-level locality flag, but not quite enough flexibility to handle this use-case. Thus, do the following:

1. add OPAL_PROC_ON_HOST flag to indicate we share a host, but not necessarily the same board

2. modify OPAL_PROC_ON_NODE to indicate we share both a host AND the same board. Note that we have to modify the OPAL_PROC_ON_LOCAL_NODE macro to explicitly check both conditions

3. add support in opal/mca/hwloc/base/hwloc_base_util.c for the host to check for coprocessors, and for daemons to check to see if they are on a coprocessor. The former is done via hwloc, but support for the latter is not yet provided by hwloc. So the code for detecting we are on a coprocessor currently is Xeon Phi specific - hopefully, we will find more generic methods in the future.

4. modify the orted and the hnp startup so they check for coprocessors and to see if they are on a coprocessor, and have the orteds pass that info back in their callback message. Automatically detect that coprocessors have been found and identify which coprocessors are on which hosts. Note that this algo isn't scalable at the moment - this will hopefully be improved over time.

5. modify the ompi proc locality detection function to look for coprocessor host info IF the OMPI_RTE_HOST_ID database key has been defined. RTE's that choose not to provide this support do not have to do anything - the associated code will simply be ignored.

6. include some cleanup of the hwloc open/close code so it conforms to how we did things in other frameworks (e.g., having a single "frame" file instead of open/close). Also, fix the locality flags - e.g., being on the same node means you must also be on the same cluster/cu, so ensure those flags are also set.

cmr:v1.7.4:reviewer=hjelmn

This commit was SVN r29435.
2013-10-14 16:52:58 +00:00

217 строки
6.5 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 = 0x0600,
OPAL_PROC_ON_HOST = 0x0700,
OPAL_PROC_ON_BOARD = 0x0680,
OPAL_PROC_ON_NODE = 0x0780, // same host and board
OPAL_PROC_ON_NUMA = 0x07c0,
OPAL_PROC_ON_SOCKET = 0x07b0,
OPAL_PROC_ON_L3CACHE = 0x07a0,
OPAL_PROC_ON_L2CACHE = 0x07a8,
OPAL_PROC_ON_L1CACHE = 0x07ac,
OPAL_PROC_ON_CORE = 0x07ab,
OPAL_PROC_ON_HWTHREAD = 0x07aa,
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_HOST(n) ((n) & OPAL_PROC_ON_HOST)
#define OPAL_PROC_ON_LOCAL_NODE(n) (((n) & OPAL_PROC_ON_HOST) && ((n) & OPAL_PROC_ON_BOARD))
#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_ */