.\" -*- nroff -*-
.\" Copyright © 2010 INRIA.  All rights reserved.
.\" Copyright © 2009-2010 Cisco Systems, Inc.  All rights reserved.
.\" See COPYING in top-level directory.
.TH HWLOC-DISTRIB "1" "#HWLOC_DATE#" "#PACKAGE_VERSION#" "#PACKAGE_NAME#"
.SH NAME
hwloc-distrib \- Build a number of cpu masks distributed on the system
.
.\" **************************
.\"    Synopsis Section
.\" **************************
.SH SYNOPSIS
.B hwloc-distrib
[\fIoptions\fR] \fI<integer>\fR
.
.\" **************************
.\"    Options Section
.\" **************************
.SH OPTIONS
.TP
\fB\-\-single\fR
Singlify each output to a single CPU.
.TP
\fB\-\-taskset\fR
Show CPU set strings in the format recognized by the taskset command-line
program instead of hwloc-specific CPU set string format.
.TP
\fB\-v\fR
Verbose messages.
.TP
\fB\-i\fR <file>, \fB\-\-input\fR <file>
Read topology from XML file <file> (instead of discovering the
topology on the local machine).  If <file> is "\-", the standard input
is used.  XML support must have been compiled in to hwloc for this
option to be usable.
.TP
\fB\-i\fR <directory>, \fB\-\-input\fR <directory>
Read topology from the chroot specified by <directory> (instead of
discovering the topology on the local machine).  This option is
generally only available on Linux.  The chroot was usually created
by gathering another machine topology with hwloc-gather-topology.
.TP
\fB\-i\fR <specification>, \fB\-\-input\fR <specification>
Simulate a fake hierarchy (instead of discovering the topology on the
local machine). If <specification> is "node:2 pu:3", the topology will
contain two NUMA nodes with 3 processing units in each of them.
The <specification> string must end with a number of PUs.
.TP
\fB\-\-if\fR <format>, \fB\-\-input\-format\fR <format>
Enforce the input in the given format, among \fBxml\fR, \fBfsroot\fR
and \fBsynthetic\fR.
.TP
\fB\-\-ignore\fR <type>
Ignore all objects of type <type> in the topology.
.TP
\fB\-\-from\fR <type>
Distribute starting from objects of the given type instead of from
the top of the topology hierarchy, i.e. ignoring the structure given by objects
above.
.TP
\fB\-\-top\fR <type>
Distribute down to objects of the given type instead of down to the bottom of
the topology hierarchy, i.e. ignoring the structure given by objects below.
This may be useful if some latitude is desired for the binding, e.g. just bind
on sockets and not to precise cores or caches.
.TP
\fB\-\-at\fR <type>
Distribute among objects of the given type.  This is equivalent to specifying
both \fB\-\-from\fR and \fB\-\-to\fR at the same time.
.TP
\fB\-\-version\fR
Report version and exit.
.
.\" **************************
.\"    Description Section
.\" **************************
.SH DESCRIPTION
.
hwloc-distrib generates a series of CPU masks corresponding to a distribution of
a given number of elements over the topology of the machine. The distribution
is done recursively from the top of the hierarchy (or from the level specified
by option \fB\-\-from\fR) down to the bottom of the hierarchy (or down to the
level specified by option \fB\-\-to\fR, or until only one element remains),
splitting the number of elements at each encountered hierarchy level not ignored
by options \fB\-\-ignore\fR.

This can e.g. be used to distribute a set of processes hierarchically according
to the topology of a machine. These masks can be used with hwloc-bind(1).
.
.PP
.B NOTE:
It is highly recommended that you read the hwloc(7) overview page
before reading this man page.  Most of the concepts described in
hwloc(7) directly apply to the hwloc-bind utility.
.
.\" **************************
.\"    Examples Section
.\" **************************
.SH EXAMPLES
.PP
hwloc-distrib's operation is best described through several examples.
.
.PP
If 4 processes have to be distributed across a machine, their CPU masks
may be obtained with:

    $ hwloc-distrib 4
    0x0000000f
    0x00000f00
    0x000000f0
    0x0000f000

To get a single processor of each CPU masks (prevent migration in case
of binding)

    $ hwloc-distrib 4 --single
    0x00000001
    0x00000100
    0x00000010
    0x00001000

Each output line may be converted independently with hwloc-calc:

    $ hwloc-distrib 4 --single | hwloc-calc --taskset
    0x1
    0x100
    0x10
    0x1000

To convert the output into a list of processors that may be passed to
dplace -c inside a mpirun command line:

    $ hwloc-distrib 4 --single | xargs hwloc-calc --pulist
    0,8,4,16
.
.
.\" **************************
.\"    Return value section
.\" **************************
.SH RETURN VALUE
Upon successful execution, hwloc-distrib displays one or more CPU mask
strings.  The return value is 0.
.
.
.PP
hwloc-distrib will return nonzero if any kind of error occurs, such as
(but not limited to) failure to parse the command line.
.
.\" **************************
.\"    See also section
.\" **************************
.SH SEE ALSO
.
.ft R
hwloc(7), hwloc-gather-topology(1)
.sp